The growing popularity of blockchain technology has underscored the need for robust network security. However, public blockchain networks remain vulnerable to attacks in which adversaries exploit numerous nonfunctional peer connections to disrupt block propagation across the entire network. In this article, we propose a practical nontargeted delay attack method and validate its feasibility, scalability, and significant impacts on blockchain networks of varying sizes, including EthereumPoW (ETHW) and premerge Ethereum Mainnet. In the ETHW network with 95 nodes, our adversarial peers introduce delays ranging from 0.33 to 2.8 s for half the nodes, with nearly one-third experiencing delays exceeding 5.9 s, derived from the 90th percentile of delay times. When in the premerge Ethereum network with 5739 nodes, over 80% of peers experience prolonged block propagation, resulting in a 77% increase in delay time, underlining the attacks' scalability and efficacy in large-scale environments. We also optimize the Ethereum client Geth by relaxing certain connection restriction, significantly reducing attack costs. Delving deeper, we analyze the implications of delay attacks on proof-of-work (PoW) and proof-of-stake (PoS) consensus mechanisms, illustrating how attackers can gain extra revenues through such attacks. Specifically, we propose a novel combined strategy to facilitate reorganization attacks under PoS. These findings highlight the urgent need to strengthen network-layer defenses and reinforce peer-to-peer (P2P) network protocol security against real-world delay exploits.

The development of mobile web services has brought significant attention to spatial crowdsourcing. The uneven distribution of tasks and workers has led to recent research on Cross-Platform Spatial Crowdsourcing (CPSC), aiming for a multi-win situation for platforms, workers, and task requesters. Previous studies on CPSC problems focused on task assignment and worker selection performance, overlooking the importance of privacy preservation. This article addresses the existing challenges of privacy preservation and service quality by formulating a Privacy-Preserving Cross-Platform Spatial Crowdsourcing (PP-CPSC) problem and proves it to be NP-hard. We propose an Evolutionary Differential Privacy (Evo-DP) approach to optimize PP-CPSC. Evo-DP’s evolutionary framework enables efficient and flexible optimization of privacy budget allocation. Within Evo-DP, each solution to the privacy budget allocation is represented as an individual in the population. To approximate the optimal solution, three evolutionary operations—mutation, crossover, and scaling—are employed for population updates, along with a selection process. A hybrid population model is introduced to balance exploration and exploitation abilities. Experimental results demonstrate Evo-DP’s superiority over previous strategies in terms of solution quality, convergence speed, and scalability.

Single-cell RNA-seq data has become a critical source in revealing cellular activities. However, the developing probing techniques and the fatal damages to the detected cells incur various kinds of noise, e.g. the batch effect and the absence of cellular correspondence between experimental groups. Therefore, many single-cell tasks are better modeled as generative rather than discriminative tasks, since, instead of the exact cell-wise ground truth, only the distribution of cellular profiles under a certain condition is measurable. Considering the highly nonlinear and complex associations between gene expressions, we developed scVDM, a latent diffusion model integrated with a transformer-based conditional denoiser to learn three different generative tasks in single-cell data, including conditional data generation, batch effect correction and drug perturbation prediction. The high dimensional transcriptomic data are firstly projected to the latent space through a conditional VAE and then the complicated relationships between latent dimensions are deeply exploited through self-attentions to generate realistic diffusion noise. Based on the evaluation of five real-world datasets, our method demonstrates outstanding performance through comprehensive experimental results in all generative tasks.

Multimodal recommendation provides richer and more accurate personalized recommendations by jointly modeling user’s historical behaviors and different modality of items, such as text, image, audio, and video in online platforms. Most existing work of multimodal recommendation focuses on leveraging modal features and modal correlation graph structures to learn user preferences. Due to insufficient exploration of user collaborative preferences and the noise during high-order multimodal data connections, valuable information may be lost, leading to deviations in understanding user preferences. Therefore, an I ndependent T opological Preference-Aware and Co operative H ypergraph D iffusion-based M ultimodal Rec ommender Model (ITCoHD-MRec) is necessary for online platforms. This article aims to develop an ITCoHD-MRec that incorporates topological perception as well as generative diffusion models in multimodal hypergraph recommendation to make the model more adaptive and robust in complex environments. Firstly, leveraging a Graph Convolutional Network (GCN), the model independently captures user preference representations for both collaborative relevance and modal relevance from the user-item interaction graph, which contains ID embeddings and modal features. This enables the extraction of deeper associations between users and items. Secondly, leveraging topological pruning techniques, the model learns differentiated features in different modal blocks to prevent node representations from becoming homogenized. This helps further identify user preferred connectivity patterns and removes redundant noisy connections. Finally, by employing the diffusion model, information regarding the higher-order interaction patterns between attributes and items within the hypergraph structure is propagated. This effectively captures the potential global dependencies between attributes and items, thereby providing deeper associations enriched with more substantial semantic information for subsequent recommendation tasks. The model autonomously learns different features and higher-order connectivity of nodes, which enables the model to obtain a wider and more accurate perception of user preferences in complex interaction environments. Experimental comparisons with 15 models on four real datasets—Baby, Sports, Clothing, and Electronics show that the model improves the recall by 0.85%–3.57% and the normalized discounted cumulative gain by 2.31%–3.43%, which validates the effectiveness of ITCoHD-MRec.

Studying the outcomes of genetic perturbation based on single-cell RNA-seq data is crucial for understanding genetic regulation of cells. However, the high cost of cellular experiments and single-cell sequencing restrict us from measuring the full combination space of genetic perturbations and cell types. Consequently, a bunch of computational models have been proposed to predict unseen combinations based on existing data. Among them, generative models, e.g. variational autoencoder and diffusion models, have the superiority in capturing the perturbed data distribution, but lack a biologically understandable foundation for generalization. On the other side of the spectrum, Gene Regulation Networks or gene pathway knowledge have been exploited for more reasonable generalization enhancement. Unfortunately, they do not reach a balanced processing of the two data modalities, leading to a degraded fitting ability. Hence, we propose a dual-stream architecture. Before the information from two modalities are merged, the sequencing data are learned with a generative model while three types of knowledge data are comprehensively processed with graph networks and a masked transformer, enforcing a deep understanding of single-modality data, respectively. The benchmark results show an approximate 20% reduction in terms of mean squared error, proving the effectiveness of the model.

Deep Neural Networks (DNNs) are notoriously susceptible to adversarial examples. To mitigate the impact of well-designed adversarial attacks on network models, researchers have developed various defense mechanisms, among which adversarial training has emerged as one of the most effective strategies to date. Adversarial training aims to augment training data with adversarial examples, thus giving DNNs a certain degree of robustness to defend against adversarial attacks. However, while obtaining adversarial robustness, this method comes at the cost of reducing the generalization performance, manifested in the reduced classification effect of clean test datasets. Researchers have been actively seeking to counter the balance between adversarial robustness and model generalization. We believe that the key to balancing these two aspects lies in identifying appropriate adversarial examples. Overly potent examples can lead to a decline in clean accuracy, whereas weaker examples may offer limited robustness. Based on our analysis, a new adversarial example generation algorithm called Denoising Projection Gradient Descent (DPGD) was proposed. DPGD adds a purification module and a constraint in generating adversarial examples, the former is used to limit the influence of too strong adversarial examples on model training and the latter is used to ensure the necessary attack intensity. Combining DPGD with the framework of traditional adversarial training, we obtain the Diffusion Adversarial Training (DifAT) approach. To verify the effectiveness of our proposed method, we conducted extensive experiments on benchmark datasets, including CIFAR-10, CIFAR-100, and Tiny-Imagenet. Our results demonstrate the effectiveness of DifAT in improving the robustness of DNNs while maintaining or even improving their generalization performance.

• We propose ABG-NAS, an adaptive NAS framework for graph representation learning. • A novel genetic search strategy dynamically balances exploration and exploitation. • Bayesian optimization is embedded to tune hyperparameters during the search process. • Our method outperforms SOTA GNAS methods on four benchmark graph datasets. • ABG-NAS achieves high F1 scores on both sparse and dense real-world graph structures. Effective and efficient graph representation learning is essential for enabling critical downstream tasks, such as node classification, link prediction, and subgraph search. However, existing graph neural network (GNN) architectures often struggle to adapt to diverse and complex graph structures, limiting their ability to produce structure-aware and task-discriminative representations. To address this challenge, we propose ABG-NAS, a novel framework for automated graph neural network architecture search tailored for efficient graph representation learning. ABG-NAS encompasses three key components: a Comprehensive Architecture Search Space (CASS), an Adaptive Genetic Optimization Strategy (AGOS), and a Bayesian-Guided Tuning Module (BGTM). CASS systematically explores diverse propagation ( P ) and transformation ( T ) operations, enabling the discovery of GNN architectures capable of capturing intricate graph characteristics. AGOS dynamically balances exploration and exploitation, ensuring search efficiency and preserving solution diversity. BGTM further optimizes hyperparameters periodically, enhancing the robustness and scalability of the resulting architectures to both large-scale graphs and high-complexity models. Empirical evaluations on benchmark datasets (Cora, PubMed, Citeseer, and CoraFull) demonstrate that ABG-NAS consistently outperforms both manually designed GNNs and state-of-the-art neural architecture search (NAS) methods. These results highlight the potential of ABG-NAS to advance graph representation learning by providing adaptive solutions that scale effectively across varying graph sizes and architectural complexities. Our code is publicly available at https://github.com/sserranw/ABG-NAS .

Location information is crucial for efficient task assignment in spatial crowdsourcing, but sharing such information raises privacy concerns. Differential privacy (DP) offers a solution by protecting location privacy while preserving data usefulness. Existing DP-based spatial crowdsourcing frameworks have two main limitations: 1) they fail to provide personalized privacy preservation for workers and 2) they prioritize incentive mechanisms (such as utility maximization and cost minimization) while overlooking quality control. To address these limitations, we formulate the multiobjective privacy-preserving task assignment (MP-TA) problem. This problem aims to maximize both incentives and quality while meeting service rate requirements and ensuring personalized privacy protection for workers. Accordingly, we present a three-phase framework comprising worker proposal, candidate worker selection, and task assignment optimization. To generate high-quality eligible solutions for both objectives, we introduce a distributed cooperative co-evolutionary multiobjective memetic algorithm (DCC-MMA) based on sequential subproblem division and knee-driven migration operation. Matching-based crossover, matching-based mutation, and fix operations are designed to enhance search efficiency. Experimental results demonstrate DCC-MMA's superiority in solution quality, convergence speed, and scalability compared to state-of-the-art algorithms.

Cross-view geo-localization (CVGL) task aims to match images of the same object captured from various platforms, such as drones and satellites. The primary challenge of CVGL is that the flight altitude and shooting angle of drones can lead to changes in the visual appearance of the same target building. Most existing methods regard CVGL task as an image retrieval problem based on classification networks. Nevertheless, the multimodal information correspondence of Drone-Satellite views and the structural features of target buildings are not fully explored. In this article, we propose a novel CVGL framework based on multimodal information, named CDM-Net. The framework consists of three stages: pre-processing, drone-view image synthesis, and structural feature matching. Specifically, the first stage employs Perspective Transformation (PT) to convert the drone’s oblique view into a vertical view and describes the remote sensing (RS) information of the drone images. In the second stage, we use a Conditional Diffusion (CD) model to synthesize high-precision vertical view by combining the converted drone-view image with RS textual information as input. In the final stage, we utilize a structural feature matching network to extract robust point-line features of the target building, subsequently outputting the retrieval list. Experiments on two widely used public benchmarks, University-1652 and SUES-200, showed that the proposed method achieved competitive results. Additionally, our method also outperformed existing methods in cross-modal dataset generalization. The datasets of this study are available at: https://github.com/cver6/CDM-Net.

This research is dedicated to addressing user recommendation matching and multi-objective optimization problems in ride-sharing services. For addressing the challenge of node classification in social networks, the Graph Attention Network with Opinion Dynamics (OD-GAT) is proposed. This model combines opinion dynamics and attention mechanism, which can make full use of multi-dimensional information for social relationship reasoning, and at the same time simulate the influence of individuals by other objects in the group, realize more accurate prediction and reasoning of social relationships, improved service quality and ride-sharing safety. To address the intricate task of balancing multiple objectives, including average detour cost, average response rate, and average user similarity rate, we introduce a novel evolutionary computation method for optimizing ride-sharing scenarios. This approach tackles the dynamic ride-sharing matching problem by emphasizing human factors in the optimization goals, successfully overcoming challenges related to local optima and convergence. Experimental validation confirms the effectiveness of OD-GAT in feature extraction and classification, showcasing the method’s fastest convergence speed and global optimum achievement across three key metrics.

Deep neural networks (DNNs) are vulnerable to adversarial examples crafted by well-designed perturbations. This could lead to disastrous results on critical applications such as self-driving cars, surveillance security, and medical diagnosis. At present, adversarial training is one of the most effective defenses against adversarial examples. However, in traditional adversarial training, it is still difficult to achieve a good trade-off between clean accuracy and robustness since DNNs still learn spurious features. The intrinsic reason is that traditional adversarial training makes it difficult to fully learn core features from adversarial examples when noise and examples cannot be disentangled. In this paper, we disentangle the adversarial examples into natural and perturbed patterns by bit-plane slicing. We assume the higher bit-planes represent natural patterns and the lower bit-planes represent perturbed patterns, respectively. We propose Feature-Focusing Adversarial Training (F$^{2}$AT), which differs from previous work in that it enforces the model to focus on the core features from natural patterns and reduce the impact of spurious features from perturbed patterns. The experimental results demonstrated that the clean accuracy and adversarial robustness with our F$^{2}$AT can be significantly improved.

This study addresses the Multiple Flying Sidekicks Traveling Salesman Problem (mFSTSP), where parallel Unmanned Aerial Vehicles (UAVs, or Drones) work alongside truck to enhance delivery efficiency. Existing scheduling approaches face challenges in high computational costs and the risk of converging to local optima due to excessive exploration in unknown environments, especially in large-scale mFSTSP. This study proposed a Large Language Model Enhanced Q-Learning Approach (LLM-QL) to solve mFSTSP, which combines the local exploration advantages of Q-Learning with the global understanding of unknown environments provided by LLMs, thus improving the efficiency of path planning. A novel prompt strategy is also provided, transforming the problem modeling into a format easily understood by LLMs, guiding the algorithm's exploration and significantly improving convergence. We also provide a proof of the convergence of LLM-QL. Experimental results demonstrate that LLM-QL achieves up to a 1.35 x improvement in key performance metrics such as total completion time, algorithm runtime, and UAV utilization, compared to existing state-of-the-art methods.

Nowadays, trajectory data is widely available and used in various real-world applications such as urban planning, navigation services, and location-based services. However, publishing trajectory data can potentially leak sensitive information about identity, personal profiles, and social relationships, and requires privacy protection. This paper focuses on optimizing Privacy-Preserving Trajectory Data Publishing (PP-TDP) problems, addressing the limitations of existing techniques in the trade-off between privacy protection and information preservation. We propose the Federated Genetic Algorithm (FGA) in this paper, aiming to achieve better local privacy protection and global information preservation. FGA consists of multiple local optimizers and a single global optimizer. The parallel local optimizer enables the local data center to retain the original trajectory data and share only the locally anonymized outcomes. The global optimizer collects the local anonymized outcomes and further optimizes the preservation of information while achieving comprehensive privacy protection. To optimize the discrete-domain PP-TDP problems more efficiently, this paper proposes a grouping-based strategy, an intersection-based crossover operation, and a complement-based mutation operation. Experimental results demonstrate that FGA outperforms its competitors in terms of solution accuracy and search efficiency.

Complex social event summarization is a problem which has been important for real-world applications, including crisis management, rumor control and government policy tracking. However, in many critical situations, social events are complex and context-sensitive, which demands the online summarization of social events in an integrated manner. Motivated by this, we propose an online complex social event summarization approach, namely SOMA, which summarizes the complex social events over multiple attributes including media content and contexts simultaneously. The evaluation shows that our proposed approach outperforms the existing solutions for event summarizaiton in terms of effectiveness and efficiency.

Abstract Insider threats pose a critical risk to organisations, impacting their data, processes, resources, and overall security. Such significant risks arise from individuals with authorised access and familiarity with internal systems, emphasising the potential for insider threats to compromise the integrity of organisations. Previous research has addressed the challenge by pinpointing malicious actions that have already occurred but provided limited assistance in preventing those risks. In this research, we introduce a novel approach based on bidirectional long short-term memory (BiLSTM) networks that effectively captures and analyses the patterns of individual actions and their sequential dependencies. The focus is on predicting whether an individual would be a malicious insider in a future day based on their daily behavioural records over the previous several days. We analyse the performance of the four supervised learning algorithms on manual features, sequential features, and the ground truth of the day with different combinations. In addition, we investigate the performance of different RNN models, such as RNN, LSTM, and BiLSTM, in incorporating these features. Moreover, we explore the performance of different predictive lengths on the ground truth of the day and different embedded lengths for the sequential features. All the experiments are conducted on the CERT r4.2 dataset. Experiment results show that BiLSTM has the highest performance in combining these features.

Intrusion detection is a crucial aspect of modern cybersecurity, aimed at identifying and responding to potential security threats within computer systems , networks, and applications. One of the major challenges faced by intrusion detection systems is the accurate detection and response to attack traffic, which is typically much lower in volume compared to normal traffic. This challenge becomes even more pronounced when the attack traffic is further classified into different attack categories, which may suffer from more severe data imbalance. To address these challenges, we present a novel approach to intrusion detection using a Multi-task Feature Fusion Pseudo-Siamese Network (MF2POSE) and a Category-distance Promotion Loss (CP Loss). The proposed MF2POSE leverages the Pseudo-Siamese Network (POSE-Net), which incorporates both a main network and a siamese network, to simultaneously perform binary-class and multi-class classification of the traffic. Furthermore, the Multi-task Feature Fusion (MF2) module enhances the multi-class classification performance of the main network by incorporating multi-scale internal features from the siamese network. Additionally, the CP Loss is introduced to aggregate the internal feature from the main network belonging to the same category, and separate the internal feature belonging to the different categories. We have conducted comprehensive experiments across two popular intrusion detection datasets, and the experimental results demonstrate the superior performance of our MF2POSE compared to existing state-of-the-art techniques, particularly in multi-class classification scenarios.

Situation-awareness (SA) has been important for natural disaster management and smart decision making. Traditionally, security officers recognize disaster situations through emergency reporting with phone calls. However, due to the busy phone lines or power outages caused by disasters, traditional SA has been limited in terms of time and mitigation response, which may cause high loss in life and properties in disaster areas. Social media-based SA has been studied recently. However, existing systems are designed for events without nonconsecutive migrations over location and time. In this demo, we design HSAP, the first human-in-the-loop social media-based SA platform for effective and efficient management of disasters with complex event migrations. HSAP is designed with a number of novel techniques, including complex social event detection, summarization, and human-in-the-loop result filtering. We demonstrate the usage of HSAP via Nepal earthquake 2015.

Distributed database system (DDBS) technology has shown its advantages with respect to query processing efficiency, scalability, and reliability. Moreover, by partitioning attributes of sensitive associations into different fragments, DDBSs can be used to protect data privacy. However, it is complex to design a DDBS when one has to optimize privacy and utility in a time-varying environment. This paper proposes a distributed prediction-randomness framework for the evolutionary dynamic multiobjective partitioning optimization of databases. In the proposed framework, two sub-populations contain individuals representing database partitioning solutions. One sub-population utilizes a Markov chain-based predictor to predict discrete-domain solutions for database partitioning when the environment changes, and the other sub-population utilizes the random initialization operator to maintain population diversity. In addition, a knee-driven migration operator is utilized to exchange information between two sub-populations. Experimental results show that the proposed algorithm outperforms the competing solutions with respect to accuracy, convergence speed, and scalability.

Recent studies have shown that Deep Neural Networks (DNNs) are easily deceived by adversarial examples, revealing their serious vulnerability. Due to the transferability, adversarial examples can attack across multiple models with different architectures, called transfer-based black-box attacks. Input transformation is one of the most effective methods to improve adversarial transferability. In particular, the attacks fusing other categories of image information reveal the potential direction of adversarial attacks. However, the current techniques rely on input transformations in the spatial domain, which ignore the frequency information of the image and limit its transferability. To tackle this issue, we propose Mixed-Frequency Inputs (MFI) based on a frequency domain perspective. MFI alleviates the overfitting of adversarial examples to the source model by considering high-frequency components from various kinds of images in the process of calculating the gradient. By accumulating these high-frequency components, MFI acquires a more steady gradient direction in each iteration, leading to the discovery of better local maxima and enhancing transferability. Extensive experimental results on the ImageNet-compatible datasets demonstrate that MFI outperforms existing transform-based attacks with a clear margin on both Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs), which proves MFI is more suitable for realistic black-box scenarios.

Deep learning-based time series classification in 6G-supported Intelligent Transportation Systems (ITS) helps transport decision-making. Deep learning classifier training necessitates a large amount of labeled data for feature extraction. Labeling time series data in 6G-supported ITS is tough. Meta-learning can be used to train deep classifiers with limited data. However, in meta-learning, the tasks are frequently modeled by a low-complexity base learner. It is unable to use more complicate and powerful structures. The meta-learning-pretrained classifier can only perform new classification problems with the same number of classes. Most pre-training strategies do not prioritize enhancing the pre-training phase’s convergence rate and lowering the computational cost. Most research work aims to improve classification performance by increasing the complexity of the classification model. However, this raises computing costs. In this paper, we propose a one-dimensional Multi-Scale Dilated Convolution Neural Network time series classifier (MSDCNN). MSDCNN combines multi-scale CNN and dilated CNN. It can extract multi-scale characteristics from time series and reduce the complexity of the classifier. Furthermore, we propose a pre-training strategy, called Meta-transfer metric Learning using Scale function (MLS). MLS allows the classifier to gain experience from different tasks with various numbers of classes. Experiments show that MLS reduces pre-training computation costs during the pre-training phase. The pre-trained classifier, without using any fine tuning techniques, achieves the highest accuracy by comparing with the state-of-the-art methods. Finally, we present a case study of applying MSDCNN and MLS to detect road accidents in 6G-supported transportation systems.

Data transparency is beneficial to data participants’ awareness, users’ fairness, and research work’s reproducibility. However, when addressing transparency requirements, we cannot ignore data privacy. This article defines the multi-objective data publishing (MODP) problem, optimizing data privacy and transparency at the same time. Accordingly, we propose a distributed cooperative coevolutionary genetic algorithm (DCCGA) to optimize the MODP problem. In the population of DCCGA, each individual represents an anonymization solution to MODP. Three modules in DCCGA, i.e., grouping module, cooperative coevolutionary module, and evolving module, are proposed for distributed sub-population update and evaluation, improving DCCGA’s optimization performance and parallel efficiency. Moreover, a matrix-based crossover operator and a matrix-based mutation operator are designed to exchange and adjust anonymization information in the individuals efficiently. Experimental results demonstrate that the proposed DCCGA outperforms the competitors with respect to solution accuracy, convergence speed, and scalability. Besides, we verify the effectiveness of all the proposed components in DCCGA.

Software vulnerabilities, also known as flaws, bugs or weaknesses, are common in modern information systems, putting critical data of organizations and individuals at cyber risk. Due to the scarcity of resources, initial risk assessment is becoming a necessary step to prioritize vulnerabilities and make better decisions on remediation, mitigation, and patching. Datasets containing historical vulnerability information are crucial digital assets to enable AI-based risk assessments. However, existing datasets focus on collecting information on individual vulnerabilities while simply storing them in relational databases, disregarding their structural connections. This article constructs a compact vulnerability knowledge graph, VulKG, containing over 276 K nodes and 1 M relationships to represent the connections between vulnerabilities, exploits, affected products, vendors, referred domain names, and more. We provide a detailed analysis of VulKG modeling and construction, demonstrating VulKG-based query and reasoning, and providing a use case of applying VulKG to a vulnerability risk assessment task, i.e., co-exploitation behavior discovery. Experimental results demonstrate the value of graph connections in vulnerability risk assessment tasks. VulKG offers exciting opportunities for more novel and significant research in areas related to vulnerability risk assessment. The data and codes of this article are available at https://github.com/happyResearcher/VulKG.git .

Graph learning is widely applied to process various complex data structures (e.g., time series) in different domains. Due to multidimensional observations and the requirement for accurate data representation, time series are usually represented in the form of multilabels. Accurately classifying multilabel time series can provide support for personalized predictions and risk assessments. It requires effectively capturing complex label relevance and overcoming imbalanced label distributions of multilabel time series. However, the existing methods are unable to model label relevance for multilabel time series or fail to fully exploit it. In addition, the existing multilabel classification balancing strategies suffer from limitations, such as disregarding label relevance, information loss, and sampling bias. This article proposes a dynamic graph attention autoencoder-based multitask (DGAAE-MT) learning framework for multilabel time series classification. It can fully and accurately model label relevance for each instance by using a dynamic graph attention-based graph autoencoder to improve multilabel classification accuracy. DGAAE-MT employs a dual-sampling strategy and cooperative training approach to improve the classification accuracy of low-frequency classes while maintaining the classification accuracy of high-frequency and mid-frequency classes. It avoids information loss and sampling bias. DGAAE-MT achieves a mean average precision (mAP) of 0.955 and an F1 score of 0.978 on a mixed medical time series dataset. It outperforms state-of-the-art works in the past two years.

Abstract The privacy-preserving data publishing (PPDP) problem has gained substantial attention from research communities, industries, and governments due to the increasing requirements for data publishing and concerns about data privacy. However, achieving a balance between preserving privacy and maintaining data quality remains a challenging task in PPDP. This paper presents an information-driven distributed genetic algorithm (ID-DGA) that aims to achieve optimal anonymization through attribute generalization and record suppression. The proposed algorithm incorporates various components, including an information-driven crossover operator, an information-driven mutation operator, an information-driven improvement operator, and a two-dimensional selection operator. Furthermore, a distributed population model is utilized to improve population diversity while reducing the running time. Experimental results confirm the superiority of ID-DGA in terms of solution accuracy, convergence speed, and the effectiveness of all the proposed components.

Quasi-periodic time series (QTS) exists widely in the real world, and it is important to detect the anomalies of QTS. In this paper, we propose an automatic QTS anomaly detection framework (AQADF) consisting of a two-level clustering-based QTS segmentation algorithm (TCQSA) and a hybrid attentional LSTM-CNN model (HALCM). TCQSA first automatically splits the QTS into quasi-periods which are then classified by HALCM into normal periods or anomalies. Notably, TCQSA integrates a hierarchical clustering and the k-means technique, making itself highly universal and noise-resistant. HALCM hybridizes LSTM and CNN to simultaneously extract the overall variation trends and local features of QTS for modeling its fluctuation pattern. Furthermore, we embed a trend attention gate (TAG) into the LSTM, a feature attention mechanism (FAM) and a location attention mechanism (LAM) into the CNN to finely tune the extracted variation trends and local features according to their true importance to yield a better representation of the fluctuation pattern of the QTS. On four public datasets, HALCM exceeds four state-of-the-art baselines and obtains at least 97.3% accuracy, TCQSA exceeds two cutting-edge QTS segmentation algorithms and can be applied to different types of QTSs.

Transcriptome-based survival modeling is a critical yet complicated task in cancer treatment due to the strong association between the prognosis of a patient and the progression of tumors based on heterogeneous molecular mechanisms. An effective prognosis model needs to consider the uncertainty that naturally stems from the high molecular heterogeneity together with numerous unforeseeable factors related to prognosis, and requires a perfect match between the selected covariates and the modeling approach of the joint distribution between covariates and right-censored survival time. Unfortunately, these necessary factors have not been fully considered in existing survival models. In this paper, we propose a novel conditional variational deep survival model (CVaDeS for short) for survival analysis. CVaDeS accurately predicts the risk values of patients and effectively distinguishes high-risk and low-risk individuals. Also, the proposed model CVaDeS can be effectively combined with Cox feature selection for survival analysis. Extensive experimental results demonstrate that the combination of Cox feature selection with CVaDeS significantly improves the predictive performance of the model, surpassing baseline models.

Abstract With the rapid development of social networks, academic social networks have attracted increasing attention. In particular, providing personalized recommendations for learners considering data sparseness and cold-start scenarios is a challenging task. An important research topic is to accurately discover potential friends of learners to build implicit learning groups and obtain personalized collaborative recommendations of similar learners according to the learning content. This paper proposes a personalized explainable learner implicit friend recommendation method (PELIRM). Methodologically, PELIRM utilizes the learner's multidimensional interaction behavior in social networks to calculate the degrees of trust between learners and applies the three-degree influence theory to mine the implicit friends of learners. The similarity of research interests between learners is calculated by cosine and term frequency–inverse document frequency. To solve the recommendation problem for cold-start learners, the learner's common check-in IP is used to obtain the learner's location information. Finally, the degree of trust, similarity of research interests, and geographic distance between learners are combined as ranking indicators to recommend potential friends for learners and give multiple interpretations of the recommendation results. By verifying and evaluating the proposed method on real data from Scholar.com, the experimental results show that the proposed method is reliable and effective in terms of personalized recommendation and explainability.

Digital Twins for Mobile Networks (DTMN) can enhance mobile health (mHealth) by increasing diagnostic and monitoring capabilities. Classifying multi-label time series mHealth data in DTMN is challenging due to complex class relevance and feature extraction difficulties. This paper proposes a Class-Driven Graph Attention network learning framework (C-DGAM) for Multi-label classification of mHealth data in DTMN. C-DGAM captures the complex class relationships by constructing a unique class relevance graph for each time series. It uses a temporal context attention module to generates class representation vectors by fusing multi-dimensional features of time and class. Then, it dynamically models different relevance among the class representation vectors through a dynamic graph attention module which improves the performance of multi-label time series classification while maintaining a smaller parameter size and lower computational complexity. The mean Average Precision achieved by C-DGAM on two different multi-label time series datasets are 0.955 and 0.776, respectively, with corresponding F1 scores of 0.867 and 0.80. It demonstrates leading performance compared to existing state-of-art works. It provides more accurate and generalized algorithmic support for DMTN systems.

Building a quality service-based system (SBS) is one of the most important research topics in software engineering. Many studies investigate intelligent methods to simplify the process of building SBSs. In particular, some keyword-based SBS building methods allow service users to automatically build an SBS by only providing a few of keywords. This type of work usually constructs a directed weighted graph of a service repository. A set of minimum-weight group Steiner trees (MSTs) is extracted from the graph to represent the service functions and their relations. However, to the best of our knowledge, none of the existing keyword-based SBS building methods allow the relaxation of the function requirements for a user. A relaxed SBS may achieve a comparable functionality versus a complete SBS containing all the query functions. To fill in the above gap, we define a new problem: a bounded skyline SBS building problem, whose solution is more adaptive and less limited than the traditional keyword-based SBS building methods. To solve this problem, we propose two algorithms based on skyline query, dynamic programming, and lower bound pruning. In the experiments, we collect real-world datasets and label the nodes with keywords. We conduct a comprehensive study to demonstrate the time efficiency of our algorithms on automatically finding SBSs. We make the annotated real-world datasets and our source code open to peer researchers.

Industrial Internet of Things (IIoT), which has the capability of perception, monitoring, communication and decision–making, has already exposed more security problems that are easy to be invaded by malware because of many simple edge devices that help smart factories, smart cities and smart homes. In this paper, a two–layer malware spread–patch modelIIPVis proposed based on a hybrid patches distribution method according to the simple edge equipments and limited central computer resources of IIoT. The spread process of malware in IIoT was deeply analyzed using differential game and a differential game model was established. Then optimization theory was further used to solve the optimization problem extracted by introducing subjective effort parameters to obtain the optimal control strategies of devices for malware and patches. In addition, we combined the deep reinforcement learning algorithm into the modelIIPVto design a new algorithmDDQN–PVsuitable for suppressing the spread of malware in IIoT during the experiments. Finally, the effectiveness of modelIIPVand algorithmDDQN–PVare verified by numerous comparative experiments.

Complex social event summarization is a problem which has been shown having great utility for real-world applications, including crisis management, rumor control and government policy tracking. In recent years there has been significant research effort spent on effectively extracting meaningful textual descriptions of an event. However, in many critical situations, social events are complex and context-sensitive, which demands the online summarization of social events in an integrated manner. In this paper, we propose the first online complex social event summarization approach, namely SOMA, which summarizes the complex social events over multiple attributes including media content and contexts simultaneously. Specifically, we first propose a deep learning model that comprehensively summarizes events in regards to the text description and locations that they appear in, by utilizing their hidden connections in posts. We then propose a summary generator over time, text and location to achieve a maximal coverage of the summary over the original social event and minimal redundancy of the summary. Furthermore, we propose a location estimation method to address the location sparsity issue of complex events by mining the correlation between text and location. The evaluation over four real-event datasets and three benchmark datasets shows that our proposed approach outperforms the existing solutions for event summarizaiton in terms of effectiveness and efficiency.

The development of information gathering and extraction technology has led to the popularity of multi-view data, which enables samples to be seen from numerous perspectives. Multi-view clustering (MVC), which groups data samples by leveraging complementary and consensual information from several views, is gaining popularity. Despite the rapid evolution of MVC approaches, there has yet to be a study that provides a full MVC roadmap for both stimulating technical improvements and orienting research newbies to MVC. In this article, we review recent MVC techniques with the purpose of exhibiting the concepts of popular methodologies and their advancements. This survey not only serves as a unique MVC comprehensive knowledge for researchers but also has the potential to spark new ideas in MVC research. We summarise a large variety of current MVC approaches based on two technical mechanisms: heuristic-based multi-view clustering (HMVC) and neural network-based multi-view clustering (NNMVC). We end with four technological approaches within the category of HMVC: nonnegative matrix factorisation, graph learning, latent representation learning, and tensor learning. Deep representation learning and deep graph learning are two technical methods that we demonstrate in NNMVC. We also show 15 publicly available multi-view datasets and examine how representative MVC approaches perform on them. In addition, this study identifies the potential research directions that may require further investigation in order to enhance the further development of MVC.

The signaling of the associations between drugs and adverse drug reactions (ADRs) is a challenging task in pharmacovigilance, especially when an association is infrequent or has never previously been reported. Most existing methods for ADR signaling are based on analyzing the frequency with which drugs tend to co-occur with ADRs. In this article, we propose a kernelized multitask learning model, KEMULA, in which information is learned and transferred from the clinical data of other patients as collaborative information to rank distinct lists of ADRs for different patients. We comprehensively compare the performance of KEMULA against three baseline methods, two state-of-the-art ADR signaling methods, and two KEMULA variants. The method is tested on adverse drug event reports retrieved from the FDA Adverse Event Reporting System (FAERS), which includes 4,106,633 unique adverse drug event reports, 7,824 unique ADRs, 114 unique biotech drugs, 1,151 unique small molecule drugs, and 3,363 unique medical conditions. The experimental results demonstrate the advantages of our method and show that it not only can signal frequent ADRs but also has the power to signal infrequent ADRs that cannot be signaled by most existing methods.

Data summarization that presents a small subset of a dataset to users has been widely applied in numerous applications and systems. Many datasets are coded with hierarchical terminologies, e.g., gene ontology, disease ontology, to name a few. In this paper, we study the weighted tree summarization. We motivate and formulate our${\mathsf {kWTS}}$-${\mathsf {problem}}$as selecting a diverse set of$k$nodes tosummarize a hierarchicaltree$T$withweighted terminologies. We first propose an efficient greedy tree summarization algorithm${\mathsf {GTS}}$. It solves the problem with$(1-1/e)$-approximation guarantee. Although${\mathsf {GTS}}$achieves quality-guaranteed answers approximately, but it is still not optimal. To tackle the problem optimally, we further develop a dynamic programming algorithm${\mathsf {OTS}}$to obtain optimal answers for${\mathsf {kWTS}}$-${\mathsf {problem}}$in$O(nhk^3)$time, where$n, h$are the node size and height in tree$T$. The algorithm complexity and correctness of${\mathsf {OTS}}$are theoretically analyzed. In addition, we propose a useful optimization technique of tree reduction to remove useless nodes with zero weights and shrink the tree into a smaller one, which ensures the efficiency acceleration of both${\mathsf {GTS}}$and${\mathsf {OTS}}$in real-world datasets. Moreover, we illustrate one useful application of graph visualization based on the answer of$k$-sized tree summarization and show it in a novel case study. Extensive experimental results on real-world datasets show the effectiveness and efficiency of our proposed approximate and optimal algorithms for tree summarization. Furthermore, we conduct a usability evaluation of attractive topic recommendation on ACM Computing Classification System dataset to validate the usefulness of our model and algorithms.

Event popularity prediction over social media is crucial for estimating information propagation scope, decision making, and emergency prevention. It has been widely inves-tigated by existing approaches focusing on predicting single attribute occurrences which are not comprehensive enough for representing complex social event propagation. Motivated by this, we propose a novel hashtag-influence-based event popularity prediction by mining the impact of an influential hashtag set on the event propagation. We have conducted extensive experiments to prove the effectiveness and efficiency of the proposed approach.

BACKGROUND: Coronavirus disease 2019 (COVID-19) has spurred a boom in uncovering repurposable existing drugs. Drug repurposing is a strategy for identifying new uses for approved or investigational drugs that are outside the scope of the original medical indication. MOTIVATION: Current works of drug repurposing for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) are mostly limited to only focusing on chemical medicines, analysis of single drug targeting single SARS-CoV-2 protein, one-size-fits-all strategy using the same treatment (same drug) for different infected stages of SARS-CoV-2. To dilute these issues, we initially set the research focusing on herbal medicines. We then proposed a heterogeneous graph embedding method to signaled candidate repurposing herbs for each SARS-CoV-2 protein, and employed the variational graph convolutional network approach to recommend the precision herb combinations as the potential candidate treatments against the specific infected stage. METHOD: We initially employed the virtual screening method to construct the 'Herb-Compound' and 'Compound-Protein' docking graph based on 480 herbal medicines, 12,735 associated chemical compounds and 24 SARS-CoV-2 proteins. Sequentially, the 'Herb-Compound-Protein' heterogeneous network was constructed by means of the metapath-based embedding approach. We then proposed the heterogeneous-information-network-based graph embedding method to generate the candidate ranking lists of herbs that target structural, nonstructural and accessory SARS-CoV-2 proteins, individually. To obtain precision synthetic effective treatments forvarious COVID-19 infected stages, we employed the variational graph convolutional network method to generate candidate herb combinations as the recommended therapeutic therapies. RESULTS: There were 24 ranking lists, each containing top-10 herbs, targeting 24 SARS-CoV-2 proteins correspondingly, and 20 herb combinations were generated as the candidate-specific treatment to target the four infected stages. The code and supplementary materials are freely available at https://github.com/fanyang-AI/TCM-COVID19.

Community detection can exhibit the aggregation behavior of complex networks. Network motifs are the fundamental building blocks which can reveal the higher-order structure of complex networks. Label propagation algorithm has the advantage of approximately linear time complexity, unfortunately, the randomness of label update is a major but unsolved issue. For these reasons, this paper proposes a novel community detection method, named motif-based embedding label propagation algorithm (MELPA). First, complex network topology is reconstructed by merging higher-order topology with lower-order connectivity features, where higher-order topology is captured by mining network motifs. Second, We design a label propagation characteristic model according to nodes influence, then a new label update rule is formulated based on reconstructed weighted network, the rule integrates frequency among neighbor labels, influence of nodes, propagation characteristics and closeness of nodes to update the node label, the purpose is to overcome the randomness of label selection and identify a better and more stable community structure. Finally, extensive experiments on synthetic networks and real-world complex networks are conducted to verify the effectiveness of MELPA, especially for the complex networks with unobvious community structure, MELPA will get unexpected results.

Event popularity prediction over social media is crucial for estimating information propagation scope, decision making, and emergency prevention. However, existing approaches only focus on predicting the occurrences of single attribute such as a message, a hashtag or an image, which are not comprehensive enough for representing complex social event propagation. In this paper, we predict the event popularity, where an event is described as a set of messages containing multiple hashtags. We propose a novel hashtag-influence-based event popularity prediction by mining the impact of an influential hashtag set on the event propagation. Specifically, we first propose a hashtag-influence-based cascade model to select the influential hashtags over an event hashtag graph built by the pairwise hashtag similarity and the topic distribution of event-related hashtags. A novel measurement is proposed to identify the hashtag influence of an event over its content and social impacts. A hashtag correlation-based algorithm is proposed to optimize the seed selection in a greedy manner. Then, we propose an event-fitting boosting model to predict the event popularity by embedding the feature importance over events into the XGBOOST model. Moreover, we propose an event-structure-based method, which incrementally updates the prediction model over social streams. We have conducted extensive experiments to prove the effectiveness and efficiency of the proposed approach.

Quasi-periodic time series (QTS) exists widely in the real world, and it is important to detect the anomalies of QTS. In this paper, we propose anautomaticQTSanomalydetectionframework (AQADF) consisting of a two-level clustering-based QTS segmentation algorithm (TCQSA) and a hybrid attentional LSTM-CNN model (HALCM). TCQSA first automatically splits the QTS into quasi-periods which are then classified by HALCM into normal periods or anomalies. Notably, TCQSA integrates a hierarchical clustering and the k-means technique, making itself highly universal and noise-resistant. HALCM hybridizes LSTM and CNN to simultaneously extract the overall variation trends and local features of QTS for modeling its fluctuation pattern. Furthermore, we embed a trend attention gate (TAG) into the LSTM, a feature attention mechanism (FAM) and a location attention mechanism (LAM) into the CNN to finely tune the extracted variation trends and local features according to their true importance to achieve a better representation of the fluctuation pattern of the QTS. On four public datasets, HALCM exceeds four state-of-the-art baselines and obtains at least 97.3 percent accuracy, TCQSA outperforms two cutting-edge QTS segmentation algorithms and can be applied to different types of QTSs. Additionally, the effectiveness of the attention mechanisms is quantitatively and qualitatively demonstrated.

Discovering regularities in Traditional Chinese Medicine (TCM) formula has been a hot topic in assisting TCM clinical treatment and poly-pharmacology research. Several machine learning methods, like topic model, auto-encoder, and GNNs, have been proposed for discovering regularities in TCM. However, they are often limited by specific data challenges (e.g., complex relations with rich TCM knowledge, sparsity and ambiguity, expensive data labeling, etc.) in TCM formulae. Addressing these challenges, we first establish a TCM Attributed Heterogeneous Information Network (TAHIN) for modeling massive formulae, which can assemble various types of additional information and capture their relations. Based on the TAHIN, we further propose a novel hybrid-scales graph contrastive learning framework to learn high-quality node representations in a whole unsupervised manner which can be helpful for various tasks of discovering regularities such as herb classification and herb similarity search, etc. Extensive experiments demonstrate the effectiveness and interpretability of our method. Our source code and datasets are available at https://github.com/Yonggie/ HsCTRD.

Retinal blood vessel can assist doctors in diagnosis of eyerelated diseases such as diabetes and hypertension, and its segmentation is particularly important for automatic retinal image analysis. However, it is challenging to segment these vessels structures, especially the thin capillaries from the color retinal image due to low contrast and ambiguousness. In this paper, we propose pyramid U-Net for accurate retinal vessel segmentation. In pyramid U-Net, the proposed pyramid-scale aggregation blocks (PSABs) are employed in both the encoder and decoder to aggregate features at higher, current and lower levels. In this way, coarse-to-fine context information is shared and aggregated in each block thus to improve the location of capillaries. To further improve performance, two optimizations including pyramid inputs enhancement and deep pyramid supervision are applied to PSABs in the encoder and decoder, respectively. For PSABs in the encoder, scaled input images are added as extra inputs. While for PSABs in the decoder, scaled intermediate outputs are supervised by the scaled segmentation labels. Extensive evaluations show that our pyramid U-Net outperforms the current state-of-the-art methods on the public DRIVE and CHASE-DB1 datasets.

Effective training of deep neural networks (DNNs) usually requires labeling a large dataset, which is time and labor intensive. Recently, various data augmentation strategies like regional dropout and mix strategies have been proposed, which are effective as the augmented dataset can guide the model to attend on less discriminative parts. However, these strategies operate only at the image level, where the objects and the background are coupled. Thus, the boundaries are not well augmented due to the fixed semantic scenario. In this paper, we propose ObjectAug to perform object-level augmentation for semantic image segmentation. Our method first decouples the image into individual objects and the background using semantic labels. Second, each object is augmented individually with commonly used augmentation methods (e.g., scaling, shifting, and rotation). Third, the pixel artifacts brought by object augmentation are further restored using image inpainting. Finally, the augmented objects and background are assembled as an augmented image. In this way, the boundaries can be fully explored in the various semantic scenarios. In addition, ObjectAug can support category-aware augmentation that gives various possibilities to objects in each category, and can be easily combined with existing image-level augmentation methods to further boost the performance. Comprehensive experiments are conducted on both natural image and medical image datasets. Experiment results demonstrate that our ObjectAug can effectively improve segmentation performance.

Abstract By breaking sensitive associations between attributes, database fragmentation can protect the privacy of outsourced data storage. Database fragmentation algorithms need prior knowledge of sensitive associations in the tackled database and set it as the optimization objective. Thus, the effectiveness of these algorithms is limited by prior knowledge. Inspired by the anonymity degree measurement in anonymity techniques such as k-anonymity, an anonymity-driven database fragmentation problem is defined in this paper. For this problem, a set-based adaptive distributed differential evolution (S-ADDE) algorithm is proposed. S-ADDE adopts an island model to maintain population diversity. Two set-based operators, i.e., set-based mutation and set-based crossover, are designed in which the continuous domain in the traditional differential evolution is transferred to the discrete domain in the anonymity-driven database fragmentation problem. Moreover, in the set-based mutation operator, each individual’s mutation strategy is adaptively selected according to the performance. The experimental results demonstrate that the proposed S-ADDE is significantly better than the compared approaches. The effectiveness of the proposed operators is verified.

Diabetic eye disease (DED) is a cluster of eye problem that affects diabetic patients. Identifying DED is a crucial activity in retinal fundus images because early diagnosis and treatment can eventually minimize the risk of visual impairment. The retinal fundus image plays a significant role in early DED classification and identification. An accurate diagnostic model's development using a retinal fundus image depends highly on image quality and quantity. This paper presents a methodical study on the significance of image processing for DED classification. The proposed automated classification framework for DED was achieved in several steps: image quality enhancement, image segmentation (region of interest), image augmentation (geometric transformation), and classification. The optimal results were obtained using traditional image processing methods with a new build convolution neural network (CNN) architecture. The new built CNN combined with the traditional image processing approach presented the best performance with accuracy for DED classification problems. The results of the experiments conducted showed adequate accuracy, specificity, and sensitivity.

Data privacy and utility are two essential requirements in outsourced data storage. Traditional techniques for sensitive data protection, such as data encryption, affect the efficiency of data query and evaluation. By splitting attributes of sensitive associations, database fragmentation techniques can help protect data privacy and improve data utility. In this article, a distributed memetic algorithm (DMA) is proposed for enhancing database privacy and utility. A balanced best random distributed framework is designed to achieve high optimization efficiency. In order to enhance global search, a dynamic grouping recombination operator is proposed to aggregate and utilize evolutionary elements; two mutation operators, namely, merge and split, are designed to help arrange and create evolutionary elements; a two-dimension selection approach is designed based on the priority of privacy and utility. Furthermore, a splicing-driven local search strategy is embedded to introduce rare utility elements without violating constraints. Extensive experiments are carried out to verify the performance of the proposed DMA. Furthermore, the effectiveness of the proposed distributed framework and novel operators is verified.

Arrhythmia detection based on ECG classification has been a hot topic in the health informatics community, where each heartbeat is assigned to one of five classes: N, S, V, F and Q. However, arrhythmia detection under the inter-patient paradigm remains a challenging task. In particular, the detection of the S class is especially hard as it is morphologically similar to the N class. Recently, an LSTM-based sequence-to-sequence (seq2seq) model with CNN-based embedding has achieved the state-of the-art (SOTA) performance (as far as we know) by capturing both intra- and inter-heartbeat information, the latter of which can be crucial to S detection. However, its performance is still limited as it lacks the ability to highlight more discriminative features. In this work, based on the current SOTA, we propose a seq2seq model with a novel two-level attentional structure for accurate inter-patient arrhythmia detection. Specifically, a local channel-wise attention is used to weight intra-heartbeat morphological features, while a contextual Bahdanau's attention is used to weight inter-heartbeat semantics. A combination of the two attentions leads to a model that can utilize highly discriminative features and strike a balance between intra-and inter-heartbeat information. So far as we are concerned, our method has the best overall performance in the literature. Our source code is available at https://github.com/hierarchyJK/ Two-level-Attention-for-Arrhythmia-Detection.

Automatic epilepsy seizure detection based on electroencephalography (EEG) signals has been a hot topic in the bioinformatics community. Recently, graph representations named complex networks have been increasingly utilized to characterize EEG signals. However, existing time-domain complex networks often suffer from undesired intra-class variance due to phase shift. Addressing this problem, we propose to obtain complex network representations in frequency domain where perfect data alignment can be achieved. The transformation to frequency domain highlights the urgency to retain sequential information in the signals. To this end, we propose to further extract features from the complex network representation using a novel deep model called Sequential Graph Convolutional Network (SGCN). Specifically, we incorporate state-of-the-art graph neural network (GNN) architecture with a novel sequential convolution operation which is key to preserving sequential information. Extensive experiments demonstrate the effectiveness and interpretability of our method. Our source code is available at https://github.com/JL-Wang-source-code/SGCN-for-epilepsy-detection.

Biomedical image segmentation plays a critical role in clinical diagnosis and medical intervention. Recently, a variety of deep neural networks have boosted the biomedical image segmentation performance with a large margin, which adopts dense connections to explore rich representations in multiple scales. In multi-scale dense connections, features from all or most scales are fused or iteratively aggregated. In this paper, we propose constrained multi-scale dense connections (CMDC) for accurate biomedical image segmentation, which only fuse features from the nearest scales containing the most relevant appearance or semantic information. Based on CMDC, we further construct constraint multi-scale dense networks (CMD-Net) by applying CMDC to existing segmentation networks. Experiments across various architectures (including FCN-8s, U-Net, and DeepLabV3) and datasets (including GlaS, CRAG, KID, and ECS) demonstrate that CMD-Net not only outperforms existing schemes on both accuracy and efficiency but also can be easily generalized to a variety of segmentation networks. In addition, CMD-Net achieves state-of-the-art performance on two instance segmentation datasets, GlaS and CRAG.

Positive unlabeled time series classification (PUTSC) refers to classifying time series with a set PL of positive labeled examples and a set U of unlabeled ones. Model selection for PUTSC is a largely untouched topic. In this paper, we look into PUTSC model selection, which as far as we know is the first systematic study in this topic. Focusing on the widely adopted self-training one-nearest-neighbor (ST-1NN) paradigm, we propose a model selection framework based on active learning (AL). We present the novel concepts of self-training label propagation, pseudo label calibration principles and ultimately influence to fully exploit the mechanism of ST-1NN. Based on them, we develop an effective model performance evaluation strategy and three AL sampling strategies. Experiments on over 120 datasets and a case study in arrhythmia detection show that our methods can yield top performance in interactive environments, and can achieve near optimal results by querying very limited numbers of labels from the AL oracle.

Absence epilepsy is one of the most common types of epilepsy. The diagnosis of absence epilepsy is among the greatest challenges faced by clinical neurologists due to a lack of easily observable symptoms that are present in conventional epilepsy (e.g. spasm and convulsion), and highly relies on the detection of Spike and Slow Waves (SSWs) in Electroencephalogram (EEG) signals. Recently, graph representations called complex networks have been increasingly applied to characterizing 1D EEG signals. However, existing methods often fail to effectively represent SSWs, struggling to capture the differences between SSW waveforms and their non-SSW counterparts, such as minute differences and distinct shapes. Addressing this issue, in this work, we propose two simple yet effective complex networks, Overlook Graph (OG) and Weighted Overlook Graph (WOG), which have been customized to expressively represent SSWs. Built upon OG and WOG, we then develop a 2D Convolutional Neural Network (2D-CNN) to further learn latent features from the graph representations and accomplish the detection task. Extensive experiments on a real-world absence epilepsy EEG dataset show that the proposed OG/WOG-2D-CNN method can accurately detect SSWs. Additional experiments on the well-known Bonn dataset further show that our method can generalize to the conventional epilepsy seizure detection task with highly competitive performances.

The outbreak of COVID-19 has brought the world to a standstill. More than half of the world's population was in lockdown at the beginning of April. People were urged not to go out and avoid public transport. A few figures to take stock of the situation: around 4 billion people subject to various movement restrictions worldwide, air traffic is reduced by about 90% and shared mobility platforms activity reduced to 2% to 5% of their regular business. The current crisis, which is impacting both the supply and demand for transport, appears to be a privileged moment to rethink mobility and place it on a more sustainable trajectory. The Covid-19 crisis has a significant repercussion on demand and supply of mobility in Victoria as the Victorian government has put citizens in lockdown to limit the spread of COVID-19. This research aims to investigate the travel containment measures (government restrictions) taken in response to the COVID-19 emergency have on Victorian's mobility as this insight is vital to estimate parameters appropriate for the different stages of the crisis, before and after the implementation of prevention policies.

Social Media platforms have become an imperative source of information related to urban functions and social behaviour. Analysis of social media data can provide meaningful insights into the personality and behaviour traits of its users. Behaviour studies have been typically conducted using questionnaire and survey data. Since most of our activities have moved online, our behaviour on social media has become a proxy for our real-world behaviour. In this paper, we collected data from Swarm and Twitter, two widely used social media platforms, to detect user's antisocial behaviour with a high degree of accuracy. The behaviour was then categorized into different classes of antisocial behaviour using cutting edge deep learning technology. Four different deep learning models and two different word embeddings were experimented with to achieve a final model accuracy of 99%. Visually enhanced interpretation of the classification process and the word clouds for some of the most commonly used antisocial terms are presented, along with model training and error analysis.

Abstract Review helpfulness prediction aims to prioritize online reviews by quality. Existing methods largely combine review texts and star ratings for helpfulness prediction. However, star ratings are used in a way that has either little representation capacity or limited interaction with review texts. As a result, rating information has yet to be fully exploited during the combination. This paper aims to overcome the two drawbacks. A deep interactive architecture is proposed to learn the text–rating interaction (TRI) for helpfulness modeling. TRI enlarges the representation capacity of star ratings while enhancing the influence of rating information on review texts. TRI is evaluated on six real-world domains of the Amazon 5-Core dataset. Extensive experiments demonstrate that TRI can better predict review helpfulness and beat the state of the art. Ablation studies and qualitative analysis are provided to further understand model behaviors and the learned parameters.

Cervical cancer ranks as the second most common cancer in women worldwide. In clinical practice, colposcopy is an indispensable part of screening for cervical intraepithelial neoplasia (CIN) grades and cervical cancer but exhibits high misdiagnosis rate. Existing computer-assisted algorithms for analyzing cervigram images have neglected that colposcopy is a sequential and multistate process, which is unsuitable for clinical applications. In this work, we construct a cervigram-based recurrent convolutional neural network (C-RCNN) to classify different CIN grades and cervical cancer. Convolutional neural networks are leveraged to extract spatial features. We develop a sequence-encoding module to encode discriminative temporal features and a multistate-aware convolutional layer to integrate features from different states of cervigram images. To train and evaluate the performance of C-RCNN, we leveraged a dataset of 4,753 real cervigrams and obtained 96.13% test accuracy with a specificity and sensitivity of 98.22% and 95.09%, respectively. Areas under each receiver operating characteristic curves are above 0.94, proving that visual representations and sequential dynamics can be jointly and effectively optimized in the training phase. Comparative analysis demonstrated the effectiveness of the proposed C-RCNN against competing methods, showing significant improvement over only focusing on a single frame. This architecture can be extended to other applications in medical image analysis.

As a powerful measure to alleviate greenhouse gas emissions and global warming issue, new energy vehicle (NEV) has aroused extensive attention from the whole society in recent years. In the past few decades, many studies have been conducted on the dispatch of traditional fuel-driven vehicles. As a means of transportation, NEV has the characteristics of fuel-driven vehicles, but the dispatch is different because of its unique refueling manner. With the popularization of NEV, its unique dispatch research is imminent. This paper comprehensively considers electricity and charging piles during the NEV dispatch (NEVD) process. An NEVD framework containing a novel dispatch model is proposed, which elaborates the application service of NEV. To the best of our knowledge, this study is the first to combine NEVD with service system. Based on the formulated model, an efficient ant colony system (EACS) approach enhanced by pre-selection strategy and local pruning strategy is designed to dispatch NEVs to passengers. Experiments are carried out to investigate the applicable scenarios of ACS-based algorithms. The results verify that the proposed EACS algorithm is an effective and efficient approach to solve the NEVD problem.

Group recommendation has become highly demanded when users communicate in the forms of group activities in online sharing communities. These group activities include student group study, family TV program watching, friends travel decision, etc. Existing group recommendation techniques mainly focus on the small user groups. However, online sharing communities have enabled group activities among thousands of users. Accordingly, recommendation over large groups has become urgent. In this paper, we propose a new framework to accomplish this goal by exploring the group interests and the connections between group users. We first divide a big group into different interest subgroups, each of which contains users closely connected with each other and sharing the similar interests. Then, for each interest subgroup, our framework exploits the connections between group users to collect a comparably compact potential candidate set of media-user pairs, on which the collaborative filtering is performed to generate an interest subgroup-based recommendation list. After that, a novel aggregation function is proposed to integrate the recommended media lists of all interest subgroups as the final group recommendation results. Extensive experiments have been conducted on two real social media datasets to demonstrate the effectiveness and efficiency of our proposed approach.

Bleeding in gastrointestinal tract (GI) is caused by many different diseases and may lead to serious consequence if not being treated correctly. The most effective method to locate bleeding area is using wireless capsule endoscopy (WCE). However, the amount of WCE images of one patient is so large that even a professional physician may take a long time on analyzing them, and human errors may also occur with work time increasing. Thus the computer-aided diagnosis methods become more attractive. In this paper, we propose a novel deep learning based method for WCE images bleeding area segmentation. We design multi-stage architecture and attention blocks to deal with small areas segmentation. The latter stages' input is the combination of feature maps transferred from former stages so that even very deep layers can obtain small areas features, and attention blocks help shallow layers to better extract small areas features thus they can transfer more useful information to latter stages. Extensive experiments are conducted on public available WCE image dataset to show the effect of multi-stage architecture and attention blocks. Compared with other bleeding areas segmentation methods, our approach achieves state-of-the-art performance with 98.5% overall accuracy, 90.1% mean accuracy and 86.3% mean intersection over union (IoU). There is a 10.7% improvement on mean IoU compared with the previous state-of-the-art WCE bleeding segmentation method.

Due to the high degree of air pollution, high smoking rate and poor production protection conditions during the industrialization process, the incidence of pulmonary diseases such as pulmonary cancer and chronic obstructive pulmonary disease has been maintained at a high level in the world and has shown an increasing trend, which has become one of the diseases with the highest mortality rate. In recent years, with the rapid development of artificial intelligence technology, the intelligent assisted diagnosis and surgery technology of pulmonary CT images has made great progress, and played an important role in the early diagnosis and precise treatment of pulmonary diseases. This paper mainly discusses the development history of image-assisted diagnosis and surgery technology for pulmonary diseases, as well as the method of segmentation and evaluation of pulmonary tissue and lesion, and the clinical application of pulmonary intelligent assisted diagnosis and surgery systems.

Segmentation of lung parenchyma as a pretreatment step for the detection of some lung lesions requires high accuracy to provide more reliable information for lesion detection. In this paper, we proposed a segmentation method of lung parenchyma from chest CT Images by Dual U-Net algorithm based on the characteristics of different lung region. Firstly, the original lung region is extracted from the full chest CT images of patient by an automatic threshold selection method. Then, the images of the different regions of lung is obtained by calculating the area. Finally, the Dual U-Net is trained according the different lung regions. The first U-Net algorithm operates these middle chest images and other images are operated by the second U-Net algorithm to reduce the interference of other images. The experimental results shown that the segmenting results of lung parenchyma by this method are more accurate than the results by single U-Net and U-Net++ algorithm.

ECG heartbeat classification plays a vital role in diagnosis of cardiac arrhythmia. Traditional heartbeat classification methods rely on handcrafted features and often fail to learn potentially abstract patterns, while current deep learning based methods usually consist of complex convolutional and recursive structures. In this paper, considering the time sequence property of ECG signals, we propose a novel heartbeat classification method based on Transformer, a sequence-to-sequence model with a relatively simple architecture and higher degree of parallelism. To adapt Transformer to our problem, we use only the encoder part of the model for that ECG signals do not have translation signals. We also replace the dropout layers with batch normalization layers, considering our small-size feature space and the natural differences among patients. Further, we fuse handcrafted temporal features with the features learnt by Transformer to better capture rhythmic patterns in ECG signals. We have conducted extensive experiments on the MIT-BIH arrhythmia database using both the original dataset and an augmented dataset with more balanced data. The results show that our model can achieve 99.62% accuracy, 95.09% precision and 94.12% sensitivity on the original dataset and 99.87% accuracy, 99.74% precision and 99.74% sensitivity on the augmented dataset. Besides, we have performed multiple experiments against state-of-the-art methods using their assessment strategies. Experimental results indicate that our model can achieve better performance under most circumstances.

The aircraft arrival scheduling (AAS) problem is an important issue in airport management that requires well-designed scheduling approaches to help improve the operating efficiency of airports. However, most of the existing approaches are based on a single runway while the multi-runway situation is more common and more complex in reality. In order to solve the multi-runway AAS (MRAAS) problem, this paper proposes a receding horizon control (RHC) based two-level ant colony system (ACS) approach. The RHC divides the problem with receding time windows. Therefore, the number of aircraft considered in each RHC stage is reduced, so that the ACS algorithm can endure less computational burden and search for good scheduling sufficiently. Moreover, in each RHC stage to schedule the aircraft, a two-level scheduling strategy is proposed to assist the ACS to deal with the multi-runway difficulty. During the first level scheduling, the ACS algorithm schedules aircraft based on a single runway. Then in the second level scheduling, we assign the aircraft to real multi-runways based on both the obtained sequence of the first level scheduling and the real occupancy condition of each runway. We have conducted experiments based on case study and compared the results with first come first serve (FCFS) approach, showing the feasibility as well as the higher performance of the proposed RHC-ACS-MRAAS approach.

This paper puts forward a LSTM and CNN based assemble neural network framework to distinguish different types of arrhythmias by integrating stacked bidirectional long shot-term memory (SB-LSTM) network and two-dimensional convolutional neural network (TD-CNN). Particularly, SB-LSTM is used to mine the long-term dependencies contained in electrocardiogram (ECG) from two directions to model the overall variation trends of ECG, while TD-CNN aims at extracting local information of ECG to characterize the local features of ECG. Moreover, we design an ensemble empirical mode decomposition (EEMD) based signal decomposition layer and a support vector machine based intermediate result fusion layer, by which ECG can be analyzed more effectively, and the final classification results can be more accurate and robust. Experimental results on public INCART arrhythmia database show that our model surpasses three state-of-the-art methods, and obtains 99.1% of accuracy, 99.3% of sensitivity and 98.5% of specificity.

As one of the most popular services over online platforms, social recommendation has attracted increasing research efforts recently. Among all the recommendation tasks, an important one is item recommendation over high speed social media streams. Existing stream recommendation techniques are not effective for handling social users with diverse interests. Meanwhile, approaches for recommending items to a particular user are not efficient when applied to a huge number of users over high speed streams. In this paper, we propose a novel framework for the social recommendation over streams. Specifically, we first propose a novel Bi-Layer Hidden Markov Model (BiHMM) that adaptively captures the users' behaviors and their interactions with influential official accounts to predict their long-term and short-term interests. Then, we design a new probabilistic entity matching scheme for identifying the relevance score of a streaming item to a user. Moreover, we propose a novel index scheme called CPPse-index for improving the efficiency of our solution. Extensive tests are conducted to prove the superiority of our approach in terms of the recommendation quality and time cost.

Regularities analysis for prescriptions is a significant task for traditional Chinese medicine (TCM), both in inheritance of clinical experience and in improvement of clinical quality. Recently, many methods have been proposed for regularities discovery, but this task is challenging due to the quantity, sparsity and free-style of prescriptions. In this paper, we address the specific problem of regularities discovery and propose a graph embedding based framework for regularities discovery for massive prescriptions. We model this task as a relation prediction in which the correlation of two herbs or of herb and symptom are incorporated to characterize the different relationships. Specifically, we first establish a heterogeneous network with herbs and symptoms as its nodes. We develop a bipartite embedding model termed HS2Vec to detect regularities, which explores multiple relations of herbherb, and herb-symptom based on the heterogeneous network. Experiments on four real-world datasets demonstrate that the proposed framework is very effective for regularities discovery.

Electrocardiogram (ECG) signal based arrhythmias classification is an important task in healthcare field. Based on domain knowledge and observation results from large scale data, we find that accurately classifying different types of arrhythmias relies on three key characteristics of ECG: overall variation trends, local variation features and their relative location. However, these key factors are not yet well studied by existing methods. To tackle this problem, we design an attention-based hybrid LSTM-CNN model which is comprised of a stacked bidirectional LSTM (SB-LSTM) and a two-dimensional CNN (TD-CNN). Specifically, SB-LSTM and TD-CNN are utilized to extract the overall variation trends and local features of ECG, respectively. Furthermore, we add a trend attention gate (TAG) to SB-LSTM, meanwhile, add a feature attention mechanism (FAM) and a location attention mechanism (LAM) to TD-CNN. Thus, the effects of important trends and features at key locations in ECG can be enhanced, which is conducive to obtaining a better understanding of the fluctuation pattern of ECG. Experimental results on the MIT-BIH arrhythmias dataset indicate that our model outperforms three state-of-the-art methods, and achieve 99.3% of accuracy, 99.6% of sensitivity and 98.1% of specificity, respectively.

With the explosive growth of online service platforms, increasing number of people and enterprises are doing everything online. In order for organizations, governments, and individuals to understand their users, and promote their products or services, it is necessary for them to analyse big data and recommend the media or online services in real time. Effective recommendation of items of interest to consumers has become critical for enterprises in domains such as retail, e-commerce, and online media. Driven by the business successes, academic research in this field has also been active for many years. Through many scientific breakthroughs have been achieved, there are still tremendous challenges in developing effective and scalable recommendation systems for real-world industrial applications. Existing solutions focus on recommending items based on pre-set contexts, such as time, location, weather etc. The big data sizes and complex contextual information add further challenges to the deployment of advanced recommender systems. This workshop aims to bring together researchers with wide-ranging backgrounds to identify important research questions, to exchange ideas from different research disciplines, and, more generally, to facilitate discussion and innovation in the area of context-aware recommender systems and big data analytics.

Abstract The problem of risk classification and prediction, an essential research direction, aiming to identify and predict risks for various applications, has been researched in this paper. To identify and predict risks, numerous researchers build models on discovering hidden information of a label (positive credit or negative credit). Fuzzy logic is robust in dealing with ambiguous data and, thus, benefits the problem of classification and prediction. However, the way to apply fuzzy logic optimally depends on the characteristics of the data and the objectives, and it is extraordinarily tricky to find such a way. This paper, therefore, proposes a general membership function model for fuzzy sets (GMFMFS) in the fuzzy decision tree and extend it to the fuzzy random forest method. The proposed methods can be applied to identify and predict the credit risks with almost optimal fuzzy sets. In addition, we analyze the feasibility of our GMFMFS and prove our GMFMFS‐based linear membership function can be extended to a nonlinear membership function without a significant increase in computing complex. Our GMFMFS‐based fuzzy decision tree is tested with a real dataset of US credit, Susy dataset of UCI, and synthetic datasets of big data. The results of experiments further demonstrate the effectiveness and potential of our GMFMFS‐based fuzzy decision tree with linear membership function and nonlinear membership function.

A phrase is a natural, meaningful, and essential semantic unit. In topic modeling, visualizing phrases for individual topics is an effective way to explore and understand unstructured text corpora. However, from phrase quality and topical cohesion perspectives, the outcomes of existing approaches remain to be improved. Usually, the process of topical phrase mining is twofold: phrase mining and topic modeling. For phrase mining, existing approaches often suffer from order sensitive and inappropriate segmentation problems, which make them often extract inferior quality phrases. For topic modeling, traditional topic models do not fully consider the constraints induced by phrases, which may weaken the cohesion. Moreover, existing approaches often suffer from losing domain terminologies since they neglect the impact of domain-level topical distribution. In this paper, we propose an efficient method for high quality and cohesive topical phrase mining. A high quality phrase should satisfy frequency, phraseness, completeness, and appropriateness criteria. In our framework, we integrate quality guaranteed phrase mining method, a novel topic model incorporating the constraint of phrases, and a novel document clustering method into an iterative framework to improve both phrase quality and topical cohesion. We also describe efficient algorithmic designs to execute these methods efficiently. The empirical verification demonstrates that our method outperforms the state-of-the-art methods from the aspects of both interpretability and efficiency.

Sparse topic models (STMs) are widely used for learning a semantically rich latent sparse representation of short texts in large scale, mainly by imposing sparse priors or appropriate regularizers on topic models. However, it is difficult for these STMs to model the sparse structure and pattern of the corpora accurately, since their sparse priors always fail to achieve real sparseness, and their regularizers bypass the prior information of the relevance between sparse coefficients. In this paper, we propose a novel Bayesian hierarchical topic models called Bayesian Sparse Topical Coding with Poisson Distribution (BSTC-P) on the basis of Sparse Topical Coding with Sparse Groups (STCSG). Different from traditional STMs, it focuses on imposing hierarchical sparse prior to leverage the prior information of relevance between sparse coefficients. Furthermore, we propose a sparsity-enhanced BSTC, Bayesian Sparse Topical Coding with Normal Distribution (BSTC-N), via mathematic approximation. We adopt superior hierarchical sparse inducing prior, with the purpose of achieving the sparsest optimal solution. Experimental results on datasets of Newsgroups and Twitter show that both BSTC-P and BSTC-N have better performance on finding clear latent semantic representations. Therefore, they yield better performance than existing works on document classification tasks.

Community detection is a fundamental and widely-studied problem that finds all densely-connected groups of nodes and well separates them from others in graphs. With the proliferation of rich information available for entities in real-world networks, it is useful to discover communities in attributed graphs where nodes tend to have attributes. However, most existing attributed community detection methods directly utilize the original network topology leading to poor results due to ignoring inherent community structures. In this paper, we propose a novel embedding based model to discover communities in attributed graphs. Specifically, based on the observation of densely-connected structures in communities, we develop a novel community structure embedding method to encode inherent community structures via underlying community memberships. Based on node attributes and community structure embedding, we formulate the attributed community detection as a nonnegative matrix factorization optimization problem. Moreover, we carefully design iterative updating rules to make sure of finding a converging solution. Extensive experiments conducted on 19 attributed graph datasets with overlapping and non-overlapping ground-truth communities show that our proposed model CDE can accurately identify attributed communities and significantly outperform 7 state-of-the-art methods.

Min Peng, Qianqian Xie, Yanchun Zhang, Hua Wang, Xiuzhen Zhang, Jimin Huang, Gang Tian. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2018.

Hypertension is a common cardiovascular disease, which will lead to severe complications without timely treatment. Accurate hypertension identification is essential to preventing the condition deteriorated. However, the state of art hypertension identification methods only extract features from very few aspects, and hence have limited identification accuracy. Furthermore, they only can judge whether the subjects are hypertensive or not, more meaningful information (such as, why the subjects suffer from hypertension) that can help doctors to improve their diagnosis level are absent. In this paper, we propose a class association rules-based method to identify hypertension. Particularly, its key idea is to utilize the relationship existing in multi-dimensional features to characterize hypertension pattern more effectively, in order to improve the identification performance. In addition, it can also generate a set of class association rules (CARs), which can reflect the subjects' physiological status and are proved to be useful for doctors to analyze subject's condition deeply. Experiments based on 128 subjects (61 hypertension patients and 67 healthy subjects) shows that our method outperforms the baseline methods and the accuracy, precision and recall reach 85.2%, 85.0%, and 83.6%, respectively. Additionally, a user study based on five clinicians demonstrates the utility of the generated CARs.

Extracting web content is to obtain the required data embedded in web pages, usually including structured records, such as product information, and text content, such as news. Web pages use a large number of HTML tags to organize and to present various information. Both knowing little about the structures of web pages and mixing kinds of information in web pages are making the extraction process very challenging to guarantee extraction performance and extraction adaptability. This study proposes a unified web content extraction framework that can be applied in various web environments to extract both structured records and text content. First, we construct a characteristic container to hold kinds of characteristics related with extraction objectives, including visual text information, content semantics(instead of HTML tag semantics), web page structures, etc. Second, the above characteristics are integrated into an extraction framework for extraction decisions on different web sites. Especially, we put forward different strategies, path aggregation for extracting text content and HMM model for structured records, to locate the extraction area by exploiting both those extraction characteristics. Comparative experiments on multiple web sites with popular extraction methods, including CETR, CETD and CNBE, show that our proposed extraction method can provide better extraction precision and extraction adaptability.

Space-time template matching is considered as a promising approach for human action recognition. However, a major drawback of template-based methods is computational overhead due to matching in spatial domain. Recently, space-time correlation-based action filters have been proposed for recognizing human actions in frequency domain. These action filters present reduction in time complexity as Fourier transform-based matching is faster than spatial template matching. However, the utility of such action filters is challenged due to a number of factors: 1) inability to deal with view variations due to implicit lack of support for view-invariance; 2) these filters can be trained only for one action class at a time, and separate filters are required for each action class with increased computational overhead; 3) these filters simply take average of similar action instances and behave no better than average filters; and 4) slightly misaligned action data sets create problems as these filters are not shift-invariant. In this paper, we try to address these shortcomings by proposing an advanced space-time filtering framework for recognizing human actions despite large viewpoint variations. Rather than using crude intensity values, we use 3D tensor structure at each pixel, which characterizes the most common local motion in action sequences. Discrete tensor Fourier transform is then applied to achieve frequency domain representations. Then, we form view clusters from multiple view action data and use space-time correlation filtering to achieve discriminative view representations. These representations are used in an innovative way to achieve action recognition despite viewpoint variations. Extensive experimentation is performed on well-known multiple view action data sets, including IXMAS, WVU, and N-UCLA action data set. A detailed performance comparison with the existing view-invariant action recognition techniques indicates that our approach works equally well for RGB and RGB-D video data with increased accuracy and efficiency.

This article presents an unsupervised multi-view hierarchical embedding (UMHE) framework to sufficiently reveal the intrinsic topical knowledge in social events. Event-oriented topics are highly related to such events as it can provide explicit descriptions of what have happened in social community. In many real-world cases, however, it is difficult to include all attributes of microblogs, more often, textual aspects only are available. Traditional topic modelling methods have failed to generate event-oriented topics with the textual aspects, since the inherent relations between topics are often overlooked in these methods. Meanwhile, the metrics in original word vocabulary space might not effectively capture semantic distances. Our UMHE framework overcomes the severe information deficiency and poor feature representation. The UMHE first develops a multi-view Bayesian rose tree to preliminarily generate prior knowledge for latent topics and their relations. With such prior knowledge, we design an unsupervised translation-based hierarchical embedding method to make a better representation of these latent topics. By applying self-adaptive spectral clustering on the embedding space and the original space concomitantly, we eventually extract event-oriented topics in word distributions to express social events. Our framework is purely data-driven and unsupervised, without any external knowledge. Experimental results on TREC Tweets2011 dataset and Sina Weibo dataset demonstrate that the UMHE framework can construct hierarchical structure with high fitness, but also yield topic embeddings with salient semantics; therefore, it can derive event-oriented topics with meaningful descriptions.

There are a variety of well-designed specification-modelling-languages serving Internet services, however, none of them is capable of describing the special features of cloud services, from both technical and business points of view. The Unified Service Description Language (USDL) provides a new way to describe Internet services from business, operational, and technical perspectives. Nevertheless, there are various issues with USDL: it lacks a comprehensive specification model, particularly for cloud services, lacks a user-centric specification modeling paradigm, lacks a mechanism to measure cloud service attributes and to present the association relationship and re-usability of the attributes, and lacks semantic representation of cloud services. Based on the above issues, we propose a unified semantic Cloud Service Description Model (CSDM) in this paper. The proposed model will be extended from the basic structure of USDL, by defining cloud-service-specific attributes. Furthermore, an additional module, named transaction module, will be defined, which models the rating system of cloud services from several aspects, such as risk, trust, and reputation. The transaction module facilitates the capability of CSDM with regard to service ranking, and enhances its flexibility and extensibility by providing an extensible sub-module. In addition, we design an OWL-based annotation system to enrich the semantic expressivity of this model. Finally, a case study is provided to explain the application of this model in actual cloud services.

Service Oriented Computing (SOC) has initially developed for the Internet, but also identified as an appealing computing paradigm for developing applications in distributed wireless environments. The open nature of wireless medium may expose services to a variety of unauthorized third parties (eavesdroppers), resulting in insecure service interactions, while cooperative jamming is promising to provide a strong form of security. This paper focuses on security performance study of wireless communications for service interactions among different parties in SOC. More specifically, this paper establishes a theoretical framework for the study of eavesdropper-tolerance capability (i.e., the maximum number of eavesdroppers that can be tolerated) in a two-hop wireless network, where the cooperative jamming is adopted to ensure security defined by secrecy outage probability (SOP) and opportunistic relaying is adopted to guarantee reliability defined by transmission outage probability (TOP). For the concerned network, exact modeling for SOP and fine approximation for TOP are first conducted based on the Central Limit Theorem. With the help of SOP and TOP models and also the Stochastic Ordering Theory, the model for eavesdropper-tolerance capability analysis is then developed. Finally, extensive simulation and numerical results are provided to illustrate the efficiency of our theoretical framework as well as the eavesdropper-tolerance capability of the concerned network from adopting cooperative jamming and opportunistic relaying.

on Web Information Systems Engineering (WISE 2016) was held in Shanghai, China, November 7-10, 2016.Building on the success of its predecessors, WISE 2016 continues to be a major international forum for researchers, professionals, and industrial practitioners to share their knowledge in the rapidly growing area of Web technologies, methodologies, and applications.The first WISE event took place in Hong Kong, China (2000).Then the trip continued to Kyoto, Japan (2001); Singapore (2002);

There has been a continuing demand for traditional and complementary medicine worldwide. A fundamental and important topic in Traditional Chinese Medicine (TCM) is to optimize the prescription and to detect herb regularities from TCM data. In this paper, we propose a novel clustering model to solve this general problem of herb categorization, a pivotal task of prescription optimization and herb regularities. The model utilizes Random Walks method, Bayesian rules and Expectation Maximization(EM) models to complete a clustering analysis effectively on a heterogeneous information network. We performed extensive experiments on the real-world datasets and compared our method with other algorithms and experts. Experimental results have demonstrated the effectiveness of the proposed model for discovering useful categorization of herbs and its potential clinical manifestations.

Data summarization that presents a small subset of a dataset to users has been widely applied in numerous applications and systems. Many datasets are coded with hierarchical terminologies, e.g., the international classification of Diseases-9, Medical Subject Heading, and Gene Ontology, to name a few. In this paper, we study the problem of selecting a diverse set of k elements to summarize an input dataset with hierarchical terminologies, and visualize the summary in an ontology structure. We propose an efficient greedy algorithm to solve the problem with (1-1/e)≈ 62%-approximation guarantee. Preliminary experimental results on real-world datasets show the effectiveness and efficiency of the proposed algorithm for data summarization.

Determining appropriate statistical distributions for modeling text corpora is important for accurate estimation of numerical characteristics. Based on the validity of the test on a claim that the data conforms to Poisson distribution we propose Poisson decomposition model (PDM), a statistical model for modeling count data of text corpora, which can straightly capture each document's multidimensional numerical characteristics on topics. In PDM, each topic is represented as a parameter vector with multidimensional Poisson distribution, which can be easily normalized to multinomial term probabilities and each document is represented as measurements on topics and thereby reduced to a measurement vector on topics. We use gradient descent methods and sampling algorithm for parameter estimation. We carry out extensive experiments on the topics produced by our models. The results demonstrate our approach can extract more coherent topics and is competitive in document clustering by using the PDM-based features, compared to PLSI and LDA.

Consensus clustering aims to find a single partition of data that agrees as much as possible with existing basic partitions. Given its robustness and generalizability, consensus clustering has emerged as a promising solution to find cluster structures inside heterogeneous big data rising from various application domains. In the area of fuzzy systems, however, research along this line is still in its initial stage with some unsystematic algorithmic studies. Finding a fuzzy consensus partition from multiple fuzzy basic partitions in an efficient, flexible, and robust way is still an exciting open problem calling for further investigation. In light of this, this paper provides a systematic study of fuzzy consensus clustering (FCC) from a utility perspective. Specifically, we first define the objective function of FCC clearly using the novel fuzzified contingency matrix. We then derive a family of FCC Utility functions termed as FCCU that can transform FCC to a weighted piecewise fuzzy $c$ -means clustering (piFCM) problem. This helps us to establish an algorithmic framework for FCC with flexible choice of utility functions, and speeds FCC significantly with a FCM-like iterative process of piFCM. To meet the big data challenge, we further parallelize FCC on the Spark platform with both vertical and horizontal segmentation schemes. Extensive experiments on various real-world datasets demonstrate the excellent performance of FCC, even with a majority of poor basic partitions. In particular, our method exhibits interesting potential for big data clustering in two real-life applications concerned with online event detection and overlapping community detection, respectively.

Compressing textstreams generated by social networks can both reduce storage consumption and improve efficiency such as fast searching. However, the compression process is a challenge due to the large scale of textstreams. In this article, we propose a textstream compression framework based on compressed sensing theory and design a series of matching parallel procedures. The new approach uses a linear projection technique in the textstream compression process, achieving fast compression speed and low compression ratio. Two processes are executed by designing elaborated parallel procedures for efficient compressing and decompressing of large-scale textstreams. The decompression process is implemented for approximate solutions of underdetermined linear systems. Experimental results show that the new method can efficiently achieve the compression and decompression tasks on a large amount of text generated by social networks.

on Web Information Systems Engineering (WISE 2015) was held in Miami, Florida, USA, November 1-3, 2015.Building on the success of its predecessors, WISE 2015 continues to be a major international forum for researchers, professionals, and industrial practitioners to share their knowledge in the rapidly growing area of Web technologies, methodologies, and applications.The first WISE event took place in Hong Kong, China (2000).Then the trip continued to Kyoto, Japan (2001); Singapore (2002);

With the increase of data and information, anomaly management has been attracting much more attention and become an important research topic gradually. Previous literatures have advocated anomaly discovery and identification ignoring the fact that practice needs anomaly detection in advance (anomaly prediction) but anomaly detection with post-hoc analysis. Given this apparent gap, this research proposes a new approach for anomaly prediction based on PCA (principle component analysis) and information entropy theory, and support vector regression. The main idea of anomaly prediction is to train the historical data and to identify and recognize outlier data according to previous streams patterns and trends. The explorative results of SO2 concentration of exhaust gas in WFGD (Wet Flue Gas Desulfurization) demonstrate a good performance (efficient and accurate) of the target data prediction approach. This robust and novel method can be used to detect and predict the anomaly in data streams, and applied to fault prediction, credit card fraud prediction, intrusion prediction in cyber-security, malignant diagnosis, etc.

Diagnosis of neurological diseases is a growing concern and one of the most difficult challenges for modern medicine. According to the World Health Organisation’s recent report, neurological disorders, such as epilepsy, Alzheimer’s disease and stroke to headache, affect up to one billion people worldwide. An estimated 6.8 million people die every year as a result of neurological disorders. Current diagnosis technologies (e.g. magnetic resonance imaging, electroencephalogram) produce huge quantity data (in size and dimension) for detection, monitoring and treatment of neurological diseases. In general, analysis of those medical big data is performed manually by experts to identify and understand the abnormalities. It is really difficult task for a person to accumulate, manage, analyse and assimilate such large volumes of data by visual inspection. As a result, the experts have been demanding computerised diagnosis systems, called “computer-aided diagnosis (CAD)” that can automatically detect the neurological abnormalities using the medical big data. This system improves consistency of diagnosis and increases the success of treatment, save lives and reduce cost and time. Recently, there are some research works performed in the development of the CAD systems for management of medical big data for diagnosis assessment. This paper explores the challenges of medical big data handing and also introduces the concept of the CAD system how it works. This paper also provides a survey of developed CAD methods in the area of neurological diseases diagnosis. This study will help the experts to have some idea and understanding how the CAD system can assist them in this point.

Uncertain data streams have been widely generated in many Web applications. The uncertainty in data streams makes anomaly detection from sensor data streams far more challenging. In this article, we present a novel framework that supports anomaly detection in uncertain data streams. The proposed framework adopts the wavelet soft-thresholding method to remove the noises or errors in data streams. Based on the refined data streams, we develop effective period pattern recognition and feature extraction techniques to improve the computational efficiency. We use classification methods for anomaly detection in the corrected data stream. We also empirically show that the proposed approach shows a high accuracy of anomaly detection on several real datasets.

Pair-wise ranking methods have been widely used in recommender systems to deal with implicit feedback. They attempt to discriminate between a handful of observed items and the large set of unobserved items. In these approaches, however, user preferences and item characteristics cannot be estimated reliably due to overfitting given highly sparse data. To alleviate this problem, in this paper, we propose a novel hierarchical Bayesian framework which incorporates ``bag-of-words'' type meta-data on items into pair-wise ranking models for one-class collaborative filtering. The main idea of our method lies in extending the pair-wise ranking with a probabilistic topic modeling. Instead of regularizing item factors through a zero-mean Gaussian prior, our method introduces item-specific topic proportions as priors for item factors. As a by-product, interpretable latent factors for users and items may help explain recommendations in some applications. We conduct an experimental study on a real and publicly available dataset, and the results show that our algorithm is effective in providing accurate recommendation and interpreting user factors and item factors.

To date, data generates and arrives in the form of stream to propagate discussions of public events in microblog services. Discovering event-oriented topics from the stream will lead to a better understanding of the change of public concern. However, as the massive scale of the data stream, traditional static topic models, such as LDA, are no longer fit for topic detection and tracking tasks. In this paper, we propose a central topic model (CenTM), where a Multi-view Clustering algorithm with Two-phase Random Walk (MC-TRW) is devised to aggregate the LDA's latent topics into central topics. Furthermore, we leverage the aggregation of central topics alternately with MC-TRW and sequential topic inference to improve the scalability in the stream fashion, so as to derive the dynamic central topic model (DCenTM). Specifically, our model is able to uncover the intrinsic characteristics of the central topics and predict the trend of their intensity along a life cycle. Experimental results demonstrate that the proposed central topic model is event-oriented and of high generalization, it therefore can dispose the topic trend prediction effectively and precisely in massive data stream.

The creation of sharing communities has resulted in the astonishing increasing of digital videos, and their wide applications in the domains such as entertainment, online news broadcasting etc. The improvement of these applications relies on effective solutions for social user access to video data. This fact has driven the recent research interest in social recommendation in shared communities. Although certain effort has been put into video recommendation in shared communities, the contextual information on social users has not been well exploited for effective recommendation. In this paper, we propose an approach based on the content and social information of videos for the recommendation in sharing communities. Specifically, we first exploit a robust video cuboid signature together with the Earth Mover's Distance to capture the content relevance of videos. Then, we propose to identify the social relevance of clips using the set of users belonging to a video. We fuse the content relevance and social relevance to identify the relevant videos for recommendation. Following that, we propose a novel scheme called sub-community-based approximation together with a hash-based optimization for improving the efficiency of our solution. Finally, we propose an algorithm for efficiently maintaining the social updates in dynamic shared communities. The extensive experiments are conducted to prove the high effectiveness and efficiency of our proposed video recommendation approach.

Diabetes, hypertension, cerebral arteriosclerosis and other diseases have become great threats to human health, so it is urgent to explore their initial symptoms for early prevention and treatment. As an important part of small and medium-sized vessels of human body, retinal vessel is the only deep capillary that can be non-traumatic directly observed and its morphology, such as vascular diameter, shape and distribution, is deeply influenced by these diseases. So an effective vascular detection and features measurement will help make more accurate diagnosis of these diseases. This paper proposes a local adaptive segmentation to detect more accurate retinal vascular network from abnormal retinal images which contain red and bright lesions. The retinal image is firstly segmented by weighted entropy with probability segmentation to detect preliminary vascular network. Then a two-dimensional partial differential matched filter is introduced into segmentation to differentiate lesions from vascular network based on a vascular property. The algorithm has been tested and compared with other vascular network segmentation algorithms on the publicly available STARE database since it contains retinal images where the vascular structure has been precisely marked by two experts. The experiments demonstrate that our approach is capable of detecting the vascular network effectively, offering a better segmentation results, especially on abnormal cases. Because of its effectiveness, simplicity and robustness for different image conditions, it is suitable for automated vascular analysis.

With the advent of Cloud computing and subsequent big data, online decision makers usually find it difficult to make informed decisions because of the great amount of irrelevant, uncertain, or inaccurate information. In this paper, we explore the application of multicriteria decision-making (MCDM) techniques in the area of Cloud computing and big data, to find an efficient way of dealing with criteria relations and fuzzy knowledge based on a great deal of information. We propose a MCDM framework, which combines the ISM-based and ANP-based techniques, to model the interactive relations between evaluation criteria, and to handle data uncertainties. We present an application of Cloud service selection to prove the efficiency of the proposed framework, in which a user-oriented sigmoid utility function is designed to evaluate the performance of each criterion.

Online health information services and self diagnosis systems become popular recent years. We propose a computing model for collaborative medical diagnosis through multi agent argumentation. In this model, the agents are able to communicate with each other to share information, critique and verify each other's knowledge, and collaboratively make diagnosis based on multiple agents' knowledge through an argumentation process. Fuzzy Petri Net (FPN) is adopted as the agents' knowledge model. Different from the commonly used FPNs that assign tokens in places, we assign tokens on arcs and also give places capability in controlling the inference of FPN. The FPN based argumentation is automated with algorithms. The proposed model can be employed to achieve collaborative healthcare diagnosis systems, where agents with different expertise collaboratively argue with each other to come up with a mutually agreed diagnosis.

With the advance of computing and electronic technology, quantitative data, for example, continuous data (i.e., sequences of floating point numbers), become vital and have wide applications, such as for analysis of sensor data streams and financial data streams. However, existing association rule mining generally discover association rules from discrete variables, such as boolean data (`O' and `l') and categorical data (`sunny', `cloudy', `rainy', etc.) but very few deal with quantitative data. In this paper, a novel optimized fuzzy association rule mining (OFARM) method is proposed to mine association rules from quantitative data. The advantages of the proposed algorithm are in three folds: 1) propose a novel method to add the smoothness and flexibility of membership function for fuzzy sets; 2) optimize the fuzzy sets and their partition points with multiple objective functions after categorizing the quantitative data; and 3) design a two-level iteration to filter frequent-item-sets and fuzzy association-rules. The new method is verified by three different data sets, and the results have demonstrated the effectiveness and potentials of the developed scheme.

QoS-based service rating has made positive contributions to the area of service selection. Especially for Cloud service users, the right decision when choosing suitable Cloud services can help them improve user satisfaction and trading revenues. This work aims to address the issue of uncertainty in service requests, service descriptions, user and expert preferences, as well as evaluation criteria in a MCDM-based service selection procedure. A hybrid fuzzy framework for Cloud service selection is proposed, addressing the challenge using three approaches: a fuzzy-ontology-based approach for function matching and service filtering, a fuzzy AHP technique for informed criterion weighting, and, a fuzzy TOPSIS approach for service ranking.

Unlike in general recommendation scenarios where a user has only a single role, users in trust rating network, e.g. Epinions, are associated with two different roles simultaneously: as a truster and as a trustee. With different roles, users can show distinct preferences for rating items, which the previous approaches do not involve. Moreover, based on explicit single links between two users, existing methods can not capture the implicit correlation between two users who are similar but not socially connected. In this paper, we propose to learn dual role preferences (truster/trustee-specific preferences) for trust-aware recommendation by modeling explicit interactions (e.g., rating and trust) and implicit interactions. In particular, local links structure of trust network are exploited as two regularization terms to capture the implicit user correlation, in terms of truster/trustee-specific preferences. Using a real-world and open dataset, we conduct a comprehensive experimental study to investigate the performance of the proposed model, RoRec. The results show that RoRec outperforms other trust-aware recommendation approaches, in terms of prediction accuracy.

With the rapid development of Internet, the amount of information on the Web grows explosively, people often feel puzzled and helpless in finding and getting the information they really need. For overcoming this problem, recommender systems such as s

Supported by the technical advances and the commercial success of GPS-enabled mobile devices, geo-tagged photos have drawn plenteous attention in research community. The explosive growth of geo-tagged photos enables many large-scale applications, such as location-based photo browsing, landmark recognition, etc. Meanwhile, as the number of geo-tagged photos continues to climb, new challenges are brought to various applications. The existence of massive near-duplicate geo-tagged photos jeopardizes the effective presentation for the above applications. A new dimension in the search and presentation of geo-tagged photos is urgently demanded. In this paper, we devise a location visualization framework to efficiently retrieve and present diverse views captured within a local proximity. Novel photos, in terms of capture locations and visual content, are identified and returned in response to a query location for diverse visualization. For real-time response and good scalability, a new Hybrid Index structure which integrates R-tree and Geographic Grid is proposed to quickly identify the Maximal Near-duplicate Photo Groups (MNPG) in the query proximity. The most novel photos from different groups are then returned to generate diverse views on the location. Extensive experiments on synthetic and real-life photo datasets prove the novelty and efficiency of our methods.

Online social networks (OSN) are facing challenges since they have been extensively applied to different domains including online social media, e-commerce, biological complex networks, financial analysis, and so on. One of the crucial challenges for OSN lies in information overload and network congestion. The demands for efficient knowledge discovery and data mining methods in OSN have been rising in recent year, particularly for online social applications, such as Flickr, YouTube, Facebook, and LinkedIn. In this paper, a Belief-Desire-Intention (BDI) agent-based method has been developed to enhance the capability of mining online social networks. Current data mining techniques encounter difficulties of dealing with knowledge interpretation based on complex data sources. The proposed agent-based mining method overcomes network analysis difficulties, while enhancing the knowledge discovery capability through its autonomy and collective intelligence.

Data clustering is one of the fundamental research problems in data mining and machine learning. Most of the existing clustering methods, for example, normalized cut and (k)-means, have been suffering from the fact that their optimization processes normally lead to an NP-hard problem due to the discretization of the elements in the cluster indicator matrix. A practical way to cope with this problem is to relax this constraint to allow the elements to be continuous values. The eigenvalue decomposition can be applied to generate a continuous solution, which has to be further discretized. However, the continuous solution is probably mixing-signed. This result may cause it deviate severely from the true solution, which should be naturally nonnegative. In this paper, we propose a novel clustering algorithm, i.e., discriminative nonnegative spectral clustering, to explicitly impose an additional nonnegative constraint on the cluster indicator matrix to seek for a more interpretable solution. Moreover, we show an effective regularization term which is able to not only provide more useful discriminative information but also learn a mapping function to predict cluster labels for the out-of-sample test data. Extensive experiments on various data sets illustrate the superiority of our proposal compared to the state-of-the-art clustering algorithms.

Argumentation plays an important role in promoting deep learning, fostering conceptual change and supporting problem solving. The new “learning by arguing” paradigm leads to new learning opportunities. However, due to the difficulties in modeling human cognition, there are few learning systems that can facilitate argumentation dialogues between systems and learners. Fuzzy Cognitive Map (FCM) is an effective tool in modeling human cognition. This paper proposes an FCM based argumentation model. Based on this model we design an argumentative software agent to facilitate argumentative learning. Provided with the domain knowledge and argumentation capability, the agent is able to simulate a peer learner and automatically conduct argumentative dialogues with learners. The argumentative agent can be applied in general school education as well as special domains like diabetes education and eHealth decision support.

In this paper, we study a problem of protecting privacy of individuals in large public survey rating data. We propose a novel (k,ϵ, l)-anonymity model to protect privacy in large survey rating data, in which each survey record is required to be similar to at least k−1 other records based on the non-sensitive ratings, where the similarity is controlled by ϵ, and the standard deviation of sensitive ratings is at least l. We study an interesting yet non-trivial satisfaction problem of the proposed model, which is to decide whether a survey rating data set satisfies the privacy requirements given by the user. For this problem, we investigate its inherent properties theoretically, and devise a novel slicing technique to solve it. We analyze the computation complexity of the proposed slicing technique and conduct extensive experiments on two real-life data sets, and the results show that the slicing technique is fast and scalable with data size and much more efficient in terms of execution time and space overhead than the heuristic pairwise method.

The current boom of the Web is associated with the revenues originated from Web advertising. As one prevalent type of Web advertising, contextual advertising refers to the placement of the most relevant commercial textual ads within the content of a Web page, so as to provide a better user experience and thereby increase the revenues of Web site owners and an advertising platform. Therefore, in contextual advertising, the relevance of selected ads with a Web page is essential. However, some problems, such as homonymy and polysemy, low intersection of keywords and context mismatch, can lead to the selection of irrelevant textual ads for a Web page, making that a simple keyword matching technique generally gives poor accuracy. To overcome these problems and thus to improve the relevance of contextual ads, in this paper we propose a novel Wikipedia-based matching technique which, using selective matching strategies, selects a certain amount of relevant articles from Wikipedia as an intermediate semantic reference model for matching Web pages and textual ads. We call this technique SIWI: Selective Wikipedia Matching, which, instead of using the whole Wikipedia articles, only matches the most relevant articles for a page (or a textual ad), resulting in the effective improvement of the overall matching performance. An experimental evaluation is conducted, which runs over a set of real textual ads, a set of Web pages from the Internet and a dataset of more than 260 000 articles from Wikipedia. The experimental results show that our method performs better than existing matching strategies, which can deal with the matching over the large dataset of Wikipedia articles efficiently, and achieve a satisfactory contextual advertising effect.

SUMMARY We study the challenges of protecting the privacy of individuals in a large public survey rating data. The survey rating data usually contains both ratings of sensitive and non‐sensitive issues. The ratings of sensitive issues involve personal privacy. Although the survey participants do not reveal any of their ratings, their survey records are potentially identifiable by using information from other public sources. None of the existing anonymization principles (e.g.k‐anonymity,l‐diversity, etc.) can effectively prevent such breaches in large survey rating data sets. In this paper, we tackle the problem by defining a principle called (k, epsilon, l)‐anonymity. The principle requires that, for each transactiontin the given survey rating dataT, at least (k− 1) other transactions inTmust have ratings similar tot, where the similarity is controlled by ε and the standard deviation of sensitive ratings is at leastl. We propose a greedy approach to anonymize the survey rating data that scales almost linearly with the input size, and we apply the method to two real‐life data sets to demonstrate their efficiency and practical utility. Copyright © 2011 John Wiley & Sons, Ltd.

Combining the Semantic Web and the Ubiquitous Web, Web 3.0 is for things . The Semantic Web enables human knowledge to be machine-readable and the Ubiquitous Web allows Web services to serve any thing, forming a bridge between the virtual world and the real world. By using context, Web services can become smarter—that is, aware of the target things' or applications' physical environments, or situations and respond proactively and intelligently. Existing methods for implementing context-aware Web services on Web 2.0 mainly enumerate different implementations corresponding to different attribute values of the context, in order to improve the Quality of Services (QoS). However, things in the physical world are extremely diverse, which poses new problems for Web services: it is difficult to unify the context of things and to implement a flexible smart Web service for things. This article proposes a novel smart Web service based on the context of things, which is implemented using a REpresentational State Transfer for Things (Thing-REST) style, to tackle the two problems. In a smart Web service, the user's description (semantic context) and sensor reports (sensing context) are two channels for acquiring the context of things which are then employed by ontology services to make the context of things machine-readable. With guidance of domain knowledge services, event detection services can analyze things' needs particularly, well through the context of things. We then propose a Thing-REST style to manage the context of things and user context, and to mashup Web services through three structures (i.e., chain, select, and merge) to implement smart Web services. A smart plant watering-service application demonstrates the effectiveness of our method.

Collaborative tagging services provided by various social web sites become popular means to mark web resources for different purposes such as categorization, expression of a preference and so on. However, the tags are of syntactic nature, in a free style and do not reflect semantics, resulting in the problems of redundancy, ambiguity and less semantics. Current tag-based recommender systems mainly take the explicit structural information among users, resources and tags into consideration, while neglecting the important implicit semantic relationships hidden in tagging data. In this study, we propose a Semantic Enhancement Recommendation strategy (SemRec), based on both structural information and semantic information through a unified fusion model. Extensive experiments conducted on two real datasets demonstarte the effectiveness of our approaches.

As a prevalent type of Web advertising, contextual advertising refers to the placement of the most relevant ads into a Web page, so as to increase the number of ad-clicks. However, some problems of homonymy and polysemy, low intersection of keywords etc., can lead to the selection of irrelevant ads for a page. In this paper, we present a new contextual advertising approach to overcome the problems, which uses Wikipedia concept and category information to enrich the content representation of an ad (or a page). First, we map each ad and page into a keyword vector, a concept vector and a category vector. Next, we select the relevant ads for a given page based on a similarity metric that combines the above three feature vectors together. Last, we evaluate our approach by using real ads, pages, as well as a great number of concepts and categories of Wikipedia. Experimental results show that our approach can improve the precision of ads-selection effectively.

This paper proposes a framework for privacy preserving access control policies and mechanisms, and describes algorithms for access policy conflicting problems. The mechanism enforces access policy to data containing personally identifiable information. The key component of the framework is purpose involved access control models (PAC) that provide full support for expressing highly complex privacy-related policies, taking into account features like purposes, conditions and obligations. Policy conflicting problems may arise when new access policies are generated that are possible to be conflicted to existing policies. As a result of the policy conflicts, private information cannot be well protected. The structure of access control policy including conditions and obligations is studied. Based on the access policy, authorization models and policy operations are analysed. Finally comparisons to related works EPAL are presented.

SUMMARY: The visualization of gene structure plays an important role in polymerase chain reaction (PCR) primer design, especially for eukaryotic genes with a number of splice variants that users need to distinguish between via PCR. Here, we describe a visualized web server for primer design named VizPrimer. It utilizes the new information technology (IT) tools, HTML5 to display gene structure and JavaScript to interact with the users. In VizPrimer, the users can focus their attention on the gene structure and primer design strategy, without wasting time calculating the exon positions of splice variants or manually configuring complicated parameters. In addition, VizPrimer is also suitable for the design of PCR primers for amplifying open reading frames and detecting single nucleotide polymorphisms (SNPs). AVAILABILITY: VizPrimer is freely available at http://biocompute.bmi.ac.cn/CZlab/VizPrimer/. The web server supported browsers: Chrome (≥5.0), Firefox (≥3.0), Safari (≥4.0) and Opera (≥10.0). CONTACT: [email protected]; [email protected].

In data gathering wireless sensor networks, data loss often happens due to external faults such as random link faults and hazard node faults, since sensor nodes have constrained resources and are often deployed in inhospitable environments. However, already known fault tolerance mechanisms often bring new internal faults (e.g. out-of-power faults and collisions on wireless bandwidth) to the original network and dissipate lots of extra energy and time to reduce data loss. Therefore, we propose a novel Dual Cluster Heads Cooperation (CoDuch) scheme to tolerate external faults while introducing less internal faults and dissipating less extra energy and time. In CoDuch scheme, dual cluster heads cooperate with each other to reduce extra costs by sending only one copy of sensed data to the Base Station; also, dual cluster heads check errors with each other during the collecting data process. Two algorithms are developed based on the CoDuch scheme: CoDuch-l for tolerating link faults and CoDuch-b for tolerating both link faults and node faults; theory and experimental study validate their effectiveness and efficiency.

Web users exhibit a variety of navigational interests through clicking a sequence of Web pages. Analyses of Web usage data will lead to discovering Web user access patterns, and in turn, facilitating users to locate more preferable Web contents via c

Microdata protection in statistical databases has recently become a major societal concern and has been intensively studied in recent years. Statistical Disclosure Control (SDC) is often applied to statistical databases before they are released for public use. Micro aggregation for SDC is a family of methods to protect micro data from individual identification. SDC seeks to protect micro data in such a way that can be published and mined without providing any private information that can be linked to specific individuals. Micro aggregation works by partitioning the micro data into groups of at least k records and then replacing the records in each group with the centroid of the group. An optimal micro aggregation method must minimize the information loss resulting from this replacement process. The challenge is how to minimize the information loss during the micro aggregation process. This paper presents a pair wise systematic (P-S) micro aggregation method to minimize the information loss. The proposed technique simultaneously forms two distant groups at a time with the corresponding similar records together in a systematic way and then anonymized with the centroid of each group individually. The structure of P-S problem is defined and investigated and an algorithm of the proposed problem is developed. The performance of the P-S algorithm is compared against the most recent micro aggregation methods. Experimental results show that P-S algorithm incurs less than half information loss than the latest micro aggregation methods for all of the test situations.

Extracting knowledge from the transaction records and the personal data of credit card holders has great profit potential for the banking industry. The challenge is to detect/predict bankrupts and to keep and recruit the profitable customers. However, grouping and targeting credit card customers by traditional data-driven mining often does not directly meet the needs of the banking industry, because data-driven mining automatically generates classification outputs that are imprecise, meaningless, and beyond users' control. In this paper, we provide a novel domain-driven classification method that takes advantage of multiple criteria and multiple constraint-level programming for intelligent credit scoring. The method involves credit scoring to produce a set of customers' scores that allows the classification results actionable and controllable by human interaction during the scoring process. Domain knowledge and experts' experience parameters are built into the criteria and constraint functions of mathematical programming and the human and machine conversation is employed to generate an efficient and precise solution. Experiments based on various data sets validated the effectiveness and efficiency of the proposed methods.

Abstract Scientific workflow offers a framework for cooperation between remote and shared resources on a grid computing environment (GCE) for scientific discovery. One major function of scientific workflow is to schedule a collection of computational subtasks in well‐defined orders for efficient outputs by estimating task duration at runtime. In this paper, we propose a novel time computation model based on algorithm complexity (termed as TCMAC model) for high‐level data intensive scientific workflow design. The proposed model schedules the subtasks based on their durations and the complexities of participant algorithms. Characterized by utilization of task duration computation function for time efficiency, the TCMAC model has three features for a full‐aspect scientific workflow including both dataflow and control‐flow: (1) provides flexible and reusable task duration functions in GCE; (2) facilitates better parallelism in iteration structures for providing more precise task durations; and (3) accommodates dynamic task durations for rescheduling in selective structures of control flow. We will also present theories and examples in scientific workflows to show the efficiency of the TCMAC model, especially for control‐flow. Copyright © 2009 John Wiley & Sons, Ltd.

Abstract Because of the lack of a uniform schema for web documents and the sheer amount and dynamics of web data, both the effectiveness and the efficiency of information management and retrieval of web data are often unsatisfactory when using conventional data management and searching techniques. To address this issue, we have adopted web mining and web community analysis approaches. On the basis of the analysis of web document contents, hyperlinks analysis, user access logs and semantic analysis, we have developed various approaches or algorithms to construct and analyze web communities, and to make recommendations. This paper will introduce and discuss several approaches on web community mining and recommendation. Copyright © 2009 John Wiley & Sons, Ltd.

A global education system, as a key area in future IT, has fostered developers to provide various learning systems with low cost. While a variety of e-learning advantages has been recognized for a long time and many advances in e-learning systems have been implemented, the needs for effective information sharing in a secure manner have to date been largely ignored, especially for virtual university collaborative environments. Information sharing of virtual universities usually occurs in broad, highly dynamic network-based environments, and formally accessing the resources in a secure manner poses a difficult and vital challenge. This paper aims to build a new rule-based framework to identify and address issues of sharing in virtual university environments through role-based access control (RBAC) management. The framework includes a role-based group delegation granting model, group delegation revocation model, authorization granting, and authorization revocation. We analyze various revocations and the impact of revocations on role hierarchies. The implementation with XML-based tools demonstrates the feasibility of the framework and authorization methods. Finally, the current proposal is compared with other related work.

With an ever-increasing number of Web services being available, finding desired Web service is crucial for service users. Current keyword search and most existing approaches are inefficient in two main aspects: poor scalability and lack of semantics. Firstly, users are overwhelmed by the huge number of irrelevant services returned. Secondly, the intentions of users and the semantics in Web services are ignored. Inspired by the success of the divide and conquer approach used to handle the complex information decomposition, we use a novel approach to partition a large set of search results into a set of smaller groups by employing a clustering approach. Then we utilize singular value decomposition (SVD) to capture the main semantics hidden behind the words in a query and the descriptions in the services, so that service matching can be carried out at the concept level. We report here on the preliminary experimental evaluation that shows improvements overall precision.

In this paper we propose a combination of the AdaBoost and random forests algorithms for constructing a breast cancer survivability prediction model. We use random forests as a weak learner of AdaBoost for selecting the high weight instances during the boosting process to improve accuracy, stability and to reduce overfitting problems. The capability of this hybrid method is evaluated using basic performance measurements (e.g., accuracy, sensitivity, and specificity), Receiver Operating Characteristic (ROC) curve and Area Under the receiver operating characteristic Curve (AUC). Experimental results indicate that the proposed method outperforms a single classifier and other combined classifiers for the breast cancer survivability prediction.

Due to the inherent correlation among Web objects and the lack of a uniform schema of Web documents, Web community mining and analysis has become an important area for Web data management and analysis. The research of Web communities spans a number of research domains such as Web mining, Web search, clustering and text retrieval. In this talk we will present some recent studies on this topic, which cover finding relevant Web pages based on linkage information, discovering user access patterns through analyzing Web log files, co-clustering Web objects and investigating social networks from Web data. The algorithmic issues and related experimental studies will be addressed. Some research directions are also to be discussed.

Web services composition techniques provide a practical foundation for business process management in loosely coupled distributed environments. Requirements analysis, however, is still the essential step for launching any commercial systems. Nevertheless, what is needed from the business world and what is available from the IT world remain indistinguishable, that obstructs the way to achieve smooth business collaboration. In order to bridge this gap, a scenario-based Petri Net approach for collaborative business process modelling is proposed. 33 scenarios from 6 projects in recent 10 years are analysed and Petri Nets methodology is used to model the elements in collaborative business process. Finally the requirements are identified from both collaboration levels and abstraction levels based on these scenarios.

Service discovery is one of challenging issues in Service-Oriented computing. Currently, most of the existing service discovering and matching approaches are based on keywords-based strategy. However, this method is inefficient and time-consuming. In this paper, we present a novel approach for discovering web services. Based on the current dominating mechanisms of discovering and describing Web Services with UDDI and WSDL, the proposed approach utilizes Probabilistic Latent Semantic Analysis (PLSA) to capture semantic concepts hidden behind words in the query and advertisements in services so that services matching is expected to carry out at concept level. We also present related algorithms and preliminary experiments to evaluate the effectiveness of our approach.

This work proposes a practical payment protocol with scalable anonymity for Internet purchases, and analyzes its role-based access control (RBAC). The protocol uses electronic cash for payment transactions. It is an offline payment scheme that can prevent a consumer from spending a coin more than once. Consumers can improve anonymity if they are worried about disclosure of their identities to banks. An agent provides high anonymity through the issue of a certification. The agent certifies reencrypted data after verifying the validity of the content from consumers, but with no private information of the consumers required. With this new method, each consumer can get the required anonymity level, depending on the available time, computation, and cost. We use RBAC to manage the new payment scheme and improve its integrity. With RBAC, each user may be assigned one or more roles, and each role can be assigned one or more privileges that are permitted to users in that role. To reduce conflicts of different roles and decrease complexities of administration, duty separation constraints, role hierarchies, and scenarios of end-users are analyzed.

Content-based image retrieval is currently a very important area of research in the area of multimedia databases. Plenty of research work has been undertaken to design efficient image retrieval techniques from image or multimedia databases. Although a large number of indexing and retrieval techniques have been developed, there are still no universally accepted feature extraction, indexing and retrieval techniques available. In this paper, we present an up-to-date review of various content-based image retrieval systems. Since the volume of literature available in the field is enormous, only selected works are mentioned.

An association rule generation algorithm usually generates too many rules including a lot of uninteresting ones. Many interestingness criteria are proposed to prune those uninteresting rules. However, they work in post-pruning process and hence do not improve the rule generation efficiency. We discuss properties of informative rule set and conclude that the informative rule set includes all interesting rules measured by many commonly used interestingness criteria, and that rules excluded by the informative rule set are forwardly prunable, i.e. they can be removed in the rule generation process instead of post pruning. Based on these properties, we propose a direct interesting rule generation algorithm, DIG, to directly generate interesting rules defined by any of 12 interestingness criteria. We further show experimentally that DIG is faster and uses less memory than Apriori.

This paper describes a novel approach to document classification that uses decision-tree machine learning based on a succinct vector of important terms in each document. The succinct vector itself is generated by a machine-learning approach which builds parsers that can identify significant features in a document by partitioning it into regions based on low-level document characteristics. The fact that the feature vector is succinct overcomes the problem of very large term vectors, which have hindered the application of conventional machine learning to document classification. The fact that the parser can be trained to extract only important terms from documents means that small training sets can be used to achieve the same classification accuracy as with conventional approaches.

This paper presents two hyperlink analysis-based algorithms to find relevant pages for a given Web page (URL). The first algorithm comes from the extended cocitation analysis of the Web pages. It is intuitive and easy to implement. The second one takes advantage of linear algebra theories to reveal deeper relationships among the Web pages and to identify relevant pages more precisely and effectively. The experimental results show the feasibility and effectiveness of the algorithms. These algorithms could be used for various Web applications, such as enhancing Web search. The ideas and techniques in this work would be helpful to other Web-related research.

Web services via wireless technologies, mobile services (M-services), HTTP, and XML have become important for conducting business. W3C XML Protocol Working Group has been developing standard techniques such as Web Services Description Language (WSDL), simple object access protocol (SOAP), universal description discovery and integration (UDDI). However, at this stage, there is no standard technique for access control in M-services. This paper describes a secure and flexible access control scheme and protocol for M-services based on role based access control (RBAC). The access control architecture involves a Trusted Credential Center (TCC), a Trusted Authentication and Registration Center (TARC) and a secure ticket based mechanism for service access. Users and service providers register with the TARC and are authenticated. Based on this, tickets are issued by the TCC to users. Tickets carry authorization information needed for the requested services. In particular, we are able to specify access control polices based on roles. The protocols between the various entities in the model are protected using appropriate security mechanisms such as signatures which are used to verify correctness of the requested service, as well as to direct billing information to the appropriate user. Our architecture supports efficient authentication of users and service providers over different domains and provides a secure access model for services to users. Our model is also able to support anonymity of users. Only the TARC is able to identify misbehaving users. We believe that the proposed architecture forms a good basis for achieving a secure and flexible M-service system.

We develop formal authorization allocation algorithms for role-based access control (RBAC). The formal approaches are based on relational structure, and relational algebra and operations. The process of user-role assignments is an important issue in RBAC because it may modify the authorization level or imply high-level confidential information to be derived while users change positions and request different roles. There are two types of problems which may arise in user-role assignment. One is related to the authorization granting process. When a role is granted to a user this role may conflict with other roles of the user or together with this role; the user may have or derive a high level of authority. Another is related to authorization revocation. When a role is revoked from a user, the user may still have the role from other roles. To solve these problems, this paper presents an authorization granting algorithm, and weak revocation and strong revocation algorithms that are based on relational algebra. The algorithms can be used to check conflicts and therefore to help allocate roles without compromising the security in RBAC. We describe how to use the new algorithms with an anonymity scalable payment scheme. Finally, comparisons with other related work are discussed.

This paper proposes a secure, scalable anonymity and practical payment protocol for Internet purchases, and uses role based access control (RBAC) to manage the new payment scheme. The protocol uses electronic cash for payment transactions. In this new protocol, from the viewpoint of banks, consumers can improve anonymity if they are worried about disclosure of their identities. An agent provides a higher anonymous certificate and improves the security of the consumers. The agent will certify re-encrypted data after verifying the validity of the content from consumers, but with no private information of the consumers required. With this new method, each consumer can get the required anonymity level, depending on the available time, computation and cost. We also analyse how to prevent a consumer from spending a coin more than once. Furthermore, we use RBAC to manage the new payment scheme. Each user may be assigned one or more roles, and each role can be assigned one or more privileges that are permitted to users in that role. Security administration with RBAC consists of determining operations that must be executed by persons in particular jobs, and assigning employees to proper roles. RBAC can improve system security and reduce conflicts of different roles. The complexities with RBAC can be decreased by mutually exclusive roles and role hierarchies.

The cost of spatial-join processing can be very high due to the large sizes of spatial objects and the computation-intensive spatial operations. A filter-and-refine strategy is usually used to reduce the computing cost of spatial join when the number of spatial objects is large. In this paper we propose a method that aims to minimize the I/O cost at the refinement step. A graph model is introduced to formalize the I/O cost, and a matrix-based algorithm is developed to cluster objects (data) such that the objects in the same cluster are closely related. The objects in the same cluster will be brought together into the main memory for the refinement process, and the I/O cost of fetching objects into memory can, be reduced. Experiments have been conducted and the results have shown that our method can save 20-35% of I/O cost compared to the cases where no clustering or a little clustering is done.

The paper presents a prototype visualization system for text information retrieval and its technical details on algorithm design. The system supports the user in constructing an initial query type and further refining the query by visual interaction. Visualization of text information retrieval is an attractive research area in information retrieval. There are many mathematical algorithms used for information retrieval. The authors investigate an approach to construct visual representations based on singular value decomposition (SVD) of matrices and implement visual interfaces using Java. Experimental results show the feasibility of the proposed approach. The ideas in this approach can also be helpful in other visualization environments.

In order to support the interaction betweeen coexisting traditional short transactions and long cooperative transactions, we propose a novel timestamp ordering approach. With this timestamp ordering method, short transactions can be processed in the traditional way, as if there were no cooperative transactions. Therefore they will not be blocked by cooperative transactions. Cooperative transactions will not be aborted when there is a conflict with short transactions. Rather, they will incorporate the recent updates into their own processing. The serializabilities, among short transactions, and between a cooperative transaction (group) and other short transactions, are all preserved.

In order to support both traditional short transaction and long cooperative transactions, we propose a novel timestamp ordering approach. With this timestamp ordering method, short transactions can be processed in the traditional way, as if there are no cooperative transactions, therefore not be blocked by long transactions; cooperative transactions will not be aborted when there is a conflict with short transactions, rather it will incorporate the recent updates into its own processing; and the serializabilities, among short transactions, and between a cooperative transaction (group) and other short transactions, are all preserved.

There are two major difficulties in real-time multicast connection setup. One is the design of an efficient distributed routing algorithm which optimizes the network cost of routing trees under the real-time constraints. The other is the integration of routing with admission control into one single phase of operations. This paper presents a real-time multicast connection setup mechanism, which integrates multicast routing with real-time admission control. The proposed mechanism performs the real-time admission tests on a COT (cost optimal tree) and a SPT (shortest path tree) in parallel, aiming at optimizing network cost of the routing tree under real-time constraints. It has the following important features: (1) it is fully distributed; (2) it achieves sub-optimal network cost of routing trees; (3) it takes less time and less network messages for a connection setup.

Real-time cooperative editing systems allow multiple users to view and edit the same text/graphic/image/multimedia document at the same time for multiple sites connected by communication networks. Consistency maintenance is one of the most significant challenges in designing and implementing real-time cooperative editing systems. In this article, a consistency model, with properties of convergence, causality preservation, and intention preservation, is proposed as a framework for consistency maintenance in real-time cooperative editing systems. Moreover, an integrated set of schemes and algorithms, which support the proposed consistency model, are devised and discussed in detail. In particular, we have contributed (1) a novel generic operation transformation control algorithm for achieving intention preservation in combination with schemes for achieving convergence and causality preservation and (2) a pair of reversible inclusion and exclusion transformation algorithms for stringwise operations for text editing. An Internet-based prototype system has been built to test the feasibility of the proposed schemes and algorithms

In real-time cooperative editing systems, independent operations on any part of the shared document may be generated from multiple cooperating sites. It is very important and technically challenging to ensure that the effect of executing an operation at remote sites, in the presence of concurrent execution of independent operations, achieves the same effect as executing this operation at the local site at the time of its generation, thus preserving its intention and maintaining system consistency. In this paper, we investigate the technical issues involved in preserving intentions of concurrent operations, explain the reasons why traditional serializationbased concurrency control strategies and existing operational transformation strategies failed to solve these problems, and propose a generic operation transformation scheme for intention preservation and consistency maintenance in real-time cooperative editing systems. The proposed scheme has been implemented in an Internetbased proto...

Knowledge bases contain specific and general knowledge. In relational database systems, specific knowledge is often represented as a set of relations. The conventional methodologies for centralized database design can be applied to develop a normalized, redundancy-free global schema. Distributed database design involves redundancy removal as well as the distribution design which allows replicated data segments. Thus, distribution design can be viewed as a process on a normalized global schema which produces a collection of fragments of relations from a global database. Clearly, not every fragment of data can be permitted as a relation. In this paper, we clarify and formally discuss three kinds of fragmentations of relational databases, and characterize their features as valid designs, and we introduce a hybrid knowledge fragmentation as the general case. For completeness of presentation, we first show an algorithm for the validity test of vertical fragmentations of normalized relations, and then extend it to the more general case of unbiased fragmentations.