In motor imagery (MI)-based brain-computer interfaces (BCIs), convolutional neural networks (CNNs) are widely employed to decode electroencephalogram (EEG) signals. However, due to their fixed kernel sizes and uniform attention to features, CNNs struggle to fully capture the time-frequency features of EEG signals. To address this limitation, this paper proposes the Multi-Domain Dynamic Weighted Network (MD-DWNet), which integrates multimodal complementary feature information across time, frequency, and spatial domains through a branch structure to enhance decoding performance. Specifically, MD-DWNet combines multi-band filtering, spatial convolution, and temporal variance calculation to extract spatial-spectral features, while a dual-scale CNN captures local spatiotemporal features at different time scales. A dynamic global filter is designed to optimize fused features, improving the adaptive modeling capability for dynamic changes in frequency band energy. A lightweight mixed attention mechanism selectively enhances salient channel and spatial features. The dual-branch joint loss function adaptively balances contributions through a task uncertainty mechanism, thereby enhancing optimization efficiency and generalization capability. Experimental results on the BCI Competition IV 2a, IV 2b, OpenBMI, and a self-collected laboratory dataset demonstrate that MD-DWNet achieves classification accuracies of 83.86%, 88.67%, 75.25% and 84.85%, respectively, outperforming several advanced methods and validating its superior performance in MI signal decoding.

Motor imagery (MI) is a popular noninvasive brain computer interface (BCI) paradigm, yet its decoding accuracy remains hindered by the inherent nonstationarity and low signal-to-noise ratio of electroencephalogram (EEG) signals. Current decoding frameworks often fail to fully exploit the intricate spatial-temporal dependencies, leading to suboptimal feature representation and the omission of latent discriminative cues. To address these challenges, we introduce a deep neural network-powered multifaceted strategy (DPMS-Net) model, a novel approach that employs dynamic convolution to unearth effective discriminative cues across multiple dimensions, including the temporal, spatial, and frequency domains. This model synergizes channel and temporal attention mechanisms to adeptly capture the salient features of EEG signals across diverse spatial-temporal dimensions, thereby mitigating the risk of omitting critical information. Furthermore, we introduce a spectral-domain analysis component that unearths subtle oscillatory signatures hidden within the EEG spectrum, providing enriched evidence for classification. We evaluated the performance of DPMS-Net on two publicly available datasets and a self-collected dataset from stroke patients. On the BCI Competition IV 2a and BCI Competition IV 2b datasets, DPMS-Net achieved subject-dependent classification accuracies of 83.93% and 88.38%, respectively, alongside subject-independent classification accuracies of 65.88% and 76.01%. In the stroke patient dataset, DPMS-Net attained a subject-dependent classification accuracy of 67.67% and a subject-independent classification accuracy of 57.58%. Experimental results indicate that DPMS-Net possesses efficient decoding capabilities and robust stability, reflecting its potential for deployment in neurorehabilitation BCI systems.

To facilitate smart wearable devices or human-like robotics with real-time first-person perspective perception ability, recent researchers proposed the Egocentric Online Action Segmentation (EOAS) task. It requires models to recognize what is happening in egocentric streaming videos and discriminate the starting and ending times of an activity in a real-time manner. However, compared with offline-recorded exocentric videos, egocentric streaming videos cannot provide equivalent sufficient temporal-spatial cues due to the limited perspective and unknown coming frames. Hence, it raises a high demand for the long-term episodic memory ability of models. To this end, most previous approaches work on compressing long-term memory into feature representations. In this paper, we propose a novel EOAS paradigm, termed Parametric Context Memory Learning (PCML), which integrates episodic memory into learnable parameters and keeps dynamic updates according to real-time frames. Concretely, we design the Parametric Context Perception layer and construct a novel Episodic Semantic Memorization Network (ESMN) based on it, which integrates episodic memory into learnable parameters and keeps dynamic updates with real-time frames. We evaluate our proposed method on three public egocentric streaming video benchmarks including EgoPER, EgoProceL, and GTEA. Extensive experiments demonstrate the ESMN model significantly outperforms recent state-of-the-art methods. Our code is available at https://github.com/XunCHN/PCML.

The grounded question answering in egocentric videos (Ego-GQA) aims to identify the relevant temporal window and generate corresponding responses in natural language given a textual question. Compared with third-person videos, egocentric video understanding requires more advanced human-centric thinking capability. However, existing Ego-GQA approaches often fail to distinguish the inherent limitations of dynamic egocentric context understanding, treating both first-person and third-person perspectives equally. This oversight leads to hallucinations and a lack of proper egocentric reasoning in first-person video understanding. To address this issue, we propose a novel Collaborated with Hallucination (CoHa) framework for the Ego-GQA, which quantifies the hallucinations generated by an Ego-GQA model and further leverages them as error demonstrations to constrain the model's reasoning process, encouraging it to ground predictions in egocentric visual cues instead of relying on biased pretraining priors. Specifically, we first employ Subjective Logic to quantify the degree of uncertainty in unreliable answers. We then generate diffusion-based noisy visual inputs to amplify the hallucinations as error demonstrations, which are used to append appropriate constraints to the model according to the uncertainty. These constraints effectively steer predictions away from the unreliable semantics induced by inherent drawbacks in egocentric thinking. Additionally, we incorporate an interactive refinement module to facilitate the model to explore more fine-grained cues observed from the first-person view. Extensive experiments on two widely used benchmarks demonstrate that our CoHa method outperforms recent state-of-the-art methods. Our code is available at https://github.com/Mrshenshen/CoHa.

Steady state visual evoked potential (SSVEP)-based brain-computer interfaces have been widely studied for their fast response speeds and high information transfer rates. However, how to fully utilize the potential information of existing subjects to realize the mining of common information among different subjects and then realize the information migration in a small amount of data scenarios is a difficult problem faced by current research. In order to solve the above problems, this study proposes a deep neural network based on the pyramid squeeze attention (PSA-DNN) mechanism to enhance the performance of SSVEP-BCI through common information migration. Specifically, the band-pass filtered EEG signals were first Fourier transformed to obtain the frequency domain information; subsequently, the frequency domain information is input into a deep neural network, followed by a spatial convolution step to extract spatial domain information. In order to further enhance the quality of information extraction, a pyramid attention module is introduced into the network to realize the enhancement of frequency domain and spatial domain information. Time domain information from the EEG signals is then mined using temporal convolution. Finally, the full connectivity layer is used to output the recognition results. The model is trained in a three-stage stepped approach for SSVEP target recognition. The first stage uses data from all participants in the training set for common information learning and transfers the model parameters trained in the first stage to the network model in the second stage. In the second stage, some of the information from participants in the test set is used for fine-tuning and to mine personalized information from these new participants. The third stage uses the remaining data from participants in the test set to produce classification results. The proposed method is systematically evaluated using the Benchmark and BETA datasets, where it demonstrates favorable performance compared to established baselines. These findings contribute theoretical insights and methodological References for the application of SSVEP-based brain-computer interfaces in real-world scenarios.

Domainadaptation has proven effective for suppressing the inter-subject variability problem in cross-subject EEG classification tasks in which labeled data is available for source subjects while only unlabeled data is provided for target subjects. Existing domain adaptation methods typically reduced the distribution discrepancy between source and target domains by directly utilizing source domain samples or features. To safeguard the privacy of source domain data, we propose to construct a Proxy Domain by simultaneously considering the prediction Consistency and Confidence (PDCC) of locally trained source models on target EEG samples, serving as the substitute to the source domain. The framework commences with the augmentation and alignment of the source domain data to enhance feature generalizability, after which source models are trained independently on each source subject's data in a decentralized manner. Knowledge transfer from source to target domains is achieved exclusively through accessing to the source domain model, enabling the PDCC-based proxy domain construction that encapsulates the source knowledge. Finally, domain adaptation is performed using the proxy domain and target domain. As a result, PDCC eliminates the need to access source domain data while effectively leveraging source knowledge. Experimental results on four benchmark EEG datasets demonstrate that PDCC consistently outperforms eleven existing methods, including several advanced transfer learning and source-free methods. Especially, the effectiveness of the proxy domain is extensively investigated.

Training-based algorithms significantly outperform training-free methods in terms of recognition performance for steady-state visual-evoked potential (SSVEP)-based brain-computer Interfaces (BCIs). However, collecting training data requires calibration experiments that are effort-intensive and often costly. These calibration demands limit the practicality of BCI, as users (and even system operators) may experience fatigue or lose interest in continued use. Transfer learning (TL) offers an effective solution, but it typically relies on either a certain amount of target domain data or extensive source domain data. To address this limitation, we introduce the concept of cross-dataset TL in SSVEP for the first time to extract transfer knowledge from other datasets. During this process, we identified a data mismatch problem that severely compromises the generalizability of transfer knowledge. To overcome this challenge, we propose a TL-SSVEP decoding algorithm calibrated with single-trial data (TL-CSTD). Specifically, we use 2 s of 8 Hz single-trial calibration data from the target domain to obtain matched transfer templates from the source domain. These templates are then corrected to extract holistic and single-period transfer knowledge, which are subsequently employed to construct an efficient TL-SSVEP decoding model for the target subject. Experimental results on three large SSVEP datasets demonstrate that TL-CSTD effectively addresses the data mismatch problem and achieves excellent SSVEP recognition performance using only 2 s of single-trial calibration data, showing its significant application potential and practicality.

Motor imagery (MI) is one of the most widely used paradigms in brain–computer interfaces (BCIs), known for its ability to trigger changes in brain activity without the need for an external “cue” stimulus. This unique characteristic has attracted significant attention from neuroscientists and researchers in fundamental science. However, compared toP300 and steady-state visual evoked potential (SSVEP), neural activity related to MI tends to be less stable and exhibits substantial variability between individuals. Consequently, accurately decoding MI, using both traditional machine learning and deep learning, has proven to be a considerable challenge. Moreover, given the difficulty of acquiring electroencephalography (EEG) data and the high data demands of deep learning, enhancing the accuracy of MI decoding with limited sample sizes remains a pressing issue that urgently needs to be addressed. This article addresses the challenges mentioned above by introducing a novel deep neural network designed for accurate MI decoding, which is designed to be effective with both small-sample sizes and larger datasets. This network, named the multiscale pooling spatial–temporal attention network (MPSTANet), integrates mix pooling techniques with spatial–temporal attention mechanisms. MPSTANet first employs local and global spatial attention, along with multiscale temporal attention, to thoroughly extract spatial–temporal information from EEG signals. Next, MPSTANet utilizes feature fusion and the proposed mix pooling technique to preserve as much of the extracted spatial–temporal information as possible. Finally, channel interaction attention (CIA) and 3-D weight attention (3-DWA) are employed to recalibrate the weights of the fused channels and spatial–temporal features, respectively. To validate the performance of our proposed MPSTANet model, we conducted experiments on four public datasets, including both small-sample sizes and subject-independent scenarios. MPSTANet achieved cross-session decoding accuracies of 84.82%, 72.92%, 88.20%, and 46.54% on the BCI Competition IV 2a dataset, the Open BMI dataset, the BCI Competition IV 2b dataset, and the PhysioNet dataset, respectively. Furthermore, MPSTANet demonstrated a significant lead compared to other deep learning models in both small-sample and subject-independent experiments. These results demonstrate the robustness of MPSTANet in MI decoding and its promising potential for BCI applications.

Data augmentation effectively expands feature distribution in time series classification, enhancing downstream task performance. However, existing techniques often fail to maintain semantic consistency between augmented and original time series data, causing label noise and thereby degrading downstream task performance. We argue that data augmentation should preserve time series semantic consistency and expand the non-semantic information space. In this paper, we reformulate data augmentation as a semantic path planning problem between original data and augmented data, modeled as a Markov Decision Process (MDP). We propose a reinforcement learning-based algorithm (RL) named FreqSYN, where the action space is defined by a set of learnable Gaussian kernels that perturbs the frequency domain of the original data to generate augmented samples. The confidence coefficients of augmented data in semantically relevant classification tasks are used as a reward to iteratively refine the FreqSYN. Our method is validated across four datasets, achieving state-of-the-art performance, with a 2% improvement in F1 score over the SimPSI method. The code and models are available at https://github.com/NKU-EmbeddedSystem/FreqSYN.

Electroencephalography (EEG) is a time-series signal containing semantic information that can be used to determine human brain activities. Artifacts within EEG data can interfere with the intrinsic distribution of this semantic information, so removing artifacts is crucial for improving EEG analysis performance on downstream tasks. In this paper, we redefine the efficacy of the artifact removal model by evaluating the performance of the noisy EEG data in downstream tasks before and after artifact removal. Currently, most artifact removal models fail to ensure semantic consistency, rendering them ineffective. To solve it, we propose an artifact removal model based on the 1-dimensional diffusion model utilizing the U-Net, referred to as Essentia. Moreover, we find that the skip-connection layer in U-Net contains mid-to-high-frequency information that interferes with the semantic representation. We introduce a semantic guidance module (SGM) that leverages contrastive learning to generate semantic distribution weights, boosting semantic representation. We evaluate Essentia on three datasets with six solutions. The accuracy of downstream tasks from the denoised EEG data increased by 4% compared with the DeepSeparetor. The code and models are available at https://github.com/NKU-EmbeddedSystem/Essentia.

Based on adversarial training and hierarchical alignment structure, domain adaptive object detection methods have made impressive progress. However, current adaptation methods treats each feature equally, and exerts unchanged alignment strength during alignment process, without sufficiently considering the transferability inconsistency of different features. Such static alignment can only achieve approximate alignment and will bring about negative transfer eventually. To address these issues, we propose the Multi-Perspective Feature Dynamic Adaptation Network (MPFDAN). In this network, the transferability of features is thoroughly considered and utilized from three different perspectives, allowing the alignment process to be dynamically adjusted in different ways. Firstly, regarding local transferability, Shannon entropy is used to adjust the weights of features in different local regions to focus more on regions with higher transferability. Next, from the perspective of global alignment, we dynamically adjust the alignment strength applied during the image-level adaptation process to avoid overfitting. Finally, category information is introduced to achieve category-aware instance-level adaptation, dynamically adjusted based on the differences in category transferability. Experiments on various domain transfer scenarios demonstrate that our MPFDAN outperforms all compared methods, thereby proving the effectiveness of our proposed approach.

The decoding approach of steady-state visual evoked potentials (SSVEPs) based on supervised learning has achieved remarkable results. However, these approaches require extensive calibration efforts to train the mode parameters for each stimulus. To facilitate the calibration process, we proposed a cross-stimulus transfer learning framework using the common periodic repetition components (CSTLF-CPRC) in fast calibration scenario. First, a source stimulus mode was constructed, which can use periodic repetition components to obtain a source synthetic SSVEP template and source ensemble spatial filter. Second, leveraging the common information between period repeated component templates across multistimulus periods, the common source aliasing matrix was further estimated. Finally, leveraging the commonality between target and source stimuli, a cross-stimulus transfer learning mode was constructed for SSVEP cross-stimulus recognition. Offline tests on public datasets show that the CSTLF-CPRC outperforms the state-of-the-art (SOTA) methods, such as filter band CCA, transfer learning CCA, and common impulse response cross-stimulus transfer learning, in a fast calibration scenario. Our method only needs 16 s to calibrate 40 targets on two public datasets and achieves an average information transfer rate of$227.86~\pm ~106.47$bit/min and$162.41~\pm ~124.29$bit/min, respectively. The study has the requirement of a few calibration data to achieve high-performance recognition and to promote effective development of the practical system.

Brain-computer interface (BCI) technology enables the control of external devices by recognizing user intentions. Steady-state visual evoked potential (SSVEP)-based BCI technology has been widely applied in the field of Internet of Things (IoT) device control, including smart healthcare, smart homes, and robotics, and has achieved significant results. However, as the field of BCI-based IoT device control is still in its development stage, there remains considerable room for improvement in terms of accuracy, efficiency, and cost. Therefore, enhancing the classification accuracy of SSVEP decoding using a short time window, reducing both human and material costs, and improving work efficiency are crucial for the theoretical research and engineering applications of BCI technology in IoT device control. Based on this, we propose a novel approach to address the challenge of high-accuracy feature extraction within brief timeframes. Our approach integrates a multiscale convolutional neural network with a squeeze excitation module (SEMSCNN). This fusion leverages convolutional neural networks (CNNs)’ local feature learning capacity and the advantageous feature importance distinction offered by the squeeze excitation mechanism. First, the electroencephalogram signals are band-pass filtered into distinct frequency bands and frequency band and channel features are extracted by a two-layer convolution. Then, temporal features are extracted via a multibranch convolution of different scales. Finally, the squeeze and excitation (SE) module is introduced to learn the interdependence between features to improve the quality of the extracted features. The first stage of training exploits statistical commonalities across research participants by learning the global model, and the second stage fine-tunes each participant’s features separately by exploiting participant-specific differences in features. We evaluate our SEMSCNN model on two large public datasets, Benchmark and BETA, and we compare our model to other state-of-the-art models in order to evaluate the effectiveness of our proposed network. Our experimental results indicate that our method effectively improves the accuracy of target recognition and information transfer rate under short-duration stimuli, showing a significant advantage compared to other baseline methods. This provides a broad prospect for the practical application of BCIs in the field of IoT.

Hyperscanning enables simultaneous electroencephalography (EEG) recording from multiple individuals, facilitating collaborative brain activity to reduce individual biases and enhance the reliability of decision-making. The decoding of such collaborative paradigm tasks has traditionally relied solely on simple fusion methods based on each individual brain activity, without incorporating cross-brain coupling information. Inspired by social interaction studies on enhanced inter-brain synchrony in collaborative tasks using hyperscanning, we propose a joint learning framework for dual-brain target detection that integrates a shared space construction module and shared feature-guided module. The shared space construction module incorporates brain-to-brain coupling analysis to identify cross-brain synchrony, and further integrates shared and private features through a multi-head fusion mechanism for joint representation learning in shared feature-guided module. Experimental results show an average 10% improvement in balanced accuracy across 12 participant groups compared to traditional single-brain approaches, with some groups achieving up to a 5% gain over state-of-the-art (SOTA) methods. Notably, higher-performing groups exhibit stronger inter-brain coupling and more synchronized target-related responses. These findings advance the development of collaborative brain-computer interface (BCI) systems for more robust and effective target detection.

Clustering has long been a fundamental problem in machine learning and data mining, with the aim of grouping data samples on the basis of their intrinsic similarity. However, the consensus that different features often exhibit varying levels of discriminative power in clustering model learning is under explored sufficiently in collaboration with the pseudo-label guided unsupervised discriminative analysis. To this end, we propose an Adaptive Feature-Weighted Local-global data Clustering (AFW-LGC) model which is featured by two improvements. First, AFW-LGC takes into account both global separability (between-cluster scatter) and local compactness (within-cluster scatter) whose impacts are mediated by a learnable parameter. Second, the different contributions of features are adaptively learned in AFW-LGC for further discriminative ability enhancement. Both improvements are seamlessly integrated for feature-weighted unsupervised discriminative subspace clustering nature of AFW-LGC. Extensive experiments on eight data sets demonstrate the superior clustering performance of AFW-LGC over some SOTA methods as well as the rationality of our proposed feature importance exploration strategy.

Motor imagery, one of the main brain-computer interface (BCI) paradigms, has been extensively utilized in numerous BCI applications, such as the interaction between disabled people and external devices. Precise decoding, one of the most significant aspects of realizing efficient and stable interaction, has received a great deal of intensive research. However, the current decoding methods based on deep learning are still dominated by single-scale serial convolution, which leads to insufficient extraction of abundant information from motor imagery signals. To overcome such challenges, we propose a new end-to-end convolutional neural network based on multiscale spatial-temporal feature fusion (MSTFNet) for EEG classification of motor imagery. The architecture of MSTFNet consists of four distinct modules: feature enhancement module, multiscale temporal feature extraction module, spatial feature extraction module and feature fusion module, with the latter being further divided into the depthwise separable convolution block and efficient channel attention block. Moreover, we implement a straightforward yet potent data augmentation strategy to bolster the performance of MSTFNet significantly. To validate the performance of MSTFNet, we conduct cross-session experiments and leave-one-subject-out experiments. The cross-session experiment is conducted across two public datasets and one laboratory dataset. On the public datasets of BCI Competition IV 2a and BCI Competition IV 2b, MSTFNet achieves classification accuracies of 83.62% and 89.26%, respectively. On the laboratory dataset, MSTFNet achieves 86.68% classification accuracy. Besides, the leave-one-subject-out experiment is performed on the BCI Competition IV 2a dataset, and MSTFNet achieves 66.31% classification accuracy. These experimental results outperform several state-of-the-art methodologies, indicate the proposed MSTFNet's robust capability in decoding EEG signals associated with motor imagery.

The multi-user motor imagery brain-computer interface (BCI) is a new approach that uses information from multiple users to improve decision-making and social interaction. Although researchers have shown interest in this field, the current decoding methods are limited to basic approaches like linear averaging or feature integration. They ignored accurately assessing the coupling relationship features, which results in incomplete extraction of multi-source information. To overcome these limitations, we propose a new reinforcement learning electroencephalography (EEG) decoding method based on mutual information mechanisms. Our method enhances the extraction of multi-source common information and uses a dynamic feedback model for inter-brain mutual information reward and punishment mechanisms in the reinforcement learning channel selection module. We feed the single-brain and inter-brain signals after channel selection into deep neural networks, which automatically extract coupled features. Finally, based on the attention indices calculated from EEG signals at prefrontal electrode positions, the output is obtained by voting. Our experimental results show that the average accuracy of dual-brain recognition is improved by 16% compared to single-brain mode. Furthermore, ablation experiments demonstrate that the reinforcement learning module and attention voting module enhance accuracy by 14.5% and 15.7%, respectively.

Normalizing flows, a category of probabilistic models famed for their capabilities in modeling complex data distributions, have exhibited remarkable efficacy in unsupervised anomaly detection. This paper explores the potential of normalizing flows in multi-class anomaly detection, wherein the normal data is compounded with multiple classes without providing class labels. Through the integration of vector quantization (VQ), we empower the flow models to distinguish different concepts of multi-class normal data in an unsupervised manner, resulting in a novel flow-based unified method, named VQ-Flow. Specifically, our VQ-Flow leverages hierarchical vector quantization to estimate two relative codebooks: a Conceptual Prototype Codebook (CPC) for concept distinction and its concomitant Concept-Specific Pattern Codebook (CSPC) to capture concept-specific normal patterns. The flow models in VQ-Flow are conditioned on the concept-specific patterns captured in CSPC, capable of modeling specific normal patterns associated with different concepts. Moreover, CPC further enables our VQ-Flow for concept-aware distribution modeling, faithfully mimicking the intricate multi-class normal distribution through a mixed Gaussian distribution reparametrized on the conceptual prototypes. Through the introduction of vector quantization, the proposed VQ-Flow advances the state-of-the-art in multi-class anomaly detection within a unified training scheme, yielding the Det./Loc. AUROC of 99.5%/98.3% on MVTec AD.

Perceiving temporal events and discriminating their modality types in audible videos, which is also called audio-visual video parsing (AVVP), is becoming a research hotspot in multimodal video understanding. The AVVP task generally follows weakly supervised learning settings, since only video-level labels are provided. Most existing works usually generate modalitywise pseudo labels (PLs) first and then learn to parse audio or visual events from the audible videos. However, this paradigm inevitably results in two defects: 1) the generated PLs for each modality are not fully reliable, which may confuse models if they are adopted as supervision signals for discriminating modalities; and 2) the absence of temporal annotations increases the ambiguities in localizing foregrounds in videos, furtherly causing models prone to being disturbed by noisy labels. To tackle these problems, we propose a novel AVVP framework termed noise-resistant event parsing (NREP), which introduces evidential deep learning (EDL) to overcome the limitations of noisy pseudo supervision. Specifically, our NREP framework consists of three key components: 1) modalitywise evidential learning (MEL) that discriminates the modality-class dependency; 2) temporalwise evidential learning (TEL) that explores meaningful foregrounds; and 3) foreground-background consistency learning (FBCL) for collaborating two evidential learning branches above. Through perceiving meaningful video content and learning evidence for modality dependencies, our method suppresses the disturbance of noise in generated PLs thus achieving remarkable performance with different PL generation strategies. We evaluate our NREP method on two AVVP benchmark datasets and demonstrate it consistently to establish new state-of-the-art. Our implementation codes are available at https://github.com/CFM-MSG/NREP.

Multimodal sarcasm analysis is one of the most challenging research branch of the sentiment analysis area, due to the presence of cross-modality incongruity. However, existing works mainly attend to the coarse-grained incongruity analysis, and totally ignore the sentiment semantic coupling issue. This indeed limits the discriminate capability and robustness of the sarcasm analysis model. In order to address the above issue, we propose a novel Fine-grained Semantic Disentanglement Network (FSDN). Specifically, the intra-modality semantic disentanglement is performed to investigate the more intrinsic semantic cues of the same modality. Additionally, the inter-modality semantic disentanglement is leveraged to simultaneously facilitate the common and intrinsic semantic cues across modalities. Furthermore, the dual-spatial semantic interaction block is presented to explore the long-range cross-spatial semantic context between the obtained verbal and non-verbal semantic space with the global view. The above semantic disentanglement processes with both local and global views significantly unleash much more robustness even for the sarcasm case consisting of multiple semantic message. Various experiments indicate that the FSDN can receive state-of-the-art or competitive performance.

Small samples and significant inter-subject variability are the two main challenges in current electroencephalogram (EEG) based Motor Imagery (MI) Brain-Computer Interface (BCI) decoding methods. To overcome these challenges, we proposed an EEG-based decoding method for MI intentions in mixed-subject settings with adversarial disentanglement, which utilize the EEG decoding focusing on MI related task information and decrease the inference of inter-subject variability under mixed-subject setting. The method includes three main modules: data augmentation module, dual-label training module, disentanglement training module. It first uses a mixed-subject settings approach, which involves shuffling the data from all subjects to augment the data for a single model. We then create a dual-label dataset using motor imagery labels and identity labels. Finally, a disentanglement training strategy is employed to optimize the negative entropy loss, measuring the inter-subject variability. Our experiment results show that our method achieves higher accuracy compared to traditional one-to-one model training methods and lower variance with the mixed-subject settings. It has achieved a $\mathbf{7 5. 9 3 \%}$ average classification accuracy across four classes on the BCIC-IV-2a dataset with the best classification accuracy reaches $\mathbf{9 0. 2 8 \%}$, indicating that our model has the capability to disentangle identity-related information during the feature extraction and has more stable performance across different subjects.

We developed a new tensor-based technique for connectivity analysis and applied it to the EEG data of 10 professional eSports players and 10 novices (control group) collected during 4 different oddball paradigms. The proposed technique utilizes a low-rank approximation of the Granger Causal autoregression with a single temporal filter, thus reducing the number of parameters and improving the convergence rate. Results showed that the temporal filter converges to a Morlet wavelet and establishes a strong connection between channels in the parietal cortex and sustainable negative connectivity between the frontal and occipital cortex, which corresponds to visual search potentials. Professional players also had significantly more prominent and faster ERP responses, which is consistent with the previous research.

Tensor decomposition of convolutional and fully-connected layers is an effective way to reduce parameters and FLOP in neural networks. Due to memory and power consumption limitations of mobile or embedded devices, the quantization step is usually necessary when pre-trained models are deployed. A conventional post-training quantization approach applied to networks with decomposed weights yields a drop in accuracy. This motivated us to develop an algorithm that finds tensor approximation directly with quantized factors and thus benefit from both compression techniques while keeping the prediction quality of the model. Namely, we propose to use Alternating Direction Method of Multipliers (ADMM) for Canonical Polyadic (CP) decomposition with factors whose elements lie on a specified quantization grid. We compress neural network weights with a devised algorithm and evaluate it’s prediction quality and performance. We compare our approach to state-of-the-art post-training quantization methods and demonstrate competitive results and high flexibility in achiving a desirable quality-performance tradeoff.

Event-related potentials (ERPs) reflect neurophysiological changes of the brain in response to external events and their associated underlying complex spatiotemporal feature information is governed by ongoing oscillatory activity within the brain. Deep learning methods have been increasingly adopted for ERP-based brain-computer interfaces (BCIs) due to their excellent feature representation abilities, which allow for deep analysis of oscillatory activity within the brain. Features with higher spatiotemporal frequencies usually represent detailed and localized information, while features with lower spatiotemporal frequencies usually represent global structures. Mining EEG features from multiple spatiotemporal frequencies is conducive to obtaining more discriminative information. A multiscale feature fusion octave convolution neural network (MOCNN) is proposed in this article. MOCNN divides the ERP signals into high-, medium- and low-frequency components corresponding to different resolutions and processes them in different branches. By adding mid- and low-frequency components, the feature information used by MOCNN can be enriched, and the required amount of calculations can be reduced. After successive feature mapping using temporal and spatial convolutions, MOCNN realizes interactive learning among different components through the exchange of feature information among branches. Classification is accomplished by feeding the fused deep spatiotemporal features from various components into a fully connected layer. The results, obtained on two public datasets and a self-collected ERP dataset, show that MOCNN can achieve state-of-the-art ERP classification performance. In this study, the generalized concept of octave convolution is introduced into the field of ERP-BCI research, which allows effective spatiotemporal features to be extracted from multiscale networks through branch width optimization and information interaction at various scales.

In this article, we study the challenging cross-modal image retrieval task,Composed Query-Based Image Retrieval (CQBIR), in which the query is not a single text query but a composed query, i.e., a reference image, and a modification text. Compared with the conventional cross-modal image-text retrieval task, the CQBIR is more challenging as it requires properly preserving and modifying the specific image region according to the multi-level semantic information learned from the multi-modal query. Most recent works focus on extracting preserved and modified information and compositing it into a unified representation. However, we observe that the preserved regions learned by the existing methods contain redundant modified information, inevitably degrading the overall retrieval performance. To this end, we propose a novel method termedCross-ModalAttentionPreservation (CMAP). Specifically, we first leverage the cross-level interaction to fully account for multi-granular semantic information, which aims to supplement the high-level semantics for effective image retrieval. Furthermore, different from conventional contrastive learning, our method introduces self-contrastive learning into learning preserved information, to prevent the model from confusing the attention for the preserved part with the modified part. Extensive experiments on three widely used CQBIR datasets, i.e., FashionIQ, Shoes, and Fashion200k, demonstrate that our proposed CMAP method significantly outperforms the current state-of-the-art methods on all the datasets. The anonymous implementation code of our CMAP method is available at https://github.com/CFM-MSG/Code_CMAP.

Due to the weak and nonstationary properties, electroencephalogram (EEG) data present significant individual differences. To align data distributions of different subjects, transfer learning showed promising performance in cross-subject EEG emotion recognition. However, most of the existing models sequentially learned the domain-invariant features and estimated the target domain label information. Such a two-stage strategy breaks the inner connections of both processes, inevitably causing the suboptimality. In this article, we propose a joint EEG feature transfer and semisupervised cross-subject emotion recognition model in which the shared subspace projection matrix and target label are jointly optimized toward the optimum. Extensive experiments are conducted on SEED-IV and SEED, and the results show that the emotion recognition performance is significantly enhanced by the joint learning mode and the spatial-frequency activation patterns of critical EEG frequency bands and brain regions in cross-subject emotion expression are quantitatively identified by analyzing the learned shared subspace.

In this article, sparse nonnegative matrix factorization (SNMF) is formulated as a mixed-integer bicriteria optimization problem for minimizing matrix factorization errors and maximizing factorized matrix sparsity based on an exact binary representation of$l_{0}$matrix norm. The binary constraints of the problem are then equivalently replaced with bilinear constraints to convert the problem to a biconvex problem. The reformulated biconvex problem is finally solved by using a two-timescale duplex neurodynamic approach consisting of two recurrent neural networks (RNNs) operating collaboratively at two timescales. A Gaussian score (GS) is defined as to integrate the bicriteria of factorization errors and sparsity of resulting matrices. The performance of the proposed neurodynamic approach is substantiated in terms of low factorization errors, high sparsity, and high GS on four benchmark datasets.

The steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) has received extensive attention in research for the less training time, excellent recognition performance, and high information translate rate. At present, most of the powerful SSVEPs detection methods are similarity measurements based on spatial filters and Pearson's correlation coefficient. Among them, the task-related component analysis (TRCA)-based method and its variant, the ensemble TRCA (eTRCA)-based method, are two methods with high performance and great potential. However, they have a defect, that is, they can only suppress certain kinds of noise, but not more general noises. To solve this problem, a novel time filter was designed by introducing the temporally local weighting into the objective function of the TRCA-based method and using the singular value decomposition. Based on this, the time filter and (e)TRCA-based similarity measurement methods were proposed, which can perform a robust similarity measure to enhance the detection ability of SSVEPs. A benchmark dataset recorded from 35 subjects was used to evaluate the proposed methods and compare them with the (e)TRCA-based methods. The results indicated that the proposed methods performed significantly better than the (e)TRCA-based methods. Therefore, it is believed that the proposed time filter and the similarity measurement methods have promising potential for SSVEPs detection.

We present a novel procedure for optimization based on the combination of efficient quantized tensor train representation and a generalized maximum matrix volume principle.We demonstrate the applicability of the new Tensor Train Optimizer (TTOpt) method for various tasks, ranging from minimization of multidimensional functions to reinforcement learning.Our algorithm compares favorably to popular gradient-free methods and outperforms them by the number of function evaluations or execution time, often by a significant margin.

Though Electroencephalogram (EEG) could objectively reflect emotional states of our human beings, its weak, non-stationary, and low signal-to-noise properties easily cause the individual differences. To enhance the universality of affective brain-computer interface systems, transfer learning has been widely used to alleviate the data distribution discrepancies among subjects. However, most of existing approaches focused mainly on the domain-invariant feature learning, which is not unified together with the recognition process. In this paper, we propose a joint feature adaptation and graph adaptive label propagation model (JAGP) for cross-subject emotion recognition from EEG signals, which seamlessly unifies the three components of domain-invariant feature learning, emotional state estimation and optimal graph learning together into a single objective. We conduct extensive experiments on two benchmark SEED_IV and SEED_V data sets and the results reveal that 1) the recognition performance is greatly improved, indicating the effectiveness of the triple unification mode; 2) the emotion metric of EEG samples are gradually optimized during model training, showing the necessity of optimal graph learning, and 3) the projection matrix-induced feature importance is obtained based on which the critical frequency bands and brain regions corresponding to subject-invariant features can be automatically identified, demonstrating the superiority of the learned shared subspace.

Schizophrenia seriously affects the quality of life. To date, both simple (e.g., linear discriminant analysis) and complex (e.g., deep neural network) machine-learning methods have been utilized to identify schizophrenia based on functional connectivity features. The existing simple methods need two separate steps (i.e., feature extraction and classification) to achieve the identification, which disables simultaneous tuning for the best feature extraction and classifier training. The complex methods integrate two steps and can be simultaneously tuned to achieve optimal performance, but these methods require a much larger amount of data for model training. To overcome the aforementioned drawbacks, we proposed a multikernel capsule network (MKCapsnet), which was developed by considering the brain anatomical structure. Kernels were set to match partition sizes of the brain anatomical structure in order to capture interregional connectivities at the varying scales. With the inspiration of the widely used dropout strategy in deep learning, we developed capsule dropout in the capsule layer to prevent overfitting of the model. The comparison results showed that the proposed method outperformed the state-of-the-art methods. Besides, we compared performances using different parameters and illustrated the routing process to reveal characteristics of the proposed method. MKCapsnet is promising for schizophrenia identification. Our study first utilized the capsule neural network for analyzing functional connectivity of magnetic resonance imaging (MRI) and proposed a novel multikernel capsule structure with the consideration of brain anatomical parcellation, which could be a new way to reveal brain mechanisms. In addition, we provided useful information in the parameter setting, which is informative for further studies using a capsule network for other neurophysiological signal classification.

Deep image prior (DIP), which uses a deep convolutional network (ConvNet) structure as an image prior, has attracted wide attention in computer vision and machine learning. DIP empirically shows the effectiveness of the ConvNet structures for various image restoration applications. However, why the DIP works so well is still unknown. In addition, the reason why the convolution operation is useful in image reconstruction, or image enhancement is not very clear. This study tackles this ambiguity of ConvNet/DIP by proposing an interpretable approach that divides the convolution into "delay embedding" and "transformation" (i.e., encoder-decoder). Our approach is a simple, but essential, image/tensor modeling method that is closely related to self-similarity. The proposed method is called manifold modeling in embedded space (MMES) since it is implemented using a denoising autoencoder in combination with a multiway delay-embedding transform. In spite of its simplicity, MMES can obtain quite similar results to DIP on image/tensor completion, super-resolution, deconvolution, and denoising. In addition, MMES is proven to be competitive with DIP, as shown in our experiments. These results can also facilitate interpretation/characterization of DIP from the perspective of a "low-dimensional patch-manifold prior."

Accurate electroencephalogram (EEG) pattern decoding for specific mental tasks is one of the key steps for the development of brain-computer interface (BCI), which is quite challenging due to the considerably low signal-to-noise ratio of EEG collected at the brain scalp. Machine learning provides a promising technique to optimize EEG patterns toward better decoding accuracy. However, existing algorithms do not effectively explore the underlying data structure capturing the true EEG sample distribution and, hence, can only yield a suboptimal decoding accuracy. To uncover the intrinsic distribution structure of EEG data, we propose a clustering-based multitask feature learning algorithm for improved EEG pattern decoding. Specifically, we perform affinity propagation-based clustering to explore the subclasses (i.e., clusters) in each of the original classes and then assign each subclass a unique label based on a one-versus-all encoding strategy. With the encoded label matrix, we devise a novel multitask learning algorithm by exploiting the subclass relationship to jointly optimize the EEG pattern features from the uncovered subclasses. We then train a linear support vector machine with the optimized features for EEG pattern decoding. Extensive experimental studies are conducted on three EEG data sets to validate the effectiveness of our algorithm in comparison with other state-of-the-art approaches. The improved experimental results demonstrate the outstanding superiority of our algorithm, suggesting its prominent performance for EEG pattern decoding in BCI applications.

Jiajia Tang, Kang Li, Xuanyu Jin, Andrzej Cichocki, Qibin Zhao, Wanzeng Kong. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

This paper proposes a constrained canonical polyadic (CP) tensor decomposition method with low-rank factor matrices. In this way, we allow the CP decomposition with high rank while keeping the number of the model parameters small. First, we propose an algorithm to decompose the tensors into factor matrices of given ranks. Second, we propose an algorithm which can determine the ranks of the factor matrices automatically, such that the fitting error is bounded by a user- selected constant. The algorithms are verified on the decomposition of a tensor of the MNIST hand-written image dataset.

The common spatial patterns (CSP) algorithm is one of the most frequently used and effective spatial filtering methods for extracting relevant features for use in motor imagery brain-computer interfaces (MI-BCIs). However, the inherent defect of the traditional CSP algorithm is that it is highly sensitive to potential outliers, which adversely affects its performance in practical applications. In this work, we propose a novel feature optimization and outlier detection method for the CSP algorithm. Specifically, we use the minimum covariance determinant (MCD) to detect and remove outliers in the dataset, then we use the Fisher score to evaluate and select features. In addition, in order to prevent the emergence of new outliers, we propose an iterative minimum covariance determinant (IMCD) algorithm. We evaluate our proposed algorithm in terms of iteration times, classification accuracy and feature distribution using two BCI competition datasets. The experimental results show that the average classification performance of our proposed method is 12% and 22.9% higher than that of the traditional CSP method in two datasets ([Formula: see text]), and our proposed method obtains better performance in comparison with other competing methods. The results show that our method improves the performance of MI-BCI systems.

Tactile P300 brain-computer interface (BCI) generally has a worse accuracy and information transfer rate (ITR) than the visual-based BCI. It may be due to the fact that human beings have a relatively poor tactile perception. This study investigated the influence of visual attention on the performance of a tactile P300 BCI. We designed our paradigms based on a novel cheeks-stim paradigm which attached the stimulators on the subject's cheeks. Two paradigms were designed as follows: a paradigm with no visual attention and another paradigm with visual attention to the target position. Eleven subjects were invited to perform the two paradigms. We also recorded and analyzed the eyeball movement data during the paradigm with visual attention to explore whether the eyeball movement would have an effect on the BCI classification. The average online accuracy was 89.09% for the paradigm with visual attention, which was significantly higher than that of the paradigm with no visual attention (70.45%). Significant difference in ITR was also found between the two paradigms ([Formula: see text]). The results demonstrated that visual attention was an effective method to improve the performance of tactile P300 BCI. Our findings suggested that it may be feasible to complete an efficient tactile BCI system by adding visual attention.

Motor imagery (MI) based brain-computer interfaces help patients with movement disorders to regain the ability to control external devices. Common spatial pattern (CSP) is a popular algorithm for feature extraction in decoding MI tasks. However, due to noise and nonstationarity in electroencephalography (EEG), it is not optimal to combine the corresponding features obtained from the traditional CSP algorithm. In this paper, we designed a novel CSP feature selection framework that combines the filter method and the wrapper method. We first evaluated the importance of every CSP feature by the infinite latent feature selection method. Meanwhile, we calculated Wasserstein distance between feature distributions of the same feature under different tasks. Then, we redefined the importance of every CSP feature based on two indicators mentioned above, which eliminates half of CSP features to create a new CSP feature subspace according to the new importance indicator. At last, we designed the improved binary gravitational search algorithm (IBGSA) by rebuilding its transfer function and applied IBGSA on the new CSP feature subspace to find the optimal feature set. To validate the proposed method, we conducted experiments on three public BCI datasets and performed a numerical analysis of the proposed algorithm for MI classification. The accuracies were comparable to those reported in related studies and the presented model outperformed other methods in literature on the same underlying data.

The common spatial pattern (CSP) algorithm is a well-recognized spatial filtering method for feature extraction in motor imagery (MI)-based brain-computer interfaces (BCIs). However, due to the influence of nonstationary in electroencephalography (EEG) and inherent defects of the CSP objective function, the spatial filters, and their corresponding features are not necessarily optimal in the feature space used within CSP. In this work, we design a new feature selection method to address this issue by selecting features based on an improved objective function. Especially, improvements are made in suppressing outliers and discovering features with larger interclass distances. Moreover, a fusion algorithm based on the Dempster-Shafer theory is proposed, which takes into consideration the distribution of features. With two competition data sets, we first evaluate the performance of the improved objective functions in terms of classification accuracy, feature distribution, and embeddability. Then, a comparison with other feature selection methods is carried out in both accuracy and computational time. Experimental results show that the proposed methods consume less additional computational cost and result in a significant increase in the performance of MI-based BCI systems.

This work proposes a novel approach for multiple time series forecasting. At first, multi-way delay embedding transform (MDT) is employed to represent time series as low-rank block Hankel tensors (BHT). Then, the higher-order tensors are projected to compressed core tensors by applying Tucker decomposition. At the same time, the generalized tensor Autoregressive Integrated Moving Average (ARIMA) is explicitly used on consecutive core tensors to predict future samples. In this manner, the proposed approach tactically incorporates the unique advantages of MDT tensorization (to exploit mutual correlations) and tensor ARIMA coupled with low-rank Tucker decomposition into a unified framework. This framework exploits the low-rank structure of block Hankel tensors in the embedded space and captures the intrinsic correlations among multiple TS, which thus can improve the forecasting results, especially for multiple short time series. Experiments conducted on three public datasets and two industrial datasets verify that the proposed BHT-ARIMA effectively improves forecasting accuracy and reduces computational cost compared with the state-of-the-art methods.

Measuring the sleep quality is important or even crucial for people who are engaged in dangerous jobs such as the high-speed train drivers. Since the scalp EEG data are generated by the neural activities of the brain cortex, it is collected from subjects with different hours of sleep time (4 hours, 6 hours and 8 hours) to conduct sleep quality evaluation. To suppress the cross-subject variances of EEG data, in this paper, we propose a joint feature auto-weighting and semi-supervised classification model, termed GRLSR, which is formulated by introducing an auto-weighting variable into the least square regression to adaptively and quantitatively measure the importance of each dimension of the feature. Once the model is solved, besides the measurement results, we can use the auto-weighting variable to 1) analyze the importance of each frequency band in sleep quality expression and 2) identify the capacity of different channels connecting to the sleep effect. Therefore, the proposed GRLSR is a pure data-driven computing model for EEG-based cross-subject sleep quality evaluation. Experimental results show its effectiveness.

Weighted canonical polyadic (CP) tensor decomposition appears in a wide range of applications. A typical situation where the weighted decomposition is needed is when some tensor elements are unknown, and the task is to fill in the missing elements under the assumption that the tensor admits a low-rank model. The traditional methods for large-scale decomposition tasks are based on alternating least-squares methods or gradient methods. Second-order methods might have significantly better convergence, but so far they were used only on small tensors. The proposed Krylov-Levenberg-Marquardt method enables to do second-order-based iterations even in large-scale decomposition problems, with or without weights. We show in simulations that the proposed technique can outperform existing state-of-the-art algorithms in some scenarios.

We propose a simple interpolation-based method for the efficient approximation of gradients in neural ODE models. We compare it with reverse dynamic method (known in literature as “adjoint method”) to train neural ODEs on classification, density estimation and inference approximation tasks. We also propose a theoretical justification of our approach using logarithmic norm formalism. As a result, our method allows faster model training than the reverse dynamic method what was confirmed and validated by extensive numerical experiments for several standard benchmarks.

Neurons selective for faces exist in humans and monkeys. However, characteristics of face cell receptive fields are poorly understood. In this theoretical study, we explore the effects of complexity, defined as algorithmic information (Kolmogorov complexity) and logical depth, on possible ways that face cells may be organized. We use tensor decompositions to decompose faces into a set of components, called tensorfaces, and their associated weights, which can be interpreted as model face cells and their firing rates. These tensorfaces form a high-dimensional representation space in which each tensorface forms an axis of the space. A distinctive feature of the decomposition algorithm is the ability to specify tensorface complexity. We found that low-complexity tensorfaces have blob-like appearances crudely approximating faces, while high-complexity tensorfaces appear clearly face-like. Low-complexity tensorfaces require a larger population to reach a criterion face reconstruction error than medium- or high-complexity tensorfaces, and thus are inefficient by that criterion. Low-complexity tensorfaces, however, generalize better when representing statistically novel faces, which are faces falling beyond the distribution of face description parameters found in the tensorface training set. The degree to which face representations are parts based or global forms a continuum as a function of tensorface complexity, with low and medium tensorfaces being more parts based. Given the computational load imposed in creating high-complexity face cells (in the form of algorithmic information and logical depth) and in the absence of a compelling advantage to using high-complexity cells, we suggest face representations consist of a mixture of low- and medium-complexity face cells.

In this paper, the problem of time series reconstruction in a multiway delay embedded space using Tensor Train decomposition is addressed. A new algorithm has been developed in which an incomplete signal is first transformed to a Hankel matrix and in the next step to a higher order tensor using extended Multiway Delay embedded Transform. Then, the resulting higher order tensor is completed using low rank Tensor Train decomposition. Comparing to previous Hankelization approaches, in the proposed approach, blocks of elements are used for Hankelization instead of individual elements, which results in producing a higher order tensor. Simulation results confirm the effectiveness and high performance of the proposed completion approach. Although in this paper we focus on single time series, our method can be straightforwardly extended to reconstruction of multivariate time series, color images and videos.

The canonical polyadic decomposition (CPD) is a convenient and intuitive tool for tensor factorization; however, for higher order tensors, it often exhibits high computational cost and permutation of tensor entries, and these undesirable effects grow exponentially with the tensor order. Prior compression of tensor in-hand can reduce the computational cost of CPD, but this is only applicable when the rank R of the decomposition does not exceed the tensor dimensions. To resolve these issues, we present a novel method for CPD of higher order tensors, which rests upon a simple tensor network of representative inter-connected core tensors of orders not higher than 3. For rigor, we develop an exact conversion scheme from the core tensors to the factor matrices in CPD and an iterative algorithm of low complexity to estimate these factor matrices for the inexact case. Comprehensive simulations over a variety of scenarios support the proposed approach.

Decompositions of tensors into factor matrices, which interact through a core tensor, have found numerous applications in signal processing and machine learning. A more general tensor model that represents data as an ordered network of subtensors of order-2 or order-3 has, so far, not been widely considered in these fields, although this so-called tensor network (TN) decomposition has been long studied in quantum physics and scientific computing. In this article, we present novel algorithms and applications of TN decompositions, with a particular focus on the tensor train (TT) decomposition and its variants. The novel algorithms developed for the TT decomposition update, in an alternating way, one or several core tensors at each iteration and exhibit enhanced mathematical tractability and scalability for large-scale data tensors. For rigor, the cases of the given ranks, given approximation error, and the given error bound are all considered. The proposed algorithms provide well-balanced TT-decompositions and are tested in the classic paradigms of blind source separation from a single mixture, denoising, and feature extraction, achieving superior performance over the widely used truncated algorithms for TT decomposition.

Non-negative matrix factorization (NMF) is an efficient model in learning parts-based data representation. Since the local geometrical structure can be effectively modeled by a nearest neighbor graph, the graph regularized NMF (GNMF) was proposed to make the learned representation more faithfully and better characterize the intrinsic structure of data. However, GNMF shares a similar paradigm with most of existing graph-based learning models which perform learning tasks on a fixed input graph. In this paper, we propose a new Flexible NMF model with adaptively learned Graph regularization (FNMFG) in which the graph is jointly learned with simultaneous performing the matrix factorization. An efficient iterative method with guaranteed convergence and relative low complexity is developed to optimize the FNMFG objective. Experiments compare FNMFG method with state-of-the-art algorithms and demonstrate its improved performance.

As one of the matrix factorization models, concept factorization (CF) achieved promising performance in learning data representation in both original feature space and reproducible kernel Hilbert space (RKHS). Based on the consensuses that 1) learning performance of models can be enhanced by exploiting the geometrical structure of data and 2) jointly performing structured graph learning and clustering can avoid the suboptimal solutions caused by the two-stage strategy in graph-based learning, we developed a new CF model with self-expression. Our model has a combined coefficient matrix which is able to learn more efficiently. In other words, we propose a CF-based joint structured graph learning and clustering model (JSGCF). A new efficient iterative method is developed to optimize the JSGCF objective function. Experimental results on representative data sets demonstrate the effectiveness of our new JSGCF algorithm.

The central task in graph-based unsupervised feature selection (GUFS) depends on two folds, one is to accurately characterize the geometrical structure of the original feature space with a graph and the other is to make the selected features well preserve such intrinsic structure. Currently, most of the existing GUFS methods use a two-stage strategy which constructs graph first and then perform feature selection on this fixed graph. Since the performance of feature selection severely depends on the quality of graph, the selection results will be unsatisfactory if the given graph is of low-quality. To this end, we propose a joint graph learning and unsupervised feature selection (JGUFS) model in which the graph can be adjusted to adapt the feature selection process. The JGUFS objective function is optimized by an efficient iterative algorithm whose convergence and complexity are analyzed in detail. Experimental results on representative benchmark data sets demonstrate the improved performance of JGUFS in comparison with state-of-the-art methods and therefore we conclude that it is promising of allowing the feature selection process to change the data graph.

Tensor train decomposition is a powerful representation for high-order tensors, which has been successfully applied to various machine learning tasks in recent years. In this paper, we study a more generalized tensor decomposition with a ring-structured network by employing circular multilinear products over a sequence of lower-order core tensors. We refer to such tensor decomposition as tensor ring (TR) representation. Our goal is to introduce learning algorithms including sequential singular value decompositions and blockwise alternating least squares with adaptive tensor ranks. Experimental results demonstrate the effectiveness of the TR model and the learning algorithms. In particular, we show that the structure information and high-order correlations within a 2D image can be captured efficiently by employing an appropriate tensorization and TR decomposition.

Event-related potentials (ERPs) especially P300 are popular effective features for brain-computer interface (BCI) systems based on electroencephalography (EEG). Traditional ERP-based BCI systems may perform poorly for small training samples, i.e. the undersampling problem. In this study, the ERP classification problem was investigated, in particular, the ERP classification in the high-dimensional setting with the number of features larger than the number of samples was studied. A flexible group sparse discriminative analysis algorithm based on Moreau-Yosida regularization was proposed for alleviating the undersampling problem. An optimization problem with the group sparse criterion was presented, and the optimal solution was proposed by using the regularized optimal scoring method. During the alternating iteration procedure, the feature selection and classification were performed simultaneously. Two P300-based BCI datasets were used to evaluate our proposed new method and compare it with existing standard methods. The experimental results indicated that the features extracted via our proposed method are efficient and provide an overall better P300 classification accuracy compared with several state-of-the-art methods.

Canonical polyadic (CP) tensor decomposition is an important task in many applications. Many times, the true tensor rank is not known, or noise is present, and in such situations, different existing CP decomposition algorithms provide very different results. In this letter, we introduce a notion of sensitivity of CP decomposition and suggest to use it as a side criterion (besides the fitting error) to evaluate different CP decomposition results. Next, we propose a novel variant of a Krylov-Levenberg-Marquardt CP decomposition algorithm which may serve for CP decomposition with a constraint on the sensitivity. In simulations, we decompose order-4 tensors that come from convolutional neural networks. We show that it is useful to combine the CP decomposition algorithms with an error-preserving correction.

Common spatial pattern (CSP)-based spatial filtering has been most popularly applied to electroencephalogram (EEG) feature extraction for motor imagery (MI) classification in brain-computer interface (BCI) application. The effectiveness of CSP is highly affected by the frequency band and time window of EEG segments. Although numerous algorithms have been designed to optimize the spectral bands of CSP, most of them selected the time window in a heuristic way. This is likely to result in a suboptimal feature extraction since the time period when the brain responses to the mental tasks occurs may not be accurately detected. In this paper, we propose a novel algorithm, namely temporally constrained sparse group spatial pattern (TSGSP), for the simultaneous optimization of filter bands and time window within CSP to further boost classification accuracy of MI EEG. Specifically, spectrum-specific signals are first derived by bandpass filtering from raw EEG data at a set of overlapping filter bands. Each of the spectrum-specific signals is further segmented into multiple subseries using sliding window approach. We then devise a joint sparse optimization of filter bands and time windows with temporal smoothness constraint to extract robust CSP features under a multitask learning framework. A linear support vector machine classifier is trained on the optimized EEG features to accurately identify the MI tasks. An experimental study is implemented on three public EEG datasets (BCI Competition III dataset IIIa, BCI Competition IV datasets IIa, and BCI Competition IV dataset IIb) to validate the effectiveness of TSGSP in comparison to several other competing methods. Superior classification performance (averaged accuracies are 88.5%, 83.3%, and 84.3% for the three datasets, respectively) based on the experimental results confirms that the proposed algorithm is a promising candidate for performance improvement of MI-based BCIs.

In this paper, we present a multimodal emotion recognition framework called EmotionMeter that combines brain waves and eye movements. To increase the feasibility and wearability of EmotionMeter in real-world applications, we design a six-electrode placement above the ears to collect electroencephalography (EEG) signals. We combine EEG and eye movements for integrating the internal cognitive states and external subconscious behaviors of users to improve the recognition accuracy of EmotionMeter. The experimental results demonstrate that modality fusion with multimodal deep neural networks can significantly enhance the performance compared with a single modality, and the best mean accuracy of 85.11% is achieved for four emotions (happy, sad, fear, and neutral). We explore the complementary characteristics of EEG and eye movements for their representational capacities and identify that EEG has the advantage of classifying happy emotion, whereas eye movements outperform EEG in recognizing fear emotion. To investigate the stability of EmotionMeter over time, each subject performs the experiments three times on different days. EmotionMeter obtains a mean recognition accuracy of 72.39% across sessions with the six-electrode EEG and eye movement features. These experimental results demonstrate the effectiveness of EmotionMeter within and between sessions.

A potential limitation of a motor imagery (MI) based brain-computer interface (BCI) is that it usually requires a relatively long time to record sufficient electroencephalogram (EEG) data for robust classifier training. The calibration burden during data acquisition phase will most probably cause a subject to be reluctant to use a BCI system. To alleviate this issue, we propose a novel sparse group representation model (SGRM) for improving the efficiency of MI-based BCI by exploiting the intersubject information. Specifically, preceded by feature extraction using common spatial pattern, a composite dictionary matrix is constructed with training samples from both the target subject and other subjects. By explicitly exploiting within-group sparse and group-wise sparse constraints, the most compact representation of a test sample of the target subject is then estimated as a linear combination of columns in the dictionary matrix. Classification is implemented by calculating the class-specific representation residual based on the significant training samples corresponding to the nonzero representation coefficients. Accordingly, the proposed SGRM method effectively reduces the required training samples from the target subject due to auxiliary data available from other subjects. With two public EEG data sets, extensive experimental comparisons are carried out between SGRM and other state-of-the-art approaches. Superior classification performance of our method using 40 trials of the target subject for model calibration (Averaged accuracy = 78.2%, Kappa = 0.57 and Averaged accuracy = 77.7%, Kappa = 0.55 for the two data sets, respectively) indicates its promising potential for improving the practicality of MI-based BCI.

EEG-based hyper-scanning refers to two or more subjects engaged in a task together or performing the same action together while neurophysiological signals are simultaneously recorded from them. This is one of the manners for investigating between-subject neural activities involved in social interactions. Emotion perception plays an important role in human social interactions. Interaction and emotional state influence each other. In this study, we aim to investigate how between-subject interaction modulates emotion perception based on event related potentials (ERPs), connectivity analysis and classification analysis. We found that there are distinct differences appearing between paired subjects who performed the task together, which are early ERP components (N250 and N400), late ERP components (P1500 and N1500), and the greater amplitude in N250 for the seconding responding subject compared to the first one. In the exploration of connectivity using phase locking value (PLV), we found that there are significant differences among different frequency bands for each subject under positive and negative stimuli and the significant difference of hyper-connectivity existed in the gamma frequency band between positive and negative stimulus trials. In the classification analysis, we compared the hyper-features for two individual subjects separately, the performance was improved when hyper-features of the PLV was employed compared to the features of power spectrum density.

A novel method for common and individual feature analysis from exceedingly large-scale data is proposed, in order to ensure the tractability of both the computation and storage and thus mitigate the curse of dimensionality, a major bottleneck in modern data science. This is achieved by making use of the inherent redundancy in so-called multi-block data structures, which represent multiple observations of the same phenomenon taken at different times, angles or recording conditions. Upon providing an intrinsic link between the properties of the outer vector product and extracted features in tensor decompositions (TDs), the proposed common and individual information extraction from multi-block data is performed through constraints which impose physical meaning on otherwise unconstrained factorisation approaches. This is shown to dramatically reduce the dimensionality of search spaces in subsequent classification procedures and to yield greatly enhanced accuracy. Simulations on a multi-class classification task of large-scale extraction of individual features from a collection of partially related real-world images demonstrate the advantages of the “blessing of dimensionality” associated with TDs.

Canonical polyadic decomposition (CPD), also known as PARAFAC, is a representation of a given tensor as a sum of rank-one tensors. Traditional method for accomplishing CPD is the alternating least squares (ALS) algorithm. This algorithm is easy to implement with very low computational complexity per iteration. A disadvantage is that in difficult scenarios, where factor matrices in the decomposition contain nearly collinear columns, the number of iterations needed to achieve convergence might be very large. In this paper, we propose a modification of the algorithm which has similar complexity per iteration as ALS, but in difficult scenarios it needs a significantly lower number of iterations.

Decomposition of symmetric tensors has found numerous applications in blind sources separation, blind identification, clustering, and analysis of social interactions. In this paper, we consider fourth order symmetric tensors, and its symmetric tensor decomposition. By imposing unit-length constraints on components, we resort the optimisation problem to the constrained eigenvalue decomposition in which eigenvectors are represented in form of rank-1 matrices. To this end, we develop an augmented Lagrangian algorithm with simple update rules. The proposed algorithm has been compared with the Trust-Region solver over manifold, and achieved higher success rates. The algorithm is also validated for blind identification, and achieves more stable results than the ALSCAF algorithm.

Physiological signals are often organized in the form of multiple dimensions (e.g., channel, time, task, and 3-D voxel), so it is better to preserve original organization structure when processing. Unlike vector-based methods that destroy data structure, canonical polyadic decomposition (CPD) aims to process physiological signals in the form of multiway array, which considers relationships between dimensions and preserves structure information contained by the physiological signal. Nowadays, CPD is utilized as an unsupervised method for feature extraction in a classification problem. After that, a classifier, such as support vector machine, is required to classify those features. In this manner, classification task is achieved in two isolated steps. We proposed supervised CPD by directly incorporating auxiliary label information during decomposition, by which a classification task can be achieved without an extra step of classifier training. The proposed method merges the decomposition and classifier learning together, so it reduces procedure of classification task compared with that of respective decomposition and classification. In order to evaluate the performance of the proposed method, three different kinds of signals, synthetic signal, EEG signal, and MEG signal, were used. The results based on evaluations of synthetic and real signals demonstrated that the proposed method is effective and efficient.

Focal underdetermined system solver (FOCUSS) is a powerful method for basis selection and sparse representation, where it employs the [Formula: see text]-norm with p ∈ (0,2) to measure the sparsity of solutions. In this paper, we give a systematical analysis on the rate of convergence of the FOCUSS algorithm with respect to p ∈ (0,2) . We prove that the FOCUSS algorithm converges superlinearly for and linearly for usually, but may superlinearly in some very special scenarios. In addition, we verify its rates of convergence with respect to p by numerical experiments.

In this work, we introduce a new generalized nonlinear tensor regression framework called kernel-based multiblock tensor partial least squares (KMTPLS) for predicting a set of dependent tensor blocks from a set of independent tensor blocks through the extraction of a small number of common and discriminative latent components. By considering both common and discriminative features, KMTPLS effectively fuses the information from multiple tensorial data sources and unifies the single and multiblock tensor regression scenarios into one general model. Moreover, in contrast to multilinear model, KMTPLS successfully addresses the nonlinear dependencies between multiple response and predictor tensor blocks by combining kernel machines with joint Tucker decomposition, resulting in a significant performance gain in terms of predictability. An efficient learning algorithm for KMTPLS based on sequentially extracting common and discriminative latent vectors is also presented. Finally, to show the effectiveness and advantages of our approach, we test it on the real-life regression task in computer vision, i.e., reconstruction of human pose from multiview video sequences.

CANDECOMP/PARAFAC (CP) tensor factorization of incomplete data is a powerful and useful data analysis technique. This method can achieve the purpose of tensor completion through explicitly capturing the multilinear latent factors. Recently, a CP factorization based on a hierarchical probabilistic model has been proposed which is used fully Bayesian theory by incorporating a sparsity-inducing prior over multiple latent factors and the appropriate hyper-priors over all hyper-parameters. In this way, the rank of tensor can be determined automatically instead of traditional manual assignment. This method has been applied into image inpainting and facial image synthesis effectively. However, there is no research on the application in EEG signal processing of this method. Moreover, the EEG data loss often occurs during experiment recording period. In this paper, we used this newer data analysis method for processing EEG data set from P300 experiment including data completion under different levels of data missing and classification analysis on the recovered data. The experiment result shows that this method has a good processing performance on incomplete EEG signal.

Canonical polyadic decomposition of tensor is to approximate or express the tensor by sum of rank-1 tensors. When all or almost all components of factor matrices of the tensor are highly collinear, the decomposition becomes difficult. Algorithms, e.g., the alternating algorithms, require plenty of iterations, and may get stuck in false local minima. This paper proposes a novel method for such decompositions. The method injects one or a few rank-1 tensors into the data tensor in order to control the decompositions of the rank-expanded data, while still preserving the estimation accuracy of the original tensor. To achieve this, we develop a method to automatically generate the injected tensor which satisfies a specific estimation accuracy such that this tensor should not dominate rank-1 tensors of the data tensor, but is still able to be retrieved with a sufficient accuracy. Simulations on tensors with highly collinear factor matrices will illustrate efficiency of the proposed injecting method.

For the matrix/tensor completion problem with very high missing ratio, the standard local (e.g., patch, probabilistic, and smoothness) and global (e.g., low-rank) structure-based methods do not work well. To address this issue, we proposed to use local and global data structures at the same time by applying a novel functional smooth PARAFAC decomposition model for the tensor completion. This decomposition model is constructed as a sum of the outer product of functional smooth component vectors, which are represented by linear combinations of smooth basis functions. A new algorithm was developed by applying greedy deflation and smooth rank-one tensor decomposition. Our extensive experiments demonstrated the high performance and advantages of our algorithm in comparison to existing state-of-the-art methods.

High accuracy of electroencephalogram (EEG) classification can hardly be achieved if the signals are contaminated by severe artefacts. One helpless way to avoid such artefacts is usually to directly discard the severely disturbed EEG segments. This study considers a more elegant way that tries to recover the disturbed segments from other undisturbed segments. The possible artefacts in EEG are treated as missing values. A Bayesian tensor factorization (BTF) based method is proposed to implement EEG completion for artefact removal. By specifying a sparsity-inducing hierarchical prior, the underlying low-rank tensor is discovered from incomplete EEG tensor with automatically inferred model parameters. The EEG missing values are effectively predicted with robustness to overfitting. Effectiveness of the BTF algorithm is demonstrated on EEG data recorded from seven subjects in a brain-computer interface paradigm based on event-related potentials.

Reducing noise in a video sequence is of vital important in many real-world applications. One popular method is block matching collaborative filtering. However, the main drawback of this method is that noise standard deviation for the whole video sequence is known in advance. In this paper, we present a tensor based denoising framework that considers 3D patches instead of 2D patches. By collecting the similar 3D patches non-locally, we employ the low-rank tensor decomposition for collaborative filtering. Since we specify the non-informative prior over the noise precision parameter, the noise variance can be inferred automatically from observed video data. Therefore, our method is more practical, which does not require knowing the noise variance. The experimental on video denoising demonstrates the effectiveness of our proposed method.

This special issue covers relevant contemporary challenges in the field of biomedical signal processing and possibilities for future technological development.

With the increasing availability of various sensor technologies, we now have access to large amounts of multiblock (also called multiset, multirelational, or multiview) data that need to be jointly analyzed to explore their latent connections. Various component analysis methods have played an increasingly important role for the analysis of such coupled data. In this article, we first provide a brief review of existing matrix-based (two-way) component analysis methods for the joint analysis of such data with a focus on biomedical applications. Then, we discuss their important extensions and generalization to multiblock multiway (tensor) data. We show how constrained multiblock tensor decomposition methods are able to extract similar or statistically dependent common features that are shared by all blocks, by incorporating the multiway nature of data. Special emphasis is given to the flexible common and individual feature analysis of multiblock data with the aim to simultaneously extract common and individual latent components with desired properties and types of diversity. Illustrative examples are given to demonstrate their effectiveness for biomedical data analysis.

Canonical polyadic decomposition (CPD), also known as parallel factor analysis, is a representation of a given tensor as a sum of rank-one components. Traditional method for accomplishing CPD is the alternating least squares (ALS) algorithm. Convergence of ALS is known to be slow, especially when some factor matrices of the tensor contain nearly collinear columns. We propose a novel variant of this technique, in which the factor matrices are partitioned into blocks, and each iteration jointly updates blocks of different factor matrices. Each partial optimization is quadratic and can be done in closed form. The algorithm alternates between different random partitionings of the matrices. As a result, a faster convergence is achieved. Another improvement can be obtained when the method is combined with the enhanced line search of Rajihet al.Complexity per iteration is between those of the ALS and the Levenberg–Marquardt (damped Gauss–Newton) method. It is important, however, that the idea of alternating quadratic optimization with partitioned factor matrices is general and can be applied to other variants of the tensor decomposition problems, e.g., when non-Gaussian additive noise is considered.

Background subtraction has been a fundamental and widely studied task in video analysis, with a wide range of applications in video surveillance, teleconferencing, and 3D modeling. Recently, motivated by compressive imaging, background subtraction from compressive measurements (BSCM) is becoming an active research task in video surveillance. In this paper, we propose a novel tensor-based robust principal component analysis (TenRPCA) approach for BSCM by decomposing video frames into backgrounds with spatial-temporal correlations and foregrounds with spatio-temporal continuity in a tensor framework. In this approach, we use 3D total variation to enhance the spatio-temporal continuity of foregrounds, and Tucker decomposition to model the spatio-temporal correlations of video background. Based on this idea, we design a basic tensor RPCA model over the video frames, dubbed as the holistic TenRPCA model. To characterize the correlations among the groups of similar 3D patches of video background, we further design a patch-group-based tensor RPCA model by joint tensor Tucker decompositions of 3D patch groups for modeling the video background. Efficient algorithms using the alternating direction method of multipliers are developed to solve the proposed models. Extensive experiments on simulated and real-world videos demonstrate the superiority of the proposed approaches over the existing state-of-the-art approaches.

Recurrent neural networks, as neurodynamic systems, are a class of connectionist models that capture the dynamics of sequences via cycles in artificial neurons. Since the invention of Hopfield neural network, recurrent neural networks have attracted considerable attention, which marks the beginning of the modern age of neural network studies. Thanks to their inherent nature of parallel and distributed information processing, many computationally intensive applications can be solved by recurrent neural networks in the real-time environment.

Regularization has been one of the most popular approaches to prevent overfitting in electroencephalogram (EEG) classification of brain-computer interfaces (BCIs). The effectiveness of regularization is often highly dependent on the selection of regularization parameters that are typically determined by cross-validation (CV). However, the CV imposes two main limitations on BCIs: 1) a large amount of training data is required from the user and 2) it takes a relatively long time to calibrate the classifier. These limitations substantially deteriorate the system's practicability and may cause a user to be reluctant to use BCIs. In this paper, we introduce a sparse Bayesian method by exploiting Laplace priors, namely, SBLaplace, for EEG classification. A sparse discriminant vector is learned with a Laplace prior in a hierarchical fashion under a Bayesian evidence framework. All required model parameters are automatically estimated from training data without the need of CV. Extensive comparisons are carried out between the SBLaplace algorithm and several other competing methods based on two EEG data sets. The experimental results demonstrate that the SBLaplace algorithm achieves better overall performance than the competing algorithms for EEG classification.

We propose a generative model for robust tensor factorization in the presence of both missing data and outliers. The objective is to explicitly infer the underlying low-CANDECOMP/PARAFAC (CP)-rank tensor capturing the global information and a sparse tensor capturing the local information (also considered as outliers), thus providing the robust predictive distribution over missing entries. The low-CP-rank tensor is modeled by multilinear interactions between multiple latent factors on which the column sparsity is enforced by a hierarchical prior, while the sparse tensor is modeled by a hierarchical view of Student-t distribution that associates an individual hyperparameter with each element independently. For model learning, we develop an efficient variational inference under a fully Bayesian treatment, which can effectively prevent the overfitting problem and scales linearly with data size. In contrast to existing related works, our method can perform model selection automatically and implicitly without the need of tuning parameters. More specifically, it can discover the groundtruth of CP rank and automatically adapt the sparsity inducing priors to various types of outliers. In addition, the tradeoff between the low-rank approximation and the sparse representation can be optimized in the sense of maximum model evidence. The extensive experiments and comparisons with many state-of-the-art algorithms on both synthetic and real-world data sets demonstrate the superiorities of our method from several perspectives.

Real-world data are often acquired as a collection of matrices rather than as a single matrix. Such multiblock data are naturally linked and typically share some common features while at the same time exhibiting their own individual features, reflecting the underlying data generation mechanisms. To exploit the linked nature of data, we propose a new framework for common and individual feature extraction (CIFE) which identifies and separates the common and individual features from the multiblock data. Two efficient algorithms termed common orthogonal basis extraction (COBE) are proposed to extract common basis is shared by all data, independent on whether the number of common components is known beforehand. Feature extraction is then performed on the common and individual subspaces separately, by incorporating dimensionality reduction and blind source separation techniques. Comprehensive experimental results on both the synthetic and real-world data demonstrate significant advantages of the proposed CIFE method in comparison with the state-of-the-art.

In multi-data learning, it is usually assumed that common latent factors exist among multi-datasets, but it may lead to deteriorated performance when datasets are heterogeneous and unbalanced. In this paper, we propose a novel common structure for multi-data learning. Instead of common latent factors, we assume that datasets share Common Adjacency Graph (CAG) structure, which is more robust to heterogeneity and unbalance of datasets. Furthermore, we utilize CAG structure to develop a new method for multi-tensor completion, which exploits the common structure in datasets to improve the completion performance. Numerical results demostrate that the proposed method not only outperforms state-of-the-art methods for video in-painting, but also can recover missing data well even in cases that conventional methods are not applicable.

It is known that network impairments cause degradation in the online playing experience. Awareness of this degradation can enable game servers to take adaptive action that can mitigate or alleviate the game degradation quickly before it causes a player to leave the game in frustration. In this paper, we focus on a first person shooter game and determine the impact of network impairments on game performance using experimentation with player bots. We analyze game metrics such as the affected player's score, accuracy and effectiveness in shooting and taking evasive action. We show the use of statistical and machine learning techniques to determine the set of game metrics that can be used to discriminate between game states in near real-time. Our results indicate that the game state classifiers were very accurate in detecting high levels of impairments and were also reasonably accurate down to the time scale of 20-second intervals. These prediction techniques can be incorporated into gaming middleware to enable the mitigation of network-caused impairments.

In this paper, we propose a low-rank tensor deconvolution problem which seeks multiway replicative patterns and corresponding activating tensors of rank-1. An alternating least squares (ALS) algorithm has been derived for the model to sequentially update loading components and the patterns. In addition, together with a good initialisation method using tensor diagonalization, the update rules have been implemented with a low cost using fast inversion of block Toeplitz matrices as well as an efficient update strategy. Experiments show that the proposed model and the algorithm are promising in feature extraction and clustering.

Very often data we encounter in practice is a collection of matrices rather than a single matrix. These multi-block data often share some common features, due to the background in which they are measured. In this study we propose a new concept of linked blind source separation (BSS) that aims at discovering and extracting unique and physically meaningful common components from multi-block data, which also contain strong individual components. The validity and potential of the proposed method is justified by simulations.

The P300-based brain-computer interface (BCI) is an extension of the oddball paradigm, and can facilitate communication for people with severe neuromuscular disorders. It has been shown that, in addition to the P300, other event-related potential (ERP) components have been shown to contribute to successful operation of the P300 BCI. Incorporating these components into the classification algorithm can improve the classification accuracy and information transfer rate (ITR). In this paper, a single character presentation paradigm was compared to a presentation paradigm that is based on the visual mismatch negativity. The mismatch negativity paradigm showed significantly higher classification accuracy and ITRs than a single character presentation paradigm. In addition, the mismatch paradigm elicited larger N200 and N400 components than the single character paradigm. The components elicited by the presentation method were consistent with what would be expected from a mismatch paradigm and a typical P300 was also observed. The results show that increasing the signal-to-noise ratio by increasing the amplitude of ERP components can significantly improve BCI speed and accuracy. The mismatch presentation paradigm may be considered a viable option to the traditional P300 BCI paradigm.

CANDECOMP/PARAFAC (CP) tensor factorization of incomplete data is a powerful technique for tensor completion through explicitly capturing the multilinear latent factors. The existing CP algorithms require the tensor rank to be manually specified, however, the determination of tensor rank remains a challenging problem especially for CP rank . In addition, existing approaches do not take into account uncertainty information of latent factors, as well as missing entries. To address these issues, we formulate CP factorization using a hierarchical probabilistic model and employ a fully Bayesian treatment by incorporating a sparsity-inducing prior over multiple latent factors and the appropriate hyperpriors over all hyperparameters, resulting in automatic rank determination. To learn the model, we develop an efficient deterministic Bayesian inference algorithm, which scales linearly with data size. Our method is characterized as a tuning parameter-free approach, which can effectively infer underlying multilinear factors with a low-rank constraint, while also providing predictive distributions over missing entries. Extensive simulations on synthetic data illustrate the intrinsic capability of our method to recover the ground-truth of CP rank and prevent the overfitting problem, even when a large amount of entries are missing. Moreover, the results from real-world applications, including image inpainting and facial image synthesis, demonstrate that our method outperforms state-of-the-art approaches for both tensor factorization and tensor completion in terms of predictive performance.

Nonnegative matrix factorization (NMF) with orthogonality constraints is quite important due to its close relation with the K-means clustering. While existing algorithms for orthogonal NMF impose strict orthogonality constraints, in this letter we propose a penalty method with the aim of performing approximately orthogonal NMF, together with two efficient algorithms respectively based on the Hierarchical Alternating Least Squares (HALS) and the Accelerated Proximate Gradient (APG) approaches. Experimental evidence was provided to show their high efficiency and flexibility by using synthetic and real-world data.

In this paper, we propose a method for solving the permutation problem that is inherent in the separation of convolved mixtures of speech signals in the time-frequency domain. The proposed method obtains the solution through maximization of a contrast function that exploits the similarity of the temporal envelope of the speech spectrum. For this purpose, the contrast calculation uses a global measure of similarity based on the recently developed family of generalized Alpha-Beta divergences, which depend on two tuning parameters, alpha and beta. This parameterization is exploited to best measure the similarity of the speech spectrum and to obtain solutions that are robust against noise and outliers. The ability of this contrast function to solve the permutation problem is supported by a theoretical study that shows that for a simple time-frequency speech model, the contrast value reaches its maximum when the estimated components are properly aligned. Several performance studies demonstrate that the proposed method maintains a high level of permutation correction accuracy in a wide variety of acoustic environments. Moreover, it produces better results than other state-of-the-art methods for solving permutations in highly reverberant environments.

Nonnegative Tucker decomposition (NTD) is a powerful tool for the extraction of nonnegative parts-based and physically meaningful latent components from high-dimensional tensor data while preserving the natural multilinear structure of data. However, as the data tensor often has multiple modes and is large scale, the existing NTD algorithms suffer from a very high computational complexity in terms of both storage and computation time, which has been one major obstacle for practical applications of NTD. To overcome these disadvantages, we show how low (multilinear) rank approximation (LRA) of tensors is able to significantly simplify the computation of the gradients of the cost function, upon which a family of efficient first-order NTD algorithms are developed. Besides dramatically reducing the storage complexity and running time, the new algorithms are quite flexible and robust to noise, because any well-established LRA approaches can be applied. We also show how nonnegativity incorporating sparsity substantially improves the uniqueness property and partially alleviates the curse of dimensionality of the Tucker decompositions. Simulation results on synthetic and real-world data justify the validity and high efficiency of the proposed NTD algorithms.

Focal Underdetermined System Solver (FOCUSS) is a powerful and easy to implement tool for basis selection and inverse problems. One of the fundamental problems regarding this method is its convergence, which remains unsolved until now. We investigate the convergence of the FOCUSS algorithm in this paper. We first give a rigorous derivation for the FOCUSS algorithm by exploiting the auxiliary function. Following this, we further prove its convergence by stability analysis.

Traffic forecasting is increasingly taking on an important role in many intelligent transportation systems (ITS) applications. However, prediction is typically performed for individual road segments and prediction horizons. In this study, we focus on the problem of collective prediction for multiple road segments and prediction-horizons. To this end, we develop various matrix and tensor based models by applying partial least squares (PLS), higher order partial least squares (HO-PLS) and N-way partial least squares (N-PLS). These models can simultaneously forecast traffic conditions for multiple road segments and prediction-horizons. Moreover, they can also perform the task of feature selection efficiently. We analyze the performance of these models by performing multi-horizon prediction for an urban subnetwork in Singapore.

With the rise in the population of the world's cities, understanding the dynamics of commuters' transportation patterns has become crucial in the planning and management of urban facilities and services. In this study, we analyze how commuter patterns change during different time instances such as between weekdays and weekends. To this end, we propose two data mining techniques, namely Common Orthogonal Basis Extraction (COBE), and Joint and Individual Variation Explained (JIVE) for Integrated Analysis of Multiple Data Types and apply them to smart card data available for passengers in Singapore. We also discuss the issues of model selection and interpretability of these methods. The joint and individual patterns can help transportation companies optimize their resources in light of changes in commuter mobility behavior.

We introduce a reconstruction formula that allows one to recover an N-order tensor X ϵ RI1×...×Infrom a reduced set of multi-way compressive measurements by exploiting its low multilinear rank structure. It is proved that, in the matrix case (N = 2), the proposed reconstruction is stable in the sense that the approximation error is proportional to the one provided by the best low-rank approximation, i.e ||X - X||2≤ K||X - X0||2, where K is a constant and X0is the corresponding truncated SVD of X. We also present simulation results indicating that the same stable behavior is observed with higher order tensors (N > 2). In addition, it is shown that, an interesting property of multi-way measurements allows us to build the reconstruction based on compressive linear measurements of fibers taken only in two selected modes, independently of the tensor order N. Simulation results using real-world 2D and 3D signals are presented illustrating our results and comparing the reconstructions against the best low multilinear rank approximations and the reconstructions obtained by using the Kronecker-CS approach.

Meditation is a fascinating topic that is still relatively poorly understood. To investigate its physiological traits, electroencephalograms (EEG) were recorded during meditation sessions. In a recent study, paroxysmal gamma waves (PGWs) have been discovered in EEG of meditators practicing Bhramari Pranayama (BhPr). In this paper, the synchrony between those PGWs is investigated, revealing functional connectivity patterns in the brain during BhPr. Specifically, the method “Stochastic Event Synchrony” (SES) is applied to pairs of PGW sequences in order to assess their synchrony. From those pairwise synchrony measures, large-scale functional connectivity patterns are extracted. Three subjects possessing different levels of expertise in BhPr are considered. Strong synchrony can be observed in the temporal lobes for all three subjects, in addition to long-range interhemispheric connections. Consistent connectivity patterns are present for exhalation periods of BhPr, while those patterns are substantially less stationary for inhalation periods. Interestingly, the synchrony seems to increase gradually during the meditation sessions. Moreover, the distribution of synchrony values seems to depend on the level of expertise in practicing BhPr: the higher the expertise, the more concentrated the intensity values.

We propose algorithms for Tucker tensor decomposition, which can avoid computing singular value decomposition or eigenvalue decomposition of large matrices as in the work-horse higher order orthogonal iteration (HOOI) algorithm. The novel algorithms require computational cost of O(I3R), which is cheaper than O(I3R + IR4+ R6) of HOOI for multilinear rank-(R, R, R) tensors of size I × I × I.

CANDECOMP/PARAFAC tensor decomposition (CPD) approximates multiway data by rank-1 tensors. Unlike matrix decomposition, the procedure which estimates the best rank-R tensor approximation through R sequential best rank-1 approximations does not work for tensors, because the deflation does not always reduce the tensor rank. In this paper we propose a novel deflation method for the problem in which rank R does not exceed the tensor dimensions. A rank-R CPD can be performed through (R − 1) rank-1 reductions. At each deflation stage, the residue tensor is constrained to have a reduced multilinear rank.

We present a novel framework for tensor valued Gaussian processes (GP) regression, which exploits a covariance function defined on tensor representation of data inputs. In this way, we bring together the powerful GP methods supported by Bayesian inference and higher-order tensor analysis techniques into one framework. This enables us to account for the underlying structure of data within the model, providing a powerful framework for structural data analysis, such as 3D video sequences. To this end, we propose a new kernel function with tensor arguments under the assumption of generative models, in the form of product kernels where a symmetrical Kullback-Leibler divergence measure is exploited to define the covariance function for tensorial data. A fully Bayesian treatment is employed to estimate the hyperparameters and infer the predictive distributions. Simulation results on both the synthetic data and a real world application of estimating the crowd size from 3D videos demonstrate the effectiveness of the proposed framework.

In this paper, we proposed a Nonnegative Shifted Tensor Factorization (NSTF) model considering multiple component delays by time frequency analysis. Explicit mathematical representation for the delays is presented to recover the patterns from the original data. In order to explore multilinear shifted component in different modes, we use fast fourier transform (FFT) to transform the non-integer delays into frequency domain by gradients search. The ALS algorithm for NSTF is developed by alternating least square procedure to estimate the nonnegative factor matrices in each mode and enforce the sparsity of model. Simulation results indicate that ALS-NSTF algorithm can extract the shift-invariance sparse features and improve the recognition performance of robust speaker identification and structural magnetic resonance imaging (sMRI) diagnosis for Alzheimer's Disease.

Non-negative tensor factorization (NTF) has been successfully applied to analyze event-related potentials (ERPs), and shown superiority in terms of capturing multi-domain features. However, the time-frequency representation of ERPs by higher-order tensors are usually large-scale, which prevents the popularity of most tensor factorization algorithms. To overcome this issue, we introduce a non-negative canonical polyadic decomposition (NCPD) based on low-rank approximation (LRA) and hierarchical alternating least square (HALS) techniques. We applied NCPD (LRAHALS and benchmark HALS) and CPD to extract multi-domain features of a visual ERP. The features and components extracted by LRAHALS NCPD and HALS NCPD were very similar, but LRAHALS NCPD was 70 times faster than HALS NCPD. Moreover, the desired multi-domain feature of the ERP by NCPD showed a significant group difference (control versus depressed participants) and a difference in emotion processing (fearful versus happy faces). This was more satisfactory than that by CPD, which revealed only a group difference.

Recent research has shown that a new face paradigm is superior to the conventional "flash only" approach that has dominated P300 brain-computer interfaces (BCIs) for over 20 years. However, these face paradigms did not study the repetition effects and the stability of evoked event related potentials (ERPs), which would decrease the performance of P300 BCI. In this paper, we explored whether a new "multi-faces (MF)" approach would yield more distinct ERPs than the conventional "single face (SF)" approach. To decrease the repetition effects and evoke large ERPs, we introduced a new stimulus approach called the "MF" approach, which shows different familiar faces randomly. Fifteen subjects participated in runs using this new approach and an established "SF" approach. The result showed that the MF pattern enlarged the N200 and N400 components, evoked stable P300 and N400, and yielded better BCI performance than the SF pattern. The MF pattern can evoke larger N200 and N400 components and more stable P300 and N400, which increase the classification accuracy compared to the face pattern.

Canonical correlation analysis (CCA) has been one of the most popular methods for frequency recognition in steady-state visual evoked potential (SSVEP)-based brain-computer interfaces (BCIs). Despite its efficiency, a potential problem is that using pre-constructed sine-cosine waves as the required reference signals in the CCA method often does not result in the optimal recognition accuracy due to their lack of features from the real electro-encephalo-gram (EEG) data. To address this problem, this study proposes a novel method based on multiset canonical correlation analysis (MsetCCA) to optimize the reference signals used in the CCA method for SSVEP frequency recognition. The MsetCCA method learns multiple linear transforms that implement joint spatial filtering to maximize the overall correlation among canonical variates, and hence extracts SSVEP common features from multiple sets of EEG data recorded at the same stimulus frequency. The optimized reference signals are formed by combination of the common features and completely based on training data. Experimental study with EEG data from 10 healthy subjects demonstrates that the MsetCCA method improves the recognition accuracy of SSVEP frequency in comparison with the CCA method and other two competing methods (multiway CCA (MwayCCA) and phase constrained CCA (PCCA)), especially for a small number of channels and a short time window length. The superiority indicates that the proposed MsetCCA method is a new promising candidate for frequency recognition in SSVEP-based BCIs.

Two main issues for event-related potential (ERP) classification in brain-computer interface (BCI) application are curse-of-dimensionality and bias-variance tradeoff, which may deteriorate classification performance, especially with insufficient training samples resulted from limited calibration time. This study introduces an aggregation of sparse linear discriminant analyses (ASLDA) to overcome these problems. In the ASLDA, multiple sparse discriminant vectors are learned from differently l1-regularized least-squares regressions by exploiting the equivalence between LDA and least-squares regression, and are subsequently aggregated to form an ensemble classifier, which could not only implement automatic feature selection for dimensionality reduction to alleviate curse-of-dimensionality, but also decrease the variance to improve generalization capacity for new test samples. Extensive investigation and comparison are carried out among the ASLDA, the ordinary LDA and other competing ERP classification algorithms, based on different three ERP datasets. Experimental results indicate that the ASLDA yields better overall performance for single-trial ERP classification when insufficient training samples are available. This suggests the proposed ASLDA is promising for ERP classification in small sample size scenario to improve the practicability of BCI.

As tensors provide a natural and efficient representation of multidimensional structured data, in this paper, we consider probabilistic multinomial probit classification for tensor-variate inputs with Gaussian processes (GP) priors placed over the latent function. In order to take into account the underlying multimodes structure information within the model, we propose a framework of probabilistic product kernels for tensorial data based on a generative model assumption. More specifically, it can be interpreted as mapping tensors to probability density function space and measuring similarity by an information divergence. Since tensor kernels enable us to model input tensor observations, the proposed tensor-variate GP is considered as both a generative and discriminative model. Furthermore, a fully variational Bayesian treatment for multiclass GP classification with multinomial probit likelihood is employed to estimate the hyperparameters and infer the predictive distributions. Simulation results on both synthetic data and a real world application of human action recognition in videos demonstrate the effectiveness and advantages of the proposed approach for classification of multiway tensor data, especially in the case that the underlying structure information among multimodes is discriminative for the classification task.

Various tensor decompositions use different arrangements of factors to explain multi-way data. Components from different decompositions can vary in the number of parameters. Allowing a model to contain components from different decompositions results in a combinatoric number of possible models. Model selection balances approximation error and the number of parameters, but due to the number of possible models, post-hoc model selection is infeasible. Instead, we incrementally build a model. This approach is analogous to sparse coding with a union of dictionaries. The proposed greedy approach can estimate a model consisting of a combination of tensor decompositions.

We propose a novel decomposition approach to impute missing values in tensor data. The method uses smaller scale multiway patches to model the whole data or a small volume encompassing the observed missing entries. Simulations on color images show that our method can recover color images using only 5–10% of pixels, and outperforms other available tensor completion methods.

A novel approach is proposed to extract high-rank patterns from multiway data. The method is useful when signals comprise collinear components or complex structural patterns. Alternating least squares and multiplication algorithms are developed for the new model with/without non negativity constraints. Experimental results on synthetic data and real-world dataset confirm the validity of the proposed model and algorithms.

In this paper, a novel implementation of the damped Gauss-Newton algorithm (also known as Levenberg-Marquart) for the CANDECOMP-PARAFAC (CP) tensor decomposition is proposed. The method is based on a fast inversion of the approximate Hessian for the problem. It is shown that the inversion can be computed on O(NR6) operations, where N and R is the tensor order and rank, respectively. It is less than in the best existing state-of-the art algorithm with O(N3R6) operations. The damped Gauss-Newton algorithm is suitable namely for difficult scenarios, where nearly-colinear factors appear in several modes simultaneously. Performance of the method is shown on decomposition of large tensors (100 × 100 × 100 and 100 × 100 × 100 × 100) of rank 5 to 90.

We present a new supervised tensor regression method based on multi-way array decompositions and kernel machines. The main issue in the development of a kernel-based framework for tensorial data is that the kernel functions have to be defined on tensor-valued input, which here is defined based on multi-mode product kernels and probabilistic generative models. This strategy enables taking into account the underlying multilinear structure during the learning process. Based on the defined kernels for tensorial data, we develop a kernel-based tensor partial least squares approach for regression. The effectiveness of our method is demonstrated by a real-world application, i.e., the reconstruction of 3D movement trajectories from electrocorticography signals recorded from a monkey brain.

Electrooculogram (EOG) signals are potential responses generated by eye movements, and event related potential (ERP) is a special electroencephalogram (EEG) pattern which evoked by external stimuli. Both EOG and ERP have been used separately for implementing human-machine interfaces which can assist disabled patients in performing daily tasks. In this paper, we present a novel EOG/ERP hybrid human-machine interface which integrates the traditional EOG and ERP interfaces together. Eye movements like the blink, wink, gaze, and frown are detected from EOG signals using double threshold algorithm. Multiple ERP components, i.e., N170, VPP and P300 are evoked by inverted face stimuli and classified by linear discriminant analysis (LDA). Based on this hybrid interface, we also design a control scheme for the humanoid robot NAO (Aldebaran robotics, Inc). On-line experiment results show that the proposed hybrid interface can effectively control the robot's basic movements and order it to make various behaviors. While normally operating the robot by hands takes 49.1 s to complete the experiment sessions, using the proposed EOG/ERP interface, the subject is able to finish the sessions in 54.1 s.

Non-negative Canonical Polyadic decomposition (NCPD) and non-negative Tucker decomposition (NTD) were compared for extracting the multi-domain feature of visual mismatch negativity (vMMN), a small event-related potential (ERP), for the cognitive research. Since signal-to-noise ratio in vMMN is low, NTD outperformed NCPD. Moreover, we proposed an approach to select the multi-domain feature of an ERP among all extracted features and discussed determination of numbers of extracted components in NCPD and NTD regarding the ERP context.

Recently there has been great interest in sparse representations of signals under the assumption that signals (data sets) can be well approximated by a linear combination of few elements of a known basis (dictionary). Many algorithms have been developed to find such representations for one-dimensional signals (vectors), which requires finding the sparsest solution of an underdetermined linear system of algebraic equations. In this letter, we generalize the theory of sparse representations of vectors to multiway arrays (tensors)--signals with a multidimensional structure--by using the Tucker model. Thus, the problem is reduced to solving a large-scale underdetermined linear system of equations possessing a Kronecker structure, for which we have developed a greedy algorithm, Kronecker-OMP, as a generalization of the classical orthogonal matching pursuit (OMP) algorithm for vectors. We also introduce the concept of multiway block-sparse representation of N-way arrays and develop a new greedy algorithm that exploits not only the Kronecker structure but also block sparsity. This allows us to derive a very fast and memory-efficient algorithm called N-BOMP (N-way block OMP). We theoretically demonstrate that under the block-sparsity assumption, our N-BOMP algorithm not only has a considerably lower complexity but is also more precise than the classic OMP algorithm. Moreover, our algorithms can be used for very large-scale problems, which are intractable using standard approaches. We provide several simulations illustrating our results and comparing our algorithms to classical algorithms such as OMP and BP (basis pursuit) algorithms. We also apply the N-BOMP algorithm as a fast solution for the compressed sensing (CS) problem with large-scale data sets, in particular, for 2D compressive imaging (CI) and 3D hyperspectral CI, and we show examples with real-world multidimensional signals.

A new generalized multilinear regression model, termed the higher order partial least squares (HOPLS), is introduced with the aim to predict a tensor (multiway array) Y from a tensor X through projecting the data onto the latent space and performing regression on the corresponding latent variables. HOPLS differs substantially from other regression models in that it explains the data by a sum of orthogonal Tucker tensors, while the number of orthogonal loadings serves as a parameter to control model complexity and prevent overfitting. The low-dimensional latent space is optimized sequentially via a deflation operation, yielding the best joint subspace approximation for both X and Y. Instead of decomposing X and Y individually, higher order singular value decomposition on a newly defined generalized cross-covariance tensor is employed to optimize the orthogonal loadings. A systematic comparison on both synthetic data and real-world decoding of 3D movement trajectories from electrocorticogram signals demonstrate the advantages of HOPLS over the existing methods in terms of better predictive ability, suitability to handle small sample sizes, and robustness to noise.

Blind separation of underdetermined instantaneous mixtures is a popular solution to inverse problems encountered in audio or biomedical applications where the number of sources exceeds the number of sensors. There are two non-equivalent tasks: to identify the mixing matrix and to separate the original sources. In this paper, we focus on the latter task by proposing a novel beamformer that minimizes the theoretical mean square error distance between the separated and original signals. The beamformer has two stages: one for the estimation of signals and one for their refinement. Within the former stage, the signals are assumed to be random and locally stationary, while the latter stage is based on a semi-deterministic model. The experiments prove superior performance of the proposed method compared to conventional MMSE beamforming.

A novel near-lossless compression algorithm for multichannel electroencephalogram (MC-EEG) is proposed based on matrix/tensor decomposition models. MC-EEG is represented in suitable multiway (multidimensional) forms to efficiently exploit temporal and spatial correlations simultaneously. Several matrix/tensor decomposition models are analyzed in view of efficient decorrelation of the multiway forms of MC-EEG. A compression algorithm is built based on the principle of “lossy plus residual coding,” consisting of a matrix/tensor decomposition-based coder in the lossy layer followed by arithmetic coding in the residual layer. This approach guarantees a specifiable maximum absolute error between original and reconstructed signals. The compression algorithm is applied to three different scalp EEG datasets and an intracranial EEG dataset, each with different sampling rate and resolution. The proposed algorithm achieves attractive compression ratios compared to compressing individual channels separately. For similar compression ratios, the proposed algorithm achieves nearly fivefold lower average error compared to a similar wavelet-based volumetric MC-EEG compression algorithm.

CANonical polyadic DECOMPosition (CANDECOMP, CPD), also known as PARAllel FACtor analysis (PARAFAC) is widely applied to Nth-order (N ≥ 3) tensor analysis. Existing CPD methods mainly use alternating least squares iterations and hence need to unfold tensors to each of their N modes frequently, which is one major performance bottleneck for large-scale data, especially when the order N is large. To overcome this problem, in this paper, we propose a new CPD method in which the CPD of a high-order tensor (i.e., N > 3) is realized by applying CPD to a mode reduced one (typically, third-order tensor) followed by a Khatri-Rao product projection procedure. This way is not only quite efficient as frequently unfolding to N modes is avoided, but also promising to conquer the bottleneck problem caused by high collinearity of components. We show that, under mild conditions, any Nth-order CPD can be converted to an equivalent third-order one but without destroying essential uniqueness, and theoretically they simply give consistent results. Besides, once the CPD of any unfolded lower order tensor is essentially unique, it is also true for the CPD of the original higher order tensor. Error bounds of truncated CPD are also analyzed in the presence of noise. Simulations show that, compared with state-of-the-art CPD methods, the proposed method is more efficient and is able to escape from local solutions more easily.

In this paper, we consider sparse representations of multidimensional signals (tensors) by generalizing the one-dimensional case (vectors). A new greedy algorithm, namely the Tensor-OMP algorithm, is proposed to compute a block-sparse representation of a tensor with respect to a Kronecker basis where the non-zero coefficients are restricted to be located within a sub-tensor (block). It is demonstrated, through simulation examples, the advantage of considering the Kronecker structure together with the block-sparsity property obtaining faster and more precise sparse representations of tensors compared to the case of applying the classical OMP (Orthogonal Matching Pursuit).

Various compression algorithms for multi-channel electroencephalograms (EEG) are proposed and compared. The multi-channel EEG is represented as a three-way tensor (or 3D volume) to exploit both spatial and temporal correlations efficiently. A general two-stage coding framework is developed for multi-channel EEG compression. In the first stage, we consider (i) wavelet-based volumetric coding; (ii) energy-based lossless compression of wavelet subbands; (iii) tensor decomposition based coding. In the second stage, the residual is quantized and coded. Through such two-stage approach, one can control the maximum error (worst-case distortion). Numerical results for a standard EEG data set show that tensor-based coding achieves lower worst-case error and comparable average error than the wavelet- and energy-based schemes.

We propose a regularization based on geometric structure for feature extraction in a sensor array for brain data recordings. The purpose of the study is to add a penalty term using distances between sensors as the geometric information for finding spatial weights. The regularization term is derived under the definition of neighbors of sensors. We evaluate the proposed regularization in common spatial pattern (CSP) which is a well-known feature extraction method for EEG based brain computer interface (BCI). We have demonstrated the CSP procedure with the regularization by simulation for artificial signals. The results show that the proposed method works better than standard CSP in extracting of a component generated in a certain brain spot. Moreover, the classification experimental results using dataset of motor imagery based BCI suggest that the proposed method achieved maximum improvement by 27% in the classification accuracy over the standard CSP in a setting of even when we use only five samples.

Classification methods have been widely applied in most brain computer interfaces (BCIs) that control devices for better quality of life. Most existing classification methods for P300-based BCIs extract features based on temporal structure related to P300 components of event-related potentials (ERPs). Some others exploit the spatial distribution of ERPs optimally selected by recursive channel elimination. However, none of them employed multilinear structures which exploit hidden features in P300-based BCI data. In this paper, we propose a new feature extraction method based on tensor decomposition for ERP-based BCIs. The method seeks an optimal feature subspace simultaneously spanned by temporal and spatial bases, and additional bases which indicate a variant of ERPs obtained by different degrees of polynomial fittings. The proposed method has been evaluated by both the BCI competition III data set II and the affective face driven paradigm data set, and achieved 92% and 95% classification accuracies respectively, which were better than those of most existing P300-based BCI algorithms.

A novel blind deconvolution is proposed to seek for basis patterns and their location maps inside a nonnegative data matrix. Basis patterns can have different sizes, and shift in independent directions. Moreover, the location maps can be low-rank or rank-one matrices composed by two relatively small and tall matrices or by two vectors. A general framework to solve this problem together with algorithms are introduced. The experiments on music and texture decomposition will confirm performance of our method, and of the proposed algorithms.

This paper addresses a saccade-related electrooculogram (EOG) reduction using outer product expansion with nonlinear filter. The saccade-related electroencephalogram (EEG) signal produced by the saccadic eye movement is adopted to analyze relationship between a brain function and a human activity. Eye movement origin EOG artifacts denoising is important task to analyze the relationship between the saccade and the EEG. The tensor product expansion with absolute error (TPE-AE), which calculates two terms of outer product using reference signal, was proposed to reduce EOG artifacts. However, this TPE-AE has a significant problem corresponding to a calculation cost. In this paper, we propose and apply the median based outer product expansion with reference signal to estimate EOG component accurately. Results show that the proposed TPE-AE is effective to separate the EOG component and other noises.

Through exploiting temporal, spectral, time-frequency representations, and spatial properties of mismatch negativity (MMN) simultaneously, this study extracts a multi-domain feature of MMN mainly using non-negative tensor factorization. In our experiment, the peak amplitude of MMN between children with reading disability and children with attention deficit was not significantly different, whereas the new feature of MMN significantly discriminated the two groups of children. This is because the feature was derived from multi-domain information with significant reduction of the heterogeneous effect of datasets.

Stochastic event synchrony (SES) is a recently proposed family of similarity measures. First, "events" are extracted from the given signals; next, one tries to align events across the different time series. The better the alignment, the more similar the N time series are considered to be. The similarity measures quantify the reliability of the events (the fraction of "nonaligned" events) and the timing precision. So far, SES has been developed for pairs of one-dimensional (Part I) and multidimensional (Part II) point processes. In this letter (Part III), SES is extended from pairs of signals to N > 2 signals. The alignment and SES parameters are again determined through statistical inference, more specifically, by alternating two steps: (1) estimating the SES parameters from a given alignment and (2), with the resulting estimates, refining the alignment. The SES parameters are computed by maximum a posteriori (MAP) estimation (step 1), in analogy to the pairwise case. The alignment (step 2) is solved by linear integer programming. In order to test the robustness and reliability of the proposed N-variate SES method, it is first applied to synthetic data. We show that N-variate SES results in more reliable estimates than bivariate SES. Next N-variate SES is applied to two problems in neuroscience: to quantify the firing reliability of Morris-Lecar neurons and to detect anomalies in EEG synchrony of patients with mild cognitive impairment. Those problems were also considered in Parts I and II, respectively. In both cases, the N-variate SES approach yields a more detailed analysis.

A new canonical polyadic (CP) decomposition method is proposed in this letter, where one factor matrix is extracted first by using any standard blind source separation (BSS) method and the remainder components are computed efficiently via sequential singular value decompositions of rank-1 matrices. The new approach provides more interpretable factors and it is extremely efficient for ill-conditioned problems. Especially, it overcomes the bottleneck problems, which often cause very slow convergence speed in CP decompositions. Simulations confirmed the validity and efficiency of the proposed method.

Compression schemes for EEG signals are developed based on matrix and tensor decomposition. Various ways to arrange EEG signals into matrices and tensors are explored, and several matrix and tensor decomposition schemes are applied, including SVD, CUR, PARAFAC, the Tucker decomposition, and recent random fiber selection approaches. Rate-distortion curves for the proposed matrix and tensor-based EEG compression schemes are computed. It shown that PARAFAC has the best compression performance in this context.

The multiplicative algorithms are well-known for nonnegative matrix and tensor factorizations. The ALS algorithm for canonical decomposition (CP) has been proved as a "work horse" algorithm for general multiway data. Unfortunately, for CP with nonnegativity constraints, this algorithm with a rectifier (projection) may not converge to the desired solution without additional regularization parameters in matrix inverses. The hierarchical ALS algorithm improves the performance of the ALS algorithm, outperforms the multiplicative algorithm. However, NTF algorithms can face problem with collinear or bias data. In this paper, we propose a novel algorithm which overwhelmingly outperforms all the multiplicative, and (H)ALS algorithms. By solving the nonnegative quadratic programming problems, a general algorithm of the HALS has been derived and experimentally confirmed its validity and high performance for normal and difficult bench marks, and for real-world EEG dataset.

Alternating optimization algorithms for canonical polyadic decomposition (with/without nonnegative constraints) often accompany update rules with low computational cost, but could face problems of swamps, bottlenecks, and slow convergence. All-at-once algorithms can deal with such problems, but always demand significant temporary extra-storage, and high computational cost. In this paper, we propose an all-at-once algorithm with low complexity for sparse and nonnegative tensor factorization based on the damped Gauss-Newton iteration. Especially, for low-rank approximations, the proposed algorithm avoids building up Hessians and gradients, reduces the computational cost dramatically. Moreover, we proposed selection strategies for regularization parameters. The proposed algorithm has been verified to overwhelmingly outperform “state-of-the-art” NTF algorithms for difficult benchmarks, and for real-world application such as clustering of the ORL face database.

Anomalous environmental electromagnetic (EM) radiation waves have been reported as the portents of earthquakes. We have been measuring the Extremely Low Frequency (ELF) range all over Japan. Our goal is to predict earthquakes using EM radiation waves. The recorded data often contain signals unrelated to earthquakes. These signals, as noise, confound earthquake prediction efforts. It is necessary to eliminate noises from observed signals in a preprocessing step. In previous researches, we used ISRA, an algorithm of the Non-negative Matrix Factorization (NMF), to estimate source signal. However, ISRA is not robust for outliers because ISRA's cost function is based on square distance. In order to improve robustness, we should use lower order cost function. In this paper, we propose a nonnegative matrix factorization method using quasi-L1 norm in cost function (quasi-L1 NMF). In the experiment using ELF observed signals that include outliers, the proposed method extracts source signals more accurately than ISRA.

A multilinear subspace regression model based on so called latent variable decomposition is introduced. Unlike standard regression methods which typically employ matrix (2D) data representations followed by vector subspace transformations, the proposed approach uses tensor subspace transformations to model common latent variables across both the independent and dependent data. The proposed approach aims to maximize the correlation between the so derived latent variables and is shown to be suitable for the prediction of multidimensional dependent data from multidimensional independent data, where for the estimation of the latent variables we introduce an algorithm based on Multilinear Singular Value Decomposition (MSVD) on a specially defined cross-covariance tensor. It is next shown that in this way we are also able to unify the existing Partial Least Squares (PLS) and N-way PLS regression algorithms within the same framework. Simulations on benchmark synthetic data confirm the advantages of the proposed approach, in terms of its predictive ability and robustness, especially for small sample sizes. The potential of the proposed technique is further illustrated on a real world task of the decoding of human intracranial electrocorticogram (ECoG) from a simultaneously recorded scalp electroencephalograph (EEG).

Nonnegative matrix factorization (NMF) is an unsupervised learning method useful in various applications including image processing and semantic analysis of documents. This paper focuses on symmetric NMF (SNMF), which is a special case of NMF decomposition. Three parallel multiplicative update algorithms using level 3 basic linear algebra subprograms directly are developed for this problem. First, by minimizing the Euclidean distance, a multiplicative update algorithm is proposed, and its convergence under mild conditions is proved. Based on it, we further propose another two fast parallel methods: α-SNMF and β -SNMF algorithms. All of them are easy to implement. These algorithms are applied to probabilistic clustering. We demonstrate their effectiveness for facial image clustering, document categorization, and pattern clustering in gene expression.

In this paper, we consider the problem of quantifying synchrony between multiple simultaneously recorded electroencephalographic signals. These signals exhibit nonlinear dependencies and non-Gaussian statistics. A copula based approach is presented to model the joint statistics. We then consider the application of copula derived synchrony measures for early diagnosis of Alzheimer's disease. Results on real data are presented.

A problem of eye-movement muscular interference removal from EEG recordings is described. In many experiments in neuroscience it is crucial to separate different sources of electrical activity within human body in a situation when a very limited knowledge about nonlinear and nonstationary nature of the mixing process is available. A new two step extension to bivariate empirical mode decomposition is proposed to remove ocular artifacts from EEG with a use of fractional Gaussian noise as a reference first to preprocess EOG signal, which is next used in the second step as a reference to clean EEG signals. Results with EEG experimental data validate the proposed approach.

Nonnegative Matrix/Tensor factorization (NMF/NTF) have been used in the study of EEG, and the fit (explained variation) is often used to evaluate the performance of a nonnegative decomposition algorithm. However, this parameter only reveals the information derived from the mathematical model and just exhibits the reliability of the algorithms, and the property of EEG can not be reflected. If fits of two algorithms are identical, it is necessary to examine whether the desired components extracted by them are identical too. In order to verify this doubt, we performed NMF and NTF on the same dataset of an auditory event-related potentials (ERPs), and found that the identical fits of NMF and NTF under the hierarchical alternating least squares algorithms corresponded to different desired ERPs extracted by NMF and NTF, moreover, NTF contributed the ERP with much better timing and spectral properties. Such analysis implies that to combine the fit and property of the desired ERP component together helps evaluate the performance of NMF and NTF algorithms in the study of ERPs.

A new noise reduction method for speech signals is proposed in this paper. The method is based upon the N-mode singular value decomposition algorithm, which exploits the multilinear subspace analysis of given speech data. Simulation results using both synthetically generated and real broadband noise components show that the enhancement quality obtained by the multilinear subspace analysis method in terms of both segmental gain and cepstral distance, as well as informal listening tests, is superior to that by a conventional nonlinear spectral subtraction method and the previously proposed approach based upon sliding subspace projection.

Recently, there has been a growing interest in multiway probabilistic clustering. Some efficient algorithms have been developed for this problem. However, not much attention has been paid on how to detect the number of clusters for the general n-way clustering (n ≥ 2). To fill this gap, this problem is investigated based on n-way algebraic theory in this paper. A simple, yet efficient, detection method is proposed by eigenvalue decomposition (EVD), which is easy to implement. We justify this method. In addition, its effectiveness is demonstrated by the experiments on both simulated and real-world data sets.

We propose a novel efficient method of blind signal extraction from multi-sensor networks when each observed signal consists of one global signal and local uncorrelated signals. Most of existing blind signal separation and extraction methods such as independent component analysis have constraints such as statistical independence, non-Gaussianity, and underdetermination, and they are not suitable for global signal extraction problem from noisy observations. We developed an estimation algorithm based on alternating iteration and the smart weighted averaging. The proposed method does not have strong assumptions such as independence or non-Gaussianity. Experimental results using a musical signal and a real electroencephalogram demonstrate the advantage of the proposed method.

A problem of information separation in multichannel recordings is important in engineering applications such as brain computer/machine interfaces (BCI/BMI). Whereas this problem is not entirely new, engineering approaches connecting the mental states of humans and the observed electroencephalography (EEG) recordings are still in their infancy, mostly due to problems with electrophysiological denoising. The electrophysiological signals captured in form of the EEG carry brain activity in form of the neurophysiological components which are usually embedded in much higher power electrical muscle activity components (electromyography - EMG; electrooculography - EOG; etc.). In this paper we present an approach to remove muscular interference caused by eye-movements from EEG recorded during auditory experiments in an eight channel recording setting. This is achieved by analyzing the correlation of the oscillatory modes within a multichannel signal in the Hilbert domain. Simulations in a real world auditory BCI setting support the analysis.

The Common Spatial Patterns (CSP) algorithm has been widely used in EEG classification and Brain Computer Interface (BCI). In this paper, we propose a multilinear formulation of the CSP, termed as TensorCSP or Common Tensor Discriminant Analysis (CTDA) for high-order tensor data. As a natural extension of CSP, the proposed algorithm uses the analogous optimization criteria in CSP and a new framework for simultaneous optimization of projection matrices on each mode based on tensor analysis theory is developed. Experimental results demonstrate that our proposed algorithm is able to improve classification accuracy of multi-class motor imagery EEG.

Blind source extraction is one of the most important problems for multi-sensor networks. We propose a blind source extraction and deconvolution method in the presence of noise. We use MA-model for the signal generation model, and the convolutive observation model. The parameter of MA-model and the observations are obtained from an alternating least square (ALS) algorithm. The reconstruction is done by an spatiotemporal inverse filter such that it minimizes the Euclidean distance between the original signal and the reconstruction signal. Experimental results demonstrate advantages of the proposed method.

In this letter, we propose a new algorithm for estimating sparse nonnegative sources from a set of noisy linear mixtures. In particular, we consider difficult situations with high noise levels and more sources than sensors (underdetermined case). We show that when sources are very sparse in time and overlapped at some locations, they can be recovered even with very low signal-to-noise ratio, and by using many fewer sensors than sources. A theoretical analysis based on Bayesian estimation tools is included showing strong connections with algorithms in related areas of research such as ICA, NMF, FOCUSS, and sparse representation of data with overcomplete dictionaries. Our algorithm uses a Bayesian approach by modeling sparse signals through mixed-state random variables. This new model for priors imposes l(0) norm-based sparsity. We start our analysis for the case of nonoverlapped sources (1-sparse), which allows us to simplify the search of the posterior maximum avoiding a combinatorial search. General algorithms for overlapped cases, such as 2-sparse and k-sparse sources, are derived by using the algorithm for 1-sparse signals recursively. Additionally, a combination of our MAP algorithm with the NN-KSVD algorithm is proposed for estimating the mixing matrix and the sources simultaneously in a real blind fashion. A complete set of simulation results is included showing the performance of our algorithm.

We present a novel approach to quantify the statistical interdependence of two time series, referred to as stochastic event synchrony (SES). The first step is to extract the two given time series. The next step is to try to align events from one time series with events from the other. The better the alignment the more similar the two series are considered to be. More precisely, the similarity is quantified by the following parameters: time delay, variance of the time jitter, fraction of noncoincident events, and average similarity of the aligned events. The pairwise alignment and SES parameters are determined by statistical inference. In particular, the SES parameters are computed by maximum a posteriori (MAP) estimation, and the pairwise alignment is obtained by applying the max product algorithm. This letter deals with one-dimensional point processes; the extension to multidimensional point processes is considered in a companion letter in this issue. By analyzing surrogate data, we demonstrate that SES is able to quantify both timing precision and event reliability more robustly than classical measures can. As an illustration, neuronal spike data generated by Morris-Lecar neuron model are considered.

Stochastic event synchrony is a technique to quantify the similarity of pairs of signals. First, events are extracted from the two given time series. Next, one tries to align events from one time series with events from the other. The better the alignment, the more similar the two time series are considered to be. In Part I, the companion letter in this issue, one-dimensional events are considered; this letter concerns multidimensional events. Although the basic idea is similar, the extension to multidimensional point processes involves a significantly more difficult combinatorial problem and therefore is nontrivial. Also in the multidimensional case, the problem of jointly computing the pairwise alignment and SES parameters is cast as a statistical inference problem. This problem is solved by coordinate descent, more specifically, by alternating the following two steps: (1) estimate the SES parameters from a given pairwise alignment; (2) with the resulting estimates, refine the pairwise alignment. The SES parameters are computed by maximum a posteriori (MAP) estimation (step 1), in analogy to the one-dimensional case. The pairwise alignment (step 2) can no longer be obtained through dynamic programming, since the state space becomes too large. Instead it is determined by applying the max-product algorithm on a cyclic graphical model. In order to test the robustness and reliability of the SES method, it is first applied to surrogate data. Next, it is applied to detect anomalies in EEG synchrony of mild cognitive impairment (MCI) patients. Numerical results suggest that SES is significantly more sensitive to perturbations in EEG synchrony than a large variety of classical synchrony measures.

A novel approach to measure the interdependence of time series is proposed, based on the alignment ("matching") of their Huang-Hilbert spectra. The method consists of three steps: first, empirical modes are extracted from the signals; those functions carry non-linear and non-stationary components in frequency limited bands. Second, the empirical modes are Hilbert transformed, resulting in very sharply localized ridges in the time- frequency plane; the obtained time-frequency representations are known as Huang-Hilbert spectra. At last, the latter are pairwise aligned by means of the stochastic-event synchrony method (SES), a recently proposed procedure to match pairs of multi-dimensional point processes. The level of similarity of two Huang-Hilbert spectra is quantified by three parameters: timing and frequency jitter of coincident ridges, and fraction of non-coincident ridges. The proposed method is used to detect steady-state visually evoked potentials (SSVEP) in electroencephalography (EEG) signals; numerical results indicate that the method is vastly more sensitive to SSVEP than classical synchrony measures, and therefore, it may prove to be useful in applications such as brain-computer interfaces. Although the paper mostly deals with EEG, the presented synchrony measure may also be applied to other kinds of time series.

Nonnegative tucker decomposition (NTD) is a recent multiway extension of nonnegative matrix factorization (NMF), where nonnega- tivity constraints are incorporated into Tucker model. In this paper we consider alpha-divergence as a discrepancy measure and derive multiplicative updating algorithms for NTD. The proposed multiplicative algorithm includes some existing NMF and NTD algorithms as its special cases, since alpha-divergence is a one-parameter family of divergences which accommodates KL-divergence, Hellinger divergence, X2divergence, and so on. Numerical experiments on face images show how different values of alpha affect the factorization results under different types of noise.

Anomalous environmental electromagnetic (EM) radiation waves have been reported as the portents of earthquakes. We have been measuring the Extremely Low Frequency (ELF) range all over Japan. Our goal is to predict earthquakes using EM radiation waves. Previously, we proposed a method of detecting anomalous signals by focusing on linear prediction errors. However, this method also sensitively responds to earthquake-unrelated anomaly. For accurate earthquake-prediction, we should eliminate earthquake-unrelated signals. In this paper, we try to reduce false detection rate by global signal elimination using Non-negative Matrix Factorization (NMF) and evaluate the effectiveness of this method.

The paper presents the application of a single-class Support Vector Machine (SVM) for localization of the focus region at the epileptic seizure on the basis of EEG registration. The diagnostic features used in recognition are derived from the directed transfer function description, determined for different ranges of EEG signals. The results of the performed numerical experiments for the localization of the seizure focus in the brain have been confirmed by the real surgery of the brain for few patients.

A major challenge in applying machine learning methods to Brain-Computer Interfaces (BCIs) is to overcome the on-line non-stationarity of the data blocks. An effective BCI system should be adaptive to and robust against the dynamic variations in brain signals. One solution to it is to adapt the model parameters of BCI system online. However, CSP is poor at adaptability since it is a batch type algorithm. To overcome this, in this paper, we propose the Incremental Common Spatial Pattern (ICSP) algorithm which performs the adaptive feature extraction on-line. This method allows us to perform the online adjustment of spatial filter. This procedure helps the BCI system robust to possible non-stationarity of the EEG data. We test our method to data from BCI motor imagery experiments, and the results demonstrate the good performance of adaptation of the proposed algorithm.

Overcomplete representations have greater robustness in noise environment and also have greater flexibility in matching structure in the data. Lewicki and Sejnowski (2000) proposed an efficient extended natural gradient for learning the overcomplete basis and developed an overcomplete representation approach. However, they derived their gradient by many approximations, and their proof is very complicated. To give a stronger theoretical basis, we provide a brief and more rigorous mathematical proof for this gradient in this note. In addition, we propose a more robust constrained Lewicki-Sejnowski gradient.

This paper discusses the estimation and numerical calculation of the probability that the 0-norm and 1-norm solutions of underdetermined linear equations are equivalent in the case of sparse representation. First, we define the sparsity degree of a signal. Two equivalence probability estimates are obtained when the entries of the 0-norm solution have different sparsity degrees. One is for the case in which the basis matrix is given or estimated, and the other is for the case in which the basis matrix is random. However, the computational burden to calculate these probabilities increases exponentially as the number of columns of the basis matrix increases. This computational complexity problem can be avoided through a sampling method. Next, we analyze the sparsity degree of mixtures and establish the relationship between the equivalence probability and the sparsity degree of the mixtures. This relationship can be used to analyze the performance of blind source separation (BSS). Furthermore, we extend the equivalence probability estimates to the small noise case. Finally, we illustrate how to use these theoretical results to guarantee a satisfactory performance in underdetermined BSS.

In this paper we propose new algorithms for 3D tensor decomposition/factorization with many potential applications, especially in multi-way blind source separation (BSS), multidimensional data analysis, and sparse signal/image representations. We derive and compare three classes of algorithms: multiplicative, fixed-point alternating least squares (FPALS) and alternating interior-point gradient (AIPG) algorithms. Some of the proposed algorithms are characterized by improved robustness, efficiency and convergence rates and can be applied for various distributions of data and additive noise.

A novel measure to quantify the synchrony between two sparse binary strings is proposed, referred to as "stochastic event synchrony" (SES). It is computed by performing inference in a probabilistic model. SES can amongst other be used to detect synchrony in neural signals, in particular, spike trains (obtained from electrophysiological recordings) and EEG signals. It is demonstrated how SES can quantify the firing reliability of a neuron. It is also shown how SES can be used as a feature to detect Alzheimer's disease based on EEG signals.

Electroencephalographic (EEG) recordings are, most of the times, corrupted by spurious artifacts, which should be rejected or cleaned by the practitioner. As human scalp EEG screening is error-prone, automatic artifact detection is an issue of capital importance, to ensure objective and reliable results. In this paper we propose a new approach for discrimination of muscular activity in the human scalp quantitative EEG (QEEG), based on the time-frequency shape analysis. The impact of the muscular activity on the EEG can be evaluated from this methodology. We present an application of this scoring as a preprocessing step for EEG signal analysis, in order to evaluate the amount of muscular activity for two sets of EEG recordings for dementia patients with early stage of Alzheimer's disease and control age-matched subjects.

We propose a novel similarity measure, called the correntropy coefficient, sensitive to higher order moments of the signal statistics based on a similarity function called crosscorrentopy. Crossorrentropy nonlinearly maps the original time series into a high-dimensional reproducing kernel Hilbert space (RKHS). The correntropy coefficient computes the cosine of the angle between the transformed vectors. Preliminary experiments with simulated data and multichannel electroencephalogram (EEG) signals during behavior studies elucidate the performance of the new measure versus the well established correlation coefficient.

A novel approach to measure the interdependence of two time series is proposed, referred to as “stochastic event synchrony” (SES); it quantifies the alignment of two point processes by means of the following parameters: time delay, variance of the timing jitter, fraction of “spurious” events, and average similarity of events. SES may be applied to generic one-dimensional and multi-dimensional point pro- cesses, however, the paper mainly focusses on point processes in time-frequency domain. The average event similarity is in that case described by two parameters: the average frequency offset between events in the time-frequency plane, and the variance of the frequency offset (“frequency jitter”); SES then consists of five pa- rameters in total. Those parameters quantify the synchrony of oscillatory events, and hence, they provide an alternative to existing synchrony measures that quan- tify amplitude or phase synchrony. The pairwise alignment of point processes is cast as a statistical inference problem, which is solved by applying the max- product algorithm on a graphical model. The SES parameters are determined from the resulting pairwise alignment by maximum a posteriori (MAP) estimation. The proposed interdependence measure is applied to the problem of detecting anoma- lies in EEG synchrony of Mild Cognitive Impairment (MCI) patients; the results indicate that SES significantly improves the sensitivity of EEG in detecting MCI.

The most popular algorithms for Nonnegative Matrix Factorization (NMF) belong to a class of multiplicative Lee-Seung algorithms which have usually relative low complexity but are characterized by slow-convergence and the risk of getting stuck to in local minima. In this paper, we present and compare the performance of additive algorithms based on three different variations of a projected gradient approach. Additionally, we discuss a novel multilayer approach to NMF algorithms combined with multi-start initializations procedure, which in general, considerably improves the performance of all the NMF algorithms. We demonstrate that this approach (the multilayer system with projected gradient algorithms) can usually give much better performance than standard multiplicative algorithms, especially, if data are ill-conditioned, badly-scaled, and/or a number of observations is only slightly greater than a number of nonnegative hidden components. Our new implementations of NMF are demonstrated with the simulations performed for Blind Source Separation (BSS) data.

In this paper we present a method for continuous EEG classification, where we employ nonnegative tensor factorization (NTF) to determine discriminative spectral features and use the Viterbi algorithm to continuously classify multiple mental tasks. This is an extension of our previous work on the use of nonnegative matrix factorization (NMF) for EEG classification. Numerical experiments with two data sets in BCI competition, confirm the useful behavior of the method for continuous EEG classification.

Convolutive blind source separation (CBSS) that exploits the sparsity of source signals in the frequency domain is addressed in this paper. We assume the sources follow complex Laplacian-like distribution for complex random variable, in which the real part and imaginary part of complex-valued source signals are not necessarily independent. Based on the maximum a posteriori (MAP) criterion, we propose a novel natural gradient method for complex sparse representation. Moreover, a new CBSS method is further developed based on complex sparse representation. The developed CBSS algorithm works in the frequency domain. Here, we assume that the source signals are sufficiently sparse in the frequency domain. If the sources are sufficiently sparse in the frequency domain and the filter length of mixing channels is relatively small and can be estimated, we can even achieve underdetermined CBSS. We illustrate the validity and performance of the proposed learning algorithm by several simulation examples.

A critical analysis of the canonical correlation analysis (CCA) approach in blind source separation (BSS) is provided. It is proved that by maximizing the autocorrelation functions of the recovered signals we can separate the source signals successfully. It is further shown that the CCA approach represents the same class of generalized eigenvalue decomposition (GEVD) problems as the matrix pencil method. Finally, online realizations of the CCA approach are discussed with a linear-predictor-based algorithm studied as an example.

Awareness-enabled coordination (AEC) is a platform designed to address the problem of scaling collaboration to large multi-organizational teams. Such collaboration is inhibited by the complexity in multi-organizational environments and lack of efficiency in achieving team objectives. AEC provides a contextualization mechanism that deals with such complex, real world environments where teams involve humans, tools, software services, and agents that come from different organizations, are subject to multiple jurisdictions, and provide diverse expertise. To provide efficiency in achieving team objectives, AEC provides situation- and project-related awareness, as well as process-based coordination and automation. We describe the AEC architecture and discuss AEC models and mechanisms for computing awareness and coordinating action. We use examples from the homeland security domain to illustrate these AEC technical capabilities and their benefits

Approximate non-negative matrix factorization (NMF) is an emerging technique with a wide spectrum of potential applications in biomedical data analysis. In this paper, we proposed a new NMF algorithm with temporal smoothness constraint that aims to extract non-negative components that have meaningful physical or physiological interpretations. We propose two constraints and derive new multiplicative learning rules. Specifically, we apply the proposed algorithm, combined with advanced time-frequency analysis and machine learning techniques, to early detection of Alzheimer disease using clinical EEG recordings. Empirical results show promising performance.

In this paper we introduce a new error measure, integrated reconstruction error (IRE), the minimization of which leads to principal eigenvectors (without rotational ambiguity) of the data covariance matrix. Then we present iterative algorithms for the IRE minimization, through the projection approximation. The proposed algorithm is referred to as COnstrained Projection Approximation (COPA) algorithm and its limiting case is called COPAL. We also discuss regularized algorithms, referred to as R-COPA and R-COPAL. Numerical experiments demonstrate that these algorithms successfully find exact principal eigenvectors of the data covariance matrix.

In this paper we develop several algorithms for non-negative matrix factorization (NMF) in applications to blind (or semi blind) source separation (BSS), when sources are generally statistically dependent under conditions that additional constraints are imposed such as nonnegativity, sparsity, smoothness, lower complexity or better predictability. We express the non-negativity constraints using a wide class of loss (cost) functions, which leads to an extended class of multiplicative algorithms with regularization. The proposed relaxed forms of the NMF algorithms have a higher convergence speed with the desired constraints. Moreover, the effects of various regularization and constraints are clearly shown. The scope of the results is vast since the discussed loss functions include quite a large number of useful cost functions such as weighted Euclidean distance, relative entropy, Kullback Leibler divergence, and generalized Hellinger, Pearson's, Neyman's distances, etc

In this paper we propose a new algorithm for identifying mixing (basis) matrix A knowing only sensor (data) matrix X for linear model X = AS + E, under some weak or relaxed conditions, expressed in terms of sparsity of latent (hidden) components represented by the matrix S. We present a simple and efficient on-line algorithm for such identification and illustrate its performance by estimation of unknown matrix A and source signals S. The main feature of the proposed algorithm is its adaptivity to changing environment and robustness in respect to noise and outliers that do not satisfy sparseness conditions

An analysis of the canonical correlation analysis (CCA) approach in blind source separation is provided. In particular, it is proved that by maximizing the autocorrelation functions of the recovered signals we can separate the source signals successfully. We show that the CCA approach represents the same generalised eigenvalue decomposition problem introduced in the matrix pencil method. Finally, an adaptive blind source extraction (BSE) algorithm is derived as an online realisation of the CCA approach. Simulation results verify the proposed approach

The blind source extraction (BSE) problem for noisy measurements is addressed using the linear predictor method. Based on a previously proposed method for the noise-free case, we propose a cost function with the effect of noise removed. Two adaptive algorithms are next introduced, one of which is based on minimisation of the normalised mean square prediction error (MSPE), whereas the other minimises the MSPE using prewhitening followed by regularisation of the demixing vector. The successful operation of these algorithms requires the knowledge of the correlation matrix of noise

In this paper, we introduce a new error measure, integrated reconstruction error (IRE) and show that the minimization of IRE leads to principal eigenvectors (without rotational ambiguity) of the data covariance matrix. Then, we present iterative algorithms for the IRE minimization, where we use the projection approximation. The proposed algorithm is referred to as COnstrained Projection Approximation (COPA) algorithm and its limiting case is called COPAL. Numerical experiments demonstrate that these algorithms successfully find exact principal eigenvectors of the data covariance matrix.

An important application of sparse representation is underdetermined blind source separation (BSS), where the number of sources is greater than the number of observations. Within the stochastic framework, this paper discusses recoverability of underdetermined BSS based on a two-stage sparse representation approach. The two-stage approach is effective when the source matrix is sufficiently sparse. The first stage of the two-stage approach is to estimate the mixing matrix, and the second is to estimate the source matrix by minimizing the 1-norms of the source vectors subject to some constraints. After estimating the mixing matrix and fixing the number of nonzero entries of a source vector, we estimate the recoverability probability (i.e., the probability that the source vector can be recovered). A general case is then considered where the number of nonzero entries of the source vector is fixed and the mixing matrix is drawn from a specific probability distribution. The corresponding probability estimate on recoverability is also obtained. Based on this result, we further estimate the recoverability probability when the sources are also drawn from a distribution (e.g., Laplacian distribution). These probability estimates not only reflect the relationship between the recoverability and sparseness of sources, but also indicate the overall performance and confidence of the two-stage sparse representation approach for solving BSS problems. Several simulation results have demonstrated the validity of the probability estimation approach.

In this paper, we use a two-stage sparse factorization approach for blindly estimating the channel parameters and then estimating source components for electroencephalogram (EEG) signals. EEG signals are assumed to be linear mixtures of source components, artifacts, etc. Therefore, a raw EEG data matrix can be factored into the product of two matrices, one of which represents the mixing matrix and the other the source component matrix. Furthermore, the components are sparse in the time-frequency domain, i.e., the factorization is a sparse factorization in the time frequency domain. It is a challenging task to estimate the mixing matrix. Our extensive analysis and computational results, which were based on many sets of EEG data, not only provide firm evidences supporting the above assumption, but also prompt us to propose a new algorithm for estimating the mixing matrix. After the mixing matrix is estimated, the source components are estimated in the time frequency domain using a linear programming method. In an example of the potential applications of our approach, we analyzed the EEG data that was obtained from a modified Sternberg memory experiment. Two almost uncorrelated components obtained by applying the sparse factorization method were selected for phase synchronization analysis. Several interesting findings were obtained, especially that memory-related synchronization and desynchronization appear in the alpha band, and that the strength of alpha band synchronization is related to memory performance.

A novel stereophonic noise reduction method is proposed. This method is based upon a combination of a subspace approach realized in a sliding window operation and two-channel adaptive signal enhancing. The signal obtained from the signal subspace is used as the input signal to the adaptive signal enhancer for each channel, instead of noise, as in the ordinary adaptive noise canceling scheme. Simulation results based upon real stereophonic speech contaminated by noise components show that the proposed method gives improved enhancement quality in terms of both segmental gain and cepstral distance performance indices in comparison with conventional nonlinear spectral subtraction approaches.

In this letter, we solve the problem of identifying matrices S is an element of R(n x N) and A is an element of R(m x n) knowing only their multiplication X = AS, under some conditions, expressed either in terms of A and sparsity of S (identifiability conditions), or in terms of X (sparse component analysis (SCA) conditions). We present algorithms for such identification and illustrate them by examples.

We formulate conditions (k-SCA-conditions) under which we can represent a given (m/spl times/N)-matrix, X, (data set) uniquely (up to scaling and permutation) as a multiplication of m/spl times/n and n/spl times/N matrices, A and S, (often called mixing matrix or dictionary and source matrix, respectively), such that S is sparse of level n-m+k in the sense that each column of S has at least n-m+k zero elements. We call this the k-sparse component analysis problem (k-SCA). Conditions on a matrix, S, are presented such that the k-SCA-conditions are satisfied for the matrix X=AS, where A is an arbitrary matrix from some class. This is the blind source separation problem and the above conditions are called identifiability conditions. We present new algorithms for matrix identification (under k-SCA-conditions), and for source recovery (under identifiability conditions). The methods are illustrated with examples, showing good separation of the high-frequency part of mixtures of images after appropriate sparsification.

We introduce a new extended model for independent component analysis (ICA) and/or blind source separation (BSS), in which the assumption of the standard ICA model that the source signals are mutually independent (or spatio-temporally uncorrelated) is relaxed. The source is presumed to be the sum of some independent and/or dependent subcomponents. We show a practical solution for this class of blind separation problem by using subband decomposition (SD) and the independence test by analyzing global mixing-demixing matrices obtained for various subbands or multi-bands. This is a very simple but efficient technique, and users just apply the proposed method to conventional ICA/BSS algorithms as pre- and post-processing. The proposed method has been tested for blind separation problems with partially dependent sources. The results indicate that the method is promising for the signal separation problem of speech, image, EEG data, etc.

In this letter, we analyze a two-stage cluster-then-l(1)-optimization approach for sparse representation of a data matrix, which is also a promising approach for blind source separation (BSS) in which fewer sensors than sources are present. First, sparse representation (factorization) of a data matrix is discussed. For a given overcomplete basis matrix, the corresponding sparse solution (coefficient matrix) with minimum l(1) norm is unique with probability one, which can be obtained using a standard linear programming algorithm. The equivalence of the l(1)-norm solution and the l(0)-norm solution is also analyzed according to a probabilistic framework. If the obtained l(1)-norm solution is sufficiently sparse, then it is equal to the l(0)-norm solution with a high probability. Furthermore, the l(1)- norm solution is robust to noise, but the l(0)-norm solution is not, showing that the l(1)-norm is a good sparsity measure. These results can be used as a recoverability analysis of BSS, as discussed. The basis matrix in this article is estimated using a clustering algorithm followed by normalization, in which the matrix columns are the cluster centers of normalized data column vectors. Zibulevsky, Pearlmutter, Boll, and Kisilev (2000) used this kind of two-stage approach in underdetermined BSS. Our recoverability analysis shows that this approach can deal with the situation in which the sources are overlapped to some degree in the analyzed domain and with the case in which the source number is unknown. It is also robust to additive noise and estimation error in the mixing matrix. Finally, four simulation examples and an EEG data analysis example are presented to illustrate the algorithm's utility and demonstrate its performance.

This paper reports a study on the problem of the blind simultaneous extraction of specific groups of independent components from a linear mixture. This paper first presents a general overview and unification of several information theoretic criteria for the extraction of a single independent component. Then, our contribution fills the theoretical gap that exists between extraction and separation by presenting tools that extend these criteria to allow the simultaneous blind extraction of subsets with an arbitrary number of independent components. In addition, we analyze a family of learning algorithms based on Stiefel manifolds and the natural gradient ascent, present the nonlinear optimal activations (score) functions, and provide new or extended local stability conditions. Finally, we illustrate the performance and features of the proposed approach by computer-simulation experiments.

Independent component analysis is to extract independent signals from their linear mixtures without assuming prior knowledge of their mixing coefficients. As we know, a number of factors are likely to affect separation results in practical applications, such as the number of active sources, the distribution of source signals, and noise. The purpose of this paper to develop a general framework of blind separation from a practical point of view with special emphasis on the activation function adaptation. First, we propose the exponential generative model for probability density functions. A method of constructing an exponential generative model from the activation functions is discussed. Then, a learning algorithm is derived to update the parameters in the exponential generative model. The learning algorithm for the activation function adaptation is consistent with the one for training the demixing model. Stability analysis of the learning algorithm for the activation function is also discussed. Both theoretical analysis and simulations show that the proposed approach is universally convergent regardless of the distributions of sources. Finally, computer simulations are given to demonstrate the effectiveness and validity of the approach.

This paper proposes a novel grouping decision approach for blind deconvolution of FIR channels with binary sources. First, necessary and sufficient conditions for recoverability are derived. For single-input systems, a new deterministic algorithm based on grouping and decision is propose to recover the source up to a delay. Then the algorithm is extended to deal with high noise case and long decaying channel case. Furthermore blind deconvolution for multi-input systems also can be carried out as with the case of single input systems. All sources can be recovered sequentially. Finally, the validity and performance of the algorithms are illustrated by several simulation examples.

In this paper, sparse representation (factorization) of a data matrix is first discussed. An overcomplete basis matrix is estimated by using the K(cid:0)means method. We have proved that for the estimated overcom- plete basis matrix, the sparse solution (coefficient matrix) with minimum l1(cid:0)norm is unique with probability of one, which can be obtained using a linear programming algorithm. The comparisons of the l1(cid:0)norm so- lution and the l0(cid:0)norm solution are also presented, which can be used in recoverability analysis of blind source separation (BSS). Next, we ap- ply the sparse matrix factorization approach to BSS in the overcomplete case. Generally, if the sources are not sufficiently sparse, we perform blind separation in the time-frequency domain after preprocessing the observed data using the wavelet packets transformation. Third, an EEG experimental data analysis example is presented to illustrate the useful- ness of the proposed approach and demonstrate its performance. Two almost independent components obtained by the sparse representation method are selected for phase synchronization analysis, and their peri- ods of significant phase synchronization are found which are related to tasks. Finally, concluding remarks review the approach and state areas that require further study.

Redundancy reduction as a form of neural coding has been since the early sixties a topic of large research interest. A number of strategies has been proposed, but the one which is attracting most attention recently assumes that this coding is carried out so that the output signals are mutually independent. In this work we go one step further and suggest an strategy to deal also with non-orthogonal signals (i.e., "dependent" signals). Moreover, instead of working with the usual squared error, we design a neuron where the non-linearity is operating on the error. It is computationally more economic and, importantly, the permutation/scaling problem is avoided. The framework is given with a biological background, as we avocate throughout the manuscript that the algorithm fits well the single neuron and redundancy reduction doctrine. Moreover, we show that wavelet-like receptive fields emerges from natural images processed by this algorithm.

We propose a robust approach for independent component analysis (ICA) of signals where observations are contaminated with high-level additive noise and/or outliers. The source signals may contain mixtures of both sub-Gaussian and super-Gaussian components, and the number of sources is unknown. Our robust approach includes two procedures. In the first procedure, a robust prewhitening technique is used to reduce the power of additive noise, the dimensionality and the correlation among sources. A cross-validation technique is introduced to estimate the number of sources in this first procedure. In the second procedure, a nonlinear function is derived using the parameterized t-distribution density model. This nonlinear function is robust against the undue influence of outliers fundamentally. Moreover, the stability of the proposed algorithm and the robust property of misestimating the parameters (kurtosis) have been studied. By combining the t-distribution model with a family of light-tailed distributions (sub-Gaussian) model, we can separate the mixture of sub-Gaussian and super-Gaussian source components. Through the analysis of artificially synthesized data and real-world magnetoencephalographic (MEG) data, we illustrate the efficacy of this robust approach.

We show that statistically independent source signals can be separated simultaneously, if for some time delays p they have nonzero cumulants cusi(p) = cu{si(k), Si(k), Si(k − p), Si(k − p)}. If the sources have distinct cumulant functions, then the separation is possible with another procedure, which could be more effective for large scale problems. In both cases the problem of blind source separation can be converted to a symmetric eigenvalue problem of a generalized cumulant matrices, which are not sensitive to Gaussian noise. We propose new algorithms, based on the non-smooth optimization theory, which disperse the eigenvalues of these generalized cumulant matrices. We propose new orthogonalization procedure for the mixing matrix, which is robust to additive Gaussian noise.

Operation support systems (OSSs) integrate software components and network elements to automate the provisioning and monitoring of telecommunications services. This paper illustrates Telcordia's Cable OSS and shows how customers may use this OSS to provision IP and telephone services over the cable infrastructure. Telcordia's Cable OSS is a process-based application, i.e. a collection of flows, specialized components (e.g. a billing system, a call agent soft switch, network services and elements, cable modems, etc.) and corresponding adaptors that are integrated, coordinated and monitored using CMI (Collaboration Management Infrastructure), Telcordia's advanced process-based integration technology. Customers interact with the Cable OSS by using Web or IVR (interactive voice response) interfaces.

Collaboration management involves capturing the collaboration process, coordinating the activities of the participating applications and humans, and/or providing awareness, i.e. information that is highly relevant to a specific role and situation of a process participant. In this paper, we propose an awareness provisioning solution that allows focusing, customizing, and temporally constraining the awareness delivered to each process participant. Unlike existing collaboration management technologies (such as workflow and groupware) that provide only a few built-in awareness choices, the proposed awareness solution allows the specification of what information is to be given to what users and at what time. To support this advanced level of awareness, we require the definition of awareness roles and the specification of corresponding awareness descriptions. Awareness roles can be dynamically created and associated with any process scope. Awareness descriptions define what information is to be given to users in an awareness role. Since awareness roles are created or become visible when they are needed, the existence of an awareness role also determines the appropriate time interval during which the information specified in the awareness description can be delivered. This awareness provisioning approach minimizes information overloading and allows the combination of process-relevant information with external information as needed by the process participants. The proposed awareness provisioning solution is employed by the Collaboration Management Infrastructure (CMI), a federated system for collaboration process management. In this paper, we introduce an Awareness Model (AM) for creating awareness specifications and defining related execution semantics. Awareness specifications in AM are specialized composite event specifications that define patterns of process-related events and external events, as well as how information should be digested from them. We also describe the implementation of CMI's awareness provisioning engine and related tools.

In this letter, we consider the problem of simultaneous blind signal extraction of arbitrary group sources from a rather large number of observations. Amari (2000) proposed a gradient algorithm that optimizes the maximum-likelihood (ML) criteria on the Stiefel manifold and solves the problem when the approximate (or hypothetical) densities of the desired signals are a priori known. This letter shows how to extend this result to other contrast functions that do not require explicit knowledge of the sources densities. We also present the algorithm necessary and sufficient local stability conditions, providing useful bounds for the learning step size.

A novel approach is proposed in order to reduce the number of sweeps (trials) required for the efficient extraction of the brain evoked potentials (EP). This approach is developed by combining both the Wiener filtering and the subspace methods. First, the signal subspace is estimated by applying the singular-value decomposition (SVD) to an enhanced version of the raw data obtained by Wiener filtering. Next, estimation of the EP data is achieved by orthonormal projection of the raw data onto the estimated signal subspace. Simulation results show that combination of both methods provides much better capability than each of them separately.

This paper presents a novel adaptive filtering approach for the classification and tracking of the electroencephalogram (EEG) waves. In this approach, an adaptive recursive bandpass filter is employed for estimating and tracking the center frequency associated with each EEG wave. The main advantage inherent in the approach is that the employed adaptive filter only requires one coefficient to be updated. This coefficient represents an efficient distinct feature for each EEG specific wave and its time function reflects the nonstationarity of the EEG signal. Extensive simulations for synthetic and real world EEG data for the detection of sleep spindles show the effectiveness and usefulness of the presented approach.

In this work we develop a very simple batch learning algorithm for semiblind extraction of a desired source signal with temporal structure from linear mixtures. Although we use the concept of sequential blind extraction of sources and independent component analysis, we do not carry out the extraction in a completely blind manner; neither do we assume that sources are statistically independent. In fact, we show that the a priori information about the autocorrelation function of primary sources can be used to extract the desired signals (sources of interest) from their linear mixtures. Extensive computer simulations and real data application experiments confirm the validity and high performance of the proposed algorithm.

This paper addresses local stability analysis for the flexible independent component analysis (ICA) algorithm where the generalized Gaussian density model was employed for blind separation of mixtures of sub- and super-Gaussian sources. In the flexible ICA algorithm, the shape of nonlinear function in the learning algorithm varies depending on the Gaussian exponent which is properly selected according to the kurtosis of estimated source. In the framework of the natural gradient in Stiefel manifold, the flexible ICA algorithm is revisited and some new results about its local stability analysis are presented.

This paper investigates new algorithms for blind source separation that use cumulants instead of nonlinearities matched to the probability distribution of the sources. It is demonstrated that separation is a saddle point of a cumulant-based entropy cost function. To determine this point we propose two quasi-Newton algorithms whose convergence is isotropic and does not depend on the sources distribution. Moreover, convergence properties remain the same when there is Gaussian noise in the mixture.

Processes for crisis mitigation must permit coordination flexibility and dynamic change to empower crisis mitigation coordinators and experts to deal with unexpected situations. However, such mitigation processes must also provide enough structure to prevent chaotic response and increase mitigation effectiveness. Such combination of structure and flexibility cannot be effectively supported by existing workflow or groupware technologies. In this paper, we introduce the Collaboration Management Infrastructure (CMI) and describe its capabilities for supporting crisis mitigation processes. CMI provides a comprehensive Collaboration Management Model (CMM) and a corresponding federated system. CMM supports process templates that provide the initial activities, control and data flow structure, and resources needed to start mitigating a variety of crisis situations. In the event of a crisis, the appropriate process template is selected and instantiated. Crisis mitigation is achieved by escalating the instantiated process template. Escalation involves selecting and adding new process templates, creating new activities, roles, and task forces as needed to deal with the current demands in the crisis, and delegating responsibilities to process participants and task forces. CMM provides advanced composable primitives that empower crisis mitigation coordinators and experts to escalate the process. We provide an overview of the implementation of a federated CMI system and discuss our initial experience with various applications in the area of crisis management.

The Collaboration Management lnfrastructure (CMI) has been developed at MCC to manage collaboration processes in both traditional and virtual enterprises, and to provide combined process and situation awareness. CMI technology development is driven by the requirements of many advanced applications provided by the companies that are members of the consortial CMI project. Such advanced applications include crisis mitigation, command and control, logistics, and service provisioning in virtual enterprises. These applications are not effectively supported by existing workflow and groupware technologies. To address the requirements imposed by these applications CMI provides a sophisticated Collaboration Management Model (CMM) and a corresponding component-oriented system that implements the CMM. CMM draws existing primitives from workflow and groupware models and introduces new primitives that address previously unsupported requirements of the CMI driver applications. In this paper, a crisis mitigation application is presented that involves several process templates which are extended dynamically as details about the crisis become known.

Independent component analysis or blind source separation extracts independent signals from their linear mixtures without assuming prior knowledge of their mixing coefficients. It is known that the independent signals in the observed mixtures can be successfully extracted except for their order and scales. In order to resolve the indeterminacy of scales, most learning algorithms impose some constraints on the magnitudes of the recovered signals. However, when the source signals are nonstationary and their average magnitudes change rapidly, the constraints force a rapid change in the magnitude of the separating matrix. This is the case with most applications (e.g., speech sounds, electroencephalogram signals). It is known that this causes numerical instability in some cases. In order to resolve this difficulty, this article introduces new nonholonomic constraints in the learning algorithm. This is motivated by the geometrical consideration that the directions of change in the separating matrix should be orthogonal to the equivalence class of separating matrices due to the scaling indeterminacy. These constraints are proved to be nonholonomic, so that the proposed algorithm is able to adapt to rapid or intermittent changes in the magnitudes of the source signals. The proposed algorithm works well even when the number of the sources is overestimated, whereas the existent algorithms do not (assuming the sensor noise is negligibly small), because they amplify the null components not included in the sources. Computer simulations confirm this desirable property.

In this paper we present an iterative inversion (II) approach to blind source separation (BSS). It consists of a quasi-Newton method for the resolution of an estimating equation obtained from the implicit inversion of a robust estimate of the mixing system. The resulting learning rule includes several existing algorithms for BSS as particular cases giving them a novel and unified interpretation.It also provides a justification of the Cardoso and Laheld step size normalization. The II method is first presented for instantaneous mixtures and then extended to the problem of blind separation of convolutive mixtures. Finally, we derive the necessary and sufficient asymptotic stability conditions for both the instantaneous and convolutive methods to converge.

Collaboration management involves capturing the collaboration process, coordinating the activities of the participating applications and humans, and/or providing awareness, i.e., information that is highly relevant to a specific role and situation of a process participant. We propose an awareness provisioning solution that allows customization of the awareness delivered to each process participant. Unlike existing collaboration management technologies (such as workflow and groupware) that provide only a few built-in awareness choices, the proposed awareness solution allows the specification of what information is to be given to what users and at what time. To support this advanced level of awareness, we require the definition of awareness roles and the specification of corresponding awareness descriptions. Awareness roles can be dynamically created and associated with any process scope. Awareness descriptions define what information is to be given to users in an awareness role. Since awareness roles are created or become visible when they are needed, the existence of an awareness role also determines the appropriate time interval during which the information specified in the awareness description can be delivered. This customized awareness provisioning approach minimizes information overloading and allows the combination of process-relevant information with external information as needed by the process participants. The proposed awareness provisioning solution is employed by the Collaboration Management Infrastructure (CMI), a federated system for collaboration process management. Examples from the crisis management domain are presented.

We present and compare two different spatio-temporal decorrelation learning algorithms for updating the weights of a linear feedforward network with FIR synapses (MIMO FIR filter). Both standard gradient and the natural gradient are employed to derive the spatio-temporal decorrelation algorithms. These two algorithms are applied to multichannel blind deconvolution task and their performance is compared. The rigorous derivation of algorithms and computer simulation results are presented.

We study the natural gradient approach to blind separation of overdetermined mixtures. First we introduce a Lie group on the manifold of overdetermined mixtures, and endow a Riemannian metric on the manifold based on the property of the Lie group. Then we derive the natural gradient on the manifold using the isometry of the Riemannian metric. Using the natural gradient, we present a new learning algorithm based on the minimization of mutual information.

Learning algorithms and underlying basic mathematical ideas are presented for the problem of adaptive blind signal processing, especially instantaneous blind separation and multichannel blind deconvolution/equalization of independent source signals. We discuss developments of adaptive learning algorithms based on the natural gradient approach and their properties concerning convergence, stability, and efficiency. Several promising schemas are proposed and reviewed in the paper. Emphasis is given to neural networks or adaptive filtering models and associated online adaptive nonlinear learning algorithms. Computer simulations illustrate the performances of the developed algorithms. Some results presented in this paper are new and are being published for the first time.

This paper presents the derivation of an unsupervised learning algorithm, which enables the identification and visualization of latent structure within ensembles of high-dimensional data. This provides a linear projection of the data onto a lower dimensional subspace to identify the characteristic structure of the observations independent latent causes. The algorithm is shown to be a very promising tool for unsupervised exploratory data analysis and data visualization. Experimental results confirm the attractiveness of this technique for exploratory data analysis and an empirical comparison is made with the recently proposed generative topographic mapping (GTM) and standard principal component analysis (PCA). Based on standard probability density models a generic nonlinearity is developed which allows both 1) identification and visualization of dichotomised clusters inherent in the observed data and 2) separation of sources with arbitrary distributions from mixtures, whose dimensionality may be greater than that of number of sources. The resulting algorithm is therefore also a generalized neural approach to independent component analysis (ICA) and it is considered to be a promising method for analysis of real-world data that will consist of sub- and super-Gaussian components such as biomedical signals.

Recursive radial basis function (RRBF) neural networks are introduced and discussed. We study in detail the nets with diagonal receptive field matrices. Parameters of the networks are learned by a simple procedure. Convergence and the rates of convergence of RRBF nets in the mean integrated absolute error (MIAE) sense are studied under mild conditions imposed on some of the network parameters. The obtained results also give the upper bounds on the performance of RRBF nets learned by minimizing the empirical L/sub 1/ error.

The paper presents a principal component analysis (PCA) approach to the reduction of noise contaminating the data. The PCA performs the role of lossy compression and decompression. The compression/decompression provides the means of coding the data and then recovering it with some losses, dependent on the realized compression ratio. In this process some part of the information contained in the data is lost. When the loss tolerance is equal to the noise strength, the noise and the loss tolerance are augmented and the decompressed signal is deprived of noise. This way of noise filtering has been checked on examples of 1-dimensional and 2-dimensional data and the results of numerical experiments are included.

We present a neural-network approach which allows sequential extraction of source signals from a linear mixture of multiple sources in the order determined by absolute values of normalized kurtosis. To achieve this, we develop a non-linear Hebbian learning rule for extraction of a single signal. We discuss several techniques which enable extraction of signals not randomly but in the desired order. To prevent the same signals from being extracted several times, a robust deflation technique is used which eliminates from the mixture the already extracted signals. Extensive computer simulations confirm the validity and high performance of our method.

The goal of the InfoSleuth project at MCC is to exploit and synthesize new technologies into a unified system that retrieves and processes information in an ever-changing network of information sources. InfoSleuth has its roots in the Carnot project at MCC, which specialized in integrating heterogeneous information bases. However, recent emerging technologies such as internetworking and the World Wide Web have significantly expanded the types, availability, and volume of data available to an information management system. Furthermore, in these new environments, there is no formal control over the registration of new information sources, and applications tend to be developed without complete knowledge of the resources that will be available when they are run. Federated database projects such as Carnot that do static data integration do not scale up and do not cope well with this ever-changing environment. On the other hand, recent Web technologies, based on keyword search engines, are scalable but, unlike federated databases, are incapable of accessing information based on concepts. In this experience paper, we describe the architecture, design, and implementation of a working version of InfoSleuth. We show how InfoSleuth integrates new technological developments such as agent technology, domain ontologies, brokerage, and internet computing, in support of mediated interoperation of data and services in a dynamic and open environment. We demonstrate the use of information brokering and domain ontologies as key elements for scalability.

Article Free Access Share on The InfoSleuth Project Authors: R. J. Bayardo Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, Texas Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, TexasView Profile , W. Bohrer Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, Texas Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, TexasView Profile , R. Brice Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, Texas Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, TexasView Profile , A. Cichocki Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, Texas Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, TexasView Profile , J. Fowler Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, Texas Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, TexasView Profile , A. Halal Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, Texas Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, TexasView Profile , V. Kashyap Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, Texas Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, TexasView Profile , T. Ksiezyk Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, Texas Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, TexasView Profile , G. Martin Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, Texas Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, TexasView Profile , M. Nodine Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, Texas Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, TexasView Profile , M. Rashid Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, Texas Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, TexasView Profile , M. Rusinkiewicz Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, Texas Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, TexasView Profile , R. Shea Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, Texas Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, TexasView Profile , C. Unnikrishnan Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, Texas Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, TexasView Profile , A. Unruh Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, Texas Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, TexasView Profile , D. Woelk Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, Texas Microelectronics and Computer Technology Corporation (MCC), 3500 West Balcones Center Drive, Austin, TexasView Profile Authors Info & Claims SIGMOD '97: Proceedings of the 1997 ACM SIGMOD international conference on Management of dataJune 1997 Pages 543–545https://doi.org/10.1145/253260.253401Online:01 June 1997Publication History 7citation339DownloadsMetricsTotal Citations7Total Downloads339Last 12 Months2Last 6 weeks0 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteeReaderPDF

Noise is an unavoidable factor in real sensor signals. We study how additive and convolutive noise can be reduced or even eliminated in the blind source separation (BSS) problem. Particular attention is paid to cases in which the number of sensors is larger than the number of sources. We propose various methods and associated adaptive learning algorithms for such an extended BSS problem. Performance and validity of the proposed approaches are demonstrated by extensive computer simulations.

It is known that the independent component analysis (ICA) (also called blind source separation) can be applied only if the number of received signals (sensors) is at least equal to the number of mixed sources, contained in the sensor signals. In this paper an application of the ICA is proposed for hidden (secured) image transmission by communication channels. We assume that only a single image mixture is transmitted. A friendly receiver contains the remaining original sources and therefore it can separate the hidden image of lowest energy. The influence of two nonlossless signal reduction stages, compression by principal component analysis and signal quantization, onto the separation ability is tested. Constraints of the mixing process are discussed that make impossible the hidden image separation without the key images.

In this paper a new class of simplified low-cost analog artificial neural networks with on chip adaptive learning algorithms are proposed for solving linear systems of algebraic equations in real time. The proposed learning algorithms for linear least squares (LS), total least squares (TLS) and data least squares (DLS) problems can be considered as modifications and extensions of well known algorithms: the row-action projection-Kaczmarz algorithm and/or the LMS (Adaline) Widrow-Hoff algorithms. The algorithms can be applied to any problem which can be formulated as a linear regression problem. The correctness and high performance of the proposed neural networks are illustrated by extensive computer simulation results.

In many application areas the information that may be of interest to a user is stored under the control of multiple, autonomous database systems. To support global transactions in a multidatabase environment, we must coordinate the activities of multiple Database Management Systems that were designed for independent, stand-alone operation. The autonomy and heterogeneity of these systems present a major impediment to the direct adaptation of transaction management mechanisms developed for distributed databases. In this paper we introduce a transaction model designed for a multidatabase environment. A multidatabase transaction is defined by providing a set of (local) sub-transactions, together with their precedence and dataflow requirements. Additionally, the transaction designer may specify failure atomicity and execution atomicity requirements of the multidatabase transaction. These high-level specifications are then used by the scheduler of a multidatabase transaction to assure that its execution satisfies the constraints imposed by the semantics of the application. Uncontrolled interleaving of multidatabase transactions may lead to the violation of interdatabase integrity constraints. We discuss the issues involved in a concurrent execution of multidatabase transactions and propose a new concurrency control correctness criterion that is less restrictive than global serializability. We also show how the multidatabase SQL can be extended to allow the user to specify multidatabase transactions in a nonprocedural way.