The World Wide Web thrives on intelligent services that rely on accurate time series classification, which has recently witnessed significant progress driven by advances in deep learning. However, existing studies face challenges in domain incremental learning. In this paper, we propose a lightweight and robust dual-causal disentanglement framework (DualCD) to enhance the robustness of models under domain incremental scenarios, which can be seamlessly integrated into time series classification models. Specifically, DualCD first introduces a temporal feature disentanglement module to capture class-causal features and spurious features. The causal features can offer sufficient predictive power to support the classifier in domain incremental learning settings. To accurately capture these causal features, we further design a dual-causal intervention mechanism to eliminate the influence of both intra-class and inter-class confounding features. This mechanism constructs variant samples by combining the current class's causal features with intra-class spurious features and with causal features from other classes. The causal intervention loss encourages the model to accurately predict the labels of these variant samples based solely on the causal features. Extensive experiments on multiple datasets and models demonstrate that DualCD effectively improves performance in domain incremental scenarios. We summarize our rich experiments into a comprehensive benchmark to facilitate research in domain incremental time series classification.

Although Transformers excel in natural language processing, their extension to time series forecasting remains challenging due to insufficient consideration of the differences between textual and temporal modalities. In this paper, we develop a novel Transformer architecture designed for time series data, aiming to maximize its representational capacity. We identify two key but often overlooked characteristics of time series: (1) unidirectional influence from the past to the future, and (2) the phenomenon of decaying influence over time. These characteristics are introduced to enhance the attention mechanism of Transformers. We propose TimeFormer, whose core innovation is a self-attention mechanism with two modulation terms (MoSA), designed to capture these temporal priors of time series under the constraints of the Hawkes process and causal masking. Additionally, TimeFormer introduces a framework based on multi-scale and subsequence analysis to capture semantic dependencies at different temporal scales, enriching the temporal dependencies. Extensive experiments conducted on multiple real-world datasets show that TimeFormer significantly outperforms state-of-the-art methods, achieving up to a 7.45% reduction in MSE compared to the best baseline and setting new benchmarks on 94.04% of evaluation metrics. Moreover, we demonstrate that the MoSA mechanism can be broadly applied to enhance the performance of other Transformer-based models.

Currently, most spiking neural networks (SNNs) still mimic the chain-like hierarchical architecture in traditional artificial neural networks (ANNs). This method significantly differs from random connections between neurons found in biological brains, limiting the ability to model the evolving mechanisms of neural pathways in biological neural systems, particularly in terms of dynamic depth-scalability and adaptive path-plasticity. This paper develops a new modeling paradigm for SNNs with random graph architecture (RGA), termed Cognition-aware SNN (CogniSNN). Furthermore, we model the depth-scalability and path-plasticity in CogniSNN by introducing a modified spiking residual neural node (ResNode) to counteract network degradation in deeper graph pathways, as well as a critical path-based algorithm that enables CogniSNN to perform path reusability on new tasks leveraging the features of the data and the RGA learned in old tasks. Experiments show that the performance of CogniSNN with redesigned ResNode is comparable, even superior, to current state-of-the-art SNNs on neuromorphic datasets. The critical path-based approach effectively achieves path reuse capability while maintaining expected performance in learning new tasks that are similar to or distinct from the old ones. This study showcases the potential of RGA-based SNNs and paves a new path for modeling the fusion of computational neuroscience and deep intelligent agents. The code is available at github.com/Yongsheng124/CogniSNN.

Stock trend prediction involves forecasting the future price movements by analyzing historical data and various market indicators. With the advancement of machine learning, graph neural networks (GNNs) have been extensively employed in stock prediction due to their powerful capability to capture spatiotemporal dependencies of stocks. However, despite the efforts of various GNN stock predictors to enhance predictive performance, the improvements remain limited, as they focus solely on analyzing historical spatiotemporal dependencies, overlooking the correlation between historical and future patterns. In this study, we propose a novel distillation-based future-aware GNN framework (DishFT-GNN) for stock trend prediction. Specifically, DishFT-GNN trains a teacher model and a student model, iteratively. The teacher model learns to capture the correlation between distribution shifts of historical and future data, which is then utilized as intermediate supervision to guide the student model to learn future-aware spatiotemporal embeddings for accurate prediction. Through extensive experiments on two real-world datasets, we verify the state-of-the-art performance of DishFT-GNN.

The Spiking Neural Network (SNN) has drawn increasing attention for its energy-efficient, event-driven processing and biological plausibility. To train SNNs via backpropagation, surrogate gradients are used to approximate the non-differentiable spike function, but they only maintain nonzero derivatives within a narrow range of membrane potentials near the firing threshold—referred to as the surrogate gradient support width gamma. We identify a major challenge, termed the dilemma of gamma: a relatively large gamma leads to overactivation, characterized by excessive neuron firing, which in turn increases energy consumption, whereas a small gamma causes vanishing gradients and weakens temporal dependencies. To address this, we propose a temporal Inhibitory Leaky Integrate-and-Fire (ILIF) neuron model, inspired by biological inhibitory mechanisms. This model incorporates interconnected inhibitory units for membrane potential and current, effectively mitigating overactivation while preserving gradient propagation. Theoretical analysis demonstrates ILIF’s effectiveness in overcoming the gamma dilemma, and extensive experiments on multiple datasets show that ILIF improves energy efficiency by reducing firing rates, stabilizes training, and enhances accuracy. The code is available at github.com/kaisun1/ILIF.

Real-world time series typically exhibit complex temporal variations, making the time series classification task notably challenging. Recent advancements have demonstrated the potential of multi-scale analysis approaches, which provide an effective solution for capturing these complex temporal patterns. However, existing multi-scale analysis-based time series prediction methods fail to eliminate redundant scale-shared features across multi-scale time series, resulting in the model over- or under-focusing on scale-shared features. To address this issue, we propose a novel end-to-end Disentangled Multi-Scale framework for Time Series classification (DisMS-TS). The core idea of DisMS-TS is to eliminate redundant shared features in multi-scale time series, thereby improving prediction performance. Specifically, we propose a temporal disentanglement module to capture scale-shared and scale-specific temporal representations, respectively. Subsequently, to effectively learn both scale-shared and scale-specific temporal representations, we introduce two regularization terms that ensure the consistency of scale-shared representations and the disparity of scale-specific representations across all temporal scales. Extensive experiments conducted on multiple datasets validate the superiority of DisMS-TS over its competitive baselines, with the accuracy improvement up to 9.71%.

Diabetic retinopathy (DR) is a major cause of blindness, but current classification models suffer from low interpretability and difficulty in adjustment. To address these issues, a two-stage deep learning method for DR classification has been proposed, featuring lesion-sliced detection and DR classification stages. In the lesion-sliced detection stage, an improved neural process model extracts information from fundus images by fusing lesion details from various image locations, significantly enhancing accuracy. In the DR classification stage, an enhanced deep forest model was used to identify critical features influencing DR grades, boosting the credibility of the grading outcomes. Tests on the IDRiD and E-ophtha datasets demonstrated superior performance and generalisation ability of the lesion-sliced detection model compared to mainstream neural networks. Meanwhile, experiments on the Kaggle dataset confirmed that the deep forest-based DR classification model outperformed both traditional forest models and residual networks, marking its first application in DR classification. This approach achieves high accuracy and reliability, with improvements in both detection efficiency and generalisation.

This paper proposes a rumor control model based on community immunization. Based on the community division and the trust network inference algorithm, the model redefines the standard to measure the importance of nodes in the network. First, the model uses the Louvain clustering algorithm based on the Ochiai coefficient to discover the network community and then presents the trust network inference algorithm. By analyzing the key factors that affect trust transfer between nodes, the trust evaluation between unfamiliar nodes is inferred, and important nodes with a high degree of trust in the network community are calculated. Finally, combined with the characteristics of inner degree and outer degree centrality of nodes in the network community, five types of important nodes in the network are screened out. To avoid repeated selection of nodes, this paper identifies a group of key nodes in the network community for local immunization by means of deduplication and taking intersection, so as to realize effective control of rumors in the network.

Abstract The original online fountain codes discard a large number of symbols that do not meet the requirements at the decoder. To improve channel utilization, this article proposes a new online fountain code. In the completion phase, the proposed code improves the receiving rules of encoded symbols, that is, the encoded symbols discarded in the original online fountain codes are selectively cached. Moreover, an optimal degree selection strategy of encoded symbols is obtained in the proposed scheme. The valid degree range of the proposed strategy is also analyzed, leading to an upper bound of cached events which eventually limits the number of feedbacks. The theoretical analysis and simulation results reveal that the proposed scheme outperforms two state‐of‐the‐art online fountain codes in terms of overhead factors, number of feedback transmissions, and encoding/decoding efficiency.

Deep ensemble models have been demonstrated to show promising generalization capability. A deep ensemble model includes several deep neural networks as base-learners. Building a deep ensemble model is a challenging task, since maintaining the prediction performance of each base-learner and the diversity among base-learners at the same time is difficult. To address this problem, this paper proposes a two-stage optimization algorithm for deep ensemble model generation, called ELDE-TS. ELDE-TS aims to build a weighted voting-based deep ensemble model for classification tasks end-to-end. The ensemble model includes several convolutional neural network classifiers with different hyperparameters. Each classifier is assigned a weight. The first stage of ELDE-TS is a bi-objective algorithm that generates candidate classifiers for the ensemble model. It takes the validation accuracy and the diversity among classifiers as the optimization objectives. A novel objective function is proposed for the first stage to describe the diversity among the classifiers. The second stage is a single-objective algorithm, which selects representative classifiers for the ensemble model and calculates a weight for each classifier. A tree-based non-repetitive evaluation mechanism is embedded in the second stage to accelerate the search process. The experimental results show that the ensemble model generated by ELDE-TS has competitive performance over the state-of-the-art ensemble models and hand-designed deep models on the Fashion-MNIST, CIFAR-10, and CIFAR-100 datasets. Furthermore, further analysis demonstrates that the proposed ensemble selection method and the non-repetitive evaluation mechanism positively contribute to improving the performance of the ensemble model.

In this article, we present a coding method called expanding-window zigzag decodable fountain code with unequal error protection property (EWF-ZD UEP code) to achieve scalable multimedia transmission. The key idea of the EWF-ZD UEP code is to utilize bit-shift operation and expanding-window strategy to improve the decoding performance of the high-priority data without performance deterioration of the low-priority data. To provide more protection for the high-priority data, we precode the different importance level using LDPC codes of varying code rates. The generalized variable nodes of different importance levels are further grouped into several windows. Each window is associated with a selection probability and a bit-shift distribution. The combination of bit-shift and symbol exclusive-or operations is used to generate an encoded symbol. Theoretical and simulation results on input symbols of two importance levels reveal that the proposed EWF-ZD UEP code exhibits UEP property. With a small bit shift, the decoding delay for recovering high-priority input symbols is decreased without degrading the decoding performance of the low-priority input symbols. Moreover, according to the simulation results on scalable video coding, our scheme provides better basic video quality at a lower proportion of received symbols compared to three state-of-art UEP fountain codes.

The research on detecting violent behavior in videos has made good progress, which provides good support for monitoring abnormal videos spread in the network, so as to achieve the effect of purifying the network space environment. A large number of current violence detection models have achieved good performance in experimental environments, but their generalization ability is insufficient. Violent behavior often occurs in a variety of scenarios, automatic detection of violent behavior requires a model with strong generalization. In this paper, a crowd violence behavior detection model with good generalization ability based on human contour and dynamic characteristics was designed. The model generalization ability is improved by focusing on the human features in the video and using the human dynamic features obtained from adjacent frames. In our model, a 3D-CNN framework was used to extract spatial features of the input feature map, and LSTM was used to fuse the temporal feature, we call this model HD-Net. Through multiple contrast experiments, the generalization ability of HD-Net is tested on three datasets: RLVS, Hockey and violent flow. Comparing with other classical violence detection models, the good generalization ability of the model is verified.

In recent multi-speaker speech separation researches, the overall deep-learning-based architecture consists of three parts: encoder, separator, and decoder. But improvement strategies generally only focus on the separator in the middle, regardless of its input. The most common encoder structure at present is a single 1D convolution layer followed by a nonlinear activation function, ReLU. In this paper, we firstly propose a new encoder named Attention DE, trying to improve the input effectiveness of the separator. The new encoder adds extra 1D convolutional layers and the multi-head attention mechanism to enhance the feature aggregation ability of input speech. Secondly, instead of RNNs, our separator uses SepFormer Blocks to improve the training efficiency and learn the speech sequence patterns better. Experiments show that the Attention DE is generally applicable to improve the performance of the single-channel speech separation model based on the time domain. The method of Attention DE fusion SepFormer blocks achieves an advanced SI-SNRi of 20.3dB on WSJ0-2MIX. Code is publicly available at https://github.com/TAN-OpenLab/AttentionDE.

Abstract By combining bit‐shift and exclusive‐or operations, a weighted zigzag decodable fountain code is proposed to achieve an unequal error protection property. In the proposed scheme, the input symbols of different importance levels are first pre‐coded into variable nodes using low‐density parity‐check codes. Then, bit‐shift operations prior to exclusive‐or are performed on the non‐uniformly selected variable nodes to generate encoded symbols. An analysis of the erasure probabilities based on the and‐or tree is further introduced. Simulation results show that by appropriately choosing the maximum bit‐shift amount, the proposed weighted zigzag decodable fountain codes can successfully recover the more important input symbols prior to the less important ones.

The object detection task is to locate and classify objects in an image. The current state-of-the-art high-accuracy object detection algorithms rely on complex networks and high computational cost. These algorithms have high requirements on the memory resource and computing capability of the deployed device, and are difficult to apply to mobile and embedded devices. Through the depthwise separable convolution and multiple efficient network structures, this paper designs a lightweight backbone network and two different multiscale feature fusion structures, and proposes a lightweight one-stage object detection algorithm—MiniYOLO. With the model size of only 4.2 MB, MiniYOLO still maintains a high detection accuracy, realizing the trade-off between the model size and detection accuracy. Experimental results on MS COCO 2017 data set show that compared to the state-of-the-art PP-YOLO-tiny, MiniYOLO achieves higher mAP with the same model size. Compared with other lightweight object detection algorithms, MiniYOLO has certain advantages in detection accuracy or model size. The code associated with this paper can be downloaded from https://github.com/CaedmonLY/MiniYOLO/.

With the rapid increase in the use of mobile devices in people’s daily lives, mobile data traffic is exploding in recent years. In the edge computing environment where edge servers are deployed in close proximity to mobile users, caching popular data on edge servers can ensure mobile users’ low-latency access to those data and reduce the data traffic between mobile users and the centralized cloud. Existing studies consider the data caching problem with a focus on the reduction of network delay and the improvement of mobile devices’ energy efficiency. In this article, we tackle this data caching problem in the edge computing environment from a service provider’s perspective with the aim to maximize its data caching revenue. This problem is challenging because there is a trade-off between the benefit produced and the cost incurred by caching data on edge servers. In the meantime, the constraint for data access latency must also be fulfilled. In this article, we formulate the data caching problem in the edge computing environment as an integer programming (IP) problem and prove its NP-completeness. To solve this problem effectively and efficiently in large-scale scenarios, we propose an approximation approach to find near-optimal solutions. Extensive experiments are conducted on a widely-used real-world dataset to evaluate our approaches.

Next Point-of-Interest (POI) recommendation plays an important role in location-based services. The state-of-the-art methods utilize recurrent neural networks (RNNs) to model users' check-in sequences and have shown promising results. However, they tend to recommend POIs similar to those that the user has often visited. As a result, users become bored with obvious recommendations. To address this issue, we propose Serendipity-oriented Next POI Recommendation model (SNPR), a supervised multi-task learning problem, with objective to recommend unexpected and relevant POIs only. To this end, we define the quantitativeserendipity as a trade-off ofrelevance andunexpectedness in the context of next POI recommendation, and design a dedicated neural network with Transformer to capture complex interdependencies between POIs in user's check-in sequence. Extensive experimental results show that our model can improverelevance significantly while theunexpectedness outperforms the state-of-the-art serendipity-oriented recommendation methods.

Mobile data traffic is exploding in recent years with the exponential growth of mobile users. In the edge computing environment where edge servers are deployed around mobile users, caching data on edge servers can ensure mobile users' fast access to those data and reduce the data traffic between mobile users and the centralized cloud. Existing studies consider the data cache and replacement problem with the consideration of the reduction of network delay and the improvement of mobile devices' energy efficiency. In this paper, we attack proactive data caching and replacement problem in the edge computing environment from the service providers' perspective, who would like to maximize their venues of caching their data. This problem is complicated because data caching produces benefits at a cost and there usually is a trade-off in-between. In this paper, we formulate the data caching and replacement problem as an integer programming problem, and maximizes the revenue of the service provider while satisfying a constraint for data access latency. We also propose an online algorithm to solve problems in large-scale scenarios. Extensive experiments are conducted on a real-world dataset that contains the locations of edge serPvers and mobile users.

This paper analyzes the limitation of baseline estimation by defining four kinds of rating personalization corresponding to four kinds of users' rating criterions, including Normal, Strict, Lenient, and Middle. We find a standard deviation proportion pattern from ratings' normal distribution to enhance the handling capability of users' personalized rating behavior, and propose a novel baseline estimation model based on Standard Deviation Proportion, named SDP model, to improve the accuracy of existing recommendation algorithms which used traditional baseline estimation. We also propose two application instances of SDP, including SDPSVD++ and SDPTrustSVD, to show how to apply the proposed SDP. Experiments show that the SDP can not only improve the baseline estimation performance, but also can effectively improve predictive accuracies of existing recommendation algorithms.

With the rapid increase in the use of mobile devices in people's daily lives, mobile data traffic is exploding in recent years. In the edge computing environment where edge servers are deployed around mobile users, caching popular data on edge servers can ensure mobile users' fast access to those data and reduce the data traffic between mobile users and the centralized cloud. Existing studies consider the data cache problem with a focus on the reduction of network delay and the improvement of mobile devices' energy efficiency. In this paper, we attack the data caching problem in the edge computing environment from the service providers' perspective, who would like to maximize their venues of caching their data. This problem is complicated because data caching produces benefits at a cost and there usually is a trade-off in-between. In this paper, we formulate the data caching problem as an integer programming problem, and maximizes the revenue of the service provider while satisfying a constraint for data access latency. Extensive experiments are conducted on a real-world dataset that contains the locations of edge servers and mobile users, and the results reveal that our approach significantly outperform the baseline approaches.

User association has emerged as a distributed resource allocation problem in the heterogeneous networks (HetNets). Although an approximate solution is obtainable using the approaches like combinatorial optimization and game theory-based schemes, these techniques can be easily trapped in local optima. Furthermore, the lack of exploring the relation between the quality of the solution and the parameters in the HetNet [e.g., the number of users and base stations (BSs)], at what levels, impairs the practicability of deploying these approaches in a real world environment. To address these issues, this paper investigates how to model the problem as a distributed constraint optimization problem (DCOP) from the point of the view of the multiagent system. More specifically, we develop two models named each connection as variable (ECAV) and each BS and user as variable (EBUAV). Hereinafter, we propose a DCOP solver which not only sets up the model in a distributed way but also enables us to efficiently obtain the solution by means of a complete DCOP algorithm based on distributed message-passing. Naturally, both theoretical analysis and simulation show that different qualitative solutions can be obtained in terms of an introduced parameter which has a close relation with the parameters in the HetNet. It is also apparent that there is 6% improvement on the throughput by the DCOP solver comparing with other counterparts when . Particularly, it demonstrates up to 18% increase in the ability to make BSs service more users when the number of users is above 200 while the available resource blocks (RBs) are limited. In addition, it appears that the distribution of RBs allocated to users by BSs is better with the variation of the volume of RBs at the macro BS.

Exploratory search is an increasingly important activity for Web searchers. However, the current search system can not provide sufficient support for exploratory search. Therefore, we made in-depth analysis for exploratory search processes, and found that there are a lot of search goal shift phenomena in exploratory search. Based on this fact, we have designed a new query recommendation method to support exploratory search. Firstly, according to the behavioral characteristics of searchers in the search goal shift processes, all the queries submitted in the search goal shift processes are extracted from search engine logs using machine learning. And then, we have used the queries to build a search goal shift graph; finally, the random walk algorithm is used to obtain the query recommendations in the search goal shift graph. In addition, we demonstrated the effectiveness of the method for exploratory search by comparing experiments with the other methods.

Because of load fluctuating, the performance of service-based system(SBS) in the cloud environment may deviate from service level agreement(SLA). In the cloud environment, it is important to dynamically allocate resource for SBS according to the predicted system load, so as to satisfy global SLA constraint and minimize resource cost. By the analysis of complex business logic in SBS and the feature of dynamic resource allocation problem, this paper models the dynamic resource allocation problem as composite optimization problem and proposes the cost optimization oriented dynamic resource allocation model. Then this paper applies genetic algorithm to solve the dynamic resource allocation model so as to improve the resolving efficiency. Finally, the approach proposed in this paper is evaluated and compared with some related algorithms. It reveals very encouraging results in terms of the quality of resource allocation.

Cloud applications usually face challenges from the dynamic changing environment, growing number of users and large amount of concurrency accesses etc. A self-management based on resource adjustment is emerging to deal with these problems. To achieve self-management, it is the key problem to make resource adjustment decisions adaptively. There are two types of decision making in self-management: static and dynamic. Static method is not suitable for cloud environments. And the existing dynamic methods (i.e. intelligence optimization algorithm-based method and off-line model-based method) are often inefficient or not adaptive to the variation of environment. In this paper, we propose a reinforcement learning-based approach to dynamic decision making in resource adjustment-based self-management. This approach enables a cloud application to guarantee its performance by learning the results of its behavior and by dynamically changing its plans based on the learning in the presence of environmental changes. The process of our decision making approach for the self-managed cloud applications is also presented in this paper. Experimental results using a prototype framework in the context of a SBS application demonstrate the effectiveness of this approach.

Community discovery is a popular way to solve the personal service recommendation problem and has recently attracted more and more attentions of the researchers. The communities are often practically overlapping with each other, thus more and more research focus on the problem of overlapping communities detection. A common drawback of the existing algorithms to this problem is the low efficiency when dealing the large scale network. In this paper, we propose a graph compression based overlapping communities discovery algorithm, which greatly enhances the power of handling large networks even using a single computer. First, a graph compression based social network model, namely agglomerative graph, is introduced, which is a lossless compression to the original network. Then, inspired by the idea of iteration based on the selected seeds, the algorithm expands the selected seeds to the communities by optimizing the proposed community fitness function iteratively. Finally, it merges the communities of high similarity with each other to get the final results. Since the network is lossless compressed, and massive redundant computations are avoided, the results can be exactly obtained in an efficient and effective way. The experiments based on both real and synthetic datasets demonstrate efficiency and effectiveness of the proposal method in detecting overlapping communities over large scale networks.

In order to manage the resources in cloud efficiently, ensure the performance of cloud services and reduce the power consumption, it is critical to predict the workload of virtual machines (VM) accurately. In this paper, a new approach for VM workload prediction based on deep learning was proposed. A deep learning prediction model was designed with a deep belief network (DBN) composed of multiple-layered restricted Boltzmann machines (RBMs) and a regression layer. The DBN is used to extract the high level features from all VMs workload data and the regression layer is used to predict the workload of the VMs in the future. With little prior knowledge, DBN could learn the features efficiently for the VM workload prediction in an unsupervised fashion. Experimental results show that the proposed approach improves the workload prediction performance compared with other widely used workload prediction approaches.

Multiobjective density driven evolutionary algorithm (MODdEA) has been quite successful in solving multiobjective optimization problems (MOPs). To further improve its performance and address its deficiencies, this paper proposes a hybrid evolutionary algorithm based on dimensional diversity (DD) and firework explosion (FE). DD is defined to reflect the diversity degree of population dimension. Based on DD, a selection scheme is designed to balance diversity and convergence. A hybrid variation based on FE and genetic operator is designed to facilitate diversity of population. The proposed algorithm is tested on 14 tests problems with diverse characteristics and compared with three state-of-the-art designs. Experimental results show that the proposed design is better or at par with the chosen state-of-the-art algorithms for multiobjective optimization.

In cloud computing environments, each service-oriented application is often instantiated with multiple workflow instances, and each of them provides a specific QoS level for a particular user category. In recent researches, most of works deploy service instances for each workflow independently, and the sharing of service instance is not considered across compositions related with different SLAs. This may cause several high-performance service instances are exclusively accessed by specific workflow instances, which can incur the following two issues: First, the remaining service instances cannot satisfy SLA for other users when high-performance ones are monopolized by some requests. Second, the utilization ratio of high-performance services will be decreased. To address these problems, a service composition model supporting the instances sharing in multiple SLA environments is provided in this paper. Since the QoS-aware service composition problem is known as NP-hard, which needs a significant amount of computation time to discover optimal solutions, a solving method based on multi-objective genetic algorithm, called MSCS, is proposed to solve it heuristically. The effectiveness of this approach is demonstrated via experiments.

Reselection of composition service is one of the core research issues in the service computing field. Most of the existing researches for this problem are based on the assumption that the tasks involved are independent. However, in practical scenar-ios, the QoS of some candidate services have correlations with other services, which makes the corresponding tasks be correlated with each other. This leads the QoS used to determine the binding relationship between tasks and concrete services to be inaccurate, so the reselected composite service is not the optimal one in the real executing environment for these existing reselection methods. To address this problem, this paper considers task correlations for runtime rebinding. Firstly, the QoS dependencies among services are extracted from the log repository through the APRIORI data mining method. Then, the acquired QoS dependencies are mapped to the tasks correlations by the defined mapping rules. Finally, the reselection process is implemented by making the tasks which have related relationships as a task unit, and the related services of each task unit as its candidate service set. The effectiveness of this approach, in terms of time and quality, is demonstrated via experiments.

This paper proposes a method for predicting the performance interference of applications in the virtualized environment. In this method, we firstly analyze the relationship between the performance interference degree and the system-level workloads, and based on this we propose a linear regression algorithm to model relationship between the performance interference degree and the system-level workloads by using the historical data about performance interference degree as the training data set. For the applications without historical data about performance interference degree, we develop a method for predicting the performance interference by clustering the available models of performance interference and matchmaking between the workload pattern of the application and the workload patterns of the available models to generate the performance interference model for the application whose performance interference will to be predicted. By use of the available model, the performance interference of the application can be predicted without historical data about the performance interference among the applications co-located on the same physical host. The experiments show the effectiveness of the proposed measurement and prediction methods of the performance interference among the virtual machines.

SUMMARY Composite service selection is one of the core research issues in Web service composition. Because of the complex service correlation context, candidate services may perform differently when being used with other services. Presently, most service selection approaches ignore this issue, which makes the selected composite services less efficient than expected. To solve this problem, a service correlation context‐aware composite service selection approach is proposed on the basis of the concept of single‐entry single‐exit (SESE) region. The general process of our approach is as follows: (1) mining the SESE patterns that are frequently used together in the set of efficiently executed instances of a composite service; (2) dividing the process model of the composite service into SESE regions and generating the candidate SESE pattern set of each region, using the discovered SESE pattern set; and (3) optimizing composite service selection globally on the basis of QoS using divided regions as selection units and their candidate pattern sets as candidate service sets. Because SESE patterns are testified by large amount of efficiently executed instances, they have higher quality than the results of independent selection of services in an SESE region. Experimental results demonstrated that our approach can improve the quality of selected composite services effectively in the correlation context. Concurrency and Computation: Practice and Experience, 2012.© 2013 Wiley Periodicals, Inc.

It is important that during the execution of a business process built from composable Web services from multiple domains, the component service be able to verify the identity of the user to check it has the required permissions for accessing the services, while at the same time identity attributes need to be protected properly as they can be target of attacks. In such context, we propose a privacy-preserved multi-domain identity attributes verification model BPVrfy. It extends federate identity management with support for multiple identity verification policies and privacy enhancement. Identity attributes verification process is partitioned into three sub-procedures consisting of attribute provision, federation enrollment and attributes transfer, and then a series of protocols based on cryptographic schemes is proposed respectively. BPVrfy adopts Perdersen Commitment, Zero-Knowledge Proof of Knowledge, BGLS Aggregate Signature and Certificate-Based Signature (CBS) cryptographic schemes together to give a privacy-preserved federate identity attributes verification solution for multi-domain Web services-based business processes.

Social Tagging is a free but also uncontrolled way to index and organize Web 2.0 resources. Many works have been proposed to leverage such tagging information. However, although previous studies have shown that users could reach consensus on which tags should be attached to a resource, the study about the consensus showing how to use a tag is still lack. This paper proposes a text chance discovery and subjective Bayes based approach to model and detect consensus of tags. In the proposed approach, tag consensus is modeled using characteristics of resources annotated by the tag. Experiment results show that the proposed method could more properly capture to what extent the users have reached consensus about the tag in advance of usage frequency.

An aggregated privacy-preserving identity verification scheme is proposed for composite Web services. It aggregates multiple component providers' interactions of identity verification to a single one involving the user. Besides, it protects users from privacy disclosure through the adoption of zero-knowledge of proof of knowledge. This approach can dramatically reduce the computation time, independently on the number of identity attributes and component providers.

Service-based software system (SBS) is a software system based on service-oriented architecture (SOA). Although often treated as a composite service, an SBS is proposed from a more practical point of view based on restricted service provisions. In the highly competitive market, just meeting such requirements seems not enough to get more customers for service providers, and they usually provide additional preferential policies, such as a special order "buy-two-get-one-free". However, most of current adaptation approaches focus on single transaction, which makes it hard to take full advantage of such preferential policies in reselecting substitutable services. In this paper, we try to make the adaptation decision and reselect services from a broader view, i.e. expand the computation domain from single transaction to the whole lifecycle of an SBS by considering all of the past, current and predicable future executions. We call it "long-term benefit" to distinguish benefit in current approaches and propose a long-term benefit driven adaptation approach in this paper. In our approach, services that would bring the max expected long-term benefit would be selected and substituted into current instance in once adaptation. As the long-term benefit is accumulated in several executions, i.e. it depends on a decision sequence, we model the decision making problem as a sequential decision problem, and describe a realization based on partially observable Markov decision process (POMDP) for maximizing the real income in providing an SBS as an example.

This paper presents a composite service execution engine, which can support human tasks and improve their execution by an approach of human task scheduling. In the approach, the performance evaluation model is proposed, which can reflect the performance of the human service resources objectively and comprehensively. Based on this model, the initial scheduling as well as re-scheduling methods for solving the problem is proposed to find the human service resource with better performance.

Software as a service (SaaS) is an emerging software framework in which business data and logic typically integrate with other applications. It requires a unified subscriber to describe SaaS to make for easy integration, however, SaaS provides services to different tenants by running only one instance. In order to satisfy personalized needs from different tenants, the business logic becomes correspondingly complex. As this logic is cumbersome to reveal to every individual tenant, we propose the use of Web Services Conversation Language (WSCL) to express the views of tenant and provider separately. To overcome deficiencies in WCSL for expressing heterogeneous data, process rules, and business rules, we extend the syntax of WSCL. We also put forward a new modeling method for constructing SaaS Service, describing the modeling process and the algorithm for obtaining the tenant model from the business model. In conclusion, we describe the modeling tools and validation methods.

With the increasing numbers of Web services and service users on World Wide Web, predicting QoS(Quality of Service) for users will greatly aid service selection and discovery. Due to the different backgrounds and experiences of users, they have different QoS experiences when interacting with the same service. Even two users who have similar experiences on some services can have diverging views when considering other services. This paper proposes an approach to predict QoS. It is based on not only other users' QoS experiences, but also the environment factor and user input factor. First bring forwards usage information feature model and calculate the similarity of two users based on the feature model. Then consider not only the historic information, but also environment and users' inputs, such as bandwidth and data size. Before calculating the user similarity, select a set of Web services that have the highest degree of similarity with the target service, not all of the services. The missing value can be calculated through the data of similar services. The results of the experiment prove that our approach is feasible and effective.

The development of Service-Oriented Systems has gained a considerable momentum as a means for building distributed applications and business processes. It emphasizes the loosely coupled construction of services from independent providers over the network. As a consequence, the dependability of such systems strongly depends on their ability to self-adapt to changes in its execution environment, such as unreachable component services, or changed delivered QoS. In this paper, we propose a two-stage approach to realize a self-adaptive SOA system, aimed at the fulfillment of dependability requirements. Specifically, we divide the adaptation process into two stages, proactive adaptation and reactive adaptation, to implement self-protecting and self-healing respectively, and provide a methodology driving the system adaptation. To bring this approach to fruition, a prototype system A-ServiceMix is developed by extending Apache ServiceMix.

With the increasing numbers of Web services and service users on World Wide Web, predicting QoS (Quality of Service) for users will greatly aid service selection and discovery. Due to the different backgrounds and experiences of users, they have different QoS experiences when interacting with the same service. Even two users who have similar experiences on some services can have diverging views when considering services. This paper proposes an approach to predict QoS based on other users' QoS experiences. This method employs similarity mining and prediction from users' experience by firstly selecting a set of web services that have the highest degree of similarity with the target service by comparing the target service with the others services used by target user. Secondly, the missing value can be calculated through the data of similar services. On the basis of that, we calculate the user similarity and predict QoS data for target user. Experimental results show that it can improve the prediction accuracy of QoS for Web service by using this method.

Composite Web services are often long-running, loosely coupled and cross-organizational applications. They always run in a highly dynamic environment. For the applications and environment, advanced transaction support is required to ensure the quality of reliable execution. Towards composite service adaptive mechanism unavailable for lacking transaction support, this paper proposes a self-healing model for Web service reliable execution, which is an integration of flexible compensation service in selection and reselecting in execution. In order to make the composite service healing itself as quickly as possible and minimize the number of reselections, away of mining cascading scope of replacement in advance by considering full multi-relation among transaction Web services is proposed in this paper. Further more, a new comprehensive, objective QoS-driven service replacement model with compensation support is presented, and the self-healing algorithm is proposed. Experiments show that the model guarantees business process reliability.

Community structure has been recognized as an important statistical feature of network systems over the past decade. The web service in SOA system naturally forms into some service community during execution process, within which the links between nodes are very dense, but between which they are quite sparse. These service communities were generated by repeatedly interaction between composite services which accomplish the same task. Mining and analysis web service community will help design SOA system and predict service behavior. This article addresses the problem of how to discovering and quantifying web services community formed by closely interactive web services and gives the composite web service discovery technique. We consider the case where the details usage record is logging by execution engine. We proposed a novel approach which construct web service interactive network (WSIN) from usage log and get community structure by spectrum clustering. Generally, the web services belong to same cluster have strong relative to same task object and we call it web service community. The approach has been implemented in an experience system for web services dynamic composition and discovery, and the experimental results demonstrated the efficiency and effectiveness of the proposed algorithm.

To objectively assess quality of web services, we propose a six-dimensional QoWS model which includes expected QoWS, agreed QoWS, delivered QoWS, perceived QoWS, transmitted QoWS, and statistic QoWS. Then a trusted QoWS monitoring model is presented. It adopts Simple Network Management Protocol (SNMP) to respectively capture delivered QoWS, perceived QoWS, and transmitted QoWS. A new style assessment method is proposed to have two capabilities, one is assessing the given service deliver from the view of delivered QoWS and perceived QoWS, the other is assessing the given service over a period of time from the view of reputation and statistic performance experienced by consumers.

We propose a six dimensional QoWS model including expected QoWS, agreed QoWS, delivered QoWS, perceived QoWS, transmitted QoWS, and statistic QoWS to assess quality of Web services comprehensively and objectively. Meanwhile, the proposed assessment mechanism evaluates Web services from the view of compliance, end-to-end performance, and long-term performance.

With the rapid development of Web services technologies, discovering Web services is becoming the most urgent problem to be resolved. The existing Web service discovery methods are not mature, and cannot cope with the requests from different fields very well. In this paper we suggest an effective and feasible approach of Web service discovery based on functional semantics. We define Web services functional semantic description that provides a unified manner to semantically describe the function of Web service for service providers and customers. In order to avoid semantic heterogeneity, we build domain-oriented functional ontology and propose semantic annotation mechanism. Then we describe the matching algorithm. Finally we evaluate the performance of our algorithm by an experimental setup. The results of the experiment prove that our approach is feasible and effective

Nowadays, Web services are usually aggregated into a composite one to satisfy customer’s more and more complex requirements. Generally, there may be several different candidate services to carry out one task in a composite service, so a choice needs to be made to help users select the most suitable one. Based on the quality of services, this paper generates a Weighted Multistage Graph for composite service, and transforms the problem of service selection into the one of how to get a longest path. Considering the problem of Interface Matching, this paper presents a 3-layer Web service organization model (WS3LM), which can help get an executable composite service. This paper describes and compares two types of selection approaches: one type of local optimal selection and the other type of global optimal selection using Exhaustive Search Algorithm, Dynamic Programming.

Task scheduling is one of the core steps to effectively exploit the capabilities of resources in the grid. The task scheduling problem is an NP-complete problem. This paper studied on the task scheduling problem in grid environment and proposed a task scheduling mechanism, which expressed each possible task scheduling scheme as a task-resource assignment graph (T-RAG) and thus mapped the task scheduling problem into a graph optimal selection problem. Moreover, in order to find the optimal solution quickly and accurately, a task scheduling algorithm based on particle swarm optimization (PSO) was proposed. This algorithm regards the longest path of the task-resource assignment graph as fitness value and encodes every task-resource assignment as a particle. Finally, the experimentation shows that the approach proposed in this paper is effective to solve task scheduling problem

Traditional Chinese medicine is special for Western people. Its diagnosis and treatment depend on syndrome. Syndrome is composed of some symptoms, and each symptom demonstrates different values in different syndrome. In this paper, we first describe approach of syndrome and symptom in TCM. Then, a hierarch model of syndrome differentiation in traditional Chinese medicine is proposed. According to the model, data mining model is designed to complete it. Given special data mining schema and character of high dimensional data sets, we introduce hypergraph in cluster and attributes combination in association procedure. Finally, the result of model in syndrome differentiation of traditional Chinese medicine is given

How to classify automatically Web information that grows explosive is becoming an imminent problem needed to be resolved. Based on site structure, we propose, in this paper, a new mechanism of automatic classification of Web information, which downloads Web pages within a Web site, records the hyperlinks among Web pages, catches the site structure, extracts the classifying system of the site itself, and then links categorizing information with the correspondent position in the site structure. Therefore automatic classification of Web information can be realized through matching the positions of categorizing information with the positions of Web pages. Experiments show that such classification based on site structure works more accurately and efficiently.

In order to realize a high-quality and good-performance service composition, based on current approach, we propose a new QoS-driven dynamic selection of composite Web services, which takes account of both the QoS properties and interface parameters matching degree. When doing the selection, we aware that the task is more or less a multistage decision-making process. Motivated by neural networks' high parallel performance and genetic algorithm's powerful computation ability, a genetic algorithm optimized neural network algorithm is proposed in this paper for such task. In order to make this algorithm more adaptable for multistage decision-making problem, we propose a new structured neural network to express the composed service instead of using the traditional neural networks, which minimizes the neurons involved and shows high performance than the earlier ones. Finally, through experimentation one can find that method proposed in this paper is more practical and effective than others

This paper first presents a 3-layer organization model and an evaluation model for services composition. Then it presents an approach for selecting global optimal execution plan of Web services composition, which is based on weighted multistage graph and fully considering interface-matching between Web services. Based on this approach, we can select the optimal execution plan dynamically by Dynamic Programming, Integer Programming, Genetic Algorithm or Immune Algorithm, which can solve the problem efficiently and make the selection more correct.

For the widely use of multistage decision-making problem in our normal life such as in the new research area of dynamic selection of composite web services, this paper exerts all its effort on proposing a new approach to solve such problem. Motivated by neural networks’ high parallel performance and Genetic Algorithm’s powerful computation, a novel Genetic Algorithm optimized neural network is proposed in this paper for this task. In order to make this algorithm more adaptable for multistage decision-making problem, a new neural network structure for implementing the algorithm is proposed which is a modification to the one used by Thomopoulos or Rauch and Winarske.

The paper presents a three level schema integration architecture which consists of local schemas, mapped schemas, and a global schema for global multidatabase systems. Schema mapping rules, merging and restructuring rules are also presented for mapping local schemas into mapped schemas and for merging and restructuring the mapped schemas to get a final global schema.