Traffic forecasting is pivotal but challenging due to intricate spatio-temporal dynamics. Existing models often apply a uniform spatial mechanism across distinct temporal scales and rely on static feature embeddings. Consequently, they are inadequate in capturing scale-specific spatial heterogeneity and dynamic feature interdependencies. To address these limitations, we propose the Multi-Scale Spatio-Temporal Attention Network (MSSTAN) with a novel dual-branch architecture: (1) A Global-Local Feature Attention Network (GLFAN) that explicitly decouples spatial interactions across decomposed temporal components to capture multi-scale spatial patterns; and (2) A Spatio-Temporal Feature Attention Network (STFAN) that dynamically recalibrates feature importance based on specific spatio-temporal contexts. A dynamic branch fusion mechanism integrates these branches to optimally aggregate their complementary views. Extensive experiments on five real-world datasets demonstrate that MSSTAN achieves state-of-the-art or highly competitive performance, validating its efficacy for traffic forecasting.

Improving the performance of single image super-resolution (SISR) via extending the effective receptive field (ERF) of the model has become an admired paradigm in the field due to the universal self-similarity prior of natural images. However, it cannot fully explore model capability by solely increasing the ERF to capture long-range dependencies as the non-local self-similarity is typically multi-scale and cross-scale. To this end, a Long-range Multi-scale Fusion Network (LMFN) is devised in this work to simultaneously excavate both long-range and multi-scale priors in images, and the interaction between the both. Within the same scale, our model employs large kernel attention (LKA) and multi-scale modulation (MSM) to learn long-range and multi-scale features. To exploit the interaction between long-range and multi-scale dependencies within one single scale and across scales, we design an Interactive Fusion Modulation (IFM) module for the effective fusion of the non-local and multi-scale features. Extensive experiments on the benchmark datasets illustrate the significant superiority of the proposed LMFN over the advanced SISR models.

In the realm of dermatology, Convolutional Neural Networks (CNNs) have exhibited immense potential, emerging as vital tools to aid physicians for precise diagnosis. However, current work generally faces two main challenges: (1) the inadequate samples in dermatological image datasets hinder sufficiently training high-performance deep models; (2) the pronounced issue of class imbalance significantly undermines the models’ ability to recognize minority class conditions. In response to these problems, this work introduces a novel network architecture and loss called Hierarchical Feature Learning (HFL), aimed at enhancing the model’s feature representation capabilities and adaptability to imbalanced data. Specifically, we devise a CNN architecture based on hierarchical feature storage, which effectively augments the network’s proficiency in extracting and preserving rich, hierarchical features through the incorporation of a multi-level feature memory mechanism. To further mitigate the impact of data imbalance on model training, we propose an Adaptive Re-weighted Loss (ARL). This loss dynamically adjusts the loss weights according to the real-time distribution of samples across classes, ensuring that minority class samples receive adequate attention during training. Experimental results on ISIC-2017, ISIC-2018 and 7-PT datasets demonstrate the effectiveness of our proposed methodology.

Temporal data analysis plays a pivotal role in applications such as weather forecasting, traffic flow management, energy consumption monitoring, and other areas of urban computing. In recent years, temporal data modeling has transitioned from traditional deep learning methods to pre-trained models. However, existing approaches often exhibit significant task-specific limitations, requiring bespoke model designs and extensive domain data for training. To address these challenges, this study introduces KPT, a novel foundation model for temporal data analysis in urban computing. By leveraging temporal competitive attention and feature interaction attention mechanisms, KPT can effectively capture global context, integrate cross-variable features precisely, and achieve universal feature learning across diverse time series tasks. Additionally, the knowledge prompt network facilitates the deep fusion of cross-layer features via an intricate interaction mechanism, enabling the model to identify and align shared temporal patterns across different time series data. These patterns then transformed into knowledge prompts, thereby enhancing the universal feature learning capabilities of the pre-trained model. Experimental results demonstrate that KPT excels in four core temporal analysis tasks within urban computing, outperforming task-specific models. This highlights KPT’s ability to generalize across tasks and underscores its potential as a foundation model for multi-task scenarios in urban computing.

Predicting the metabolic pathway classes of compounds in the human body is an important problem in drug research and development. For this purpose, we propose a Multi-Scale Graph Neural Network framework, named MSGNN. The framework includes a subgraph encoder, a feature encoder and a global feature processor, and a graph augmentation strategy is adopted. The subgraph encoder is responsible for extracting the local structural features of the compound, the feature encoder learns the characteristics of the atoms, and the global feature processor processes the information from the pre-training model and the two molecular fingerprints, while the graph augmentation strategy is to expand the train set through a scientific and reasonable method. The experiment result illustrates that the accuracy, precision, recall and F1 metrics of MSGNN reach 98.17%, 94.18%, 94.43% and 94.30%, respectively, which is superior to the similar models we have known. In addition, the ablation experiment demonstrates the indispensability of MSGNN modules.

Multimodal video sentiment analysis aims to integrate multiple modal information to analyze the opinions and attitudes of speakers. Most previous work focuses on exploring the semantic interactions of intra- and inter-modality. However, these works ignore the reliability of multimodality, i.e., modalities tend to contain noise, semantic ambiguity, missing modalities, etc. In addition, previous multimodal approaches treat different modalities equally, largely ignoring their different contributions. Furthermore, existing multimodal sentiment analysis methods directly regress sentiment scores without considering ordinal relationships within sentiment categories, with limited performance. To address the aforementioned problems, we propose a trustworthy multimodal sentiment ordinal network (TMSON) to improve performance in sentiment analysis. Specifically, we first devise a unimodal feature extractor for each modality to obtain modality-specific features. Then, an uncertainty distribution estimation network is customized, which estimates the unimodal uncertainty distributions. Next, Bayesian fusion is performed on the learned unimodal distributions to obtain multimodal distributions for sentiment prediction. Finally, an ordinal-aware sentiment space is constructed, where ordinal regression is used to constrain the multimodal distributions. Our proposed TMSON outperforms baselines on multimodal sentiment analysis tasks, and empirical results demonstrate that TMSON is capable of reducing uncertainty to obtain more robust predictions.

As the spatio-temporal data of a city is not always available, insufficient data would lead to poor performance in some urban prediction tasks. Existing works utilize transfer learning to solve the data scarcity problem, but they ignore the differences in data distributions across cities, which leads to the ineffectiveness of knowledge transfer. In this paper, we propose a domain adversarial model with knowledge transfer for spatio-temporal prediction across cities, entitledCityTrans. Specifically, 1) the self-adaptive spatio-temporal knowledge (namely ST-Knowledge) is mined, to learn the latent spatial and temporal patterns among cities; 2) the domain-adversarial training strategy is introduced to enhance domain invariance; 3) a knowledge attention mechanism is proposed to extract the transferable information from the ST-Knowledge. Note that our CityTrans is an end-to-end domain adversarial spatio-temporal network without two-stage training (i.e., pre-training and fine-tuning). Finally, we conduct extensive experiments on two spatio-temporal prediction tasks: traffic (flow and speed) prediction, and air quality prediction. Experimental results demonstrate that CityTrans outperforms state-of-the-art models on all tasks by a significant margin.

Protein sequences accumulate in large quantities, and the traditional method of annotating protein function by experiment has been unable to bridge the gap between annotated proteins and unannotated proteins. Machine learning-based protein function prediction is an effective approach to solve this problem. Most of the existing methods only use the protein sequence but ignore the three-dimensional structure which is closely related to the protein function. And the hierarchy of protein functions is not adequately considered. To solve this problem, we propose a graph neural network (GNNGO3D) that combines the three-dimensional structure and functional hierarchy learning. GNNGO3D simultaneously uses three kinds of information: protein sequence, tertiary structure, and hierarchical relationship of protein function to predict protein function. The novelty of GNNGO3D lies in that it integrates the learning of functional level information into the method of predicting protein function by using tertiary structure information, fully learning the relationship between protein functions, and helping to better predict protein function. Experimental results show that our method is superior to existing methods for predicting protein function based on sequence and structure.

Cracks are one of the most common and significant types of road surface damage, posing a threat to the safety of pedestrians and vehicles. If left untreated, cracks can lead to severe consequences such as road and bridge collapse. Therefore, it is essential to develop an efficient road crack detection method. Traditional crack identification methods have the problem of being largely affected by the environment and having low recognition accuracy. In this paper, we propose a road crack detection model based on an improved You Only Look Once version 5 (YOLOv5) model that addresses the limitations of existing state-of-the-art crack detection methods in terms of accuracy and detection speed. First, we replace the intersection over union (IoU) loss function with the SCYLLA-IoU (SIoU) loss function for better accuracy. Second, to enhance detection performance, we replace the feature pyramid network (FPN) with a bi-directional feature pyramid network (BiFPN). Finally, to better extract spatial feature information of different sizes, we modify the original Spatial Pyramid Pooling-Fast (SPPF) module of YOLOv5 by using Spatial Pyramid Pooling Cross-Stage Partial Connections (SPPCSPC). We evaluated our YOLOv5s-BiFPN-SPPCSPC-SIoU (YOLOv5s-BSS) method on the dataset from the IEEE 2020 Global Road Damage Detection Challenge (GRDDC) and achieved promising results on road damage datasets from China, Japan, and the United States. The [email protected] of different cracks in three datasets reached 84.9%, 54.6%, and 71%. Our method outperforms related methods, with an increase of 0.7%, 0.7%, and 2.8% over YOLOv5s.

Retrosynthesis and forward synthesis prediction are fundamental challenges in organic synthesis, computer-aided synthesis planning (CASP), and computer-aided drug design (CADD). The objective is to predict plausible reactants for a given target product and its corresponding inverse task. With the rapid development of deep learning, numerous approaches have been proposed to solve this problem from various perspectives. The methods based on molecular graphs benefit from their rich features embedded inside but face difficulties in applying existing sequence-based data augmentations due to the permutation invariance of graph structures. In this work, we propose SeqAGraph, a template-free approach that annotates input graphs with its root atom index to ensure compatibility with sequence-based data augmentation. The matrix product for global attention in graph encoders is implemented by indexing, elementwise product, and aggregation to fuse global attention with local message passing without graph padding. Experiments demonstrate that SeqAGraph fully benefits from molecular graphs and sequence-based data augmentation and achieves state-of-the-art accuracy in template-free approaches.

Traffic prediction is the cornerstone of the intelligent transportation system (ITS), and accurate prediction is essential for planning route, alleviating traffic pressure, and optimizing public transportation resource allocation. Although many methods have been proposed, they still have deficiencies in capturing the spatial-temporal dependence of traffic data. In specific, their network structures are usually discrete, making it is challenging to continuously model the dynamic spatial-temporal patterns of the road network. Besides, static graph structure of the road network is not sufficient to express dynamic traffic patterns. In this paper, we propose a diffusion graph neural ordinary differential equation network (DGODE) to address the above challenges for traffic prediction. Firstly, DGODE represents the node relationships of the road network as a bidirectional spatial graph and the node relationships of the time as a unidirectional temporal graph, and then generates an adaptive diffusion matrix to explore potential node relationships and capture spatial and temporal dependencies. Next, the neural ordinary differential equation (NODE) is introduced to contin-uously model the dynamical change of traffic network, making it possible to capture global dependence at a deeper network structure. Since the solution of the ordinary differential equation is determined by the initial state, we design the structure with a jump link to supplement the spatial-temporal information in the historical data. Finally, the experimental evaluation on four real-world datasets shows that DGODE is significantly superior to several baseline methods.

Multi-view or even multi-modal data is appealing yet challenging for real-world applications. Detecting anomalies in multi-view data is a prominent recent research topic. However, most of the existing methods 1) are only suitable for two views or type-specific anomalies, 2) suffer from the issue of fusion disentanglement, and 3) do not support online detection after model deployment. To address these challenges, our main ideas in this paper are three-fold: multi-view learning, disentangled representation learning, and generative model. To this end, we propose dPoE, a novel multi-view variational autoencoder model that involves (1) a Product-of-Experts (PoE) layer in tackling multi-view data, (2) a Total Correction (TC) discriminator in disentangling view-common and view-specific representations, and (3) a joint loss function in wrapping up all components. In addition, we devise theoretical information bounds to control both view-common and view-specific representations. Extensive experiments on six real-world datasets demonstrate that the proposed dPoE outperforms baselines markedly.

Identifying protein-protein interaction (PPI) site is an important step in understanding biological activity, apprehending pathological mechanism and designing novel drugs. Developing reliable computational methods for predicting PPI site as screening tools contributes to reduce lots of time and expensive costs for conventional experiments, but how to improve the accuracy is still challenging. We propose a PPI site predictor, called Augmented Graph Attention Network Protein-Protein Interacting Site (AGAT-PPIS), based on AGAT with initial residual and identity mapping, in which eight AGAT layers are connected to mine node embedding representation deeply. AGAT is our augmented version of graph attention network, with added edge features. Besides, extra node features and edge features are introduced to provide more structural information and increase the translation and rotation invariance of the model. On the benchmark test set, AGAT-PPIS significantly surpasses the state-of-the-art method by 8% in Accuracy, 17.1% in Precision, 11.8% in F1-score, 15.1% in Matthews Correlation Coefficient (MCC), 8.1% in Area Under the Receiver Operating Characteristic curve (AUROC), 14.5% in Area Under the Precision-Recall curve (AUPRC), respectively.

Multi-modal Named Entity Recognition (MNER), which mainly focuses on enhancing text-only NER with visual information, has recently attracted considerable attention. Most current MNER models have made significant progress by jointly understanding visual and language modalities through layers of cross-modality attention. However, these approaches largely ignore the visual bias brought by the image contents and barely consider exploiting the multi-granularity representations and the interactions between visual objects, which are essential in recognizing ambiguous entities. In this paper, we propose aScene graph drivenMulti-modalMulti-granularityMulti-task learning (M3S) framework to better exploit visual and textual information in MNER. Specifically, to explicitly alleviate visual bias, we present a novel multi-task approach by employing the task of Named Entity Segmentation (NES) cascade with Named Entity Categorization (NEC). To obtain detailed visual semantics by explicitly modeling objects and relationships between paired objects, we construct scene graphs as a structured representation of the visual contents. Furthermore, a well-designed Multi-granularity Gated Aggregation (MGA) mechanism is introduced to capture inter-modality interactions and extract critical features for named entity recognition. Extensive experiments on two real public datasets demonstrate the effectiveness of our proposed M3S.

Air quality prediction has received widespread attention from both the governments and citizens due to its close relation to our lives. Analyzing the spatial relations and temporal trends in air quality data is essential for air quality prediction task. However, most existing approaches require a pre-defined graph structure to capture the spatial dependencies of air quality data, and thus they can not be applied when a well-defined graph structure is unavailable. Besides, those methods do not give sufficient consideration to the latent relationships among entities of the graph over time. To overcome the above limitations, we propose a Spatial-Temporal Dynamic Graph Convolution Neural Network (ST-DGCN) in this paper. Our approach develops a dynamic adjacency matrix into graph convolution layer, which extracts the potential and time-varying spatial dependencies. To jointly model the spatial and temporal correlations, we combine dynamic graph convolution with gated recurrent unit and propose a unified DGC-GRU block. Next, a residual operation is further introduced into the DGC-GRU to simultaneously handle the information from different particles. Experimental results demonstrate that the proposed method outperforms the state-of-art baselines on two real-world air quality datasets.

Abstract Hierarchical image segmentation is a prevalent technique in the literature for improving segmentation quality, where the segmentation result needs to be searched at different scales of the hierarchy to identify objects represented from various scales. In this paper, a novel framework for improving the quality of object segmentation is presented. To this end, the authors first select the optimal segments among several hierarchical scales of the input image using simple mid‐level features and dynamic programming. Simultaneously, deep seeds are localised on the input image for the foreground and background classes using a deep classification network and a saliency network, respectively. Then, a graphical model is constructed as a set of nodes that jointly propagate information from deep seeds to unmarked regions to obtain the final object segmentation. Comprehensive experiments are performed on different datasets for popular hierarchical image segmentation algorithms. The experimental results show that the proposed framework can significantly improve the quality of object segmentation at low computational costs and without training any segmentation network.

Deep convolutional neural networks (DCNNs) trained on the pixel-level annotated images have achieved improvements in semantic segmentation. Due to the high cost of labeling training data, their applications may have great limitation. However, weakly supervised segmentation approaches can significantly reduce human labeling efforts. In this paper, we introduce a new framework to generate high-quality initial pixel-level annotations. By using a hierarchical image segmentation algorithm to predict the boundary map, we select the optimal scale of high-quality hierarchies. In the initialization step, scribble annotations and the saliency map are combined to construct a graphic model over the optimal scale segmentation. By solving the minimal cut problem, it can spread information from scribbles to unmarked regions. In the training process, the segmentation network is trained by using the initial pixel-level annotations. To iteratively optimize the segmentation, we use a graphical model to refine segmentation masks and retrain the segmentation network to get more precise pixel-level annotations. The experimental results on Pascal VOC 2012 dataset demonstrate that the proposed framework outperforms most of weakly supervised semantic segmentation methods and achieves the state-of-the-art performance, which is [Formula: see text] mIoU.

Air quality forecasting has been regarded as the key problem of air pollution early warning and control management. In this article, we propose a novel deep learning model for air quality (mainly PM2.5) forecasting, which learns the spatial-temporal correlation features and interdependence of multivariate air quality related time series data by hybrid deep learning architecture. Due to the nonlinear and dynamic characteristics of multivariate air quality time series data, the base modules of our model include one-dimensional Convolutional Neural Networks (1D-CNNs) and Bi-directional Long Short-term Memory networks (Bi-LSTM). The former is to extract the local trend features and spatial correlation features, and the latter is to learn spatial-temporal dependencies. Then we design a jointly hybrid deep learning framework based on one-dimensional CNNs and Bi-LSTM for shared representation features learning of multivariate air quality related time series data. We conduct extensive experimental evaluations using two real-world datasets, and the results show that our model is capable of dealing with PM2.5 air pollution forecasting with satisfied accuracy.

The classic deep learning paradigm learns a model from the training data of a single task and the learned model is also tested on the same task.This paper studies the problem of learning a sequence of tasks (sentiment classification tasks in our case).After each sentiment classification task is learned, its knowledge is retained to help future task learning.Following this setting, we explore attention neural networks and propose a Bayes-enhanced Lifelong Attention Network (BLAN).The key idea is to exploit the generative parameters of naïve Bayes to learn attention knowledge.The learned knowledge from each task is stored in a knowledge base and later used to build lifelong attentions.The constructed lifelong attentions are then used to enhance the attention of the network to help new task learning.Experimental results on product reviews from Amazon.com show the effectiveness of the proposed model.

Multi-view graph-based clustering aims to provide clustering solutions to multi-view data. However, most existing methods do not give sufficient consideration to weights of different views and require an additional clustering step to produce the final clusters. They also usually optimize their objectives based on fixed graph similarity matrices of all views. In this paper, we propose a general Graph-based Multi-view Clustering (GMC) to tackle these problems. GMC takes the data graph matrices of all views and fuses them to generate a unified graph matrix. The unified graph matrix in turn improves the data graph matrix of each view, and also gives the final clusters directly. The key novelty of GMC is its learning method, which can help the learning of each view graph matrix and the learning of the unified graph matrix in a mutual reinforcement manner. A novel multi-view fusion technique can automatically weight each data graph matrix to derive the unified graph matrix. A rank constraint without introducing a tuning parameter is also imposed on the graph Laplacian matrix of the unified matrix, which helps partition the data points naturally into the required number of clusters. An alternating iterative optimization algorithm is presented to optimize the objective function. Experimental results using both toy data and real-world data demonstrate that the proposed method outperforms state-of-the-art baselines markedly.

This paper studies the problem of learning a sequence of sentiment classification tasks. The learned knowledge from each task is retained and later used to help future or subsequent task learning. This learning paradigm is called \textit{lifelong learning}. However, existing lifelong learning methods either only transfer knowledge forward to help future learning and do not go back to improve the model of a previous task or require the training data of the previous task to retrain its model to exploit backward/reverse knowledge transfer. This paper studies reverse knowledge transfer of lifelong learning. It aims to improve the model of a previous task by leveraging future knowledge without retraining using its training data, which is challenging now. In this work, this is done by exploiting a key characteristic of the generative model of naïve Bayes. That is, it is possible to improve the naïve Bayesian classifier for a task by improving its model parameters directly using the retained knowledge from other tasks. Experimental results show that the proposed method markedly outperforms existing lifelong learning baselines.

Parkinson's Disease (PD) is a progressive neurodegenerative disorder, which is characterized by motor symptoms. In recent years, machine learning based approaches have been proposed to assist the diagnosis of PD. However, existing approaches mainly concerned classification task and mostly studied using single-view data. In this paper, we tackle PD screening task using multi-view data. A PD screening task aims to use the diagnostic data from brain magnetic resonance imaging (MRI) as an assistance to prevent and delay the deterioration of PD. To perform this task, we propose a novel deep learning architecture called Deep neural networks with Broad Views (DBV). The proposed model builds upon Wasserstein Generative Adversarial Networks (WGAN) and ResNeXt, which can exploit multi-view data jointly. Experimental results using multi-view brain MRI data from the Parkinson's Progression Markers Initiative (PPMI) database show that the proposed model outperforms several existing solid deep learning baselines dramatically.

Hao Wang, Bing Liu, Chaozhuo Li, Yan Yang, Tianrui Li. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Beyond existing multi-view clustering, this paper studies a more realistic clustering scenario, referred to as incomplete multi-view clustering, where a number of data instances are missing in certain views. To tackle this problem, we explore spectral perturbation theory. In this work, we show a strong link between perturbation risk bounds and incomplete multi-view clustering. That is, as the similarity matrix fed into spectral clustering is a quantity bounded in magnitude O(1), we transfer the missing problem from data to similarity and tailor a matrix completion method for incomplete similarity matrix. Moreover, we show that the minimization of perturbation risk bounds among different views maximizes the final fusion result across all views. This provides a solid fusion criteria for multi-view data. We motivate and propose a Perturbation-oriented Incomplete multi-view Clustering (PIC) method. Experimental results demonstrate the effectiveness of the proposed method.

Traffic flow prediction has been regarded as a key research problem in the intelligent transportation system. In this paper, we propose an encoder-decoder model with temporal attention mechanism for multi-step forward traffic flow prediction task, which uses LSTM as the encoder and decoder to learn the long dependencies features and nonlinear characteristics of multivariate traffic flow related time series data, and also introduces a temporal attention mechanism for more accurately traffic flow prediction. Through the real traffic flow dataset experiments, it has shown that the proposed model has better prediction ability than classic shallow learning and baseline deep learning models. And the predicted traffic flow value can be well matched with the ground truth value not only under short step forward prediction condition but also under longer step forward prediction condition, which validates that the proposed model is a good option for dealing with the realtime and forward-looking problems of traffic flow prediction task.

In recent years, Generative adversial network(GAN) becomes prevalent in the research and was applied in various fields. Though GAN attracting great attention undoubtedly, it was still blamed for the difficulty of training. Training a GAN is very likely to get into undesirable results such as gradient vanishing, gradient explosion, model collapse. In order to train GAN more efficiently, this study proposes the Swap Ensemble Generative Adversial Network(SE-GAN), a framework for training an ensemble GAN. Based on the concept of information sharing, SE-GAN allows serveral GANs to be trained in parallel: one of them is the leader, while the others are the workers. The leader pair swaps with each worker periodically to collect the information of all workers. At the same time, each worker acquires the information the leader learned. Under such implementation, the leader and workers would help each other. In this paper, a toy dataset was used to describe the concept and better show the effect of swap ensemble framework. And three real-world datasets were used to validate the effect. Results of the experiments shows this framework improves the performance and efficiency in training GAN.

Multi-view learning take full advantage of multiple perspectives of data to improve learning performance. However, there are a lot of single-view data with high dimensions and low quantity in real life. Although traditional feature reduction methods can achieve the purpose of dimensionality reduction, a part of information will be lost. In order to make full use of the existing information of data and play advantages of multi view learning, a multi-view construction method based on feature set partitioning is proposed. This method firstly constructs the initial view by using a series of feature selection algorithms and then presents a multi-view evaluation method that is used to look for the most suitable view for a single feature to insert until all irrelevant features in original feature set are discarded while achieving the optimal partitioning, thereby multiple views are constructed. Experiments show that this method builds high quality multiple views to further improve clustering performance.

Urban resource scheduling is an important part of the development of a smart city, and transportation resources are the main components of urban resources. Currently, a series of problems with transportation resources such as unbalanced distribution and road congestion disrupt the scheduling discipline. Therefore, it is significant to predict travel demand for urban resource dispatching. Previously, the traditional time series models were used to forecast travel demand, such as AR, ARIMA and so on. However, the prediction efficiency of these methods is poor and the training time is too long. In order to improve the performance, deep learning is used to assist prediction. But most of the deep learning methods only utilize temporal dependence or spatial dependence of data in the forecasting process. To address these limitations, a novel deep learning traffic demand forecasting framework which based on Deep Spatio-Temporal ConvLSTM is proposed in this paper. In order to evaluate the performance of the framework, an end-to- end deep learning system is designed and a real dataset is used. Furthermore, the proposed method can capture temporal dependence and spatial dependence simultaneously. The closeness, period and trend components of spatio-temporal data are used in three predicted branches. These branches have the same network structures, but do not share weights. Then a linear fusion method is used to get the final result. Finally, the experimental results on DIDI order dataset of Chengdu demonstrate that our method outperforms traditional models with accuracy and speed.

Semi-supervised clustering ensemble has emerged as an important elaboration of classical clustering problem that improves quality and robustness in clustering by combining the results of different clustering components with user provided constraints. MapReduce is a parallel programming model for processing big data using large numbers of distributed computers (nodes). In this paper, we propose a novel semi-supervised multi-ant colonies consensus clustering algorithm and implement the parallelization of this algorithm using MapReduce on Hadoop platform. Our method incorporates pairwise constraints not only in each ant colony clustering process, but also in computing new similarity matrix during the process of the multi-ant colonies ensemble. In addition, it enhances the computational efficiency for big data by adopting a MapReduce Framework. Experimental results demonstrate the effectiveness of the proposed method.

In this paper, we present a steering system for a space-saving four-wheel steering and four-wheel drive (4WS4WD) electric vehicle (EV) with higher maneuverability and flexibility. The proposed system consists of three main parts, namely, an improved two-front-wheel steering (2FWS) mechanism, an omnidirectional independent steering (OIS) mechanism integrated with steer-by-wire, and a control strategy for the space-saving steering system of an EV. First, the 2FWS mechanism of the proposed 4WS4WD EV is designed to control the front wheels via the redesigned steering system when the vehicle is traveling at high speeds. Second, a retrofitted OIS mechanism is proposed to achieve an angle range of -35° ~ +90°, which is a solid basis for zero radius turning (ZRT) and lateral parking (LP) motion. The driver can control the OIS to turn the four wheels independently, which is assisted by steer-by-wire technologies. Finally, the control strategy for the space-saving steering system of the EV is redefined for the integrated 2FWS and OIS, which can easily handle the EV for high-speed driving or high-maneuverability turning, such as ZRT and LP motion. This system was field tested on a homemade 4WS4WD EV, and the final system simulation and performance evaluation demonstrated the validity of the proposed steering system for the space-saving 4WS4WD EV.

Real-world datasets often have representations in multiple views or come from multiple sources. Exploiting consistent or complementary information from multi-view data, multi-view clustering aims to get better clustering quality rather than relying on the individual view. In this paper, we propose a novel multi-view clustering method called multi-view concept clustering based on concept factorization with local manifold regularization, which drives a common consensus representation for multiple views. The local manifold regularization is incorporated into concept factorization to preserve the locally geometrical structure of the data space. Moreover, the weight of each view is learnt automatically and a co-normalized approach is designed to make fusion meaningful in terms of driving the common consensus representation. An iterative optimization algorithm based on the multiplicative rules is developed to minimize the objective function. Experimental results on nine reality datasets involving different fields demonstrate that the proposed method performs better than several state-of-the-art multi-view clustering methods.

Deep Belief Network (DBN) learns the features of the raw data automatically, and develops a new idea for the study of fault analysis of High Speed Train (HST). Combining deep learning and classification ensemble technology, this paper presents a novel DBN hierarchical ensemble model for HST fault analysis. Firstly, Fast Fourier Transform (FFT) coefficients of the HST vibration signals are extracted as the state of the visible layer of the model, and then DBN is used to learn the hierarchical features of the vibration signals automatically. The features of each layer learned by DBN are used to train Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Radial Basis Function (RBF) Neural Network respectively. Finally, the Majority Voting (MV), the Classification Entropy Voting Principle (CE), and the Winner Takes All (WTA) ensemble strategies are used for combination to get the final results. The experiments are conducted by using laboratory data sets and simulation data sets. The results show that the fault recognition rate of the proposed model is much higher than the traditional fault analysis methods. In addition, unlike the DBN model, the proposed model is affected slightly by the number of network layers and the size of hidden units.

This paper studies the problem of how to efficiently minimize network coding resource. A modified particle swarm optimization (PSO) algorithm is proposed to tackle the problem, with the concept of path-relinking (PR) integrated into the evolutionary framework. As an efficient local search heuristic that makes use of problem-specific domain knowledge, PR helps strike a better balance between global exploration and local exploitation for the evolutionary search. Simulation results demonstrate that the proposed algorithm overweighs a number of existing and commonly used evolutionary algorithms (EAs) in terms of the solution quality, convergence, and computational time.

Quantitative evaluation of image segmentation quality is usually based on comparing a segmentation with multiple reference segmentations. Instead of holistically comparing with each reference, we propose a region based evaluation framework, where an exemplar reference is adaptively constructed and applied to a generally defined evaluation measure. As examples, we implement three well-known evaluation measures and present an efficient scheme to compute each measure. Extensive experiments on the benchmark databases show that the proposed evaluation framework can improve the evaluation precision of existing measures.

Co-clustering aims to simultaneously cluster the objects and features to explore intercorrelated patterns. However, it is usually difficult to obtain good co-clustering results by just analyzing the object-feature correlation data due to the sparsity of the data and the noise. Meanwhile, most co-clustering algorithms cannot take the prior information into consideration and may produce unmeaningful results. Semi-supervised co-clustering aims to incorporate the known prior knowledge into the co-clustering algorithm. In this paper, a new technique named constraint co-projections for semi-supervised co-clustering (CPSSCC) is presented. Constraint co-projections can not only make use of two popular techniques including pairwise constraints and constraint projections, but also simultaneously perform the object constraint projections and feature constraint projections. The two popular techniques are illustrated for semi-supervised co-clustering when some objects and features are believed to be in the same cluster a priori. Furthermore, we also prove that the co-clustering problem can be formulated as a typical eigen-problem and can be efficiently solved with the selected eigenvectors. To the best of our knowledge, constraint co-projections is first stated in this paper and this is the first work on using CPSSCC. Extensive experiments on benchmark data sets demonstrate the effectiveness of the proposed method. This paper also shows that CPSSCC has some favorable features compared with previous related co-clustering algorithms.

This paper presents a modified ant colony optimization (ACO) approach for the network coding resource minimization problem. It is featured with several attractive mechanisms specially devised for solving the concerned problem: 1) a multidimensional pheromone maintenance mechanism is put forward to address the issue of pheromone overlapping; 2) problem-specific heuristic information is employed to enhance the capability of heuristic search (neighboring area search); 3) a tabu-table-based path construction method is devised to facilitate the construction of feasible (link-disjoint) paths from the source to each receiver; 4) a local pheromone updating rule is developed to guide ants to construct appropriate promising paths; and 5) a solution reconstruction method is presented, with the aim of avoiding prematurity and improving the global search efficiency of proposed algorithm. Due to the way it works, the ACO can well exploit the global and local information of routing-related problems during the solution construction phase. The simulation results on benchmark instances demonstrate that with the integrated five extended mechanisms, our algorithm outperforms a number of existing algorithms with respect to the best solutions obtained and the computational time.

Aiming at open domain question answering system evaluation task in the fourth CCF Natural Language Processing and Chinese Computing Conference (NLPCC2015), a solution of automatic question answering which can answer natural language questions is proposed. Firstly, SPE (Subject Predicate Extraction) algorithm is presented to find answers from the knowledge base, and then WKE (Web Knowledge Extraction) algorithm is used to extract answers from search engine query result. Experimental data provided in the evaluation task includes the knowledge base and questions in natural language. The evaluation result shows that MRR is 0.5670, accuracy is 0.5700, and average F1 is 0.5240, and indicates the proposed method is feasible in open domain question answering system.

Feature extraction is one of key steps in fault diagnosis for High Speed Train (HST). In this work, we present a method that can automatically extract high-level features from HST vibration signals and recognize the faults. The method is composed of a Deep Belief Network (DBN) on Fast Fourier Transform (FFT) of vibration signals. DBNs can be trained greedily, layer by layer, using a model referred to as a Restricted Boltzmann Machine (RBM). The real data sets and simulation data sets of HST vibration signals are selected in experiments. First, the vibration signals are preprocessed by FFT. Then, the FFT coefficient-vectors are used to set the states of the visible units of DBNs. Finally, n label units are connected to the "top" layer of the DBNs to identify different faults. The experimental results show that the method may learn useful high-level features from vibration signals and diagnose the different faults of HST.

Semi-supervised clustering aims to incorporate the known prior knowledge into the clustering algorithm. Pairwise constraints and constraint projections are two popular techniques in semi-supervised clustering. However, both of them only consider the given constraints and do not consider the neighbors around the data points constrained by the constraints. This paper presents a new technique by utilizing the constrained pairwise data points and their neighbors, denoted as constraint neighborhood projections that requires fewer labeled data points (constraints) and can naturally deal with constraint conflicts. It includes two steps: 1) the constraint neighbors are chosen according to the pairwise constraints and a given radius so that the pairwise constraint relationships can be extended to their neighbors, and 2) the original data points are projected into a new low-dimensional space learned from the pairwise constraints and their neighbors. A CNP-Kmeans algorithm is developed based on the constraint neighborhood projections. Extensive experiments on University of California Irvine (UCI) datasets demonstrate the effectiveness of the proposed method. Our study also shows that constraint neighborhood projections (CNP) has some favorable features compared with the previous techniques.

Clustering with pairwise constraints has received much attention in the clustering community recently. Particularly, must-link and cannot-link constraints between a given pair of instances in the data set are common prior knowledge incorporated in many clustering algorithms today. This approach has been shown to be successful in guiding a number of famous clustering algorithms towards more accurate results. However, recent work has also shown that the incorporation of must-link and cannot-link constraints makes clustering algorithms too much sensitive to “the assignment order of instances” and therefore results in consequent constraint violation. The major contributions of this paper are two folds. One is to address the issue of constraint violation in Cop-Kmeans by emphasizing a sequenced assignment of cannot-link instances after conducting a Breadth-First Search of the cannot-link set. The other is to reduce the computational complexity of Cop-Kmeans for massive data sets by adopting a MapReduce Framework. Experimental results show that our approach performs well on massive data sets while may overcome the problem of constraint violation.

Abstract The rapid development of wireless technology plays extremely important roles in monitoring, control, and collaboration related applications. This paper aims at state‐of‐the‐art self‐stabilizing flocking control of wireless mobile robots with memory corruption. Flocking of a group of wireless mobile robots has gained a lot of attention due to its wide applications in recent years. While there are few works addressed on fault tolerance issue of flocking, especially for transient failure of robots. However, in the practical applications of robots, for the weak robots, some of their parts, like sensor, moving actuator, or memory etc., are prone to be crashed due to the complex environment. So, it is interesting to explore such kind of component crash or corruption (partly crash), especially for transient failure. The transient failure means the failure is temporary and after a while the robots will not be influenced by outside environment. Specially, in this paper, we mainly focus on how one kind of transient failure—memory corruption affects robot flocking, especially for the existed fault tolerant flocking. Copyright © 2009 John Wiley & Sons, Ltd.

Spatial Audio Coding (SAC) is an emerging technology with a distinguishing feature of delivering good even excellent audio quality at monotonic or stereo bitrate of conventional perceptual transform coders. By a systematic exploitation of spatial hearing, Binaural Cue Coding illustrates the power and potentials of SAC in the future for intelligent multimedia services. MPEG Surround, receiving cumulative efforts from industry and academy, strives to build a SAC system with great versatility and high quality. The initial test results of MPEG Surround show its performance advantage over conventional state-of-the-art coders in a wide range of coding configurations.

Considering a large part of node failures in a storage clusters cannot actually destroy data in disks and even some failed nodes can soon recover, a policy that deferring a reconstruction until recover during a certain time after a node failure can lessen unnecessary data rebuilding process is absolutely possible and favorable, but it also undoubtedly introduces a certain risk of data loss.

Consider a system composed of mobile robots (mobile sensors) that move on the plane, each of which independently executing its own instance of an algorithm. Given a desired geometric pattern, the flocking problem consists in ensuring that the robots form this pattern and maintain it while moving together on the plane. In this paper, we look at the flocking problem in the presence of faulty robots, where the desired pattern is a regular polygon. We propose a distributed algorithm assuming a semi-synchronous model with a k-bounded scheduler, in the sense that no robot is activated more than k times between any two consecutive activations of any other robot. The algorithm is composed of three parts: failure detector, ranking assignment and flocking algorithm. The rank assignment part is to provide a persistent ranking for the robots in the system. Then, the failure detector can select the set of correct robots from all the robots. Finally, the flocking algorithm handles the movement and reconfiguration of the flock, while maintaining the desired shape. The difficulty of the problem comes from the combination of the three parts together with the necessity to prevent collision and allow the rotation of the flock. Different from the existed work, our algorithm can make the formation rotate freely and has good maneuverability.

With the ever-increasing number of multicast data applications recently, considerable efforts have been focused on the design of flow control schemes for multicast services. The main difficulties in designing a flow controller for multicast service are caused by heterogeneous multicast receivers, especially those with large propagation delays, since the feedback arriving at the source is somewhat outdated, and can be harmful to the control operations. To attack the above problem, the present paper describes a novel multicast flow control scheme, the so-called proportional, integrative, derivative plus neural network (PIDNN) predictive technique, which consists of two components: the proportional integrative plus derivative (PID) controller and the back propagation BP neural network (BPNN). This network-assisted property is different from the existing control schemes, in that the PIDNN controller can release the irresponsiveness of a multicast flow caused by those long propagation delays from the receivers. By using BPNN for the receivers with longer propagation delay, this active scheme makes the control more responsive to network status. Thus the rate adaptation can be performed in a timely manner, for the sender to respond to network congestion quickly. We analyze the theoretical aspects of the proposed algorithm, show how the control mechanism can be used to design a controller to support multi-rate multicast transmission based on feedback of explicit rates, and verify this matching using simulations. Simulation results demonstrate the efficiency of our scheme in terms of high link utilization, quick response, scalability, high unitary throughput, intra-session fairness and inter-session fairness.

The control and coordination of mobile robots in groups that can freely cooperate and move on a plane is a widely studied topic in distributed robotics. In this paper, we focus on the flocking problem: there are two kinds of robots: the leader robot and the follower robots. The follower robots are required to follow the leader robot wherever it goes (following), while keeping a formation they are given in input (flocking). A novel scheme is proposed based on the relative motion theory. Extensive theoretical analysis and simulation results demonstrate that this scheme provides the follower robots an efficient method to follow the leader as soon as possible with the shortest path. Furthermore, this scheme is scalable, and the processing load for every robot is not increased with the addition of more robots.

This paper compares several parametric and adaptive failure detection schemes in terms of their respective QoS. We introduce an improvement over existing methods, and evaluate their benefits. First, we propose an optimization to enhance the adaptation of Chen's FD, which significantly improves QoS, especially in the aggressive range and when the network is unstable. Second, we address the problem of most adaptive schemes, namely their need for a large window of samples. We study a scheme that is designed to use a fixed and very limited amount of memory for each monitored-monitoring link. Our experimental results over several kinds of networks (Cluster, WiFi, wired LAN, WAN) show that the properties of the existing adaptive FDs, and that the optimization is reasonable and acceptable. Furthermore, the extensive experimental results show what is the effect of memory size on the overall QoS of each adaptive FD.

The detection of failures is a fundamental issue for fault tolerance in distributed systems. Recently, many people have come to realize that failure detection ought to be provided as some form of generic service, similar to IP address lookup. However, this has not been successful so far; one of the reasons being the fact that classical failure detectors were not designed to satisfy several application requirements simultaneously. More specifically, traditional implementations of failure detectors are often tuned for running over local networks and fail to address some important problems found in wide-area distributed systems with a large number of monitored components. In this paper, we study the quality of service (QoS) of failure detectors. We first present a novel failure detector scheme combined with control theory that can help in solving or optimizing some problems. Furthermore, this paper discusses the design and analysis of implementing a scalable failure detection service for such large wide-area distributed systems considering dynamically adjusting the heartbeat streams, so that it satisfies the bottleneck router requirements. We further show how the online failure detector control algorithm can be used to design a controller, analyze the theoretical aspects of the proposed algorithm and verify its agreement. Simulation results show the efficiency of our scheme in terms of high utilization of the bottleneck link, fast response and good stability of the bottleneck router buffer occupancy as well as of the controlled sending rates. In conclusion, the new failure detector algorithm provides a better QoS.

With the increase of multicast data applications, research interests have focused on the design of congestion control schemes for multicast communications. This paper describes a novel control-theoretic multicast congestion control scheme, which is based on the distributed self-tuning proportional plus integrative (SPI) controller. The control parameters can be designed to ensure the stability of the control loop in terms of source rate. The distributed explicit rate SPI overcomes the vulnerability that suffers from the heterogeneous multicast receivers. It is suggested that the congestion controller is located at the multipoint-to-multipoint multicast source to regulate the transmission rate. We further analyze the theoretical aspects of the proposed algorithm, and show how the control mechanism can be used to design a controller to support multicast transmissions. Simulation results demonstrate the efficiency of the proposed scheme in terms of system stability and fast response of the buffer occupancy, as well as controlled sending rates, low packet loss, and high scalability

This paper discusses document clustering using ant colony algorithm and validity index. Clusterings are formed on the plane by ants walking, picking up or dropping down projected document vectors with different probability. The proposed model uses a clustering validity index not only to evaluate the performance of the algorithm, but also to find the optimal number of clusters and reduce outliers. Experiments on data from the Reuters-21578 collection show that the proposed model has better performance than that of LF algorithm and ART neural networks.

In this paper, we propose a novel active queue management (AQM) scheme based on the Random Early Detection (RED) of the loss ratio and the total sending rate control, called LRC-RED, to regulate the queue length with small variation and to achieve high utilization with small packet loss. This scheme measures the latest packet loss ratio, and uses it and the total sending rate as complements to queue length in order to dynamically adjust packet drop probability. Further, we also provide the design rules for this scheme based on the well-known TCP control model. On the basis of the design rules, we develop a simple, scalable and systematic rule for tuning the control parameters which can be adaptive to dynamic network conditions. Through ns 2 simulations, we show the faster response time and better robustness of the proposed LRC-RED as compared with the Loss Ratio based RED (LRED) [5] algorithm.

This paper presents a clustering ensemble using three colonies of ants, each colony having different ant speed model: constant, random, and randomly decreasing. The algorithm is a two-phase process. Initially clusterings are visually formed on the plane by ants walking, picking up or dropping down projected data objects with different probability, and then a hypergraph model is used to combine clusterings. Results on synthetic and real data sets are given to show that the number of clusters can be adaptively determined and clustering ensembles can improve the clustering performance.