Search

Malware detection is an important task for the ecosystem of mobile applications (APPs), especially for the Android ecosystem, and is vital to guarantee the user experience of Android APPs. There have been some exiting methods trying to solve the problem of malware detection, but the methods suffer from several defects, such as high time complexity and mediocre accuracy, which seriously decrease the practicability of existing methods. To solve these problems, in this study, we propose a novel Android malware detection framework, where we contribute an efficient Application Programming Interface (API) call sequences extraction algorithm and an investigation of different types of classifiers. In API call sequences extraction, we propose an algorithm for transforming the function call graph from a multigraph into a directed simple graph, which successfully avoids the unnecessary repetitive path searching. We also propose a pruning search, which further reduces the number of paths to be searched. Our algorithm greatly reduces the time complexity. We generate the transition matrix as classification features and investigate three types of machine learning classifiers to complete the malware detection task. The experiments are performed on real‐world Android Packages (APKs), and the results demonstrate that our method significantly reduces the running time and produces high detection accuracy. [ABSTRACT FROM AUTHOR]

In the development of applications for mobile multimedia computing, it has been a core problem to improve the efficiency of applications development. The use of Web APIs has played an important role in applications development and mashups creation, but it takes a lot of time to find a suitable Web API. In this paper, we propose to employ APIs recommendation to solve this problem. We use the matrix factorization (MF) model to predict the relationship between user and Web APIs. The relationship between user and Web APIs is represented by latent features. But different from MF model, we find that the relationship between Web APIs have an impact on prediction performance. This paper uses the embedding technique and mines the latent relationships between APIs and we develop a novel prediction model that leverages the latent relationships between APIs, which is named as LRM (LRM is short for latent relationships mining). The latent relations are input into the LRM model to produce the relation prediction between APIs and developers. The experimental results show that our method achieves high performance and behaves the best compared to existing baselines. [ABSTRACT FROM AUTHOR]

The rapid development of Internet-of-Things (IoT) computing leads to many problems, among which the management of massive mobile services has attracted much attention. When developers are looking for a service for IoT computing from mobile services, they typically try to discover the services according to annotations. If the mobile services are not assigned by proper annotations, it will be difficult for developers to find the suitable service. For providers, if the services that they provide cannot be used by developers, there will be no revenue. Therefore, it is a critical to assign proper semantic annotations to the mobile services. Existing approaches usually use the call records between services and developers to construct a score matrix, and compute the similarity between services and semantic annotations. However, these approaches do not leverage the natural association between services, providers and users. To make full use of the information inherent in services, we construct a heterogeneous information network (HIN) for service data, and propose a new model named GoT, which fully utilizes the structural and semantic information. GoT contains four components, which are the metapath construction, the intra-metapath fusion, the inter-metapath fusion, and the semantic annotation recommendation. We collected a real-world Web API dataset and performed adequate experiments. The experimental results show that our model produces superior recommendation accuracy and alleviates the cold-start problem. [ABSTRACT FROM AUTHOR]

In recent years, with the development of software development, a large number of developers develop software by invoking API. With the increasing number of APIs, how to accurately recommend the APIs to developers has become a urgently necessary task. In this paper, we discover that there is a relationship between the user and the API, and use such relationships and collaborative learning techniques to finish APIs recommendation. We propose a holistic framework that contains three models. In the models, we design a joint matrix factorization technique and try to discover the preference among APIs invocation process. In natural language processing, word embedding is widely used. In our models, we use doc2vec to turn the representation of users and APIs into vector representation and calculate the similarity separately to generate the relationships. Besides the two modes in users side and APIs side, we also propose an ensemble model fully leveraging the preference mined from both users side and APIs side. We conduct the experiments on a real-world dataset and the experimental results show that our models perform better than all compared methods. [ABSTRACT FROM AUTHOR]

Sentiment classification is a key task in sentiment analysis, reviews mining, and other text mining applications. Various models have been proposed to build sentiment classifiers, but the classification performances of some existing methods are not good enough. Meanwhile, as a subproblem of sentiment classification, positive and unlabeled learning (PU learning) problem widely exists in real‐world cases, but it has not been given enough attention. In this article, we aim to solve the two problems in one framework. We first build a model for traditional sentiment classification based on adversarial learning, attention mechanism, and long short‐term memory (LSTM) network. We further propose an enhanced adversarial learning method to tackle PU learning problem. We conducted extensive experiments in three real‐world datasets. The experimental results demonstrate that our models outperform the compared methods in both traditional sentiment classification problem and PU learning problem. Furthermore, we study the effect of our models on word embedding. Finally, we report and discuss the sensitivity of our models to parameters. [ABSTRACT FROM AUTHOR]

Traditional topic modeling has been widely studied and popularly employed in expert systems and information systems. However, traditional topic models cannot discover structural relations among topics, thus losing the chance to explore the data more deeply. Hierarchical topic modeling has the capability of learning topics, as well as discovering the hierarchical topic structure from text data. But purely unsupervised models tend to generate weak topic hierarchies. To solve this problem, we propose a novel knowledge-based hierarchical topic model (KHTM), which can incorporate prior knowledge into topic hierarchy building. A key novelty of this model is that it can mine prior knowledge automatically from the topic hierarchies of multiple domains corpora. In this paper, the knowledge is represented as the word pairs which satisfy the requirement of frequent co-occurrence, and knowledge is organized in form of hierarchical structure. We also propose an iterative learning algorithm. For evaluation, we crawled two new multi-domain datasets and conducted comprehensive experiments. The experimental results show that our algorithm and model can generate more coherent topics, and more reasonable hierarchical structure. [ABSTRACT FROM AUTHOR]

Topic models are a prevailing tool for exploring latent topics in documents, and for helping to complete many NLP tasks. To obtain good topics for a corpus, a preprocessing step is often needed to remove common stop words and identify topic general words (TGW) from the corpus. Such words can seriously harm the topic formation because they create spurious co-occurrence of unrelated words. Also, they are likely to occupy top positions of multiple topics, lead to many unrelated words being grouped under a topic, and consequently result in inscrutable and similar topics. In an application, one typically manually identifies and removes a list of TGWs in the corpus. This is a time consuming process and very hard to do by a layman user. In this paper, we aim to solve this problem automatically. The proposed approaches can be based on the current corpus alone or multiple corpora. In the latter case, a novel continuous learning method is proposed that learns from past results of multiple domain corpora to help identify TGWs in the current domain. We conduct experiments in two real-world datasets, and the experimental results show that the proposed approaches achieve superior results. [ABSTRACT FROM AUTHOR]

According to the features of the AICE protocol, the authors select and extend the SVO logic to conduct the formal analysis of the protocol from the perspective of theoretical analysis of modal logic. The authors give the information flows of the AICE protocol by combining the privacy-preserving authentication (PPA) protocol and integrity checking protocol for MEC (ICE) together. In recent years, mobile networks and wireless networks have experienced explosive growth. [Extracted from the article]

QoS prediction is one of the key problems in Web service recommendation and selection. The context information is a dominant factor affecting QoS, but is ignored by most of existing works. In this paper, we employ the context information, from both the user side and service side, to achieve superior QoS prediction accuracy. We propose two novel prediction models, which are capable of using the context information of users and services respectively. In the user side, we use the geographical information as the user context, and identify similar neighbors for each user based on the similarity of their context. We study the mapping relationship between the similarity value and the geographical distance. In the service side, we use the affiliation information as the service context, including the company affiliation and country affiliation. In the two models, the prediction value is learned by the QoS records of a user (or a service) and the neighbors. Also, we propose an ensemble model to combine the results of the two models. We conduct comprehensive experiments in two real-world datasets, and the experimental results demonstrate the effectiveness of our models. [ABSTRACT FROM AUTHOR]

In the age of Web 2.0, user generated content (UGC), such as user review and social tag, ubiquitously exists on the Internet. Although there exist different kinds of UGC in recommender systems, the existing works only studied a single kind of UGC in each of their papers. Thus, the previous works lose a chance to uncover the similar effects of different kinds of UGC in recommender systems. In this paper, we propose a unified way to utilize various types of UGC to enhance the recommendation accuracy. We build two novel statistical models, which are based on collaborative filtering and topic modeling. Incorporating UGC text, one model focuses on learning user preferences, and the other model aims to learn user preferences and item aspects jointly. With an effective parameter estimation algorithm, our models can not only acquire prediction values of missing ratings, but also produce interpretable topics. We conducted comprehensive experiments on three real-world datasets. The experimental results demonstrate that our proposed models can achieve large improvements compared to several well-known baseline models. [ABSTRACT FROM AUTHOR]

Due to the positive impact of ride sharing on urban traffic and environment, it has attracted a lot of research attention recently. However, most existing researches focused on the profit maximization or the itinerary minimization of drivers, only rare work has covered on adjustable price function and matching algorithm for the batch requests. In this paper, we propose a request matching algorithm and an adjustable price function that benefits drivers as well as passengers. Our request-matching algorithm consists of an exact search algorithm and a group search algorithm. The exact search algorithm consists of three steps. The first step is to prune some invalid groups according to the total number of passengers and the capacity of vehicles. The second step is to filter out all candidate groups according to the compatibility of requests in same group. The third step is to obtain the most profitable group by the adjustable price function, and recommend the most profitable group to drivers. In order to enhance the efficiency of the exact search algorithm, we further design an improved group search algorithm based on the idea of original simulated annealing. Extensive experimental results show that our method can improve the income of drivers, and reduce the expense of passengers. Meanwhile, ride sharing can also keep the utilization rate of seats 80%, driving distance is reduced by 30%. [ABSTRACT FROM AUTHOR]

Indoor multiple target tracking is a promising research field that attracts many efforts. Traditional approaches for tackling this problem are usually model-based methods. WiFi-based tracking approaches suffer from high cost in retrieving the CSI information. Most RF signal-based methods provide a mathematical framework correlating movement in space to a link's RSS value. Real RSS values are used to model the signal attenuation, and the distance correlation with signal attenuation is used to estimate locations. In this paper, we propose DCT, a noise-tolerant, unobtrusive and device-free tracking framework. DCT adopts density-based clustering to find the centers. We further use a linear function of mean RSS variances and target amount and FCM algorithm to adjust the number of targets and positions. The multiple particle filter (MPF) is adopted to refine the target tracking accuracy. DCT is tolerant for noise and multi-path effects, and can fast simultaneously tracking with a O(N) time complexity. The extensive experiments in trace-driven simulations and real implementations show that DCT is efficient and effective in tracking multiple target, and can achieve a high precision. [ABSTRACT FROM AUTHOR]

Along with the popularity of intelligent services and mobile services, service recommendation has become a key task, especially the task based on quality-of-service (QoS) in edge computing environment. Most existing service recommendation methods have some serious defects, and cannot be directly adopted in edge computing environment. For example, most of existing methods cannot learn deep features of users or services, but in edge computing environment, there are a variety of devices with different configurations and different functions, and it is necessary to learn deep features behind those complex devices. In order to fully utilize hidden features, this paper proposes a new matrix factorization (MF) model with deep features learning, which integrates a convolutional neural network (CNN). The proposed mode is named Joint CNN-MF (JCM). JCM is capable of using the learned deep latent features of neighbors to infer the features of a user or a service. Meanwhile, to improve the accuracy of neighbors selection, the proposed model contains a novel similarity computation method. CNN learns the neighbors features, forms a feature matrix and infers the features of the target user or target service. We conducted experiments on a real-world service dataset under a batch of cases of data densities, to reflect the complex invocation cases in edge computing environment. The experimental results verify that compared to counterpart methods, our method can consistently achieve higher QoS prediction results. [ABSTRACT FROM AUTHOR]

Multi-view clustering, which utilizes the ample information provided by multiple sources to obtain better performance, has attracted much attention. However, existing clustering algorithms either have no ability to offer confidence for each assignment or suffer from the disturbance of outliers. To address these problems, in this paper, we propose a novel multi-view fuzzy clustering method via transferring softmin to fuzzy models. To obtain fuzzy assignments, we utilize the softmin with temperature and further develop an efficient algorithm to solve the non-convex problem approximately. We also show another explanation for the algorithm from the aspect of the prior distribution of various views. Besides, we design a scalable robust loss function, which interpolates between ℓ 2 -norm and the squared ℓ 2 -norm, to enhance the robustness to outliers. Extensive experiments show the superiority of our model under different clustering metrics. [ABSTRACT FROM AUTHOR]

The multiturn dialogue system has been prevalently used in e‐commerce websites and modern information systems, which significantly improves the efficiency of problem solving and further promotes the service quality. In a multiturn dialogue system, the problem of intention classification is a core task, as the intention of a customer is the basis of subsequent problems handling. However, traditional related methods are unsuitable for the classification of multiturn dialogues. Because traditional methods do not distinguish the importance of each sentence and concatenate all sentences in the text, which is likely to generate a model with low prediction accuracy. In this paper, we propose a method of multiturn dialogue classification based on key sentences mining. We design a keywords extraction algorithm, mining key sentences from the dialogue text. We propose an algorithm finishing the computation of the weights of each sentence. According to the sentence weight and the sentence vector, the dialogue text is transformed to a dialogue vector. The dialogue text is classified by a classifier, and the input is the dialogue vector. We conducted sufficient experiments on a real‐world dataset, evaluating the performance of the proposed method. The experimental results show that our method outperforms the related methods on a series of evaluation metrics. [ABSTRACT FROM AUTHOR]

An accurate call traffic forecasting can help the call center to schedule and manage its employees more scientifically. Meanwhile, to meet the needs that some tasks in the call center require the prediction of call traffic in different time buckets for a future long term, it is necessary to forecast the call traffic in a long-term and multi-step way. However, existing forecasting methods cannot solve this problem as (1) Most existing methods merely focus on short-term forecasting for the next hour or the next day. (2) The temporal features of call traffic are ignored, which leads to a lower accuracy in long-term forecasting. Hence, in this paper, we propose a holistic solution for forecasting long-term multi-step ahead call traffic. In our method, we give a categorized way for temporal features by studying the call traffic data. After data preprocessing, we develop an extraction method for temporal features extraction for training the forecasting model. We propose two forecasting strategies based on taking different types of features as input. Experimental results on the real-world call traffic dataset show the effectiveness of our solution, including data preprocessing, temporal features mining, and the forecasting model. [ABSTRACT FROM AUTHOR]

Most of the existing similarity metrics in heterogeneous information networks depend on the pre-specified meta-path or meta-structure. This dependency may cause them to be sensitive to different meta-paths or meta-structures. In this paper, we propose a stratified meta-structure-based similarity measure named SMSS in heterogeneous information networks. The stratified meta-structure can be constructed automatically and capture rich semantics.Then, we define the commuting matrix of the stratified meta-structure by virtue of the commuting matrices of meta-paths and meta-structures. As a result, the SMSS is defined by virtue of this commuting matrix. Experimental evaluations show that the existing metrics are sensitive to different meta-paths or meta-structures and that the proposed SMSS outperforms the state-of-the-art metrics in terms of ranking and clustering. [ABSTRACT FROM AUTHOR]

With the development of sensors and of the Internet of Things (IoT), smart cities can provide people with a variety of information for a more convenient life. Effective on-street parking availability prediction can improve parking efficiency and, at times, alleviate city congestion. Conventional methods of parking availability prediction often do not consider the spatial–temporal features of parking duration distributions. To this end, we propose a parking space prediction scheme called the hybrid spatial–temporal graph convolution networks (HST-GCNs). We use graph convolutional networks and gated linear units (GLUs) with a 1D convolutional neural network to obtain the spatial features and the temporal features, respectively. Then, we construct a spatial–temporal convolutional block to obtain the instantaneous spatial–temporal correlations. Based on the similarity of the parking duration distributions, we propose an attention mechanism called d i s t A t t to measure the similarity of parking duration distributions. Through the d i s t A t t mechanism, we add the long-term spatial–temporal correlations to our spatial–temporal convolutional block, and thus, we can capture complex hybrid spatial–temporal correlations to achieve a higher accuracy of parking availability prediction. Based on real-world datasets, we compare the proposed scheme with the benchmark models. The experimental results show that the proposed scheme has the best performance in predicting the parking occupancy rate. [ABSTRACT FROM AUTHOR]