Next Point-of-Interest (POI) recommendation, which predicts users' future destinations based on their potential interests, has emerged as a critical task in location-based social networks (LBSNs). However, this task remains challenged by issues such as popularity bias, exposure bias, and limited representational capacity, all of which impede the accurate modeling of users and POIs, thereby restricting balanced and effective recommendations. Therefore, we propose Trajectory Collaborative Filtering Mamba (TCFMamba), which integrates two specially designed modules, i.e., Joint Learning of Static and Dynamic Representations (JLSDR) and Preference State Mamba Network (PSMN), for debiased Point-of-Interest recommendation.

Although the Massive Open Online Courses (MOOC) platform provides learners with convenient learning environments, it brings the problem of information overload due to the huge amount of learning resources which MOOC platforms offer. During the past decade, many course recommendation methods have been proposed to alleviate this problem. Some of them model learners (users) based on static preferences, while others recognize the dynamic nature of learner preferences and model learners based on their sequential learning behaviors through the self-attention mechanism or Convolutional Neural Networks (CNNs). However, the recommendation performance still remains unsatisfactory. We believe that learners’ course selection is jointly influenced by their long-term and short-term preferences, as well as intents. To precisely capture these subtle pieces of information is conducive to enhancing recommendation performance. In this paper, we propose a new model named Convolutional Self-Attention Network with Disentangled Intents (CSAD), which effectively captures the long-term and short-term preferences of learners, and extracts more effective information from course embeddings. Additionally, it disentangles different intents for learners to further improve recommendation performance. Extensive experiments conducted on two publicly available MOOC datasets show the superior performance of CSAD over the state-of-the-arts.

Microbenchmark-based performance regression detection is critical for software quality assurance but faces limitations in continuous integration (CI) environments. Existing test case prioritization methods primarily rely on code coverage and historical stability, overlooking the complex relationships between code changes and performance impacts. To address this, we presents JMH-TCP, an intelligent prioritization framework that leverages predictive modeling to establish connections between code changes and performance variations. Our method introduces a multi-dimensional analysis that integrates novel features, including semantic code distance metrics and change impact assessment powered by large language models, while incorporating traditional metrics such as historical performance stability and code coverage. Experimental evaluations across 10 open-source Java projects show that JMH-TCP achieving a 10.8% improvement in the Average Position of Faults in the Defect Prioritization (APFD-P) metric and an 18.2% enhancement in ranking effectiveness (NDCG) compared to state-of-the-art methods. Furthermore, our detailed ablation and correlation study reveals the synergistic effects of different features on prioritization effectiveness, offering valuable insights for optimizing performance testing strategies.

Predictive business process monitoring aims to forecast the future behaviors of ongoing process instances by analyzing historical event logs. Previous studies in this field have predominantly focused on one specific task, that is, to predict the next activity, the next resource that executes the next activity, the remaining execution time, etc., which ignore the mutual effects among various tasks. In this article, a framework that simultaneously performs multiple prediction tasks is proposed, which provides decision-makers with more comprehensive information and better adapts to complex business scenarios. Specifically, multi-view frequent patterns are firstly conducted from various perspectives to uncover explicit features of different prediction tasks, which serve as additional input for the prediction. Then, a multi-task learning model is designed to learn the implicit characteristics and relations among different prediction tasks as well as obtain accurate prediction results. Experiments on five real-life datasets prove that the proposed method outperforms state-of-the-art methods, and soft parameter sharing in multi-task learning is more effective than hard parameter sharing for PBPM tasks.

Extreme precipitation, as a core causative factor of meteorological disasters, poses significant challenges for accurate short-term forecasting due to the chaotic nature of precipitation systems and their multi-scale spatio-temporal evolution. Traditional numerical models are notably affected by error accumulation, while existing deep learning models still face dual limitations in physical fidelity and multi-scale feature extraction. To Address these issues, we propose an innovative Multi-scale Physics-informed Transformer with spatio-temporal feature adapter for extreme precipitation nowcasting, termed MPFormer. Our framework comprises two core components: the deterministic Evolution Network and the stochastic Generative Network. The Evolution Network integrates a novel Scale-Aware Temporal Residual Modulation Transformer (STRMT) encoder that captures multi-scale storm dynamics through residual temporal attention. The Generative Network introduces spatio-temporal adapters as lightweight transfer modules for probabilistic modeling. We develop a Multi-scale Physics-informed Loss with three innovations: 1) dynamic weight scheduling for feature fusion, 2) physical constraints preserving storm evolution patterns, and 3) entropy-based uncertainty calibration. Experiments based on MRMS radar data from North America demonstrate that the model can generate high-resolution forecasts (2km grid) with a 3-hour lead time over an area of 2048×2048 square kilometers. Compared to the state-of-the-art technologies, the proposed framework shows significant effectiveness and superiority in metrics such as CSIN, offering a new paradigm that combines physical interpretability with engineering practicality for extreme weather warnings and disaster prevention in smart cities.

During software development, developers often need appropriate but unfamiliar APIs to implement a specific functionality. Under such circumstances, developers tend to leverage search tools to seek for the relevant APIs. However, there are always semantic gaps between query words and APIs, which negatively affects the performance of these tools. In this study, we introduce Glo-APIRec, a method that combines global semantics with local context to estimate the semantic relevance between query words and APIs to recommend APIs. In this method, the Transformer model is employed to obtain global semantics, while the Word2Vec model is utilized to capture local context using a fixed-size window. First, Glo-APIRec collects millions of Java projects from GitHub to construct the corpus. Afterward, a set of tuples consisting of words and APIs is built by extracting comments and API sequences from the source code files. Finally, Transformer is employed to capture long distance semantics about API sequences and code comments. Meanwhile, Word2Vec is used to generate word vectors to capture the local context by introducing the random shuffling strategy to break the positions of words and APIs in the tuples. We evaluate the performance of Glo-APIRec with 30 sentence-level queries. Experimental results show that Glo-APIRec can achieve 0.600 in terms of SuccessRate for top-1 recommendation and 0.900 for top-10 recommendation. When recommending 10 APIs, Glo-APIRec can achieve 0.480, 0.703 and 0.717 in terms of precision, Mean Reciprocal Rank ([Formula: see text]) and Normalized Discounted Cumulative Gain ([Formula: see text]), and outperforms the state-of-the-art method by 26.2%, 31.7% and 27.9%, respectively.

ABSTRACT Introduction Microservices architecture is one of the most popular design approaches in software development. The granularity smell of microservices is a topic of great interest, which often leads to a degradation in the quality of the microservices architecture, so it needs to be eliminated through architecture refactoring. Existing research on architecture refactoring to address granularity smells in microservices is limited, with a lack of consideration for the semantic information of business logic, and suggestions for microservice refactoring rely too much on manual experience and lack standardized descriptions. Objectives This paper aims to provide a novel approach for refactoring granularity smells in microservice architectures, addressing the existing shortcomings in considering semantic information of microservice business logic, the reliance on empirical experience for refactoring suggestions, and the lack of standardized suggestions for refactoring. Methods This paper introduces a novel method for refactoring granularity smells in microservices architecture based on business topic clusters, named ASRMG. This method extracts business topic clusters from the business logic code of interfaces, thereby defining the cohesion and coupling semantics of the system. It then employs an enhanced genetic algorithm for refactoring the microservices system, using a refactoring pattern database to automate the generation of fine‐grained refactoring suggestions. Results Experiments conducted on five open‐source microservices systems of varying scales and domains achieved a 99.24% elimination rate of granularity smells, with cohesion metrics improving by an average of 60.19% and coupling metrics reducing by an average of 15.32%, indicating a significant enhancement in the quality of microservice architecture. Conclusion This paper introduces a novel method for refactoring and evaluating microservice systems, named ASRMG. ASRMG extracts business topic clusters from the code of microservice systems and refines the evaluation method for refactored microservice, and proposes an automated method for generating refactoring suggestions for granularity smells, enhancing the efficiency and quality of architecture smell refactoring.

As one of the location-based social network (LBSN) applications, next point-of-interest (POI) recommendation is devoted to predicting a user’s next interested locations based on check-in trajectories, which has received a lot of attention. In recent research endeavors, graph neural network (GNN) has demonstrated exceptional performance by incorporating global user/POI features into the learning framework. Nevertheless, most existing approaches merely target on one or two factors present in trajectories, such as geographic location, social networks, or user reviews, failing to fully exploit the multimodal information in real-world scenarios. Additionally, user’s behavior patterns embedded in historical trajectories have not been effectively partitioned, posing challenges to the learning of user’s evolving preferences over time. To this end, this study proposes multimodal intertwined network (MINet), a novel model based on dynamic and static knowledge graphs, to tackle the challenges of multimodality in the next POI recommendation. On the one hand, temporal dynamic knowledge graph is established to learn the evolution of user preferences by capturing behavior patterns at various time slices. On the other hand, a grouping static knowledge graph is constructed to learn the stable user/POI features through aggregating multimodal relations. Furthermore, to achieve enhanced information fusion, this study learns the features of POIs and users from the two types of knowledge graphs, respectively. Experiments on three real-world datasets demonstrated that MINet outperforms the state-of-the-art methods.

The escalating challenges in urban traffic highlight the importance of accurate traffic forecasting for enhancing the Intelligent Transportation Systems (ITS), given its pivotal role in optimizing traffic management strategies. Due to the impressive performance of Graph Neural Networks in spatio-temporal data analysis, Spatio-Temporal Graph Neural Networks (STGNNs) have emerged as a mainstream approach for traffic forecasting. However, many recent STGNN-based works often utilize redundant and intricate architectures, leading to increased computational costs with only minor improvements in performance. To solve this issue, we propose a concise but effective Lightweight Spatio-Temporal Neural Network architecture, LSTNN. Specifically, we design two sampling strategies, downsampling and patched sampling, to decompose the time series and separately fit the seasonal component and trend components. Based on sampling strategies, we introduce a spatio-temporal localization module based on the raw traffic data and learnable spatio-temporal indexing. In particular, this module models spatio-temporal correlations by appending the spatio-temporal indexing to the traffic sequences. We visualized the spatio-temporal indexing, confirming the effectiveness of the spatio-temporal localization module design. Extensive experiments are conducted on four widely utilized real-world traffic datasets, showing the significant improvement of LSTNN compared to baselines, including several state-of-the-art models. Furthermore, we conducted extensive experiments on four long-term time series datasets to validate the effectiveness of LSTNN in the Long-term Time Series Forecasting (LTSF) task. Our findings may inspire and encourage the design of more concise neural prediction architectures for real-world applications. We release the datasets and baseline implementations at: github.com/HduDBSI/LSTNN

In recent years, researchers have proposed various approaches to detect code comments that explicitly acknowledge Technical Debt (TD), which are referred to as Self-Admitted Technical Debt (SATD) comments. Previous studies have proven that hidden patterns can be learned from SATD code snippets to predict whether the code snippets hold TD without the aid of comments. In this study, we refer to such TD as unadmitted TD, i.e., TD whose code snippets exhibit patterns similar to those of SATD, but are not annotated with comments indicating the existence of TD. Given that current unadmitted TD datasets are limited to method-level and conditional-statement-level code snippets, we construct the world’s most comprehensive dataset of code snippets and their corresponding comments, which includes 18 popular Java open-source projects and covers code snippets at the file, class, method and block levels. Around this dataset, we have conducted four key research activities.Firstly, we propose an automated framework for data collection and annotation, which extracts commented code snippets of varying granularity from projects and assigns SATD labels using three state-of-the-art SATD detection approaches. Secondly, we conduct a rigorous evaluation process, including the validity test, reliability test and manual verification, to ensure the accuracy and consistency of the dataset before further analysis and utilization. Additionally, we propose a metric-based detection approach named LiteM that detects unadmitted TD solely based on code metrics. As for the real-world scenarios where training data is scarce, we further introduce LiteMC, which generates pseudo-labels for commented code snippets and then employs LiteM to train a model on these pseudo-labeled data, enabling the detection of unadmitted TD in uncommented code snippets. The experimental results demonstrate the effectiveness and efficiency of both LiteM and LiteMC. The dataset and the code are available athttps://github.com/HduDBSI/Dataset4TD.

Representation learning remains one of the most important but challenging tasks within industrial music rec-ommendation systems. In the context of the Matthew effect, item exposure frequency demonstrates substantial inequality, leading to the Harry Potter problem for popular items and the long-tail issue for less interacted items, collectively impairing the adequacy and accuracy of representation learning. In this paper, to alleviate the negative impact of bias on representation learning in music recommendation systems, we propose a unified model based on introducing the unbiased Cascading Multimodal Feature, called CMF4Rec. Specifically, with our cascading feature enhancement module, we implement a dual-stage representation enhancement strategy. In the first stage, the pivotal subsequence is extracted from the coarse-grained similarity sequence derived from cascading multimodal features, which is subsequently ag-gregated to generate the enhanced representation of the candidate item. Moreover, in the feature interaction module, the enhanced representation is crossed with user behaviors to capture the diverse and dynamic interests of users. Furthermore, we employ contrastive learning and design an auxiliary contrastive task to provide high-quality gradients for the main recommendation task. We demonstrate the effectiveness of this model with extensive experiments on public and industrial datasets. Moreover, the deployment of CMF4Rec in a real music recommendation system has also yielded significant improvements.

With the explosion in the number of mobile applications (apps), it becomes increasingly difficult to find a suitable app that aligns with user’s needs and preferences. Recommender systems help simplify this process as they have done in the field of e-commerce. However traditional recommendation methods suffer from poor performance, if their designs are not well tailored to the specific characteristics of mobile application. In fact, when recommending apps, their categories play a sensitive role. Meanwhile, recently emerged deep learning-based methods come with high computational costs, limiting their applicability in the lightweight mobile scenarios. To address these issues, in this paper, we propose a heterogeneous graph collaborative filtering approach applied to app recommendations. Firstly, we propose a review processing method that can effectively capture the features of users, apps and categories through reviews and likes. Then, we build a heterogeneous graph containing multiple nodes such as users, apps and categories, and further learn the latent features and complex relationships of nodes through lightweight graph convolution operations. Finally, we predict the apps for users by node embeddings. The extensive experimental results based on real dataset demonstrate the proposed model has achieved significant improvement in recommendation performance compared with the baselines.

Recommender models aimed at mining users' behavioral patterns have raised great attention as one of the essential applications in daily life. Recent work on graph neural networks (GNNs) or debiasing methods has attained remarkable gains. However, they still suffer from (1) over-smoothing node embeddings caused by recursive convolutions with GNNs, and (2) the skewed distribution of interactions due to popularity and user-individual biases. This paper proposes a contextualized and debiased recommender model (CaDRec). To overcome the over-smoothing issue, we explore a novel hypergraph convolution operator that can select effective neighbors during convolution by introducing both structural context and sequential context. To tackle the skewed distribution, we propose two strategies for disentangling interactions: (1) modeling individual biases to learn unbiased item embeddings, and (2) incorporating item popularity with positional encoding. Moreover, we mathematically show that the imbalance of the gradients to update item embeddings exacerbates the popularity bias, thus adopting regularization and weighting schemes as solutions. Extensive experiments on four datasets demonstrate the superiority of the CaDRec against state-of-the-art (SOTA) methods. Our source code and data are released at https://github.com/WangXFng/CaDRec.

Graph neural network (GNN)-based models have been extensively studied for recommendations, as they can extract high-order collaborative signals accurately which is required for high-quality recommender systems. However, they neglect the valuable information gained through negative feedback in two aspects: (1) different users might hold opposite feedback on the same item, which hampers optimal information propagation in GNNs, and (2) even when an item vastly deviates from users' preferences, they might still choose it and provide a negative rating. In this paper, we propose a negative feedback-aware recommender model (NFARec) that maximizes the leverage of negative feedback. To transfer information to multi-hop neighbors along an optimal path effectively, NFARec adopts a feedback-aware correlation that guides hypergraph convolutions (HGCs) to learn users' structural representations. Moreover, NFARec incorporates an auxiliary task - predicting the feedback sentiment polarity (i.e., positive or negative) of the next interaction - based on the Transformer Hawkes Process. The task is beneficial for understanding users by learning the sentiment expressed in their previous sequential feedback patterns and predicting future interactions. Extensive experiments demonstrate that NFARec outperforms competitive baselines. Our source code and data are released at https://github.com/WangXFng/NFARec.

Abstract As a new software design paradigm, microservices structure an application as a collection of services that are independently deployable and loosely coupled. A key step of migrating non‐microservices‐based systems to microservices‐based systems is the identification of microservices in the target application. Traditional approaches to identify microservices, however, usually suffer from lack of full automation and low effectiveness. This paper puts forward an expert system to identify microservices automatically from legacy systems by leveraging the similarity of RESTful APIs. The system consists of three major parts. The first part calculates the candidate topic similarity and the response message similarity of APIs, and the overall similarity is obtained through their combination. Afterwards, the second part constructs a graph of API similarities with API as the node and the overall similarity as the weight. The third part employs a graph‐based clustering algorithm to identify candidate microservices from the API similarity graph. Experiments conducted on open‐source projects demonstrate the effectiveness of our system.

Abstract Next activity prediction of business processes (BPs) provides valid execution information of ongoing (i.e., unfinished) process instances, which enables process executors to rationally allocate resources and detect process deviations in advance. Current researches on next activity prediction, however, concentrate mostly on model construction without in‐depth analysis of historical event logs. In this article, we are dedicated to proposing an approach to forecast the next activity effectively in BPs. After in‐depth analysis of historical event logs, three types of candidate activity attributes are defined and calculated as additional input for the prediction based on three essential elements, that is, frequent activity patterns, trace similarity and position information. Furthermore, we construct an effective hybrid prediction model combining the popular convolutional neural network (CNN) and bidirectional long short‐term memory (Bi‐LSTM) with self‐attention mechanism. Specifically, CNN is used to extract the temporal features before importing into Bi‐LSTM for accurate prediction, and self‐attention mechanism is applied to strengthen features that have decisive effects on the prediction results. Comparison experiments on four real‐life datasets demonstrate that our hybrid model with selected attributes achieves better performance on next activity prediction than single models, and improves the prediction accuracy by 2.98%, 6.05%, 2.70% and 5.26% on Helpdesk, Sepsis, BPIC2013 Incidents and BPIC2012O datasets than the state‐of‐the‐art methods, respectively.

Process discovery techniques analyze process logs to extract models that characterize the behavior of business processes. In real-life logs, however, noises exist and adversely affect the extraction and thus decrease the understandability of discovered models. In this paper, we propose a novel double granularity filtering method, executed on both the event and trace levels, to detect noises by analyzing the directly-following and parallel relations between events. Based on the probability of an event occurring in a sequence, the infrequent behaviors and redundant events in the logs can be filtered out. In addition, the missing events in parallel blocks are detected to further improve the performance of filtering. Experiments on synthetic logs and five real-life datasets demonstrate that our method significantly outperforms other state-of-the-art methods.

The execution of a business process usually involves the cooperation of many resources (actors) performing various tasks (activities). Generally speaking, the cooperation among actors could significantly influence the efficiency of process execution. The better cooperation among actors, the higher performance the process instance would achieve. The task allocation is, therefore, expected to ensure that the actors are compatible well with each other when performing tasks. However, the decision of task allocation is always ad-hoc or performed manually in many organizations. As for some automatic methods, they usually serve only for sequentially structured simple processes. In addition, the existing studies only concentrate on the cooperation between two actors and fail to consider the effects from the context of performing different tasks by these two actors especially in the business process with many-to-many relationships among the resources and activities. To address these issues, we handle the process with complex block structures including iteration, choice and parallelism, and propose an effective entity-wise method to measure the cooperation by combining both actors and activities together. Based on them, we present two approaches, one greedy-based and the other A*-based, to assign actors for maximum cooperation in the complex structured business process with many-to-many relationships among the resources and activities. The experimental results on both public released and synthetic datasets demonstrate the effectiveness and efficiency of our approaches.

Abstract Recommender systems have become indispensable for addressing information overload for micro-video services. They are used to characterize users’ preferences from their historical interactions and recommend micro-videos accordingly. Existing works largely leverage the multi-modal contents of micro-videos to enhance recommendation performance. However, limited efforts have been made to understand users’ complex behavior patterns, including their long- and short-term interests, as well as their temporal diversity preferences. In micro-video recommendation scenarios, users tend to have both stable long-term interests and dynamic short-term interests, and may feel tired after incessantly receiving numerous similar recommendations. In this paper, we propose a Temporal Diversity-aware micro-videorecommender (TD-VideoRec) for user behavior modeling, simultaneously capturing users’ long- and short-term preferences. Specifically, we first adopt a user-centric attention mechanism to cope with long-term interests. Then, we utilize an attention network on top of a long-short term memory network to obtain users’ short-term interests. Finally, a temporal diversity coefficient is introduced to characterize the temporal diversity preferences of users’ click behaviors. The value of the coefficient depends on the distinction between users’ long- and short-term interests extracted by vector orthogonal projection. Extensive experiments on two real-world datasets demonstrate that TD-VideoRec outperforms state-of-the-art methods.

Abstract 3D CNN networks can model existing large action recognition datasets well in temporal modeling and have made extremely great progress in the field of RGB-based video action recognition. However, the previous 3D CNN models also face many troubles. For video feature extraction convolutional kernels are often designed and fixed in each layer of the network, which may not be suitable for the diversity of data in action recognition tasks. In this paper, a new model called Multipath Attention and Adaptive Gating Network (MAAGN) is proposed. The core idea of MAAGN is to use the spatial difference module (SDM) and the multi-angle temporal attention module (MTAM) in parallel at each layer of the multipath network to obtain spatial and temporal features, respectively, and then dynamically fuses the spatial-temporal features by the adaptive gating module (AGM). SDM explores the action video spatial domain using difference operators based on the attention mechanism, while MTAM tends to explore the action video temporal domain in terms of both global timing and local timing. AGM is built on an adaptive gate unit, the value of which is determined by the input of each layer, and it is unique in each layer, dynamically fusing the spatial and temporal features in the paths of each layer in the multipath network. We construct the temporal network MAAGN, which has a competitive or better performance than state-of-the-art methods in video action recognition, and we provide exhaustive experiments on several large datasets to demonstrate the effectiveness of our approach.

Recommender system helps address information overload problem and satisfy consumers’ personalized requirement in many applications such as e-commerce, social networks, and in-game store. However, existing approaches mainly focus on improving the accuracy of recommendation tasks but usually ignore how to improve the interpretability of recommendation, which is still a challenging and crucial task, especially for some complicated scenarios such as large-scale online games. A few previous attempts on explainable recommendation mostly depend on a large amount of a priori knowledge or user-provided review corpus, which is labor consuming as well as often suffers from data deficiency. To relieve this issue, we propose a Multi-source Heterogeneous Graph Attention Network for Explainable Recommendation (MHANER) for the case without enough a priori knowledge or corpus of user comments. Specifically, MHANER employs the attention mechanism to model players’ preference to in-game store items as the support for the explanation of recommendation. Then a graph neural network–based method is designed to model players’ multi-source heterogeneous information, including the players’ historical behavior data, historical purchase data, and attributes of the player-controlled character, which is leveraged to recommend possible items for players to buy. Finally, the multi-level subgraph pattern mining is adopted to combine the characteristics of a recommendation list to generate corresponding explanations of items. Extensive experiments on three real-world datasets, two collected from JD and one from NetEase game, demonstrate that the proposed model MHANER outperforms state-of-the-art baselines. Moreover, the generated explanations are verified by human encoding comprised of hard-core game players and endorsed by experts from game developers.

Traditional music recommender systems are mainly based on users’ interactions, which limit their performance. Particularly, various kinds of content information, such as metadata and description can be used to improve music recommendation. However, it remains to be addressed how to fully incorporate the rich auxiliary/side information and effectively deal with heterogeneity in it. In this paper, we propose a M ulti-view E nhanced G raph A ttention N etwork (named MEGAN ) for session-based music recommendation. MEGAN can learn informative representations (embeddings) of music pieces and users from heterogeneous information based on graph neural network and attention mechanism. Specifically, the proposed approach MEGAN firstly models users’ listening behaviors and the textual content of music pieces with a Heterogeneous Music Graph (HMG). Then, a devised Graph Attention Network is used to learn the low-dimensional embedding of music pieces and users and by integrating various kinds of information, which is enhanced by multi-view from HMG in an adaptive and unified way. Finally, users’ hybrid preferences are learned from users’ listening behaviors and music pieces that satisfy users real-time requirements are recommended. Comprehensive experiments are conducted on two real-world datasets, and the results show that MEGAN achieves better performance than baselines, including several state-of-the-art recommendation methods.

Familiar analysis for malware plays an important role in comprehending the diversity of malicious behaviors and identifying the emerging security threats. Existing studies mainly focus on classifying malware into known families by supervised learning. However, these methods face two main challenges, 1) the lack of a large amount of labeled data and 2) the poor effectiveness in identifying unknown families of malware. To overcome these challenges, we propose a new method called multiple features (MulFC) based on unsupervised learning. In the method, we first leverage a decompiling tool to extract multiple features, including manifest features, application programming interface (API) features, and opcode features. Then, the opcode features are preprocessed to filter out the redundant ones to reduce the calculation cost. After that, we adopt the Jaccard index to calculate the similarities between malware and construct a malware network. Finally, InfoMap is applied to perform the clustering on the basis of the malware network. Overall, MulFC does not require the use of labeled data and can identify unknown families of malware. Experiments are conducted on two datasets for the performance evaluation of MulFC. The experimental results show that MulFC achieves 0.810 in terms of normalized mutual information, 0.576 in terms of adjusted rand index, 0.620 in terms of the Fowlkes–Mallows index, and 0.805 in terms of V-measure on average, and outperforms the state-of-the-art baseline method by 0.060, 0.054, 0.038, and 0.065, respectively.

This paper proposes a novel architecture of Recommendation-Enabled Edge Caching and Device-to-Device (D2D) Offloading via Incentive-driven Deep Reinforcement Learning (DRL), which can not only solve the problem of inaccurate recommendation caused by sparse rating matrix, but also encourage users to participate in D2D offloading through an effective incentive mechanism. Specifically, we define Pseudo Markov Decision Process (PMDP) for the first time, which enables the conversion of the non-sequential process (e.g. rating prediction) into a sequential one, making it suitable for DRL. Then, combining Supervised Learning (SL) and DRL, a Supervised DRL for Collaborative Filtering (CF) algorithm, named SDRLCF, is proposed to predict missing ratings. After that, from the perspective of Content Service Center (CSC), the incentive-driven recommendation-enabled edge caching and D2D offloading can be formulated as a Non-Linear Integer Programming (NLIP) problem, which belongs to NP-hard, and is difficult to obtain the optimal solution in polynomial time. To address this issue, a DRL based Edge Caching and Recommendation algorithm, named DRLECR, is proposed to minimize the cost of CSC. Finally, combining with economic theory, a Reverse Auction based Payment Determination algorithm under Vickrey-Clarke-Groves (VCG) scheme, named RAPD, is proposed, which can stimulate users to participate in edge caching and D2D offloading while guaranteeing the individual rationality and truthfulness of participants. Extensive experiment results on both realistic and synthetic datasets demonstrate that the proposed algorithms outperform other baseline methods under different scenarios.

Automated software fault localization has become one of the hot spots on which researchers have focused in recent years. Existing studies have shown that learning-based techniques can effectively localize faults leveraging various information. However, there exist two problems in these techniques. The first is that they simply represent various information without caring the contribution of different information. The second is that the data imbalance problem is not considered in these techniques. Thus, their effectiveness is limited in practice. In this paper, we propose HetFL, a novel heterogeneous graph-based software fault localization technique to aggregate different information into a heterogeneous graph in which program entities and test cases are regarded as nodes, and coverage, change histories, and call relationships are viewed as edges. HetFL first extracts textual and structure information from source code as attributes of nodes and integrates them to form an attribute vector. Then, for a given node, HetFL finds its neighbor nodes based on the types of edges and aggregates corresponding neighbor nodes to form type vectors. After that, the attribute vector and all the type vectors of each node are aggregated to generate the final vector representation by an attention mechanism. Finally, we leverage a convolution neural network (CNN) to obtain the suspicious score of each method. To validate the effectiveness of HetFL, experiments are conducted on the widely used dataset Defects4J (v1.2.0). The experimental results show that HetFL can localize 217 faults within Top-1 that is 25 higher than the state-of-the-art technique DeepFL, and achieve 6.37 and 5.58 in terms of MAR and MFR which improve DeepFL by 9.0% and 5.6%, respectively. In addition, we also perform experiments on the latest version of Defects4J (v2.0.0). The experimental results show that HetFL has better performance than the baseline methods.

The point-of-interest (POI) recommendation predicts users' destinations, which might be of interest to users and has attracted considerable attention as one of the major applications in location-based social networks (LBSNs). Recent work on graph-based neural networks (GNN) or matrix factorization-based (MF) approaches has resulted in better representations of users and POIs to forecast users' latent preferences. However, they still suffer from the implicit feedback and cold-start problems of check-in data, as they cannot capture both local and global graph-based relations among users (or POIs) simultaneously, and the cold-start neighbors are not handled properly during graph convolution in GNN. In this paper, we propose an enhanced encoder-decoder network (EEDN) to exploit rich latent features between users, POIs, and interactions between users and POIs for POI recommendation. The encoder of EEDN utilizes a hybrid hypergraph convolution to enhance the aggregation ability of each graph convolution step and learns to derive more robust cold-start-aware user representations. In contrast, the decoder mines local and global interactions by both graph- and sequential-based patterns for modeling implicit feedback, especially to alleviate exposure bias. Extensive experiments in three public real-world datasets demonstrate that EEDN outperforms state-of-the-art methods. Our source codes and data are released at https://github.com/WangXFng/EEDN

Abstract Temporal action localisation is a challenging task, and video context is crucial to localisation actions. Most existing cases that incorporate temporal and semantic contexts into video features suffer from single contextual representation and blurred temporal boundaries. In this study, a multi‐temporal resolution pyramid structure model is proposed. Firstly, a temporal‐semantic context aggregation module (TSCF) is designed to assign different attention weights to temporal contexts and combine them with multi‐level semantics into video features. Secondly, for the problem of large differences in the time span between different actions in the video, a local‐global attention module is designed to combine local and global temporal dependencies for each temporal point to obtain a more flexible and robust representation of contextual relations. The redundant representation of the convolution kernel is reduced by modifying the convolution and the arithmetic power is redeployed at a microscopic granularity. To verify the effectiveness of the model, extensive experiments on three challenging datasets are performed. On THUMOS14, the best performance is obtained in [email protected]–0.6 with an average mAP of 47.02%. On ActivityNet‐1.3, an average mAP of 34.94% was obtained. On HACS, an average mAP of 28.46% was achieved.

Abstract Code vulnerabilities can have serious consequences such as system attacks and data leakage, making it crucial to perform code vulnerability detection during the software development phase. Deep learning is an emerging approach for vulnerability detection tasks. Existing deep learning‐based code vulnerability detection methods are usually based on word2vec embedding of linear sequences of source code, followed by code vulnerability detection through RNNs network. However, such methods can only capture the superficial structural or syntactic information of the source code text, which is not suitable for modeling the complex control flow and data flow and miss edge information in the graph structure constructed by the source code, with limited effect of neural network model. To solve the above problems, this article proposes a code vulnerability detection method, named VulGraB, which is based on graph embedding and bidirectional gated graph neural networks. VulGraB uses node2vec to convert the program‐dependent graphs into graph embeddings of the code, which contain rich structure information of the source code, improving the ability of features to express nonlinear information to a certain extent. Then the BiGGNN is used for training, and finally the accuracy of the detection results is evaluated using target program. The bi‐directional gated neural network utilizes a bi‐directional recurrent structure, which is beneficial to global information aggregation. The experimental results show that the accuracy of VulGraB is significantly improved over the baseline models on two datasets, with F1 scores of 85.89% and 97.24% being the highest, demonstrating that VulGraB consistently outperforms other effective vulnerability detection models.

Edge caching has been a research hotspot of the Mobile Edge Computing (MEC) in recent years, which is an effective way to ease the burden of traffic in cellular networks. It places contents to the edge of the networks and assists contents transmission via Device-to-Device (D2D) links. Traditional caching strategies strictly depend on the personal preferences of users, and they are scarcely possible to reduce the transmission cost while ensuring the high effectiveness. Fortunately, recent studies have found that the combination of caching and recommendation can effectively improve the efficiency of edge caching and reduce the transmission cost. In this article, we jointly consider the content caching and recommendation through Opportunistic Mobile Networks (OMNs) to reduce the cost of Content Service Center (CSC). In order to obtain the optimal caching and recommendation solutions with sparse rating matrix, we propose a Joint Content Caching and Recommender System (JCCRS). In JCCRS, a Broad Incremental Learning based Collaborative Filtering algorithm, named BILCF, is first proposed to predict the missing ratings. Afterwards, we quantify the relationship between each pair of Mobile Users (MUs) according to their mobility, similarity and preference. The content caching and recommendation problem is then modeled as a Non-Linear Integer Programming (NLIP) problem and we prove that it belongs to NP-hard. To solve this problem, a Deep Deterministic Policy Gradient (DDPG) based Content Caching and Recommendation method, named DCRM, is further proposed to obtain the approximate optimal solutions. Extensive experiments on both a realistic dataset and a synthetic dataset validated by the realistic data show that the proposed algorithms outperform other baseline methods under different scenarios.

As one of the most common code smells, feature envy reduces the cohesion of classes and increases the coupling between classes, thus leading to difficulty of software maintainability. Though many studies have made good achievements on feature envy detection, they often despise or even ignore the inherent calling relationships between methods, causing unimpressive detection efficiency. To address this problem, we propose a Graph Neural Network (GNN) based approach towards feature envy detection. We first collect code metrics and calling relationships, and then convert them to the form of a graph, where the node represents the code metrics of a method and the edge represents the calling relationship between methods. Particularly, considering the unbalance of positive and negative samples, we introduce a graph augmenter to obtain an enhanced graph. Finally, we feed the enhanced graph into a GNN model for training and predicting. We conducted extensive experiments on a dataset containing five open-source software projects. The result shows that our approach achieves 78.90% in terms of average F1-score, which is 37.98% absolutely higher than the best comparison approach. Besides, we propose a refactoring recommendation approach based on calling strength. It achieves 61.44% of accuracy, which is 5.13% absolutely higher than the best competitive. Our code and datasets are available at https://github.com/HduDBSI/Feature-Envy-Detection.

Abstract As a new cloud service for delivering complex business applications, Business Process as a Service (BPaaS) is another challenge faced by cloud service platforms recently. To effectively reduce the security risk caused by business process execution load in BPaaS, it is necessary to detect the non-compliant process executions (instances) from tenants in advance by checking and monitoring the conformance of the executing process instances in real-time. However, the vast majority of existing conformance checking techniques can only be applied to the process instances that have been executed completely offline and only focus on the conformance from the single control-flow perspective. We develop an extensible multi-perspective conformance measurement method to address these issues first and then investigate the predictive conformance monitoring approach by automatically constructing an online multi-perspective conformance prediction model based on deep learning techniques. In addition, to capture more decisive features in the model from both local information and long-distance dependency within an executed process instance, we propose an approach, called CNN-BiGRU, by combining Convolutional Neural Network (CNN) with a variant and enhancement of Recurrent Neural Network (RNN). Extensive experiments on two data sets demonstrate the effectiveness and efficiency of the proposed CNN-BiGRU.

Continuous integration is a growing trend in the software engineering community and industry. Performance testing is becoming more important in this context. To support precise and fine-grained monitoring, performance unit tests are applied for small software components. However, the benchmarks for performance unit testing are still insufficient, which means that benchmark coverage is low and there is a room for improvement. Therefore, focusing on the most important parts of the software, such as methods, and ensuring that their performance is monitored closely with performance unit tests can greatly reduce the amount of work that needs to be done for testing and to prepare benchmarks. This paper aims to provide an assisting approach for detecting methods that need to be benchmarked in performance unit tests. We start by defining 30 features to characterize the methods in the projects and show that they can be used to tell the benchmarked methods (short for BDMs) from those that are not. Then, using the proposed features, we build machine learning-based models to detect BDMs. We perform an experiment with 10 open source projects from GitHub to see how well our approach works. First, we use seven binary classification techniques to evaluate the prediction performance of our machine learning models. We find that Random Forest makes the best predictions where AUC and MCC are between 0.77 and 0.89 and 0.5 and 0.75, respectively. In terms of cost effectiveness, the experiment reveals that by inspecting only 5% of the candidate methods detected by our model, 43% of the total real BDMs can be retrieved. Second, we conduct feature importance evaluations for individual features and feature categories. We find that eight features related to Scope, History, and Complexity are individually important for good predictions and that the combination of all features in the Scope category is paramount for our model, while the combination of features in the Control Flow category is less important. Third, we investigate the performance of our detection approach with different feature selection strategies and data sources. Our results show that we can make good predictions about whether a method needs to be benchmarked by using machine learning models. Practitioners can use our method and the results of the study to deal with BDMs detection effectively.

Recommender systems are important approaches for dealing with the information overload problem in the big data era, and various kinds of auxiliary information, including time and sequential information, can help improve the performance of retrieval and recommendation tasks. However, it is still a challenging problem how to fully exploit such information to achieve high-quality recommendation results and improve users' experience. In this work, we present a novel sequential recommendation model, called multivariate Hawkes process embedding with attention (MHPE-a), which combines a temporal point process with the attention mechanism to predict the items that the target user may interact with according to her/his historical records. Specifically, the proposed approach MHPE-a can model users' sequential patterns in their temporal interaction sequences accurately with a multivariate Hawkes process. Then, we perform an accurate sequential recommendation to satisfy target users' real-time requirements based on their preferences obtained with MHPE-a from their historical records. Especially, an attention mechanism is used to leverage users' long/short-term preferences adaptively to achieve an accurate sequential recommendation. Extensive experiments are conducted on two real-world datasets (lastfm and gowalla), and the results show that MHPE-a achieves better performance than state-of-the-art baselines.

With recent developments in communication technologies, vehicular networks have become a reality with various applications. However, the cybersecurity aspect of vehicular networks is still an open issue that needs to be addressed with novel defence mechanisms against attacks. This paper first presents the state-of-the-art communication technologies in vehicular networks (either inter-vehicle networking or in-vehicle networking) along with their applications. Then we explore novel technologies including machine learning and blockchain as cybersecurity defence mechanisms in vehicular networks. Based on the extensive survey, we highlight some insights for future research to secure vehicular networks.

Recommender systems, which aim to provide personalized suggestions for users, have proven to be an effective approach to cope with the information overload problem existing in many online applications and services. In this paper, we target two specific sequential recommendation tasks,next music recommendation and next new music recommendation, to predict the next (new) music piece that users would like based on their historical listening records. In current music recommender systems, various kinds of auxiliary/side information, e.g., item contents and users’ contexts, have been taken into account to facilitate user/item preference modeling and have yielded comparable performance improvement. Despite the gained benefits, it is still a challenging and important problem to fully exploit sequential music listening records due to the complexity and diversity of interactions and temporal contexts among users and music, as well as the dynamics of users’ preferences. To this end, this paper proposes a novelAttentiveTemporalPointProcess (ATPP) approach for sequential music recommendation, which is mainly composed of a temporal point process model and an attention mechanism. OurATPPcan effectively capture the long- and short-term preferences from the sequential behaviors of users for sequential music recommendation. Specifically,ATPPis able to discover the complex sequential patterns from the interaction between users and music with the temporal point process, as well as model the dynamic impact of historical music listening records on next (new) music pieces adaptively with an attention mechanism. Comprehensive experiments on four real-world music datasets demonstrate that the proposed approachATPPoutperforms state-of-the-art baselines in both next and next new music recommendation tasks.

In software development, due to the demands from users or the limitations of time and resources, developers tend to adopt suboptimal solutions to achieve quick software development. In such a way, the released software usually involves not-quite-right code that is called technical debt, which will significantly decrease the quality of software and increase the maintenance cost. Recently, the concept of self-admitted technical debt (SATD) is proposed and refers to technical debt that is self-admitted by developers in code comments. Existing studies mainly focus on detecting technical debt by classifying code comments into either “SATD” or “non-SATD.” However, different types of SATD has different impacts on software maintenance and needs to be handled by different developers. Therefore, the detected SATD should be further classified so that developers can understand and remove technical debt better. In this article, we propose a new method based on eXtreme Gradient Boosting (XGBoost) to classify SATD into multiple classes. In our approach, we first preprocess the original code comments and adopt the easy data augmentation strategy to overcome the class unbalance problem. Then, chi-square is leveraged to select representative features from the textual feature set. Finally, we apply XGBoost to train a classifier and use the trained classifier to partition each comment into the corresponding class. We experimentally investigate the effectiveness of our approach on a public dataset, including 62 566 code comments from 10 open-source projects. Experimental results show that our approach achieves 56.66% in terms of macroaveraged precision, 59.07% in terms of macroaveraged recall, and 55.77% in terms of macroaveraged F-measure on average, and outperforms the natural language processing based method by 4.98%, 5.32%, and 3.17%, respectively. In addition, the experimental results also demonstrate that the data augmentation strategy is effective in improving the effectiveness of our approach.

Federated learning (FL) is a promising new technology in the field of IoT intelligence. However, exchanging model-related data in FL may leak the sensitive information of participants. To address this problem, we propose a novel privacy-preserving FL framework based on an innovative chained secure multiparty computing technique, named chain-PPFL. Our scheme mainly leverages two mechanisms: 1) single-masking mechanism that protects information exchanged between participants and 2) chained-communication mechanism that enables masked information to be transferred between participants with a serial chain frame. We conduct extensive simulation-based experiments using two public data sets (MNIST and CIFAR-100) by comparing both training accuracy and leak defence with other state-of-the-art schemes. We set two data sample distributions (IID and NonIID) and three training models (CNN, MLP, and L-BFGS) in our experiments. The experimental results demonstrate that the chain-PPFL scheme can achieve practical privacy preservation (equivalent to differential privacy with ∈ approaching zero) for FL with some cost of communication and without impairing the accuracy and convergence speed of the training model.

Mobile edge computing as a novel computing paradigm brings remote cloud resource to the edge servers nearby mobile users. Within one-hop communication range of mobile users, a number of edge servers equipped with enormous computation and storage resources are deployed. Mobile users can offload their partial or all computation tasks of a workflow application to the edge servers, thereby significantly reducing the completion time of the workflow application. However, due to the open nature of mobile edge computing environment, these tasks, offloaded to the edge servers, are susceptible to be intentionally overheard or tampered by malicious attackers. In addition, the edge computing environment is dynamical and time-variant, which results in the fact that the existing quasistatic workflow application scheduling scheme cannot be applied to the workflow scheduling problem in dynamical mobile edge computing with malicious attacks. To address these two problems, this paper formulates the workflow scheduling problem with risk probability constraint in the dynamic edge computing environment with malicious attacks to be a Markov Decision Process (MDP). To solve this problem, this paper designs a reinforcement learning-based security-aware workflow scheduling (SAWS) scheme. To demonstrate the effectiveness of our proposed SAWS scheme, this paper compares SAWS with MSAWS, AWM, Greedy, and HEFT baseline algorithms in terms of different performance parameters including risk probability, security service, and risk coefficient. The extensive experiments results show that, compared with the four baseline algorithms in workflows of different scales, the SAWS strategy can achieve better execution efficiency while satisfying the risk probability constraints.

With the development of video and image processing technology, the field of video tampering forensics is facing enormous challenges. Specifically, as the fundamental basis of judicial forensics, passive forensics for object removal video forgery is particularly essential. To extract tampering traces in video more sufficiently, the author proposed a spatiotemporal trident network based on the spatial rich model (SRM) and 3D convolution (C3D), which provides three branches and can theoretically improve the detection and localization accuracy of tampered regions. Based on the spatiotemporal trident network, a temporal detector and a spatial locator were designed to detect and locate the tampered regions in the temporal and spatial domains of videos. For the temporal detector, 3D CNNs were employed in three branches as the encoders and a bidirectional long short-term memory (BiLSTM) as the decoder. For the spatial locator, a backbone network named C3D-ResNet12 was designed as the encoder of the three branches, and the region proposal networks (RPNs) were employed as the decoders in three branches. In addition, we optimized the loss functions of the above two algorithms based on focal loss and GIoU loss. The experimental results revealed the effectiveness of spatiotemporal detection and localization algorithms: for temporal forgery detection, the accuracy of the frame classification increased to 99+%; for spatial forgery localization, the successful localization rate of the tampered regions in forged frames reached 96+%, and the mean intersection over union of the located tampered regions and the real tampered regions reached 62+%.

As major infrastructures are increasingly depending on electricity, the smart grid has become an important base for industrial manufacturing and residential living. Despite the benefits of smart grids, the reliability and continuity of power services are often threatened by severe nature disasters and human errors. In smart grids, the centralized and often large-sized grid equipment hinder the rapid recovery and flexible reconfiguration in an emergency. Meanwhile, the large amount of personal equipment and their invisibility make it difficult for the grid operators to utilize assets optimally and easily. In addition, since the power service is provided by multiple energy functions, which consists voltage transformation, transmission, and storage, only considering the restoration of power generation function will restrict the service capacity and lengthen the response time. To address these problems, this article proposes an energy function virtualization for smart grid to decouple the implementation of energy functions from the underlying physical infrastructure to speed up the deployment and test of energy functions. With the help of distributed infrastructure resources, manager can redeploy energy functions and accelerate the service response in smart grid. To motivate prosumers to contribute private function resources, an optimized network calculus performance assessment scheme and a game theory-based resource orchestration scheme are proposed. Simulation results show that proposed scheme can dynamically adjust the delay factor to shorten the emergency response time.

Traditional recommendation methods suffer from limited performance, which can be addressed by incorporating abundant auxiliary/side information. This article focuses on a personalized music recommender system that incorporates rich content and context data in a unified and adaptive way to address the abovementioned problems. The content information includes music textual content, such as metadata, tags, and lyrics, and the context data incorporate users' behaviors, including music listening records, music playing sequences, and sessions. Specifically, a heterogeneous information network (HIN) is first presented to incorporate different kinds of content and context data. Then, a novel method called content- and context-aware music embedding (CAME) is proposed to obtain the low-dimension dense real-valued feature representations (embeddings) of music pieces from HIN. Especially, one music piece generally highlights different aspects when interacting with various neighbors, and it should have different representations separately. CAME seamlessly combines deep learning techniques, including convolutional neural networks and attention mechanisms, with the embedding model to capture the intrinsic features of music pieces as well as their dynamic relevance and interactions adaptively. Finally, we further infer users' general musical preferences as well as their contextual preferences for music and propose a content- and context-aware music recommendation method. Comprehensive experiments as well as quantitative and qualitative evaluations have been performed on real-world music data sets, and the results show that the proposed recommendation approach outperforms state-of-the-art baselines and is able to handle sparse data effectively.

With the rapid development of various computing technologies, the constraints of data processing capabilities gradually disappeared, and more data can be simultaneously processed to obtain better performance compared to conventional methods. As a standard statistical analysis method that has been widely used in many fields, Independent Component Analysis (ICA) provides a new way for motion detection by extracting the foreground without precisely modeling the background. However, most existing ICA-based motion detection algorithms use only two-channel data for source separation and simply generate the observation vectors by decomposing and reconstructing the images by row, hence they cannot obtain an integrated and accurate shape of the moving objects in complex scenes. In this article, we propose a refined ICA algorithm for motion detection (RICA-MD), which fuses a larger number of channels than conventional ICA-based motion detection algorithms to provide more effective information for foreground extraction. Meanwhile, we propose four novel methods for generating observation vectors to further cover the diverse motion styles of the moving objects. These improvements enable RICA-MD to effectively deal with slowly moving objects, which are difficult to detect using conventional methods. Our quantitative evaluation in multiple scenes shows that our proposed method is able to achieve a better performance at an acceptable cost of false alarms.

Remaining time predictive monitoring of business processes (BPs) is a key research issue in business process mining, which provides timely predictive information for stakeholders to take proactive corrective actions to reduce process execution risk such as exceeding time limit or to adjust the priority of activities. However, current researches on remaining time prediction only consider the impact of internal attributes of single process instance, but ignore the resource competition among multiple instances executed together. Therefore, this paper takes resource competition into consideration and characterizes several inter-instance attributes as the input of prediction. We also prioritize and select some key activities that strongly impact the execution time of BPs according to historical event logs and include them as input of the prediction. Meanwhile, in order to solve the instability of one single prediction model in complex scenarios, a multilayer hybrid model constructed from XGBoost and LightGBM models using stacking technique is proposed. Experiments on four real-life datasets show that our approach of considering attributes among instances and including key activities into a hybrid model outperforms other prediction methods.

In software maintainence, defect report severity prediction is an important task which can effectively help developer judge the urgency of defects. However, manually classifying the severity of defect reports is very time consuming and tedious. Recently, researchers have proposed many advanced methods to automate the severity prediction of defect reports. But there is still room for improvement in performance. Therefore, in this paper, we propose a distinctive method for automatically identifying the severity of software defect reports using convolutional neural network (CNN). We first preprocess defect reports and select textual features by genetic algorithms (GA). Then, the Word2Vec model is employed to generate word vectors for the selected features in each defect report. Finally we train the classifier based on CNN and leverage the trained classifier to predict the severity of defect reports. To validate the performance of our method, we experiment with defect reports from four open source projects and compare our method with three common machine learning methods. The experimental results show that our method achieves 77.38% in terms of precision, 62.09% in terms of recall and 68.76% in terms of Fl-score on average, and outperforms the best baseline method by 11.61%, 7.23% and 9.32%, respectively.

The activeness of regional business entities, like restaurants, cinemas and shopping malls, represents the evolvement of their corresponding commercial districts, whose prediction helps practitioners grasp the trend of commercial development and provides support for urban layout. On the other hand, online social network services, such as Yelp, are generating massive online reviews toward business entities every day, which provide a solid data source for the prediction of regional commercial activeness and entity condition through big data technology rather than applying business data with limited access and poor time efficiency. Inspired by the outstanding performance of deep learning in the field of image and video processing, this paper proposes a deep spatio-temporal residual network (DSTRN) model for regional commercial activeness prediction using online reviews and check-in records of commercial entities. Furthermore, aiming at predicting business trend of entities, we also propose a novel multi-view entity condition prediction model (SBCE) based on online views, along with business attributes and regional commercial activeness. The experiments on the public Yelp datasets demonstrate that both DSTRN and SBCE outperform the compared approaches.

Mining high-quality process models from real-life event logs remains a huge challenge owing to the presence of noises in the logs. Noises lead to unnecessary structures in process models, which further impede their precision and fitness. This paper proposed a novel double granularity method of filtering out noise logs based on event dependency. In this method, local dependency and global dependency of events in recorded logs are coupled as a mixed dependency to conduct fine-grained filtering of noise events based on statistical analysis. Furthermore, a coarse-grained filtering strategy is added to the method for removing specific noise traces that cannot be detected by fine-grained filtering. Comparison experiments on one synthetic and five real-life datasets with two other filtering algorithms verified the superior performance and high precision of the method.

Outcome-oriented predictive process monitoring plays an important role for business process management, which is to predict the most likely outcome class (positive or negative) for an on-going case given the event log consisting of completed business process instances with labeled outcome classes. Unfortunately, the existing traditional machine learning methods for this problem require a lot of manual intervention and long time in real-time prediction applications. In order to construct a predictive classification model automatically, we propose an effective approach based on deep learning techniques, called Att-Bi-LSTM, which is combined with the bidirectional long short-term memory network and the attention-mechanism. This approach can capture and optimize the features that have a decisive effect on the outcome for a completed case so as to construct a predictive model with good performance. The extensive experiments conducted on twelve real datasets show that our approach outperforms the state-of-the-art ones in terms of prediction accuracy, earliness, and time performance.

With the continuous expansion of software market and the updating of the maturity of the software development process, the performance requirements of software users have gradually become prominent. Performance issues are closely related to the source code. Thus, with the increasing complex of the software product, its performance changed during the evolution of the software product. Performance optimization related work has always been an important goal for developers who usually coding at a low-level. However, performance problems are well studied on architecture level. All too often, some developers are ignorant of the way their code modifications affect performance and simply to wait until performance drops to a point that is unacceptable to the business side. As software developers did a lot of daily work at code level, we think code level performance awareness can help developers in sight of the performance of the code that they are working with. To deal with this, we firstly build performance-aware code change model to identify the performance changes and its related code changes at the granularity of function between each two reversions of a program. Then, we analyzed the evolution history of the code performance and mined the frequent code change patterns that used to improve performance. We have build related tool to implement the proposed approach and applied it to 8 open source projects.

Point-Of-Interest (POI) recommendation assists users to find their preferred places and helps businesses to attract potential customers.However, the data sparsity and the complexity of user check-in behavior pose a big challenge to POI recommender systems.To tackle this challenge, we propose a POI recommendation method named HeteGeoRankRec based on user contextual behavior semantics.First, to mine the fine-grained user behavioral features, we employ the meta path of Heterogeneous Information Network (HIN) to represent the complex semantic relationship among users and POIs and integrate the context constraints (such as time and weather) into the meta paths.Secondly, we propose a weighted matrix factorization model considering the influence of geographical distance to obtain semantic preference through the user-POI semantic correlativity matrixes generated by multiple meta paths.Finally, we introduce a ranking-based fusion method, which unifies the recommendation results of different meta paths as the final preference of users.Experiments on the real data collected from Foursquare show that HeteGeoRankRec has the better performance than the state-ofthe-art baselines.

Summary Fog computing is used as a popular extension of cloud computing for a variety of emerging applications. To incorporate various design choices and customized policies in fog computing paradigm, Microservices is proposed as a new software architecture, which is easy to modify and quick to deploy fog applications because of its significant features, ie, fine granularity and loose coupling. Unfortunately, the Microservices architecture is vulnerable due to its wildly distributed interfaces that are easily attacked. However, the industry has not been fully aware of its security issues. In this paper, a survey of different security risks that pose a threat to the Microservices‐based fog applications is presented. Because a fog application based on Microservices architecture consists of numerous services and communication among services is frequent, we focus on the security issues that arise in services communication of Microservices in four aspects: containers, data, permission, and network. Containers are often used as the deployment and operational environment for Microservices. Data is communicated among services and is vital for every enterprise. Permission is the guarantee of services security. Network security is the foundation for secure communication. Finally, we propose an ideal solution for security issues in services communication of Microservices‐based fog applications.

By suggesting new visiting places, point-of-interest (POI) recommendation not only assists users to find their preferred places, but also helps businesses to attract potential customers. Recent studies have proposed many approaches to the POI recommendation. However, the data sparsity and complexity of user check-in behavior still pose big challenges to accurate personalized POI recommendation. To tackle these problems, in this paper, we propose a POI recommendation model named HeteGeoRankRec based on user contextual behavior semantics. First, we employ the meta-path of heterogeneous information network (HIN) to represent the complex semantic relationship among users and POIs. Second, we introduce different context constraints (such as time and weather) into the meta-path, to reveal the fine-grained user behavioral features. Afterwards, we propose a weighted matrix factorization model which considers the influence of geographical distance through the user–POI semantic correlativity matrices generated by multiple meta-paths. Finally, we present a fusion method based on learning to rank, which unifies the recommendation results of different meta-paths as the final user preference. The experiments on the real data collected from Foursquare demonstrate that HeteGeoRankRec has the better performance than the state-of-the-art baselines.

Design patterns play an important role in the understanding and implementation of software design process, as well as the restoration of architecture. Consequently, the detection of a design pattern represents a pivotal problem for the comprehension of many complex software systems. However, most approaches based on graph matching are faced with search space explosions and low efficiency in terms of mining speed. To address this problem, this paper proposes an approach to mine design pattern instances in source code by degree-driven matching which is divided into two parts. The first part concerns the sub-system division, in which all the information related to detection is included in the relevant region for the data graph. The other concerns the match with the cross-validation sequence based on certain rules to obtain the instances of an effective region. Extensive experiments, using a design instance library, are conducted to evaluate the approach's performance in comparison with other tools on eight open source software projects. The results show that the proposed approach can detect design patterns more effectively than current state-of-the-art approaches.

Sequences of duplicate code, either with or without modification, are known as code clones or just clones. Code clones are generally considered undesirable for a number of reasons, although they can offer some convenience to developers. The detection of code clones helps to improve the quality of source code through software re-engineering. Numerous methods have been proposed for code clone detection in Java code. However, the existing methods are mostly based on the Java source code, while only a few focus on its bytecode, in fact, the Java bytecode reflects more of the semantic nature of the source code than the source code itself does. In this paper, we propose a novel code clone detection method based on Java bytecode. Using the block-level code fragments extracted from bytecode, it can simultaneously detect code clones at both method level and block level. In addition, during the process of code clone detection, the similarities of both method call sequences and instruction sequences are calculated in order to improve accuracy. We conduct two extensive experiments to evaluate the performance of our method. The results show that the proposed method can detect code clones more effectively than the state-of-the-art methods.

Developing large-scale software usually involves the interaction of a great number of engineers over a long period. To discover the collaboration patterns from developing logs helps improve the software development processes. Traditional techniques of process mining can be employed to identify such patterns. Unfortunately, due to the high uncertainty of software development process, they tend to obtain “spaghetti” models which are difficult to comprehend or even misleading. As a remedy, in this paper we propose an approach to the discovery of collaboration patterns existing in software development process by aligning development logs. It considers not only the sequence of activities, but also the collaboration of actors who perform activities. Instead of using time-consuming graph mining techniques, it employs the trace alignment, which is much more straightforward. Moreover, unlike some traditional approaches, the discovered patterns are determined because we do not depend on the mined process model that is usually uncertain due to the unstructured nature of software development process. The experimental results based on a large dataset generated from CPNTools demonstrate the effectiveness of our approach.

With the popularity of social networks, Twitter has become one of the dominant providers of massive quantities of information.Exploring the distributions and correlations from Twitter data helps accurate personalized recommendations.Online Analytical Processing, or OLAP, provides an intuitive form that is suitable for exploring Twitter data.Unfortunately, the traditional OLAP approaches can only deal with structured data, not unstructured textual data like tweets.The key to applying OLAP to Twitter data is to mine and build a dimension hierarchy of tweeter interests.However, the current methods can extract tweeter interests from Twitter data on a single level, but fail to obtain a hierarchy of tweeter interests with different granularities.To address this problem, we propose a LDA-based model, called MS-LDA, which combines tweeters' social relationships and tweets to extract and build the tweeters' interest dimension hierarchy.Such a dimension hierarchy can be further employed to apply OLAP techniques to Twitter data.In addition, we employ Word2vec to obtain the linguistic similarity of words in tweets, to improve its effectiveness.The extensive experiments demonstrate that our method can effectively extract the dimension hierarchy of tweeters' interests for multidimensional analysis.

Online Analytical Processing, or OLAP, is an approach to answering multidimensional analytical (MDA) queries in an interactive way. However, the traditional OLAP approaches can only deal with structured data, but not unstructured textual data like tweets. To address this problem, we propose a Latent Dirichlet Allocation (LDA)-based model, called Multilayered Semantic LDA (MS-LDA), which detects the hidden layered interests from Twitter data based on LDA. The layered dimension of interests can be further used to apply OLAP techniques to Twitter data. Furthermore, MS-LDA employs the semantic similarity among words of tweets based on word2vec, and also the social relationship among twitters, to improve its effectiveness. The extensive experiments demonstrate that MS-LDA can effectively extract the dimension hierarchy of tweeters' interests for OLAP.

Identifying features and creating a feature model during the process of software product line engineering is time-consuming and requires substantial effort from modelers. In recent years, a number of approaches that map goal models to feature models have been proposed so as to avoid creating the feature model from scratch. However, these approaches can only map part of the elements, such as the goals. The question of how to map the dependencies among actors to the feature model remains an open problem. In this paper, we exploit the standard goal-oriented framework, i.e., the i* framework, for constructing a more complete domain feature model. In particular, we propose mapping rules as well as an algorithm for mapping dependencies among actors to the feature model. In addition, we seek to customize the application products using the i* model evaluation approach during the application engineering phase. The case shows that our approach is practical and efficient.

Structural design patterns address concerns related to high-level structures for applications being developed. Accurately recovered instances of structural design patterns support development related tasks like program comprehension and reengineering. However, the detection of structural design pattern instances is not always a straightforward task. The lack of documentation, the ad-hoc nature of programming and the possible variants of pattern instances often lead to the low accuracy of detection. In this paper, we present an approach to the detection of instances of structural design patterns using source codes. We first transform the source codes and predefined patterns into graphs, with the classes as nodes and the relations as edges. We then identify the instances of sub-patterns that would be the possible constituents of pattern instances by means of subgraph discovery. The sub-pattern instances are further merged by joint classes to see if the collective matches one of the predefined patterns. Compared with existing approaches, our approach focuses on simple sub-patterns, not complicated patterns. In this way, it can not only simplify the detection process, but also detect multiple pattern instances at a time. The results of the experiments on detecting pattern instances of Adapter, Bridge, Composite, Decorator and Proxy from 4 open source software systems demonstrate that our approach obtains better precision than the existing approaches.

A service robot has to identify objects for given tasks by using the camera mounted on its body. In general, previously proposed object-recognition systems do not show enough performance to apply them to service robots. Since, the object-recognition system for service robots must be robust for environmental conditions and fast enough to support its tasks. Changes of Illumination, viewpoint and scale level are examples for those changes. In addition, the system must be robust for partially occluded cases. To satisfy those requirements, we propose the system with novel modeling and matching methods. Moreover, our system can show better performance by adjusting parameter based on environmental conditions. Through lots of tests for different environmental changes, our system is shown to be partially invariant to illumination and viewpoints. Moreover, our system verifies its robustness for various scale levels and partially occluded cases. Consequently, service robots can identify objects efficiently in environmental changes by adopting the recognition system we proposed.