Multi-view clustering (MVC) has attracted considerable attention in the signal processing field. However, two issues still remain: 1) They adopt the concatenation or weighted combination as the fusion strategies, which makes it difficult to ensure semantic robustness of fusion representations. 2) They suffer from dominant view dependency that models over-rely on views with stronger clustering signals and neglect weaker views. Therefore, an information-driven complementarity and consistency mining method (ICCM) is devised for multi-view clustering. Specifically, ICCM designs view-specific representation learning and cluster partitioning module to extract inherent information in each view. Then, ICCM introduces an entropy-oriented complementary aggregation module to learn semantics-robust fusion representations through inter-view nonlinear transformations. Meanwhile, it proposes an invariance-driven consistent partition module to capture consistent cluster assignments across views where an adaptive weighting strategy is introduced to balance contributions of each view via assigning greater weights to views with fuzzy structures. Finally, experiments on six datasets demonstrate that ICCM gains cutting-edge results in MVC. The code is available athttps://github.com/Yuzhe-Li123/ICCM.

Diffusion models have recently shown promise for time series forecasting (TSF), but existing methods rely solely on reverse denoising from Gaussian noise, introducing uncertainty and disrupting temporal structures. We propose Segmental Diffusion (SegDiff), a distance-aware framework for TSF that retrieves semantically similar historical segments to guide each diffusion step via an index-guided conditioning mechanism. A pretrained encoder computes pairwise segment similarities to build the retrieval index. We further introduce a Distance-Aware (DA) Module to estimate transition deltas at each reverse step, explicitly modeling temporal evolution. Trend-aware input augmentation with polynomial regression and moving average smoothing, along with a frequency decomposition module, enhances temporal consistency. Extensive experiments on benchmarks show that SegDiff consistently outperforms existing approaches, validating that segment-level retrieval and distance-aware modeling improve both forecasting accuracy and interpretability.

Multi-view representation is powerful to capture the complex characteristics of real-world data by integrating complementary information from various modalities. However, in many use cases, such as boiler combustion monitoring, factors including sensor sampling frequency, equipment malfunctions, and network delays can lead to temporal asynchrony in data collection. This asynchrony leads misaligned multi-modal data, furthering the difficulty of learning optimal fused representation. To address this misalignment in multi-view data, a body of methods based on autoencoders and non-negative matrix factorization (NMF) have been presented. However, those methods are incapable of jointly exploring the underlying structure inherent in each view as well as the semantic consistency and structural similarity across views. To these ends, we propose a novel sample-bundled optimization for multi-view aligned clustering, which is based on Enhanced Anchor Graph and Contrastive Propagation (termed asEAGCP). We state that there is semantic consistency among intra-class samples (with the same and cross views) and that the global structures across different views demonstrate similarity. By leveraging these associations, we introduce an enhanced anchor graph with learnable sample correlation and a contrastive graph with feature propagation. Specifically, each anchor graphs preserves the semantic relationship among same-view samples, while the contrastive graph propagates feature information across multi-view samples. Experimental results demonstrate the superiority of our method on benchmark datasets by validating its effectiveness in aligning and clustering multi-view data.

Due to its effectiveness and efficiency, graph-based multi-view clustering has recently attracted much attention. However, the multi-view data are often incomplete and unpaired in real-world applications as a consequence of data loss or corruption. Although efforts have been made through a series of methods to address the problems of incomplete or unpaired multi-view data, the following issues still persist: 1) Most existing methods only focus on the incomplete multi-view data or unpaired multi-view data, and exhibit weaknesses when addressing both incomplete and unpaired multi-view data simultaneously. 2) Some methods neglect the graph information of the data from different views during the learning process. To tackle these issues, we propose the Multi-view Graph Clustering framework with Cross-view Feature Fusion (MGCCFF), a novel approach for clustering incomplete and unpaired multi-view data. Specifically, MGCCFF learns soft clustering label information from complete data and utilizes this to capture category-level cross-view correspondences. It then learns latent representation enriched with cross-view information based on the established mappings. To obtain a multi-view graph structure under conditions of incomplete and unpaired data, MGCCFF innovatively integrates the concept of self-expression with the autoencoder architecture and exploits the latent relationships between labels and the graph structure, thereby enabling the generation of sparse and accurate graphical structure under multi-view conditions for the final clustering task. The experiments on incomplete and unpaired multi-view datasets demonstrate that MGCCFF outperforms state-of-the-art methods.

Automatically extracting relationships between entity pairs from vast biomedical texts presents a challenging research direction with substantial practical significance. For example, the correct identification of the interaction between drugs and drugs could help doctors guide patients to take the correct medication, thereby avoiding the occurrence of medical errors. However, the same statements containing different types of entity pair relationships are easily misclassified into the same category by classifiers because they share consistent semantic information. In order to solve the problems, a new Indexbased Triple Match BERT(ITM-BERT) method is proposed in this paper. Triple loss training strategy is introduced and triple data generation decision is made. If an instance has an identical opposite instance, no index is used to form the triple data. If not, the index method is used to match the global semantic information similarity, and the triple data is constructed according to the rules. After the construction is completed, the triple loss method is used for training, with the purpose of increasing the distance between different class instances, making the distance between the same class instances closer, and finally classifying the entity relationship category correctly. In this paper, our approach is validated on widely used benchmark datasets such as DDI2013, BioInfer, and AIMed. The results show that our approach is advanced compared with other models.

In recent years, deep learning based continuous time series prediction has achieved encouraging performance. However, there are still two problems: Firstly, existing methods struggle to accurately capture the multiple frequency components in time series data, including long-term low-frequency trends, mid-frequency intraday fluctuations, and high-frequency noise and sudden event-induced variations. Secondly, due to insufficient data volume and individual differences, current methods often encounter inadequate information extraction problems. To address these issues, this article proposes a LLM-empowered cross modal time series prediction with frequency decomposition learning (LTSP-CF). Specifically, LTSP-CF performs promptbased LLM encoding, transforming time series data into prompts and extracting feature embeddings using a pre-trained LLM. Then, it applies multi-frequency feature encoding to decompose the data and capture various frequency components. Meanwhile, cross-modal adaptive fusion integrates the extracted features through kernel-eigen pair sparse variational gaussian processes mechanisms. Furthermore, a custom decoder based on the Transformer architecture performs time-series forecasting. Finally, extensive experiments on two blood glucose datasets demonstrate that LTSP-CF achieves superior performance.

Multi-view clustering aims to divide samples into several clusters, by mining and utilizing the consistency and complementarity of multi-view data. Recent years, numerous deep contrastive multi-view clustering methods have been proposed to address the false negative issue by using self-supervised information. However, the quality of these self-supervised information was rarely taken into consideration, and using these information without discrimination can compromise training, leading to sub optimal performance. To tackle this issue, we propose Hard Sample Aware Robust Contrastive Learning for Multi-View Clustering(HearMVC). Concretely, we use self-supervised information and similarity to determine hard samples. The model focuses on these hard samples by assigning higher weights to enhance discriminative capability. Moreover, we utilize the confidence of self-supervised cluster assignment as weights, to strengthen the learning to confident samples and weaken the influence of unconfident samples. By simultaneously considering the weighting of hardness and confidence, our method can achieve best robustness and strongest discriminative capability. Extensive experiments on public datesets verify the effectiveness of our method.

In real world applications, multi-view data has attracted intensive attention due to the complex and complementary relationship across views. Multi-view representation learning (MvRL) focuses on obtaining consistent feature representation from multi-view data, and becomes a popular topic in multi-view research field. However, the relationship between different samples, i.e., the graph information, is usually ignored or excavated insufficiently in most existing MvRL methods, which only regard graph structure as regularization items instead of graph embedding for multi-view data. Besides, the limited learning capacity of the adopted shallow models is another challenge for MvRL. To tackle them, in this paper, we propose a novel unsupervised deep multi-view representation learning model guided by learnable graph structure, termed as LGG-DMRL. It first captures a multi-view consistent graph from original data based on self-representation learning, and explores the view-specific feature representation of each view by the designed graph guided attention network using the learnt graph. After that, the information bottleneck principle is employed to identify the shared representation across views integrated with the view-specific feature representations, promoting the multi-view complementarity and completeness. Experimental results on five real-world datasets demonstrate the superiority and effectiveness of our proposed LGG-DMRL compared with the recent state-of-the-art multi-view approaches.

Multi-modal data feature fusion can effectively improve the accuracy of primary modal pattern recognition and address the issue of missing data through multi-modal collaboration. To some extent, supplementing multi-view information can alleviate the conflict between medical images’ reliance on professional annotations and the limited number of annotations. However, there are still several challenges in engineering multimodal feature perception and fusion for medical images, including imbalanced patterns that make it challenging to establish a weighted allocation criterion suitable for different tasks, misleading factors not positively correlated with knowledge richness, and complexities associated with integrating modalities having diverse formats for text and time series data into overall feature engineering and similarity. This paper introduces a multi-modal semantic fusion model that is sensitive to key information represented by contextual cues. Furthermore, it incorporates a dynamic feature engineering scheme capable of acquiring and integrating important insights from three perspectives with an optimized structure. Additionally, it presents a novel similarity evaluation criteria and fusion mode that adaptively adjust weights based on their contributions, facilitating the measurement of target object category likelihoods across various modalities for weighted analyses. The system combines LSTM and CNN models to builda sequence and local information sensitive structure designed to integrate heterogeneous features while embedding the multimodal similarity fusion. Emphasizing small yet compelling pieces of information such as contextual cues that prompt medical representation assignment to the target category, our system places significant importance on specificity removal and accuracy enhancement, exemplified by introducing contextual information demonstrating our sensitivity to contextual cues despite our non-specifically structured approach.

The scarcity of annotated data and the challenge of generative models that meet the authenticity requirements collectively constrain the modeling of highly specialized deep medical models, making data remain a central issue in model training. The emergence of large-scale models has facilitated access to knowledge and data references for various tasks, even those with high specialization. Therefore, in the absence of data sources, latent knowledge and model structure can be considered for reuse instead of directly utilizing samples, and generalizing specific medical models based on large-scale models is expected to be competitive in the future. However, due to significant differences between fine-grained medical features and tasks, generalization based on large language models (LLMs) is not entirely satisfactory, it requires a more targeted inheritance of knowledge and important structures to achieve effective generalization. This paper presents a novel multi-modal medical model training approach designed to circumvent the need for extensive real data preparation, leveraging the capabilities of LLMs to generalize downstream tasks. Initially, knowledge threads are extracted to facilitate multi-modal diagnostic knowledge retrieval from LLMs without relying on massive datasets. These threads are then utilized to generate multimodal task instructions, guiding LLMs in providing feedback and further fine-tuning them for direct adaptation to downstream tasks by encoding samples into a unified feature representation, thereby simplifying the search and traversal process. Finally, an adaptive knowledge transfer strategy is proposed, implementing collaborative modeling with key patterns anchored under the joint influence of knowledge threads and task instructions, leading to the generation of an equivalent and concise initialization model guided by LLMs. The experimental design validates the efficacy of the approach in rapid generalizing specific models, demonstrating high accuracy and minimal resource consumption.

Real-world data often contain incomplete views with varying degrees of missing information. While there are existing methods for learning representations from such data, effectively utilizing all incomplete view data and ensuring robustness to different levels of completeness remains a challenging task. To address this problem, we propose a novel framework named IMRL-AGI. IMRL-AGI combines the anchor graph-based Graph Convolutional Network (GCN) and information bottleneck. Specifically, the framework starts by constructing an anchor graph to effectively captures the nonlinear information between instances. Next, an anchor graph-based GCN is designed to extract feature information from various views. IMRL-AGI maximizes the mutual information between the views obtained by the common representation and the anchor-graph-based GCN, ensuring the accurate extraction of view information. Furthermore, the minimization of mutual information is applied to promote diversity and reduce redundancy in the multi-view representation. Extensive experiments are conducted on several real-world datasets, and the results demonstrate the superiority of IMRL-AGI.

Few-shot learning has attracted considerable attention in the field of hyperspectral image (HSI) classification due to its suitability in addressing the challenges encountered in numerous real-world scenarios. However, the scarcity of labeled samples poses a significant challenge in learning informative and discriminative features, limiting the potential for achieving higher accuracy. In this paper, we propose a contextual information aggregation module (CIAM) as part of the feature extraction network for few-shot hyperspectral image classification which can aggregate more spatial-spectral information for each pixel from the neighbored pixels. Meanwhile, supervised contrastive learning is introduced to learn more discriminative representations for addressing specific challenges of high inter-class similarity and large intra-class variance in hyperspectral images. Extensive experiments on two benchmark datasets show that our proposed method achieves the state-of-the-art results.

Multiview clustering has attracted significant attention in various fields, due to the superiority in mining patterns of multiview data. However, previous methods are still confronted with two challenges. First, they do not fully consider the semantic invariance of multiview data in aggregating complementary information, degrading semantic robustness of fusion representations. Second, they rely on predefined clustering strategies to mine patterns, lacking adequate explorations of data structures. To address the challenges, deep multiview adaptive clustering via semantic invariance (DMAC-SI) is proposed, which learns an adaptive clustering strategy on semantics-robust fusion representations to fully explore structures in mining patterns. Specifically, a mirror fusion architecture is devised to explore interview invariance and intrainstance invariance hidden in multiview data, which captures invariant semantics of complementary information to learn semantics-robust fusion representations. Then, a Markov decision process of multiview data partitions is proposed within the reinforcement learning framework, which learns an adaptive clustering strategy on semantics-robust fusion representations to guarantee the structure explorations in mining patterns. The two components seamlessly collaborate in an end-to-end manner to accurately partition multiview data. Finally, extensive experiment results on five benchmark datasets demonstrate that DMAC-SI outperforms the state-of-the-art methods.

Overall survival (OS) analysis has a significant role in clinical treatment and prognosis. A singular data source’s samples may be biased, leading to low generalisable models. Multi-source data, however, may suffer from the problem of missing modalities due to different equipment and regional disparity. To address this issue, we propose a OS prediction model for gastric cancer called preference-based multimodal deep forest (PMDF). Simulating the diagnostic process of a physician, the initial input contains only basic modalities instead of complete data. Subsequently, PMDF learns from the doctor’s expertise and calculates the required supplementary examinations for each patient with these basic modalities. Finally, additional modalities are fused based on the cascade forest architecture. The efficiency of the proposed model is verified on the publicly accessible SEER database, and its applicability in clinical settings is assessed.

With the combination of natural language processing and artificial intelligence techniques, medical extractive question-answering (Q&A) provides valuable insights and assists medical professionals in daily work and scientific research, answering medical questions rapidly and accurately, thus holding significant practical significance. Therefore, research on medical extractive Q&A holds significant practical significance. However, the current state of medical extractive question-answering lacks attention to the interaction and prediction layers in the model structure. To address these issues, this paper proposes the Integrating pre-trained multi-layer structural feature information based Bio-BERT (IPMF-Bio-BERT) approach. This method leverages the rich word vector representations generated by the pre-trained Bio-BERT model, incorporating semantic and syntactic structural information to obtain multi-dimensional and complementary interactive feature information. Additionally, we introduce a flexible guidance network based on interactive information, which combines iterative and pointer network techniques to enhance the predictive performance of the question-answering model. We evaluate our proposed model on the specialized biomedical extractive question-answering BioASQ corpus. Experimental results demonstrate that the IPMF-Bio-BERT training strategy enhances the recognition and predictive capabilities of medical extractive Q&A, we establish new state-of-the-art results by outperforming existing approaches.

Medical image segmentation plays a vital role in clinical diagnosis. However, previous methods cannot handle intrinsic ambiguities in extracting deep semantics of medical images. Moreover, they neglect fruitful semantic information in segmentation maps. To address the challenges, a latent adversarial Cauchy-Schwarz autoencoder is proposed, which defines image segmentation as a cross-modal translation task from medical images to segmentation maps. Specifically, a probabilistic graph model is defined to fit the conditional distribution of the image translation between modalities, which leverages the Cauchy-Schwarz divergence to alleviate approximation errors caused by ambiguities in extracting deep semantics. Then, a novel numerical solution is derived to optimize the probabilistic graph model, which explores semantics in segmentation maps to facilitate the segmentation. Afterwards, a dual-flow architecture is proposed with an adversarial encoding-decoding paradigm to implement the numerical solution. Finally, extensive experiments in two medical scenarios illustrate that the proposed method achieves the state-of-the-art performance compared with nine baseline methods.

Many real-world data are composed of different representations or views, thus multi-view clustering (MVC) has attracted more and more attention in recent years. Its key task is how to extract sufficient fusion features from multi-view data. Because the nonnegative matrix factorization (NMF) can favorably explain the extracted features, the NMF based MVC is usually a good choice for multi-view data, and promising results are achieved. Inspired by this, we propose a multi-view graph regularized deep autoencoder-like NMF (MGANMF) framework in this paper for multi-view clustering. MGANMF uses the deep autoencoder-like NMF, which draws lessons from the idea of depth automatic encoder, to learn the hierarchical semantics of multi-view data in a layer-wise manner. Moreover, in order to describe the inherent geometric structure in each view data, graph regulators are introduced to couple the output representation of deep structure. In addition, the self-updating weights are employed to balance the effect of each view. Thus, a new objective function is defined and the optimization processes are presented. Experimental results on several multi-view datasets show the effectiveness of the proposed model.

Few-shot classification has gained significant attention owing to the effectiveness in classifying unseen classes with a few annotated images. Although previous works achieve encouraging classification performance, they heavily rely on one-hot labels during the meta-learning process, which may result in the supervision collapse and limited generalization. To address these challenges, the few-shot classification based on a self-supervised multi-task distillation (SMD) is proposed for mitigating the nuisance arising from one-hot labels. Specifically, SMD formulates multiple auxiliary tasks to enhance the cross entropy classification in a multi-task learning manner, including the self-supervised classification task and the self-distilled classification task. These auxiliary tasks do not rely on one-hot labels in meta-learning, which can effectively enhance generalization performance of the model. Finally, extensive experiment results on two benchmark datasets, i.e., CIFAR-FS and FC-100, demonstrate the superiority and effectiveness of SMD.

The emergence of big data has made knowledge graphs (KGs) an effective means of representing structured knowledge, and few-shot knowledge graph completion (FKGC) has recently received increasing attention, which attempts to forecast missing information for relations with few-shot related facts. In this regard, several deep learning-based and embedding-based methods have been proposed for FKGC. However, most existing methods overlook multi-hop path information and only utilize the immediate neighbors of relevant entities when encoding and matching entity pairs, potentially limiting their performance. In this paper, we propose an Enhancing Path Information with Reinforcement Learning (EPIRL) approach for FKGC. Specifically, we introduce a reinforcement learning framework to construct a reasoning subgraph, aiming to thoroughly uncover the inferential path rules between support and query triples. Then, we utilize an interaction focused matching model to capture the inherent connections among these reasoning paths. To further improve performance, we incorporate a relational attention mechanism aimed at emphasizing the influence of pivotal paths. Extensive experiments demonstrate that our model outperforms several state-of-the-art methods on the frequently-used benchmark datasets FB15k237-One and NELL-One.

Multi-view clustering (MVC) integrates information from different views to improve clustering performance compared to single-view clustering. However, the raw multi-view data in the feature space often contains irrelevant information to the clustering task, which is difficult to separate using existing methods. This irrelevant information is processed equally with clustering information, negatively impacting the final clustering performance. In this paper, we propose a new framework for multi-view clustering information reinforcement network (MVCIR-net) to alleviate these problems. Our method gives practical clustering meaning to the clustering distribution layer by contrastive learning. Then, the trusted neighbor instances distribution of the normalized graph is debias aggregated to form the clustering information propensity distribution, and the clustering information distribution is made to fit this distribution. In addition, the coupling degree of the clustering information distribution in different views on the same sample should be enhanced. Through the aforementioned strategies, the raw data is fuzzy mapped into clustering information, and the network's ability to recognize clustering information is strengthened. Finally, the fuzzy mapping data is input into the network and reconstructed to evaluate the quality of the extracted clustering information. Extensive experiments on public multi-view datasets show that MVCIR-net achieves superior clustering effectiveness and the ability to identify clustering information.

Unsupervised cross-modal hashing retrieval across image and text modality is a challenging task because of the suboptimality of similarity guidance, i.e., the joint similarity matrix constructed by existing methods does not possess clear enough guiding significance. How to construct more robust similarity matrix is the key to solve this problem. The unsupervised cross-modal retrieval methods based on graph have a good performance in mining semantic information of input samples, but the graph hashing based on traditional affinity graph cannot capture the high-order semantic information of input samples effectively. In order to overcome the aforementioned limitations, this paper presents a novel hypergraph-based approach for unsupervised cross-modal retrieval that differs from previous works in two significant ways. Firstly, to address the ubiquitous redundant information present in current methods, this paper introduces a robust similarity matrix constructing method. Secondly, we propose a novel hypergraph enhanced module that produces embedding vectors by hypergraph convolution and attention mechanism for input data, capturing important high-order semantics. Our approach is evaluated on the NUS-WIDE and MIRFlickr datasets, and yields state-of-the-art performance for unsupervised cross-modal retrieval.

In recent years, multi-view clustering has gained widespread attention in signal processing because multi-view data contains more information than a single view. However, multi-view data is often incomplete due to missing data in one or more random views. Therefore, several methods have been proposed for incomplete multi-view clustering to learn features that contain consensus information for clustering incomplete multi-view data (IMD). However, there is a part of the IMD that is not missing in any view, and most previous methods have not utilized this part to guide the process of learning consensus information. To address this issue, we design a knowledge distillation framework for incomplete multi-view clustering and propose an incomplete multi-view clustering with complete view guidance (IMC-CVG). We first train a robust teacher model with contrastive learning loss on the complete part of IMD to learn consensus features containing multi-view information. Then, we train a student model on all the IMD, where we mask partial views of the complete data to simulate missing data, and utilize the teacher model to guide the student model to learn consensus features that contain as much multi-view information as possible. Experiments show that our proposed method outperforms all the compared state-of-the-art methods.

Deep clustering has attracted plentiful attention in various domains owning to the superior performance. However, the previous deep clustering methods are guided by pre-specified clustering strategies that lack sustained explorations of data structures, degrading recognition of intrinsic patterns hidden in data. To address this challenge, deep reinforcement clustering (DRC) is proposed to learn an adaptive partition policy for pattern mining, which can fully explore structure knowledge of data in an adaptive manner. DRC is defined as a Markov decision process of data partitions, which chooses the optimal cluster prototype for data via maximizing the cumulative reward in state transition of environment. To implement the definition, a Bernoulli action prototype is devised to capture decision distributions in the transition of states, where the heavy-tailed Cauchy distribution precisely measures the structure divergences of data. Furthermore, a reward maximizing policy is designed to guide sustained explorations of data structures, which ensures intra-cluster compactness and inter-cluster separation of data partitions. Finally, extensive experiments are conducted on eight benchmark datasets, and the results demonstrate that DRC outperforms the state-of-the-art baseline methods.

Few-shot learning (FSL) aims to generalize from few labeled samples. Recently, metric-based methods have achieved surprising classification performance on many FSL benchmarks. However, those methods ignore the impact of noise, making the few-shot learning still tricky. In this work, we identify that noise suppression is important to improve the performance of FSL algorithms. Hence, we proposed a novel attention-based contrastive learning model with discrete cosine transform input (ACL-DCT), which can suppress the noise in input images, image labels, and learned features, respectively. ACL-DCT takes the transformed frequency domain representations by DCT as input and removes the high-frequency part to suppress the input noise. Besides, an attention-based alignment of the feature maps and a supervised contrastive loss are used to mitigate the feature and label noise. We evaluate our ACL-DCT by comparing previous methods on two widely used datasets for few-shot classification (i.e., miniImageNet and CUB). The results indicate that our proposed method outperforms the state-of-the-art methods.

Few-shot segmentation aims at segmenting target object areas with only a few labeled samples. Previous methods extract class-specific prototypes to guide segmentation. How-ever, using one or more prototypes to represent the whole object inevitably drops vital spatial information, ignoring many details in original images. To address the issue, we propose a Dual-Attention Network (DANet) for few-shot segmentation. Firstly, a light-dense attention module is proposed to set up pixel-wise relations between feature pairs at different levels to activate object regions, which can leverage semantic information in a coarse-to-fine manner. Secondly, in contrast to the previous prototype-based methods that offer a holistic representation for each object class, we propose a prototypical channel attention module which incorporates channel interdependencies to enhance the discriminative capacity of features. The extensive experiments on two benchmarks show that our approach outperforms the state-of-the-arts in most cases.

Multi-label aerial image classification (MAIC) is a fundamental but challenging task for computer vision-based remote sensing applications. Existing MAIC models suffer from the insufficient semantic information of image and label representations. To this end, we integrate commonsense knowledge into the MAIC task and propose a novel Knowledge-augmented Concept Graph Learning (KCGL) framework. KCGL first collects relevant semantic concepts for each label from a commonsense knowledge graph ConceptNet. With the guidance of semantic concepts, an image decoupling module is employed to extract concept-specific image features from the input image. Then, KCGL constructs an individual concept graph for each image, in which nodes are corresponding to concept-specific image features and edges are their relations extracted from ConceptNet. Finally, the classification probability on each label is computed in the specific concept graph via a GCN-based encoder-decoder model. Experimental results prove that the proposed KCGL outperforms existing state-of-the-art MAIC models on two aerial image datasets.

Deep learning has achieved impressive results on Hyperspectral image (HSI) classification, which generally requires sufficient training samples and a huge number of parameters. However, it is challenging to label HSIs, and likely only a few samples are available in practice. Learning a large number of parameters by the model is also resource-intensive. This paper proposes an HSI classification model that achieves promising classification performance with fewer parameters in few-shot settings. The proposed model adopts the residual 3D-CNN as feature extraction network, and contrastive learning is introduced to learn more discriminative representations for HSIs which can conquer the obstacles from HSIs’ high inter-class similarity and large intra-class variance. The proposed few-shot contrastive learning HSI classification model is tested on five popular HSI datasets and outperforms the state-of-the-art models.

Citation recommendation plays an important role in the context of scholarly big data, where finding relevant papers has become more difficult because of information overload. Applying traditional collaborative filtering (CF) to citation recommendation is challenging due to the cold start problem and the lack of paper ratings. To address these challenges, in this article, we propose a collaborative filtering with network representation learning framework for citation recommendation, namely CNCRec, which is a hybrid user-based CF considering both paper content and network topology. It aims at recommending citations in heterogeneous academic information networks. CNCRec creates the paper rating matrix based on attributed citation network representation learning, where the attributes are topics extracted from the paper text information. Meanwhile, the learned representations of attributed collaboration network is utilized to improve the selection of nearest neighbors. By harnessing the power of network representation learning, CNCRec is able to make full use of the whole citation network topology compared with previous context-aware network-based models. Extensive experiments on both DBLP and APS datasets show that the proposed method outperforms state-of-the-art methods in terms of precision, recall, and MRR (Mean Reciprocal Rank). Moreover, CNCRec can better solve the data sparsity problem compared with other CF-based baselines.

As one important technique of fuzzy clustering in data mining and pattern recognition, the possibilistic c-means algorithm (PCM) has been widely used in image analysis and knowledge discovery. However, it is difficult for PCM to produce a good result for clustering big data, especially for heterogenous data, since it is initially designed for only small structured dataset. To tackle this problem, the paper proposes a high-order PCM algorithm (HOPCM) for big data clustering by optimizing the objective function in the tensor space. Further, we design a distributed HOPCM method based on MapReduce for very large amounts of heterogeneous data. Finally, we devise a privacy-preserving HOPCM algorithm (PPHOPCM) to protect the private data on cloud by applying the BGV encryption scheme to HOPCM, In PPHOPCM, the functions for updating the membership matrix and clustering centers are approximated as polynomial functions to support the secure computing of the BGV scheme. Experimental results indicate that PPHOPCM can effectively cluster a large number of heterogeneous data using cloud computing without disclosure of private data.

Compared with natural images, aerial images collected by satellite sensors/aerial cameras can provide a much larger field of view and often contain multiple objects of interest (multiple labels). There are certain limitations of existing multilabel aerial image classification methods. First, label correlations were often ignored in previous MAIC work, and thus, multilabel classifiers failed to be self-adapted. Second, existing multilabeled data sets for aerial images only cover limited images with fixed labels. Therefore, the underlying semantic correlations of labels cannot be fully included, while such correlation information is implicitly used as common knowledge by human beings. To tackle these concerns, we propose a novel multilabel classification method for aerial images. Our contributions are twofold. First, as the first attempt, label correlations are inferred from both the specific data set and ConceptNet (a popular knowledge graph for common sense). Second, based on graph neural network (GNN), we propose a novel end-to-end aerial image classification model, named the multiple label concept graph (ML-CG). ML-CG builds a concept graph to describe the semantic correlations from both the label set and the ConceptNet. We also incorporate both semantic attention and label attention in the GNN to better extract meaningful information of image labels. Compared with state-of-the-art methods, the effectiveness of the proposed method is demonstrated on both the commonly used UCM data set and a recently proposed DFC15 data set with high image resolution.

Deep learning (DL) methods are promising for the multilabel aerial image classification (MAIC) task. However, current DL methods face a common problem: the need for large multilabeled datasets. Collecting and annotating raw aerial image datasets can be extremely time- and labor-consuming. To address this concern in MAIC, domain adaptation (DA) provides a novel solution by transferring the knowledge learned from a label-rich dataset (i.e., the source domain) to a label-scarce dataset (i.e., the target domain), while current DA models are mainly designed for single-labeled tasks. In this article, we propose a novel end-to-end MAIC model based on DA techniques, named DA-MAIC. To the best of our knowledge, this article for the first time integrates DA to tackle the label scarcity problem in the MAIC task. Specifically, the proposed DA-MAIC is composed of two main parts: the image classifier and the domain classifier. The image classifier captures task-discriminative features based on the graph convolutional network (GCN) to predict multiple image labels; and the domain classifier extracts domain-invariant representations, which mitigates the domain shift between two underlying distributions. We extensively evaluate the proposed DA-MAIC from different perspectives on three benchmark datasets, including the commonly used UCM dataset, the high-resolution AID dataset, and the recently proposed DFC15 dataset. Both quantitative and qualitative results support that the proposed DA-MAIC can generalize the source domain knowledge to new scenarios and substantially improve the classification performance on the target domain task.

Anomaly detection (such as telecom fraud detection and medical image detection) has attracted the increasing attention of people. The complex interaction between multiple entities widely exists in the network, which can reflect specific human behavior patterns. Such patterns can be modeled by higher-order network structures, thus benefiting anomaly detection on attributed networks. However, due to the lack of an effective mechanism in most existing graph learning methods, these complex interaction patterns fail to be applied in detecting anomalies, hindering the progress of anomaly detection to some extent. In order to address the aforementioned issue, we present a higher-order structure based anomaly detection (GUIDE) method. We exploit attribute autoencoder and structure autoencoder to reconstruct node attributes and higher-order structures, respectively. Moreover, we design a graph attention layer to evaluate the significance of neighbors to nodes through their higher-order structure differences. Finally, we leverage node attribute and higher-order structure reconstruction errors to find anomalies. Extensive experiments on five real-world datasets (i.e., ACM, Citation, Cora, DBLP, and Pubmed) are implemented to verify the effectiveness of GUIDE. Experimental results in terms of ROC-AUC, PR-AUC, and Recall@K show that GUIDE significantly outperforms the state-of-art methods.

Generalized zero-shot learning (GZSL) has attracted considerable attention recently, which trains models with data from seen classes and tests on data from both seen and unseen classes. Most of the existing methods attempt to find a mapping from visual space to semantic space, such mapping can easily result in the domain shift problem. To address this issue, we propose a Multiple-Input Multiple-Output Fusion Network to GZSL. It can generate similar common semantic representation to paired inputs even with only the class semantic embeddings. This makes it possible to synthesize pseudo samples from attributes of unseen classes. Extensive experiments carried out on three benchmark datasets show the effectiveness of the proposed model.

Summary Cloud computing is significantly contributing to the development of smart Chinese medicine. The diagnosis and treatment of spleen and stomach diseases has been arousing great interest in smart Chinese medicine with cloud computing since many persons are suffering from spleen and stomach diseases. Currently, spleen and stomach diseases present some new characteristics with the dramatic changes in natural climate, social environment, and human living habits. Recently, deep learning, together with cloud computing techniques, has successfully used in medical image analysis and therefore it is the most promising model for diagnosing spleen and stomach disease in smart Chinese medicine. In this paper, we present a survey on deep learning models in medical image analysis for computer‐aided diagnosis in modern medicine. Afterwards, we summarize the syndrome types of spleen and stomach diseases and furthermore analyze the causes and pathogenesis for each syndrome. Finally, we discuss the open challenges and research directions of deep learning models applicable to the computer‐aided diagnosis of spleen and stomach diseases, which is expected to contribute to the development of smart Chinese medicine with cloud computing.

Abstract In real‐world applications, large amounts of data from multiple sources come in the form of streams. This makes multi‐view feature learning cost much time when new instances rise incrementally. Dealing with these growing multi‐view data becomes a challenging problem. Some single‐view methods focus on processing the data dynamically, but they are not suitable for multi‐view data. Some online multi‐view methods are proposed to tackle it, but they ignore the influence of uncorrelated items in each view. Therefore, in this study, the authors propose a new algorithm, called Incremental Multi‐view Correlated Feature Learning (IMCFL) based on non‐negative matrix factorisation, to learn the common feature across views. By separating uncorrelated items of new instances and constructing incremental joint learning of correlated and uncorrelated features, the proposed IMCFL can eliminate the influence of uncorrelated information in the individual view and improve the effectiveness of incremental multi‐view common feature learning. Extensive experiments on real‐world datasets confirm its superiority by comparing it with other state‐of‐the‐art incremental and non‐incremental methods.

Incomplete multi-view clustering has attracted much attention in decade years. To date, most of the remarkable achievements, however, exploit shallow models to learn shared feature representations based on incomplete views. Although some deep learning methods have been proposed to solve this issue, the existing ones still have the following problems: 1) The consistency between views is ignored, which will have serious negative impacts on incomplete multi-view learning. 2) The learned features do not have sufficient cluster-friendliness, that is, the tightness within clusters and the repulsiveness between clusters are not fully considered. To tackle the above shortcomings, we propose a Dual Alignment Self-supervised Incomplete Multi-view Subspace Clustering network (DASIMSC) in this paper. Specifically, the manifold alignment constraint and consistency alignment constraint are integrated with the autoencoder to preserve the compact inherent local structure within the view and the consistency semantics between incomplete views, respectively. Moreover, a self-expression layer coupled with a spectral clustering module is designed to naturally separate different types of data, leveraging the current clustering results to supervise subspace learning, which excludes inter-cluster. Experimental results on several datasets show that our algorithm outperforms all compared state-of-the-arts.

Smart Chinese medicine has emerged to contribute to the evolution of healthcare and medical services by applying machine learning together with advanced computing techniques like cloud computing to computer-aided diagnosis and treatment in the health engineering and informatics. Specifically, smart Chinese medicine is considered to have the potential to treat difficult and complicated diseases such as diabetes and cancers. Unfortunately, smart Chinese medicine has made very limited progress in the past few years. In this paper, we present a unified smart Chinese medicine framework based on the edge-cloud computing system. The objective of the framework is to achieve computer-aided syndrome differentiation and prescription recommendation, and thus to provide pervasive, personalized, and patient-centralized services in healthcare and medicine. To accomplish this objective, we integrate deep learning and deep reinforcement learning into the traditional Chinese medicine. Furthermore, we propose a multi-modal deep computation model for syndrome recognition that is a crucial part of syndrome differentiation. Finally, we conduct experiments to validate the proposed model by comparing with the staked auto-encoder and multi-modal deep learning model for syndrome recognition of hypertension and cold.

With the widely used Internet of Things, 5G, and smart city technologies, we are able to acquire a variety of vehicle trajectory data. These trajectory data are of great significance which can be used to extract relevant information in order to, for instance, calculate the optimal path from one position to another, detect abnormal behavior, monitor the traffic flow in a city, and predict the next position of an object. One of the key technology is to cluster vehicle trajectory. However, existing methods mainly rely on manually designed metrics which may lead to biased results. Meanwhile, the large scale of vehicle trajectory data has become a challenge because calculating these manually designed metrics will cost more time and space. To address these challenges, we propose to employ network representation learning to achieve accurate vehicle trajectory clustering. Specifically, we first construct the k-nearest neighbor-based internet of vehicles in a dynamic manner. Then we learn the low-dimensional representations of vehicles by performing dynamic network representation learning on the constructed network. Finally, using the learned vehicle vectors, vehicle trajectories are clustered with machine learning methods. Experimental results on the real-word dataset show that our method achieves the best performance compared against baseline methods.

With the advancement of communication technology and location acquisition technology in the context of modern smart cities, the sharing bike systems offer users the great autonomy and convenience for the last/first-kilometer trip. Meanwhile, we can now able to collect, store, and analyze a large amount of sharing bike data. How to effectively use these massive data to provide better services is an emerging task. However, due to the skewed and imbalanced bike usages for stations located at different places, it is of great significance yet very challenging to predict the potential destinations of each individual trip beforehand so that the service providers can better schedule manual bike re-dispatch in advance. To address this issue, this paper proposes an attention-based deep learning framework for trip destination prediction (AFTER). AFTER first learns the low-dimension representations of users and sharing bike stations via negative sampling strategies. Then, a convolution neural network with an attention mechanism is utilized to predict the future trip destination. Experimental results on a real-world dataset indicate that the proposed framework outperforms several state-of-the-art approaches in terms of precision, recall, and F1.

Multi-view data can represent objects from different perspectives and thus provide complementary information for data analysis. A topic of great importance in multi-view learning is to locate a low-dimensional latent subspace, where common semantic features are shared by multiple data sets. However, most existing methods ignore uncorrelated items (i.e., view-specific features) and may cause semantic bias during the process of common feature learning. In this article, we propose a non-negative correlated and uncorrelated feature co-learning (CoUFC) method to address this concern. More specifically, view-specific (uncorrelated) features are identified for each view when learning the common (correlated) feature across views in the latent semantic subspace. By eliminating the effects of uncorrelated information, useful inter-view feature correlations can be captured. We design a new objective function in CoUFC and derive an optimization approach to solve the objective with the analysis on its convergence. Experiments on real-world sensor, image, and text data sets demonstrate that the proposed method outperforms the state-of-the-art multiview learning methods.

The introduction of deep transfer learning (DTL) further reduces the requirement of data and expert knowledge in various uses of applications, helping DNN‐based models effectively reuse information. However, it often transfers all parameters from the source network that might be useful to the task. The redundant trainable parameters restrict DTL in low‐computing‐power devices and edge computing, while small effective networks with fewer parameters have difficulty transferring knowledge due to structural differences in design. For the challenge of how to transfer a simplified model from a complex network, in this paper, an algorithm is proposed to realize a sparse DTL, which only transfers and retains the most necessary structure to reduce the parameters of the final model. Sparse transfer hypothesis is introduced, in which a compressing strategy is designed to construct deep sparse networks that distill useful information in the auxiliary domain, improving the transfer efficiency. The proposed method is evaluated on representative datasets and applied for smart agriculture to train deep identification models that can effectively detect new pests using few data samples.

Blockchain technology has advanced rapidly in recent years and is now widely used in a variety of fields. Blockchain appears to be one of the best solutions for managing massive heterogeneous devices while achieving advanced data security and data reputation, particularly in the field of large‐scale IoT (Internet of Things) networks. Despite the numerous advantages, there are still challenges while deploying IoT applications on blockchain systems due to the limited storage, power, and computing capability of IoT devices, and some of these problems are caused by the consensus algorithm, which plays a significant role in blockchain systems by ensuring overall system reliability and robustness. Nonetheless, most existing consensus algorithms are prone to poor node reliability, low transaction per second (TPS) rates, and scalability issues. Aiming at some critical problems in the existing consensus algorithms, this paper proposes the Efficient Byzantine Reputation‐based Consensus (EBRC) mechanism to resolve the issues raised above. In comparison to traditional algorithms, we reinvented ways to evaluate node reliability and robustness and manage active nodes. Our experiments show that the EBRC algorithm has lower consensus delay, higher throughput, improved security, and lower verification costs. It offers new reference ideas for solving the Internet of Things+blockchain+Internet court construction problem.

More attention is paid to personal health accompanying by the development of society and the change of lifestyle. Not limited in disease, the sub-health is bedeviling humanity more generally. An increasing number of people go in quest of Traditional Chinese Medicine (TCM) for life quality, since TCM achieves the significant and curative effectiveness in recuperating certain sub-health conditions. However, the lack of clinical data poses a vast challenge on the emerging deep-learning-based methods in modeling TCM diagnosis. In this paper, a Similar Sparse Domain Adaptation (SSDA) method is proposed in modeling the tongue inspection, which is one of the four diagnostic methods and plays important roles in TCM primary diagnosis. First, a similar domain adaptation is introduced to transfer necessary knowledge efficiently and overcome insufficient data. Then, inspired by the Lottery Ticket hypothesis, the network is pruned to generate sparse subnet using in adaptation. Finally, the model with two combined sparse network is designed. Extensive experiments are conducted on the real clinical data set collected in Dalian, China. Proposed model uses fewer training data samples and parameters, while consuming less power and memory, which make it easier to store and run on low-power hardware systems for widely promoting.

Aiming at better representing multivariate relationships, this paper investigates a motif dimensional framework for higher-order graph learning. The graph learning effectiveness can be improved through OFFER. The proposed framework mainly aims at accelerating and improving higher-order graph learning results. We apply the acceleration procedure from the dimensional of network motifs. Specifically, the refined degree for nodes and edges are conducted in two stages: (1) employ motif degree of nodes to refine the adjacency matrix of the network; and (2) employ motif degree of edges to refine the transition probability matrix in the learning process. In order to assess the efficiency of the proposed framework, four popular network representation algorithms are modified and examined. By evaluating the performance of OFFER, both link prediction results and clustering results demonstrate that the graph representation learning algorithms enhanced with OFFER consistently outperform the original algorithms with higher efficiency.

In recent years, hashing based cross-modal retrieval methods have attracted considerable attention for the high retrieval efficiency and low storage cost. However, most of the existing methods neglect the high-order relationship among data samples. In addition, most of them can only deal with two modalities, e.g., image and text, without discussing the scenario of multiple modalities. To address these issues, in this paper, we propose a novel cross-modal hashing method, named Hypergraph Based Discrete Matrix Factorization Hashing (HDMFH), for multimodal retrieval. Different from most previous approaches, our method based on hypergraph regularization and matrix factorization can handle the cross-modal retrieval of more than two modalities, which is known as multimodal retrieval. Extensive experiments demonstrate that HDMFH outperforms the state-of-the-art cross-modal hashing methods.

Hashing technique has been widely applied to large-scale image retrieval due to its efficacy in storage and retrieval. However, due to the explosive growth of multimedia data on the web, existing hashing approaches can hardly achieve satisfactory performance on the newly-emerging images of new classes. In this paper, we propose a novel Semantic Augmentation Hashing (SAH) for zero-shot image retrieval. The class semantic embeddings are used as an intermediate space between visual features and binary codes to align visual features to corresponding class semantics and to transfer knowledge from seen classes to unseen classes simultaneously. Extensive experiments conducted on two datasets with different scales demonstrate the superiority of our method as compared against the state-of-the-arts.

Abstract N‐Queens problem derives three variants: obtaining a specific solution, obtaining a set of solutions and obtaining all solutions. The purpose of the variant I is to find a constructive solution, which has been solved. Variant III is aiming to find all solutions and the largest number of queens currently being resolved is 26. Variant II whose purpose is to obtain a set of solutions for larger‐scale problems relies on various intelligent algorithms. In this paper, we use a master‐slave model genetic algorithm that combines the idea of the evolutionary algorithm and simulated annealing algorithm to solve Variant III, and use a parallel fitness function based on compute unified device architecture. Experimental results show that our scheme achieved a maximum 60‐fold speedup over the single‐CPU counterpart. On this basis, a two‐level parallel genetic algorithm based on the island model and master‐slave model is implemented on the GPU cluster by using message passing interface technology. Using two‐node and three‐node GPU cluster, speedup of 1.46 and 2.01 are obtained on average over single‐node, respectively. Compared with the sequential genetic algorithm, the two‐level parallel genetic algorithm makes full use of the parallel computing power of GPU cluster in solving N‐Queen variant II and improves the performance by 99.19 times in the best case.

With the wide deployments of heterogeneous networks, huge amounts of data with characteristics of high volume, high variety, high velocity, and high veracity are generated. These data, referred to multimodal big data, contain abundant intermodality and cross-modality information and pose vast challenges on traditional data fusion methods. In this review, we present some pioneering deep learning models to fuse these multimodal big data. With the increasing exploration of the multimodal big data, there are still some challenges to be addressed. Thus, this review presents a survey on deep learning for multimodal data fusion to provide readers, regardless of their original community, with the fundamentals of multimodal deep learning fusion method and to motivate new multimodal data fusion techniques of deep learning. Specifically, representative architectures that are widely used are summarized as fundamental to the understanding of multimodal deep learning. Then the current pioneering multimodal data fusion deep learning models are summarized. Finally, some challenges and future topics of multimodal data fusion deep learning models are described.

Multi-view feature learning can provide basic information for consistent grouping, and is very common in practical applications, such as judicial document clustering. However, it is a challenge to combine multiple heterogeneous features to learn a comprehensive description of data samples. To solve this problem, many methods explore the correlation between various features across views by assuming that all views share the same semantic information. Inspired by this, in this paper we propose a new multi-view robust feature learning (MRFL) method. In addition to projecting features from different views to a shared semantic subspace, our approach also learns the irrelevant information of data space to capture the feature dependencies between views in potential common subspaces. Therefore, the MRFL can obtain flexible feature associations hidden in multi-view data. A new objective function is designed to derive, and solve the effective optimization process of MRFL. Experiments on real-world multi-view datasets show that the proposed MRFL method is superior to the state-of-the-art multi-view learning methods.

Big data feature learning is a crucial issue for the service management for Internet of Things. However, big data collected from Internet of Things is of dynamic nature at a high speed, which poses an important challenge on wireless big data learning models, especially the deep computation model. In this paper, an incremental deep computation model is proposed for wireless big data feature learning in Internet of Things. First, two incremental tensor auto-encoders (ITAE) are developed by devising two incremental learning algorithms, namely parameter-based incremental learning algorithm (PI-TAE) and structure-based incremental learning algorithm (SI-TAE), when new wireless samples are available. PI-TAE only updates the network parameters while SI-TAE simultaneously adjusts the structure and updates the parameters to adapt to the new arriving wireless big data. Furthermore, an incremental deep computation model is constructed by stacking several ITAEs. Experiments are conducted to evaluate the performance of the proposed model by comparing with the conventional deep computation model and other two representative incremental learning algorithms, i.e., OANN and PIE. Results demonstrate that the presented model can modify the network in an incremental manner for new arriving data learning efficiently with preserving the prior knowledge for the previous data learning, proving its potential for dynamic wireless big data learning in Internet of Things.

With the rapid industrialization and urbanization, pattern mining of soil contamination of heavy metals is attracting increasing attention to control soil contamination. However, the correlation over various heavy metals and the high-dimension representation of heavy metal data pose vast challenges on the accurate mining of patterns over heavy metals of soil contamination. To solve those challenges, a multiview Gaussian mixture model is proposed in this paper, to naturally capture complicated relationships over multiviews on the basis of deep fusion features of data. Specifically, a deep fusion feature architecture containing modality-specific and modality-common stacked autoencoders is designed to distill fusion representations from the information of all views. Then, the Gaussian mixture model is extended on the fusion representations to naturally recognize the accurate patterns of the intra- and inter-views. Finally, extensive experiments are conducted on the representative datasets to evaluate the performance of the multiview Gaussian mixture model. Results show the outperformance of the proposed methods.

Cross‐modal hashing (CMH) has received widespread attention due to high retrieval efficiency, which plays an extremely important role in cross‐modal retrieval. Recently, many CMH methods have been proposed to establish the semantic connection of different modalities. However, most of these methods only use a simple quantisation strategy, resulting in large quantisation error, and inferior hash codes. To address this issue, in this study, the authors propose a novel self‐taught CMH (STCMH) to minimise the semantic encoding loss. In particular, the common semantic representations across different modalities are first learnt based on collective matrix factorisation. Then, the quantisation procedure based on orthogonal transformation is integrated to encode the semantic representations into discriminative binary codes. Moreover, similarity preservation is imposed to further boost the discriminative power. Finally, hashing functions learning is formulated as a binary classification problem by self‐taught scheme. Experimental results on three public datasets demonstrate that STCMH significantly outperforms most state‐of‐the‐art CMH methods.

With the ongoing development of sensor devices and network techniques, big data are being generated from the cyber-physical systems. Because of sensor equipment occasional failure and network transmission unreliability, a large number of low-quality data, such as noisy data and incomplete data, is collected from the cyber-physical systems. Low-quality data pose a remarkable challenge on deep learning models for big data feature learning. As a novel deep learning model, the deep computation model achieves superior performance for big data feature learning. However, it is difficult for the deep computation model to learn dependable features for low-quality data, since it uses the nonlinear function as the encoder. In this article, a dependable deep computation model is proposed for feature learning on low-quality big data in cyber-physical systems. Specially, a regularity is added into the objective function of the deep computation model to obtain reliable features in the intermediate-level representation space. Furthermore, a learning algorithm based on the back-propagation strategy is devised to train the parameters of the proposed model. Finally, experiments are conducted on three representative datasets and a real dataset to evaluate the effectiveness of the dependable deep computation model for low-quality big data feature learning. Results show that the proposed model achieves a remarkable result for the tasks of classification, restoration, and prediction, proving the potential of this work for practical applications in cyber-physical systems.

The deep convolutional computation model (DCCM) enabled remarkable progress in feature learning of industrial big data in Internet of Things. However, as a typical static deep learning model, it is difficult to learn features for incremental industrial big data. To solve this problem, we propose an incremental DCCM by developing two incremental algorithms, i.e., parameter-incremental algorithm and structure-incremental algorithm. The parameter-incremental algorithm aims to incrementally train the fully connected layers together with fine tuning for incorporating the new knowledge into the prior one. Then, the structure-incremental algorithm is used to transfer the previous knowledge by introducing an updating rule of the tensor convolutional, pooling, and fully connected layers. Furthermore, the dropout strategy is extended into the tensor fully connected layer to improve the robustness of the proposed model. Finally, extensive experiments are carried out on the representative datasets including CIFRA and CUAVE to justify the proposed model in terms of adaption, preservation, and convergence efficiency.

Deep computation, as an advanced machine learning model, has achieved the state-of-the-art performance for feature learning on big data in industrial Internet of Things (IoT). However, the current deep computation model usually suffers from overfitting due to the lack of public available labeled training samples, limiting its performance for big data feature learning. Motivated by the idea of active learning, an adaptive dropout deep computation model (ADDCM) with crowdsourcing to cloud is proposed for industrial IoT big data feature learning in this paper. First, a distribution function is designed to set the dropout rate for each hidden layer to prevent overfitting for the deep computation model. Furthermore, the outsourcing selection algorithm based on the maximum entropy is employed to choose appropriate samples from the training set to crowdsource on the cloud platform. Finally, an improved supervised learning from multiple experts scheme is presented to aggregate answers given by human workers and to update the parameters of the ADDCM simultaneously. Extensive experiments are conducted to evaluate the performance of the presented model by comparing with the dropout deep computation model and other state-of-the-art crowdsourcing algorithms. The results demonstrate that the proposed model can prevent overfitting effectively and aggregate the labeled samples to train the parameters of the deep computation model with crowdsouring for industrial IoT big data feature learning.

With the prevailing development of Cyber-physical-social systems and Internet of Things, large-scale data have been collected consistently. Mining large data effectively and efficiently becomes increasingly important to promote the development and improve the service quality of these applications. Clustering, a popular data mining technique, aims to identify underlying patterns hidden in the data. Most clustering methods assume the static data, thus they are unfavorable for analyzing large, unbalanced dynamic data. In this paper, to address this concern, we focus on incremental clustering by extending the novel [clustering by fast search (CFS) and find of density peaks] method to incrementally handle large-scale dynamic data. Specifically, we first discuss two challenges, i.e., assignment of new arriving objects and dynamic adjustment of clusters, in incremental CFS (ICFS) clustering. We then propose two ICFS clustering algorithms, ICFS with multiple representatives (ICFSMR) and the enhanced ICFSMR (E_ICFSMR) to tackle the two challenges. In ICFSMR, we explore the convex hull theory to modify the representatives identified for each cluster. E_ICFSMR improves the generality and effectiveness of ICFSMR by exploring one-time cluster adjustment strategy after integration of each data chunk. We evaluate the proposed methods with extensive experiments on four benchmark data sets, as well as the air quality and traffic monitoring time series, with comparisons to CFS and other three state-of-the-art incremental clustering methods. Experimental results demonstrate that the proposed methods outperform the compared methods in terms of both effectiveness and efficiency.

Transfer learning, which focuses on finding a favorable representation for instances of different domains based on auxiliary data, can mitigate the divergence between domains through knowledge transfer. Recently, increasing efforts on transfer learning have employeddeepneuralnetworks (DNN) to learn more robust and higher level feature representations to better tackle cross-media disparities. However, only a few articles consider the correction and semantic matching between multi-layer heterogeneous domain networks. In this article, we propose adeep semantic mapping model forheterogeneous multimediatransferlearning (DHTL) using co-occurrence data. More specifically, we integrate the DNN withcanonicalcorrelationanalysis (CCA) to derive a deep correlation subspace as the joint semantic representation for associating data across different domains. In the proposed DHTL, a multi-layer correlation matching network across domains is constructed, in which the CCA is combined to bridge each pair of domain-specific hidden layers. To train the network, a joint objective function is defined and the optimization processes are presented. When the deep semantic representation is achieved, the shared features of the source domain are transferred for task learning in the target domain. Extensive experiments for three multimedia recognition applications demonstrate that the proposed DHTL can effectively find deep semantic representations for heterogeneous domains, and it is superior to the several existing state-of-the-art methods for deep transfer learning.

Reducing energy consumption is a vital and challenging problem for the edge computing devices since they are always energy-limited. To tackle this problem, a deep Q-learning model with multiple DVFS (dynamic voltage and frequency scaling) algorithms was proposed for energy-efficient scheduling (DQL-EES). However, DQL-EES is highly unstable when using a single stacked auto-encoder to approximate the Q-function. Additionally, it cannot distinguish the continuous system states well since it depends on a Q-table to generate the target values for training parameters. In this paper, a double deep Q-learning model is proposed for energy-efficient edge scheduling (DDQ-EES). Specially, the proposed double deep Q-learning model includes a generated network for producing the Q-value for each DVFS algorithm and a target network for producing the target Q-values to train the parameters. Furthermore, the rectified linear units (ReLU) function is used as the activation function in the double deep Q-learning model, instead of the Sigmoid function in QDL-EES, to avoid gradient vanishing. Finally, a learning algorithm based on experience replay is developed to train the parameters of the proposed model. The proposed model is compared with DQL-EES on EdgeCloudSim in terms of energy saving and training time. Results indicate that our proposed model can save average 2%-2.4% energy and achieve a higher training efficiency than QQL-EES, proving its potential for energy-efficient edge scheduling.

Energy saving is a critical and challenging issue for real-time systems in embedded devices because of their limited energy supply. To reduce the energy consumption, a hybrid dynamic voltage and frequency scaling (DVFS) scheduling based on Q-learning (QL-HDS) was proposed by combining energy-efficient DVFS techniques. However, QL-HDS discretizes the system state parameters with a certain step size, resulting in a poor distinction of the system states. More importantly, it is difficult for QL-HDS to learn a system for various task sets with a Q-table and limited training sets. In this paper, an energy-efficient scheduling scheme based on deep Q-learning model is proposed for periodic tasks in real-time systems (DQL-EES). Specially, a deep Q-learning model is designed by combining a stacked auto-encoder and a Q-learning model. In the deep Q-learning model, the stacked auto-encoder is used to replace the Q-function for learning the Q-value of each DVFS technology for any system state. Furthermore, a training strategy is devised to learn the parameters of the deep Q-learning model based on the experience replay scheme. Finally, the performance of the proposed scheme is evaluated by comparison with QL-HDS on different simulation task sets. Results demonstrated that the proposed algorithm can save average$4.2\%$energy than QL-HDS.

Because of the enormous potential to guarantee road safety and improve driving experience, social Internet of Vehicle (SIoV) is becoming a hot research topic in both academic and industrial circles. As the ever-increasing variety, quantity, and intelligence of on-board equipment, along with the evergrowing demand for service quality of automobiles, the way to provide users with a range of security-related and user-oriented vehicular applications has become significant. This paper concentrates on the design of a service access system in SIoVs, which focuses on a reliability assurance strategy and quality optimization method. First, in lieu of the instability of vehicular devices, a dynamic access service evaluation scheme is investigated, which explores the potential relevance of vehicles by constructing their social relationships. Next, this work studies a trajectory-based interaction time prediction algorithm to cope with an unstable network topology and high rate of disconnection in SIoVs. At last, a cooperative quality-aware system model is proposed for service access in SIoVs. Simulation results demonstrate the effectiveness of the proposed scheme.

Recent years have witness a considerable advance of Internet of Things with the tremendous progress of communication theories and sensing technologies. A large number of data, usually referring to big data, have been generated from Internet of Things. In this paper, we present a double-projection deep computation model (DPDCM) for big data feature learning, which projects the raw input into two separate subspaces in the hidden layers to learn interacted features of big data by replacing the hidden layers of the conventional deep computation model (DCM) with double-projection layers. Furthermore, we devise a learning algorithm to train the DPDCM. Cloud computing is used to improve the training efficiency of the learning algorithm by crowdsourcing the data on cloud. To protect the private data, a privacy-preserving DPDCM (PPDPDCM) is proposed based on the BGV encryption scheme. Finally, experiments are carried on Animal-20 and NUS-WIDE-14 to estimate the performance of DPDCM and PPDPDCM by comparing with DCM. Results demonstrate that DPDCM achieves a higher classification accuracy than DCM. More importantly, PPDPDCM can effectively improve the efficiency for training parameters, proving its potential for big data feature learning.

The success of CNNs is accompanied by deep models and heavy storage costs. For compressing CNNs, we propose an efficient and robust pruning approach, cross-entropy pruning (CEP). Given a trained CNN model, connections were divided into groups in a group-wise way according to their corresponding output neurons. All connections with their cross-entropy errors below a grouping threshold were then removed. A sparse model was obtained and the number of parameters in the baseline model significantly reduced. This letter also presents a highest cross-entropy pruning (HCEP) method that keeps a small portion of weights with the highest CEP. This method further improves the accuracy of CEP. To validate CEP, we conducted the experiments on low redundant networks that are hard to compress. For the MNIST data set, CEP achieves an 0.08% accuracy drop required by LeNet-5 benchmark with only 16% of original parameters. Our proposed CEP also reduces approximately 75% of the storage cost of AlexNet on the ILSVRC 2012 data set, increasing the top-1 errorby only 0.4% and top-5 error by only 0.2%. Compared with three existing methods on LeNet-5, our proposed CEP and HCEP perform significantly better than the existing methods in terms of the accuracy and stability. Some computer vision tasks on CNNs such as object detection and style transfer can be computed in a high-performance way using our CEP and HCEP strategies.

Multiview data, which provide complementary information for consensus grouping, are very common in real-world applications. However, synthesizing multiple heterogeneous features to learn a comprehensive description of the data samples is challenging. To tackle this problem, many methods explore the correlations among various features across different views by the assumption that all views share the common semantic information. Following this line, in this letter, we propose a new unsupervised multiview nonnegative correlated feature learning (UMCFL) method for data clustering. Different from the existing methods that only focus on projecting features from different views to a shared semantic subspace, our method learns view-specific features and captures inter-view feature correlations in the latent common subspace simultaneously. By separating the view-specific features from the shared feature representation, the effect of the individual information of each view can be removed. Thus, UMCFL can capture flexible feature correlations hidden in multiview data. A new objective function is designed and efficient optimization processes are derived to solve the proposed UMCFL. Extensive experiments on real-world multiview datasets demonstrate that the proposed UMCFL method is superior to the state-of-the-art multiview clustering methods.

With the rapidly increasing popularity of economic activities, a large amount of economic data is being collected. Although such data offers super opportunities for economic analysis, its low-quality, high-dimensionality and huge-volume pose great challenges on efficient analysis of economic big data. The existing methods have primarily analyzed economic data from the perspective of econometrics, which involves limited indicators and demands prior knowledge of economists. When embracing large varieties of economic factors, these methods tend to yield unsatisfactory performance. To address the challenges, this paper presents a new framework for efficient analysis of high-dimensional economic big data based on innovative distributed feature selection. Specifically, the framework combines the methods of economic feature selection and econometric model construction to reveal the hidden patterns for economic development. The functionality rests on three pillars: (i) novel data pre-processing techniques to prepare high-quality economic data, (ii) an innovative distributed feature identification solution to locate important and representative economic indicators from multidimensional data sets, and (iii) new econometric models to capture the hidden patterns for economic development. The experimental results on the economic data collected in Dalian, China, demonstrate that our proposed framework and methods have superior performance in analyzing enormous economic data.

Currently, a large number of industrial data, usually referred to big data, are collected from Internet of Things (IoT). Big data are typically heterogeneous, i.e., each object in big datasets is multimodal, posing a challenging issue on the convolutional neural network (CNN) that is one of the most representative deep learning models. In this paper, a deep convolutional computation model (DCCM) is proposed to learn hierarchical features of big data by using the tensor representation model to extend the CNN from the vector space to the tensor space. To make full use of the local features and topologies contained in the big data, a tensor convolution operation is defined to prevent overfitting and improve the training efficiency. Furthermore, a high-order backpropagation algorithm is proposed to train the parameters of the deep convolutional computational model in the high-order space. Finally, experiments on three datasets, i.e., CUAVE, SNAE2, and STL-10 are carried out to verify the performance of the DCCM. Experimental results show that the deep convolutional computation model can give higher classification accuracy than the deep computation model or the multimodal model for big data in IoT.

The deep computation model has been proved to be effective for big data hierarchical feature and representation learning in the tensor space. However, it requires expensively computational resources including high-performance computing units and large memory to train a deep computation model with a large number of parameters, limiting its effectiveness and efficiency for industry informatics big data feature learning. In this paper, a tensor-train deep computation model is presented for industry informatics big data feature learning. Specially, the tensor-train network is used to compress the parameters significantly by converting the dense weight tensors into the tensor-train format. Furthermore, a learning algorithm is implemented based on gradient descent and back-propagation to train the parameters of the presented tensor-train deep computation model. Extensive experiments are carried on STL-10, CUAVE, and SNAE2 to evaluate the presented model in terms of the approximation error, classification accuracy drop, parameters reduction, and speedup. Results demonstrate that the presented model can improve the training efficiency and save the memory space greatly for the deep computation model with small accuracy drops, proving its potential for industry informatics big data feature learning.

Deep learning, as the most important architecture of current computational intelligence, achieves super performance to predict the cloud workload for industry informatics. However, it is a nontrivial task to train a deep learning model efficiently since the deep learning model often includes a great number of parameters. In this paper, an efficient deep learning model based on the canonical polyadic decomposition is proposed to predict the cloud workload for industry informatics. In the proposed model, the parameters are compressed significantly by converting the weight matrices to the canonical polyadic format. Furthermore, an efficient learning algorithm is designed to train the parameters. Finally, the proposed efficient deep learning model is applied to the workload prediction of virtual machines on cloud. Experiments are conducted on the datasets collected from PlanetLab to validate the performance of the proposed model by comparing with other machine-learning-based approaches for workload prediction of virtual machines. Results indicate that the proposed model achieves a higher training efficiency and workload prediction accuracy than state-of-the-art machine-learning-based approaches, proving the potential of the proposed model to provide predictive services for industry informatics.

Deep computation models achieve super performance for big data feature learning. However, training a deep computation model poses a significant challenge since a deep computation model typically involves a large number of parameters. Specially, it needs a high-performance computing server with a large-scale memory and a powerful computing unit to train a deep computation model, making it difficult to increase the size of a deep computation model further for big data feature learning on low-end devices such as conventional desktops and portable CPUs. In this paper, we propose an improved deep computation model based on the canonical polyadic decomposition scheme to compress the parameters and to improve the training efficiency. Furthermore, we devise a learning algorithm based on the back-propagation strategy to train the parameters of the proposed model. The learning algorithm can be directly performed on the compressed parameters to improve the training efficiency. Finally, we carry on the experiments on three representative datasets, i.e., CUAVE, SNAE2, and STL-10, to evaluate the performance of the proposed model by comparing with the conventional deep computation model and other two improved deep computation models based on the Tucker decomposition and the tensor-train network. Results demonstrate that the proposed model can compress parameters greatly and improve the training efficiency significantly with a low classification accuracy drop.

Summary The continuous growth of resource description framework (RDF) data poses an important challenge on RDF data partitioning that is a vital technique for effective cloud storage. Recently, many partitioning algorithms for large RDF data have been developed, and most of them are based on graph partitioning. However, existing graph partitioning methods could not partition asymmetric RDF data effectively, resulting in a lower performance for cloud storage. This paper proposes a balanced RDF graph partitioning algorithm for storing massive RDF data on cloud. We first devise a modularity‐based multi‐level label propagation algorithm (MMLP) to partition RDF graph roughly and then use a balanced K‐mediods clustering algorithm for finalk‐way partitioning. Balanced RDF graph partitioning algorithm designs an effective label update rule and a balanced modification strategy to achieve a high quality coarsening result and make the partition as equilibrium as possible. Experiments are carried on two representative RDF benchmarks and one real RDF dataset by comparison with two representative graph partitioning methods, that is, METIS and MLP+METIS. Results demonstrate that our proposed scheme can produce a high‐quality partition for massive RDF data storage on cloud. Copyright © 2016 John Wiley & Sons, Ltd.

Stable and reliable wireless communication is one of the critical demands for smart cities to connect people and devices. Although intelligent terminals can be leveraged to deliver and exchange data through Internet, poor network coverage and expensive network access challenge the deployment of network infrastructure. In this paper, we propose a social-oriented smartphone-based adaptive transmission mechanism to improve the network connectivity and throughput in Internet of Things (IoTs) for smart cities. First, a social-oriented double-auction-based relay selection scheme is investigated to stimulate the relay smartphones to forward packets for others so that the network connectivity can be strengthened. Furthermore, for the sake of achieving high throughput in smartphone-based IoTs, the relay method selection is determined by integrating various kinds of transmission schemes in an optimal fashion to make full use of wireless spectrum resource. Due to its high computational complexity, a firefly-algorithm-based scheme is investigated, by which the formulated NP-complete problem can be solved effectively. Simulation results demonstrate the superiority of our proposed method.

With the rapid advances of sensing technologies and wireless communications, large amounts of dynamic data pertaining to industrial production are being collected from many sensor nodes deployed in the industrial Internet of Things. Analyzing those data effectively can help to improve the industrial services and mitigate the system unprepared breakdowns. As an important technique of data analysis, clustering attempts to find the underlying pattern structures embedded in unlabeled information. Unfortunately, most of the current clustering techniques that could only deal with static data become infeasible to cluster a significant volume of data in the dynamic industrial applications. To tackle this problem, an incremental clustering algorithm by fast finding and searching of density peaks based on k-mediods is proposed in this paper. In the proposed algorithm, two cluster operations, namely cluster creating and cluster merging, are defined to integrate the current pattern into the previous one for the final clustering result, and k-mediods is employed to modify the clustering centers according to the new arriving objects. Finally, experiments are conducted to validate the proposed scheme on three popular UCI datasets and two real datasets collected from industrial Internet of Things in terms of clustering accuracy and computational time.

Recently, the deep computation model, as a tensor deep learning model, has achieved super performance for multimedia feature learning. However, the conventional deep computation model involves a large number of parameters. Typically, training a deep computation model with millions of parameters needs high-performance servers with large-scale memory and powerful computing units, limiting the growth of the model size for multimedia feature learning on common devices such as portable CPUs and conventional desktops. To tackle this problem, this article proposes a Tucker deep computation model by using the Tucker decomposition to compress the weight tensors in the full-connected layers for multimedia feature learning. Furthermore, a learning algorithm based on the back-propagation strategy is devised to train the parameters of the Tucker deep computation model. Finally, the performance of the Tucker deep computation model is evaluated by comparing with the conventional deep computation model on two representative multimedia datasets, that is, CUAVE and SNAE2, in terms of accuracy drop, parameter reduction, and speedup in the experiments. Results imply that the Tucker deep computation model can achieve a large-parameter reduction and speedup with a small accuracy drop for multimedia feature learning.

To improve the efficiency of big data feature learning, the paper proposes a privacy preserving deep computation model by offloading the expensive operations to the cloud. Privacy concerns become evident because there are a large number of private data by various applications in the smart city, such as sensitive data of governments or proprietary information of enterprises. To protect the private data, the proposed model uses the BGV encryption scheme to encrypt the private data and employs cloud servers to perform the high-order back-propagation algorithm on the encrypted data efficiently for deep computation model training. Furthermore, the proposed scheme approximates the Sigmoid function as a polynomial function to support the secure computation of the activation function with the BGV encryption. In our scheme, only the encryption operations and the decryption operations are performed by the client while all the computation tasks are performed on the cloud. Experimental results show that our scheme is improved by approximately 2.5 times in the training efficiency compared to the conventional deep computation model without disclosing the private data using the cloud computing including ten nodes. More importantly, our scheme is highly scalable by employing more cloud servers, which is particularly suitable for big data.

Clustering is a commonly used technique for multimedia data analysis and management. In this article, we propose a high-order clustering algorithm by fast search and find of density peaks (HOCFS) by extending the traditional clustering scheme by fast search and find of density peaks (CFS) algorithm from the vector space to the tensor space for multimedia data clustering. Furthermore, we propose a privacy preserving HOCFS algorithm (PPHOCFS) which improves the efficiency of the HOCFS algorithm by using the cloud computing to perform most of the clustering operations. To protect the private data in the multimedia data sets during the clustering process on the cloud, the raw data is encrypted by the Brakerski-Gentry-Vaikun-tanathan (BGV) strategy before being uploaded to the cloud for performing the HOCFS clustering algorithm efficiently. In the proposed method, the client is required to only execute the encryption/decryption operations and the cloud servers are employed to perform all the computing operations. Finally, the performance of our scheme is evaluated on two representative multimedia data sets, namely NUS-WIDE and SNAE2, in terms of clustering accuracy, execution time, and speedup in the experiments. The results demonstrate that the proposed PPHOCFS scheme can save at least 40% running time compared with HOCFS, without disclosing the private data on the cloud, making our scheme securely suitable for multimedia big data clustering.

Deep learning has been successfully applied to feature learning in speech recognition, image classification and language processing. However, current deep learning models work in the vector space, resulting in the failure to learn features for big data since a vector cannot model the highly non-linear distribution of big data, especially heterogeneous data. This paper proposes a deep computation model for feature learning on big data, which uses a tensor to model the complex correlations of heterogeneous data. To fully learn the underlying data distribution, the proposed model uses the tensor distance as the average sum-of-squares error term of the reconstruction error in the output layer. To train the parameters of the proposed model, the paper designs a high-order back-propagation algorithm (HBP) by extending the conventional back-propagation algorithm from the vector space to the high-order tensor space. To evaluate the performance of the proposed model, we carried out the experiments on four representative datasets by comparison with stacking auto-encoders and multimodal deep learning models. Experimental results clearly demonstrate that the proposed model is efficient to perform feature learning when evaluated using the STL-10, CUAVE, SANE and INEX datasets.

In data management protocols for Ad-hoc Social Networks (ASNETs), involvement of selfish users can pose a serious threat to network performance and fairness. Therefore, it is essential to detect and mitigate their effects on other well behaving users. We contribute to this line of research by combining the benefits of users' social behavior (social tie) with a biologically inspired approach in ASNETs. We designed a bio-inspired scheme (BoDMaS) to detect and mitigate selfish users in replication operations. Its goals include providing greater accessibility and effective detection of selfish users. The proposed scheme not only guarantees accessibility and effective detection rate, but also ensures the reliability of replica allocation operations.

Reliable social connectivity and transmission of data for popular nodes are vital in multihop Ad-hoc Social Networks (ASNETs). However, congestion may occur and hence popular nodes might not achieve required bandwidth when multiple senders share data with a single receiver. The traditional Transport Control Protocol (TCP) might not be able to perform efficiently in ASNETs. Therefore, we propose a Reliable TCP for Popular Data in Socially-aware Ad-hoc Networks called RTPS. RTPS employs a popularity level approach for every single node which partitions the bandwidth among users. The reliability of popular data is ensured since bandwidth will firstly assigned to the popular sender. Preliminary results show that by delaying the acknowledgment and improving the performance of TCP, RTPS reduces collision loss in multihop ASNETs.

To address selfishness in socially-aware networking, we propose a Community-based Incentive Scheme (CIS). CIS utilizes community to stimulate cooperation among selfish nodes and allows all nodes to behave selfishly to imitate the realistic condition. The simulation results show that CIS effectively stimulates selfish nodes to cooperate, achieves higher delivery ratio while not increasing latency dramatically.