Search

Compiler diagnostic warnings help developers identify potential programming mistakes during program compilation. However, these warnings could be erroneous due to the defects of compiler warning diagnostics. Although many techniques have been proposed to automatically generate test programs for compiler warning defect detection, the effectiveness of these techniques on defect-nding is still limited, due to their ability at generating warning-sensitive test program structures. Therefore, in this paper, we propose a DIversity-guided PROgram Mutation approach, called DIPROM, to construct diverse warning-sensitive programs for effective compiler warning defect detection. Given a seed test program, DIPROM rst removes its dead code to reduce false positive warning defects. Then, the abstract syntax tree (AST) of the test program is constructed; DIPROM iteratively mutates the structures of the AST to generate warning-sensitive program variants. To improve the diversity of program variants, DIPROM applies a novel diversity function to guide the selection of the best program variants in each iteration. With the selected program variants, differential testing is conducted to effectively detect warning defects in different compilers. In the experiments, we evaluate DIPROM with two popular C compilers (i.e., GCC and Clang). Experimental results show that DIPROM can detect 75.36% and 218.42% more warning defects than two state-of-the-art approaches (i.e., Epiphron and Csmith), respectively. Meanwhile, DIPROM is efcient, which only spends 61.14% of the time of comparative approaches on average in nding the same number of warning defects. We at last applied DIPROM on the latest development versions of GCC and Clang. After two months running, DIPROM reported 12 new warning defects; nine of them have been conrmed/xed by developers.

Optimization sequences are often employed in compilers to improve the performance of programs, but may trigger critical compiler bugs, e.g., compiler crashes. Although many methods have been developed to automatically test compilers, no systematic work has been conducted to detect compiler bugs when applying arbitrary optimization sequences. To resolve this problem, two main challenges need to be addressed, namely the acquisition of representative optimization sequences and the selection of representative testing programs, due to the enormous number of optimization sequences and testing programs. In this study, we propose CTOS, a novel compiler testing method based on differential testing, for detecting compiler bugs caused by optimization sequences of LLVM. CTOS firstly leverages the technique Doc2Vec to transform optimization sequences into vectors to capture the information of optimizations and their orders simultaneously. Secondly, a method based on the region graph and call relationships is developed in CTOS to construct the vector representations of testing programssuch that the semantics and the structure information of programs can be captured simultaneously. Then, with the vector representations of optimization sequences and testing programs, a centroid based selection scheme is proposed to address the above two challenges. Finally, CTOS takes in the representative optimization sequences and testing programs as inputs, and tests each testing program with all the representative optimization sequences. If there is an output that is different from the majority of others of a given testing program, then the corresponding optimization sequence is deemed to trigger a compiler bug. Our evaluation demonstrates that CTOS significantly outperforms the baselines by up to 24.76% 45.56% in terms of the bug-finding capability on average. Within seven month evaluations on LLVM, we have reported 104 valid bugs within 5 types, of which 21 have been confirmed or fixed. Most of those bugs are crash bugs (57) and wrong code bugs (24). 47 unique optimizations are identified to be faulty and 15 of them are loop related optimizations.

With the plain text descriptions of design patterns, developers could better learn and understand the definitions and usage scenarios of design patterns. To facilitate the automatic usage of these descriptions, e.g., recommending design patterns by free-text queries, design patterns and natural languages should be adequately associated. Existing studies usually use texts in design pattern books as the representations of design patterns to calculate similarities with the queries. However, this way is problematic. Lots of information of design patterns may be absent from design pattern books and many words would be out of vocabulary due to the content limitation of these books. To overcome these issues, a more comprehensive method should be constructed to estimate the relatedness between design patterns and natural language words. Motivated by Word2Vec, in this study, we propose DPWord2Vec that embeds design patterns and natural language words into vectors simultaneously. We first build a corpus containing more than 400 thousand documents extracted from design pattern books, Wikipedia, and Stack Overflow. Next, we redefine the concept of context window to associate design patterns with words. Then, the design pattern and word vector representations are learnt by leveraging an advanced word embedding method. The learnt design pattern and word vectors can be universally used in textual description based design pattern tasks. An evaluation shows that DPWord2Vec outperforms the baseline algorithms by 17.1%-96.5% in measuring the similarities between design patterns and words in terms of Spearman's rank correlation coefficient. Moreover, we adopt DPWord2Vec on two typical design pattern tasks. In the design pattern tag recommendation task, the DPWord2Vec based method outperforms two state-of-the-art algorithms by 6.6% and 32.7% respectively when considering Recall@10. In the design pattern selection task, DPWord2Vec improves the existing methods by 6.5%-70.7% in terms of MRR.

Code completion is to predict the rest of a statement a developer is typing. Although advanced code completion approaches have greatly improved the accuracy of code completion in modern IDEs, it remains challenging to predict project-specific API method invocations or field accesses because little knowledge about such elements could be learned in advance. To this end, in this paper we propose an accurate approach called HeeNAMA to suggesting the next project-specific API member access. HeeNAMA focuses on a specific but common case of code completion: suggesting the following member access whenever a project-specific API instance is followed by a dot on the right hand side of an assignment. By focusing on such a specific case, HeeNAMA can take full advantages of the context of the code completion, including the type of the left hand side expression of the assignment, the identifier on the left hand side, the type of the base instance, and similar assignments typed in before. All such information together enables highly accurate code completion. Given an incomplete assignment, HeeNAMA generates the initial candidate set according to the type of the base instance, and excludes those candidates that are not type compatible with the left hand side of the assignment. If the enclosing project contains assignments highly similar to the incomplete assignment, it makes suggestions based on such assignments. Otherwise, it selects the one from the initial candidate set that has the greatest lexical similarity with the left hand side of the assignment. Finally, it employs a neural network to filter out risky predictions, which guarantees high precision. Evaluation results on open-source applications suggest that compared to the state-of-the-art approaches and the state-of-the-practice tools HeeNAMA improves precision and recall by 70.68% and 25.23%, relatively.

Kernel learning is widely used in nonlinear models during the implementation of forecasting tasks in analytics. However, existing forecasting models lack robustness and accuracy. Therefore, in this study, a novel supervised forecasting approach based on robust low-rank multiple kernel learning with compound regularization is investigated. The proposed method extracts the benefits from robust regression, multiple kernel learning with low-rank approximation, and sparse learning systems. Unlike existing hybrid forecasting methods, which frequently combine different models in parallel, we embed a Huber or quantile loss function and a compound regularization composed of smoothly clipped absolute deviation and ridge regularizations in a support vector machine with predefined number of kernels. To select the optimal kernels, L 1 penalization with positive constraint is also considered. The proposed model exhibits robustness, forecasting accuracy, and sparsity in the reproducing kernel Hilbert space. For computation, a simple algorithm is designed based on local quadratic approximation to implement the proposed method. Theoretically, the forecasting and estimation error bounds of the proposed estimators are derived under a null consistency assumption. Real data experiments using datasets from various scientific research fields demonstrate the superior performances of the proposed approach compared with other state-of-the-art competitors.

Million of mobile apps have been released to the market. Developers need to maintain these apps so that they can continue to benefit end users. Developers usually extract useful information from user reviews to maintain and evolve mobile apps. One of the important activities that developers need to do while reading user reviews is to locate the source code related to requested changes. Unfortunately, this manual work is costly and time consuming since: (1) an app can receive thousands of reviews, and (2) a mobile app can consist of hundreds of source code files. To address this challenge, Palomba et al. recently proposed CHANGEADVISOR that utilizes user reviews to locate source code to be changed. However, we find that it cannot identify real source code to be changed for part of reviews. In this work, we aim to advance Palomba et al. 's work by proposing a novel approach that can achieve higher accuracy in change localization. Our approach first extracts the informative sentences (i.e., user feedback) from user reviews and identifies user feedback related to various problems and feature requests, and then cluster the corresponding user feedback into groups. Each group reports the similar users’ needs. Next, these groups are mapped to issue reports by using $Word2Vec$ W o r d 2 V e c . The resultant enriched text consisting of user feedback and their corresponding issue reports is used to identify source code classes that should be changed by using our novel weight selection -based cosine similarity metric. We have evaluated the new proposed change request localization approach ( Where2Change ) on 31,597 user reviews and 3,272 issue reports of 10 open source mobile apps. The experiments demonstrate that Where2Change can successfully locate more source code classes related to the change requests for more user feedback clusters than CHANGEADVISOR as demonstrated by higher Top-N and Recall values. The differences reach up to 17 for Top-1, 18.1 for Top-3, 17.9 for Top-5, and 50.08 percent for Recall. In addition, we also compare the performance of Where2Change and two previous Information Retrieval (IR)-based fault localization technologies: BLUiR and BLIA . The results showed that our approach performs better than them. As an important part of our work, we conduct an empirical study to investigate the value of using both user reviews and historical issue reports for change request localization; the results shown that historical issue reports can help to improve the performance of change localization.

Feature selection is an important procedure that is used in data mining to extract valuable information from large quantities of data. Existing penalization methods use a single penalty function to select important features. However, these methods do not yield sufficiently accurate predictions and selection outcomes. Therefore, construction of a concise and efficient prediction model would be beneficial. In this study, we propose a novel penalty function using a ridge and minimax concave penalty to overcome the limitations of individual penalty functions. Furthermore, we introduce a robust penalized feature selection method with Huber loss function, which is implemented by a local approximation algorithm. The theoretical properties of the algorithm have been described. Simulated and real-world data analyses are used to demonstrate the efficacy of the proposed method.

Smart healthcare systems are important components in an IoT environment that attracted the researchers’ attentions, recently. For such applications the biomedical sensors are placed on patients’ body to gather the condition of the patient through a wireless body region network (WBAN). In a WBAN, energy consumption is one of the crucial issues, in particular in emergency situations. In this paper, a solution is presented using sensor node clustering methods. In the proposed method, body region is divided into three parts, upper, lower, and middle region. An improved LEACH clustering algorithm is performed in each region. After that, an evolutionary algorithm, whale optimization algorithm (WOA), is used to select cluster heads. To evaluate the proposed method, the algorithms are implemented in MATLAB environment and compared with SEP and LEACH-H solutions that are proposed before for the similar solutions. The proposed solution outperformed the other solutions and provide longer lifespan for sensors in a wireless body region network.

As one key resource to learn Application Programming Interfaces (APIs), a lot of API reference documentation lacks code samples with usage scenarios, thus heavily hindering developers from programming with APIs. Although researchers have investigated how to enrich API documentation with code samples from general code search engines, two main challenges remain to be resolved, including the quality challenge of acquiring high-quality code samples and the mapping challenge of matching code samples to usage scenarios. In this study, we propose a novel approach named ADECK towards enriching API documentation with code samples and corresponding usage scenarios by leveraging crowd knowledge from Stack Overflow, a popular technical Question and Answer (Q&A) website attracting millions of developers. Given an API related Q&A pair, a code sample in the answer is extensively evaluated by developers and targeted towards resolving the question under the specified usage scenario. Hence, ADECK can obtain high-quality code samples and map them to corresponding usage scenarios to address the above challenges. Extensive experiments on the Java SE and Android API documentation show that the number of code-sample-illustrated API types in the ADECK-enriched API documentation is 3.35 and 5.76 times as many as that in the raw API documentation. Meanwhile, the quality of code samples obtained by ADECK is better than that of code samples by the baseline approach eXoaDocs in terms of correctness, conciseness, and usability, e.g., the average correctness values of representative code samples obtained by ADECK and eXoaDocs are 4.26 and 3.28 on a 5-point scale in the enriched Java SE API documentation. In addition, an empirical study investigating the impacts of different types of API documentation on the productivity of developers shows that, compared against the raw and the eXoaDocs-enriched API documentation, the ADECK-enriched API documentation can help developers complete 23.81 and 14.29 percent more programming tasks and reduce the average completion time by 9.43 and 11.03 percent.

In this letter, we propose a deep transfer cooperative sensing (DTCS) approach in cognitive radio networks, where multiple secondary users (SUs) cooperate to detect the presence of signals from a primary user (PU) in a shared frequency band. DTCS is a cooperative spectrum sensing (CSS) framework based on unsupervised deep transfer learning. It operates on energy vectors, whose each element is a sensing result by an energy detector from individual SU. It learns the knowledge by combining the sensing results from all SUs in one radio frequency environment and transfers it to another one. This approach is applicable for detecting the presence of arbitrary unknown signals, which enhances the generalization ability and robustness of the framework. Simulation results demonstrate the effectiveness of DTCS.

Detection of abnormal behavior in surveillance videos is essential for public safety and monitoring. However, it needs constant human focus and attention for human-based surveillance systems, which is a challenging process. Therefore, automatic detection of such events is of great significance. Abnormal event detection is a challenging problem due to the scarceness of labelled data and the low probability of occurrence of such events. In this paper, we propose a novel multi-stream two-stage architecture to detect abnormal behavior in videos. Our contributions are three-fold: 1) In the first stage, we propose a 3D Convolutional Autoencoder (3DCAE) architecture for appearance and motion feature extraction from both video frame input and dynamic flow input streams of normal event training videos in an unsupervised manner. 2) We have used a multi-objective loss function for 3DCAE reconstruction which can focus more on foreground moving objects rather that the stationary background information. 3) In the second stage, the fused latent features from both video frames and dynamic flow inputs are grouped together into different clusters of normality. Then we eliminate the smaller or sparse clusters, which are supposed to contain noisy patterns in the training data, to represent stronger normality patterns. A Deep one-class Support Vector Data Description (SVDD) classifier is then trained on these 3D normality clusters to generate anomaly scores for each sample in 3D clusters to differentiate between normal and abnormal occurrences. Experimental results on three benchmarking datasets: UCSD Pedestrian, Shanghai Tech, and Avenue, show significant improvement in the performance compared to the state-of-the-art approaches.

The fused least absolute shrinkage and selection operator (LASSO) simultaneously pursuing the joint sparsity of coefficients and their successive differences has attracted significant attention for analytics purposes. Although it is extensively used, especially when the number of features exceeds the sample size, tuning the regularization parameters, which depends on noise level σ, is a challenging task since σ is difficult to estimate accurately. To tackle this problem, in this paper, we propose and study square root fused LASSO, which combines the square root loss function and joint penalty functions. In theory, we show that the proposed method can achieve the same error rate as that of fused LASSO by proving its estimation and prediction error bounds. In addition, the error rate of square root fused LASSO is lower than those of LASSO and square root LASSO via simultaneous feature selection and clustering. The choices of the regularization parameters are also shown to be free of σ. In terms of computation, this work develops a novel algorithm based on the alternating direction method of multipliers algorithm with theoretical guarantee of its convergence. Experiments on simulation and real-world datasets demonstrate the superiority of square root fused LASSO over fused LASSO and other state-of-the-art feature selection methods.

In clustering algorithm research, objects, attributes and other aspects of data sets are usually considered to be independent and identically distributed; that is, each object is assumed to be an independent and uniformly distributed individual with no impacts between objects. However, objects in real life are often neither independently nor identically distributed; that is, they are non-IID, leading to a complex coupling relationship between objects, and objects interact with each other. The results of a clustering algorithm under an independent and identical distribution may be incomplete or even misleading. To make the results of the DBSCAN algorithm as accurate as possible, an improved numerical DBSCAN algorithm based on non-IIDness learning is proposed in this paper. The algorithm calculates the coupling relationship between objects to obtain the potential relationship between objects and determines the parameters Eps and MinPts by the distribution characteristics of the data. Experiments on large-scale real and synthetic data sets show that the algorithm achieves a higher accuracy than the original DBSCAN algorithm and the main algorithms that improved upon it.

In common design pattern collections, e.g., design pattern books, design patterns are documented with templates that consist of multiple attributes, such as intent, structure, and sample code. To adapt to modern developers, the depictions of design patterns, especially some specific attributes, should advance with the current programming technologies, for example, “known uses”, which exemplifies the use scenarios of design patterns in practice, and “related patterns”, which describes the relatedness between a design pattern and the others within a context. However, it is not easy to update the contents of these attributes manually due to the diversity of the programming technologies. To address this problem, in this work, we conducted a case study to mine design pattern use scenarios and related design pattern pairs from Stack Overflow posts to enrich the two attributes. We first extracted the question posts relevant to each design pattern by identifying the design pattern tags. Then, the topics of the posts were discovered by applying topic modeling techniques. Finally, by analyzing the topics specified for each design pattern, we detected 195 design pattern use scenarios and 70 related design pattern pairs, involving 61 design patterns totally. These findings are associated with a variety of popular software frameworks and programming techniques. They could complement the existing design pattern collections and help developers better acknowledge the usage and relatedness of design patterns in today’s programming practice.

In this paper, a novel event-sampled robust optimal controller is proposed for a class of continuous-time constrained-input nonlinear systems with unknown dynamics. In order to solve the robust optimal control problem, an online data-driven identifier is established to construct the system dynamics, and an event-sampled critic-only adaptive dynamic programming method is developed to replace the conventional time-driven actor–critic structure. The designed online identification method runs during the solving process and is not applied as a priori part for the solutions, which simplifies the architecture and reduces computational load. The proposed robust optimal control algorithm tunes the parameters of critic-only neural network (NN) by event-triggering condition and runs in a plug-n-play framework without system functions, where fewer transmissions and less computation are required as all the measurements received simultaneously. Based on the novel design, the stability of system and the convergence of critic NN are demonstrated by Lyapunov theory, where the state is asymptotically stable and weight error is guaranteed to be uniformly ultimately bounded. Finally, the applications in a basic nonlinear system and the complex rotational–translational actuator problem demonstrate the effectiveness of the proposed method.

With the penetration of computation intelligence, an increasing number of learning methods are developed into power engineering, such as dc microgrid applications. This paper establishes a distributed iterative learning framework to solve the current sharing and voltage regulation problem in an islanded dc microgrid from the perspective of game theory. The control objectives of dc microgrid include not only achieving the desired output current dispatch, but also regulating the voltage of dc bus to its rated value. Based on the two objectives, local performance indexes are established and an N -player game is formulated. Each source aims to minimize its own performance index and to achieve the current sharing objective simultaneously. Under the framework of game theory, a distributed iterative learning algorithm is designed based on the Bellman optimality principle and subsequently carried out using the approximate dynamic programming technique. The proposed algorithm is data based where it does not require to have the accurate model parameters of the dc microgrid and it ensures that the dc microgrid falls into a Nash equilibrium. Furthermore, a rigorous convergence analysis of the proposed algorithm is given. To demonstrate the effectiveness of the proposed method, simulation examples are presented on a tested dc microgrid.

In crowdsourced mobile application testing, crowd workers perform test tasks for developers and submit test reports to report the observed abnormal behaviors. These test reports usually provide important information to improve the quality of software. However, due to the poor expertise of workers and the inconvenience of editing on mobile devices, some test reports usually lack necessary information for understanding and reproducing the revealed bugs. Sometimes developers have to spend a significant part of available resources to handle the low-quality test reports, thus severely reducing the inspection efficiency. In this paper, to help developers determine whether a test report should be selected for inspection within limited resources, we issue a new problem of test report quality assessment. Aiming to model the quality of test reports, we propose a new framework named TERQAF. First, we systematically summarize some desirable properties to characterize expected test reports and define a set of measurable indicators to quantify these properties. Then, we determine the numerical values of indicators according to the contained contents of test reports. Finally, we train a classifier by using logistic regression to predict the quality of test reports. To validate the effectiveness of TERQAF, we conduct extensive experiments over five crowdsourced test report datasets. Experimental results show that TERQAF can achieve 85.18% in terms of Macro-average Precision (MacroP), 75.87% in terms of Macro-average Recall (MacroR), and 80.01% in terms of Macro-average F-measure (MacroF) on average in test report quality assessment. Meanwhile, the empirical results also demonstrate that test report quality assessment can help developers handle test reports more efficiently.

In the sequence of port throughput analysis, many nonlinear and fluctuation signals are included in order to find the accuracy of port. Besides the socioeconomic factors, the virtually decision making and execution are considered as some kind of forecast. The seasonality and volatility are the critical issues in predicting the efficiency. The forecasting is a useful tool to cross these issues. The forecasting uses many qualitative and casual models and performs time series analysis to find the information about events, pattern changes, relationship between the system elements. It assumes two different kinds of phenomena share the same model of behavior. One is to promote new issues and another is to predict the outcome of the analysis. The judgmental forecasting technique is based on present situation and past situation in order to predict the issues in port. To deal with these issues, this paper addresses a method of hyperchaotic model for optimizing the throughput based on PCA. We review the latest models to provide the theoretical basis and propose novel ideas; the proposed methodology is simulated compared with the other state-of-the-art approaches. The experimental analysis proves the robustness of the model. In the future, more scenarios will be tested.

In this paper, a data-based control method based on adaptive dynamic programming (ADP) algorithm is proposed for a class of discrete-time (DT) systems in the case of multiple delays. Data-based ADP method is implemented by virtue of the measured input and output data. The condition of the existence of the corresponding equivalent multiple delays system is derived according to the characteristics of time-delay system. A novel data-based state equation is developed that only composed of input and output data, which is very meaningful in practical applications. By using the data-based ADP method, the output feedback control problem is solved only by measuring the input and output of the system with multiple delays. The convergence proofs of the designed policy iteration and value iteration algorithms are given, respectively. The simulation example is presented to demonstrate the validity of the proposed data-based ADP method.

In practice, classification problems have appeared in many scientific fields, including finance, medicine and industry. It is critically important to develop an effective and accurate classification model. Although numerous useful classifiers have been proposed, they are unstable, sensitive to noise and slow in computation. To overcome these drawbacks, the combination of feature selection techniques with traditional machine learning models is of great help. In this paper, a novel feature selection method called the opposition-based seagull optimization algorithm (OSOA) is proposed and studied. The OSOA is constructed based on an SOA whose population is determined by the opposition-based learning (OBL) algorithm. To evaluate its overall classification performance, some measures, including classification accuracy, number of selected features, receiver operating characteristic curve (ROC), and computation time, are adopted. The empirical results indicate that the suggested method exhibits higher or similar accuracy and computational efficiency in comparison with genetic algorithm (GA)-, simulated annealing (SA)-, and Fisher score (FS)-based classification models. The experimental results show that the OSOA is a computationally efficient feature selection technique that has the ability to select relevant variables. Furthermore, it performs well with high-dimensional data whose number of variables exceeds the number of samples. Thus, the OSOA is an effective approach for the enhancement of classification performance.

An adaptive fuzzy tracking control is investigated for a category of multiple-input multiple-output switched uncertain nonlinear systems in strict-feedback form. The unknown nonlinear function and switching signals with average dwell time are contained in the systems. The control method is designed by generalized fuzzy hyperbolic model and backstepping technique. Through adding a first-order filter into conventional backstepping method, the phenomenon of “explosion of complexity” is eliminated. In the controller design process of each subsystem, only one adaptive parameter is needed to adjust online. Compared with other existing control methods, the proposed control design is more simple and calculated amount is greatly decreased. It is guaranteed that the whole closed-loop system is stable by using Lyapunov function and average dwell-time methods. The effectiveness of the proposed control method can be demonstrated in the simulation part.

Projects for the comprehensive utilization of mineral resources involve multi-disciplinary technology and management knowledge. However, enterprises often do not have relevant technical reserves and construction experience, thus posing difficulties in balancing the cost, progress, quality, and other indicators of construction while considering the team building of enterprises If not resolved, these problems may lead to resource wastage and low rates of comprehensive resource utilization. This paper introduces the advantages and disadvantages of Outsourcing, Self-management, Consultant, and Joint Management Modes in handling such projects. Taking a mining company in Guangxi as an example, the pros and cons of the above modes are analysed from different perspectives according to the actual situation of the enterprise being studied. The study’s findings have some guiding significance and can provide a comprehensively practical view from an educational significance perspective for enterprises who are planning to implement project construction.

A multiple clustering algorithm based on high-dimensional automatic identification system (AIS) data is proposed to extract the important waypoints in the ship’s navigation trajectory based on selected AIS attribute features and construct a route network using the waypoints. The algorithm improves the accuracy of route network planning by using the latitude and longitude of the historical voyage trajectory and the heading to the ground. Unlike the navigation clustering method that only uses ship latitude and longitude coordinates, the algorithm first calculates the major waypoints using Clustering in QUEst (CLIQUE) and Balance Iterative Reducing and Clustering Using Hierarchies (BIRCH) algorithms, and then builds the route network using network construction. Under the common PC specification (i5 processor), this algorithm forms 440 major waypoints from 220,133 AIS data and constructs a route network with directional features in 5 min, which is faster in computing speed and more suitable for complex ship trajectory differentiation and can extend the application boundary of ship route planning.

Recently, graph convolutional networks (GCNs) and their variants have achieved remarkable successes for the graph-based semisupervised node classification problem. With a GCN, node features are locally smoothed based on the information aggregated from their neighborhoods defined by the graph topology. In most of the existing methods, the graph typologies only contain positive links which are deemed as descriptions for the feature similarity of connected nodes. In this article, we develop a novel GCN-based learning framework that improves the node representation inference capability by including negative links in a graph. Negative links in our method define the inverse correlations for the nodes connected by them and are adaptively generated through a neural-network-based generation model. To make the generated negative links beneficial for the classification performance, this negative link generation model is jointly optimized with the GCN used for class inference through our designed training algorithm. Experiment results show that the proposed learning framework achieves better or matched performance compared to the current state-of-the-art methods on several standard benchmark datasets.

This paper concerns interference estimation problem for device-to-device (D2D) communication networks. In the considered system, D2D users share common spectrum resources, such that the D2D links have interference with each other. To achieve effective interference management, it is necessary to have an accurate understanding of the interference relationship of the D2D devices, which is difficult since the locations and the number of mobile devices can vary over time. In this paper, we formulate an interference estimation problem for the D2D communication network where the D2D users change over time. Our objective is to get accurate estimations for the interference suffered by a generic D2D link and for the interference a D2D link introduces on other users. We propose a graph convolutional neural network (GCN) based estimation model which can estimate the interference of a D2D link based on the location information of the corresponding D2D pairs. Simulation results show the performance of our method.

This paper concerns the cooperative spectrum sensing (CSS) for cognitive radio (CR) networks, where the secondary users (SUs) collaborate to detect the presence of the primary users (PUs). With CSS, the information from different SUs is first fused, then, the detection of the PU signal is implemented based on the fused information. Most of the previous works focus on the design of a mapping function that calculates the probability of the existence of the PU signal based on the fused information. In this paper, we study the fusion process which combines the information from all SUs based on the local property of each SU. A graph-based multi-view learning framework for CSS (GMCSS) is designed to better fuse the information from different SUs. In the proposed framework, the information from each SU is considered as a view of the state of the target wireless channel and is fused with the information from other SUs through a graph-based learning process. Simulation results demonstrate the effectiveness of our method.

Over the past decade, we have witnessed tremendous technology development and societal benefits for various wireless devices, such as smartphones, smart wearable devices, and the Internet of Things (IoT), among others. To meet the traffic demands from these devices and provide a higher quality of experience (QoE) for users, wireless communication systems have exploited more and more radio spectrum. Although the capacity of the radio spectrum is fairly large, the shortage problem is imminent due to the dramatic proliferation of wireless devices. Dynamic spectrum access (DSA) is proposed as one of the most promising solutions to the spectrum shortage problem. The general objective of DSA is to allocate the spectrum resources to users dynamically and efficiently, which involves several control, coordination, and optimization problems. However, with the huge increment of wireless users, our wireless communication systems are much more complex than ever before and traditional DSA solutions can be low efficient or even impractical. Recent breakthroughs achieved by the advanced neural network based machine learning algorithms have demonstrated their great potentials in solving complex large-scale problems. This dissertation focus on developing neural network based machine learning algorithms and models for problems involved in DSA. This work majorly depends on two machine learning techniques: graph neural network (GNN) and reinforcement learning (RL), which are utilized to solve different optimization, coordination, and control problems related to DSA, such as spectrum sensing, interference estimation, and dynamic spectrum allocation. The proposed algorithms and models are validated by numerous simulation studies.

Software crashes represent unexpected program interrupts that manifest as software faults and can be dangerous in that their frequent occurrence diminishes user experience, can damage the reputation of a company, and potentially cause significant losses to stakeholders. The increasing scale and complexity of modern software requires methods for preventing/handling software crashes. Here, we briefly review and summarize progress in three areas of the research field associated with handling software crashes: crash analysis, crash reproduction, and crash localization and repair.

The rapidly evolving mobile applications (apps) have brought great demand for developers to identify new features by inspecting the descriptions of similar apps and acquire missing features for their apps. Unfortunately, due to the huge number of apps, this manual process is time-consuming and unscalable. To help developers identify new features, we propose a new approach named SAFER. In this study, we first develop a tool to automatically extract features from app descriptions. Then, given an app, we leverage the topic model to identify its similar apps based on the extracted features and API names of apps. Finally, we design a feature recommendation algorithm to aggregate and recommend the features of identified similar apps to the specified app. Evaluated over a collection of 533 annotated features from 100 apps, SAFER achieves a Hit@15 score of up to 78.68% and outperforms the baseline approach KNN+ by 17.23% on average. In addition, we also compare SAFER against a typical technique of recommending features from user reviews, i.e., CLAP. Experimental results reveal that SAFER is superior to CLAP by 23.54% in terms of Hit@15.

In recent decades, compiler developers have designed and implemented many compiler-optimization options for a variety of complex optimization requirements; however, it is difficult to effectively adapt existing standard compiler-optimization sequences comprising several optimization options to complex compilation requirements. Because programs have different semantics and compilation goals, it is difficult to achieve desirable optimization results by directly employing standard compiler-optimization sequences. Additionally, the evolution of hardware architectures has increased the complexity of compilation environments, requiring compiler-optimization sequences to be adjusted accordingly. Therefore, selection of good optimization sequences for programs remains challenging. To address this, we reviewed 55 studies related to the selection of compiler-optimization sequences and summarized the research status of this area from several perspectives, including algorithmic approaches, research focuses, target compilers, and target benchmarks. The most popular algorithms used in this research area include heuristic search algorithms (e.g., genetic algorithms) and machine-learning algorithms (e.g., support vector machines). Over 80% of the existing studies focused on novel solutions or validation research. Furthermore, the most popular compiler and benchmark suites used for these experiments are GCC and miBench, respectively. This review offers insight into research trends associated with compiler optimization-sequence selection and provides possible directions for future studies in this field.

In crowdsourced mobile application testing, workers are often inexperienced in and unfamiliar with software testing. Meanwhile, workers edit test reports in descriptive natural language on mobile devices. Thus, these test reports generally lack important details and challenge developers in understanding the bugs. To improve the quality of inspected test reports, we issue a new problem of test report augmentation by leveraging the additional useful information contained in duplicate test reports. In this paper, we propose a new framework named test report augmentation framework (TRAF) towards resolving the problem. First, natural language processing (NLP) techniques are adopted to preprocess the crowdsourced test reports. Then, three strategies are proposed to augment the environments, inputs, and descriptions of the inspected test reports, respectively. Finally, we visualize the augmented test reports to help developers distinguish the added information. To evaluate TRAF, we conduct experiments over five industrial datasets with 757 crowdsourced test reports. Experimental results show that TRAF can recommend relevant inputs to augment the inspected test reports with 98.49% in terms of NDCG and 88.65% in terms of precision on average, and identify valuable sentences from the descriptions of duplicates to augment the inspected test reports with 83.58% in terms of precision, 77.76% in terms of recall, and 78.72% in terms of F-measure on average. Meanwhile, empirical evaluation also demonstrates that augmented test reports can help developers understand and fix bugs better.

Adaptive dynamic programming (ADP), an important branch of reinforcement learning, is a powerful tool in solving various optimal control problems. However, the cooperative game issues of discrete-time multi-player systems with control constraints have rarely been investigated in this field. In order to address this issue, a novel policy iteration (PI) algorithm is proposed based on ADP technique, and its associated convergence analysis is also studied in this brief paper. For the proposed PI algorithm, an online neural network (NN) implementation scheme with multiple-network structure is presented. In the online NN-based learning algorithm, critic network, constrained actor networks and unconstrained actor networks are employed to approximate the value function, constrained and unconstrained control policies, respectively, and the NN weight updating laws are designed based on the gradient descent method. Finally, a numerical simulation example is illustrated to show the effectiveness.

Deep learning has achieved remarkable breakthroughs in the past decade across a wide range of application domains, such as computer games, natural language processing, pattern recognition, and medical diagnosis, to name a few. In this article, we investigate the application of deep learning techniques for wireless communication systems with a focus on energy efficiency optimization for distributed cooperative spectrum sensing. With the continuous development of today's technologies and user demands, wireless communication systems have become larger and more complex than ever, which introduces many critical challenges that the traditional approaches can no longer handle. We envision that deep learning based approaches will play a pivotal role in addressing many such challenges in the next-generation wireless communication systems. In this article, we focus on cognitive radio, a promising technology to improve spectrum efficiency, and develop deep learning techniques to optimize its spectrum sensing process. Specifically, we investigate the energy efficiency of distributed cooperative sensing by formulating it as a combinatorial optimization problem. Based on this formulation, we develop a deep learning framework by integrating graph neural network and reinforcement learning to improve the overall system energy efficiency. Simulation studies under different network scales demonstrate the effectiveness of our proposed approach.

In this paper, the ${H_\infty }$ consensus problem for linear heterogeneous multiagent systems (LHMAS) based on event-triggered output feedback control is investigated. Two novel event-triggered control schemes including nonperiodic and periodic event-triggered control approaches are provided to make the LHMAS with external unknown disturbance achieve ${H_\infty }$ consensus. Therein, the nonperiodic event-triggered control method is designed by combining the event-triggered approach with time-triggered scheme, which can make the sampled instants be decided by the event-triggered condition and provide a fixed lower bound of sampled interval to avoid the Zeno-behavior. Then, based on this approach, the periodic event-triggered control scheme has a further improvement that only the information at fixed periodic interval is used for the event-triggered condition, which means that this method avoids the continuous-time information transfer. Besides, both schemes take output feedback control, which means that only the output information of each agent and leader is needed in this paper. Finally, a numerical example is given to support our results.

In recent decades, the integration of solar energy sources has gradually become the main challenge for global energy consumption. Therefore, it is essential to predict global solar radiation in an accurate and efficient way when estimating outputs of the solar system. Inaccurate predictions either cause load overestimation that results in increased cost or failure to gather adequate supplies. However, accurate forecasting is a challenging task because solar resources are intermittent and uncontrollable. To tackle this difficulty, several machine learning models have been established; however, the forecasting outcomes of these models are not sufficiently accurate. Therefore, in this study, we investigate ensemble learning with square root regularization and intelligent optimization to forecast hourly global solar radiation. The main structure of the proposed method is constructed based on ensemble learning with a random subspace (RS) method that divides the original data into several covariate subspaces. A novel covariate-selection method called square root smoothly clipped absolute deviation (SRSCAD) is proposed and is applied to each subspace with efficient extraction of relevant covariates. To combine the forecasts obtained using RS and SRSCAD, a firefly algorithm (FA) is used to estimate the weights assigned to individual forecasts. To handle the complexity of the proposed ensemble system, a simple and efficient algorithm is derived based on a thresholding rule and accelerated gradient method. To illustrate the validity and effectiveness of the proposed method, global solar radiation datasets of eight locations of Xinjiang province in China are considered. The experimental results show that the proposed RS-SRSCAD-FA achieves the best performances with a mean absolute percentage error, root-mean-square error, Theil inequality coefficient, and correlation coefficient of 0.066, 20.21 W/m2, 0.016, 3.40 s, and 0.98 in site 1, respectively. For the other seven datasets, RS-SRSCAD-FA still outperforms other approaches. Finally, a nonparametric Friedman test is applied to perform statistical comparisons of results over eight datasets.

The proliferation of fake news on social media has opened up new directions of research for timely identification and containment of fake news and mitigation of its widespread impact on public opinion. While much of the earlier research was focused on identification of fake news based on its contents or by exploiting users’ engagements with the news on social media, there has been a rising interest in proactive intervention strategies to counter the spread of misinformation and its impact on society. In this survey, we describe the modern-day problem of fake news and, in particular, highlight the technical challenges associated with it. We discuss existing methods and techniques applicable to both identification and mitigation, with a focus on the significant advances in each method and their advantages and limitations. In addition, research has often been limited by the quality of existing datasets and their specific application contexts. To alleviate this problem, we comprehensively compile and summarize characteristic features of available datasets. Furthermore, we outline new directions of research to facilitate future development of effective and interdisciplinary solutions.

To reduce the complexity of controller design for a type-2 polynomial fuzzy system with time delays and uncertainties, which can be translated into unknown input, the paper adopts a sum of squares (SOS) procedure different from traditional linear matrix inequality (LMI)-based approaches. Control scheme of interval type-2 fuzzy system might achieve better performance due to additional degrees of freedom, however, the complicated internal structure is still a bottleneck restriction for robust stability of nonlinear system. Proposed observer synthesis and adhibition of SOS both lower computational cost efficaciously. Investigated system malfunctions for uncertainties whose effect must be eliminated without a designed extra controller for simplification. The unknown input based observer synthesis approach for interval type-2 polynomial fuzzy system is proposed, by which, the estimation error can asymptotically converge to zero taking uncertainties as unknown input. Simulation examples are designed to demonstrate the feasibilities of proposed approach.

Compilers are widely-used infrastructures in accelerating the software development, and expected to be trustworthy. In the literature, various testing technologies have been proposed to guarantee the quality of compilers. However, there remains an obstacle to comprehensively characterize and understand compiler testing. To overcome this obstacle, we propose a literature analysis framework to gain insights into the compiler testing area. First, we perform an extensive search to construct a dataset related to compiler testing papers. Then, we conduct a bibliometric analysis to analyze the productive authors, the influential papers, and the frequently tested compilers based on our dataset. Finally, we utilize association rules and collaboration networks to mine the authorships and the communities of interests among researchers and keywords. Some valuable results are reported. We find that the USA is the leading country that contains the most influential researchers and institutions. The most active keyword is “random testing”. We also find that most researchers have broad interests within small-scale collaborators in the compiler testing area.

Recent years have witnessed the growing demands for resolving numerous bug reports in software maintenance. Aiming to reduce the time testers/developers take in perusing bug reports, the task of bug report summarization has attracted a lot of research efforts in the literature. However, no systematic analysis has been conducted on attribute construction, which heavily impacts the performance of supervised algorithms for bug report summarization. In this study, we first conduct a survey to reveal the existing methods for attribute construction in mining software repositories. Then, we propose a new method named Crowd-Attribute to infer new effective attributes from the crowd-generated data in crowdsourcing and develop a new tool named Crowdsourcing Software Engineering Platform to facilitate this method. With Crowd-Attribute, we successfully construct 11 new attributes and propose a new supervised algorithm named Logistic Regression with Crowdsourced Attributes (LRCA). To evaluate the effectiveness of LRCA, we build a series of large scale datasets with 105 177 bug reports. Experiments over both the public dataset SDS with 36 manually annotated bug reports and new large-scale datasets demonstrate that LRCA can consistently outperform the state-of-the-art algorithms for bug report summarization.

This paper investigates the robust control issues of nonlinear multiplayer systems by utilizing adaptive dynamic programming (ADP) methods and fills a gap in the ADP field, where actuator uncertainties for multiplayer systems are still not addressed. Two types of actuator uncertainties including bounded nonlinear perturbation and unknown constant actuator fault are taken into consideration. First, a data-driven reinforcement learning (RL) approach is derived to learn the optimal solutions of multiplayer nonzero-sum games. Then, based on the obtained optimal control policies, two robust control schemes are developed to handle these two different types of uncertainties, respectively, and the associated stability analysis is also provided. To implement the proposed iterative RL approach, a single neural network (NN) architecture with least-square-based updating law is given, which reduces the computation burden compared with the traditional dual NN architecture. Finally, two numerical examples are shown to test the feasibility of our proposed schemes.

This paper is concerned with a class of optimal output consensus control problems for discrete linear multiagent systems with the partially observable system state. Since the optimal control policy depends on the full system state which is not accessible for a partially observable system, traditionally, distributed observers are employed to recover the system state. However, in many situations, the accurate model of a real-world dynamical system might be difficult to obtain, which makes the observer design infeasible. Furthermore, the optimal consensus control policy cannot be analytically solved without system functions. To overcome these challenges, we propose a data-driven adaptive dynamic programming approach that does not require the complete system inner state. The key idea is to use the input and output sequence as an equivalent representation of the underlying state. Based on this representation, an adaptive dynamic programming algorithm is developed to generate the optimal control policy. For the implementation of this algorithm, we design a neural network-based actor-critic structure to approximate the local performance indices and the control polices. Two numerical simulations are used to demonstrate the effectiveness of our method.

In statistical modeling, quadratic model including both main effects and interactions has drawn a large deal of attentions from researchers in many scientific fields. Researchers have found that it is extremely significant to maintain the heredity principle such as strong or weak heredity principle among variables when demanding sparsity in quadratic model. The reason why heredity principle is preferred is that model following logic structure is invariant to any scale transformation and is more stable when implementing forecasting and classification task. Although a large bore have studied quadratic models, most of them focus on the model performances in a regression problem and no systematically comparison are made in terms of classification accuracy. This paper investigates and studies group regularized estimation under structural hierarchy for classification (C-GRESH). In computation, a fast and simple-to-implement algorithm is designed with theoretical guarantee of its convergence. Furthermore, an accelerated gradient method is applied to speed up the convergence. Theoretically, we have shown the adaptive version of the proposed approach is able to achieve oracle property which includes asymptotic normality and model selection consistency. Simulation examples and real data examples including microarray gene expression datasets are shown to demonstrate the efficiency and superior performances of the proposed method over other existing competitors.

This paper investigates the frequency regulation and active power sharing problem in AC microgrids with mobile power resource. Considering the impact of communication time-delays, a novel distributed finite-time secondary control method is proposed. The stability of the proposed control method is analyzed based on Lyapunov method. The upper bound of convergence time is derived and is only a function of the designed parameters, the topology of communication network, and communication time-delays. Numerical simulations are conducted to verify the performance of the proposed control method.

In software development, it is easy to introduce code smells owing to the complexity of projects and the negligence of programmers. Code smells reduce code comprehensibility and maintainability, making programs error-prone. Hence, code smell detection is extremely important. Recently, machine learning-based technologies turn to be the mainstream detection approaches, which show promising performance. However, existing machine learning methods have two limitations: (1) most studies only focus on common smells, and (2) the proposed metrics are not effective when being used for uncommon code smell detection, e.g., change barrier based code smells. To overcome these limitations, this paper investigates the detection of uncommon change barrier based code smells. We study three typical code smells, i.e., Divergent Change, Shotgun Surgery, and Parallel Inheritance, which all belong to change barriers. We analyze the characteristics of change barriers and extract domain-specific metrics to train a Logistic Regression model for detection. The experimental results show that our method achieves 81.8%–100% precision and recall, outperforming existing algorithms by 10%–30%. In addition, we analyze the correlation and importance of the utilized metrics. We find our domain-specific metrics are important for the detection of change barriers. The results would help practitioners better design detection tools for such code smells.

Photovoltaic power has become one of the most popular research area in new energy field. In this report, the case of household solar power system is presented. Based on the Matlab environment, the simulation is built by using Simulink and Simpowersystem. There are four parts in a household solar system, solar cell, MPPT system, battery and power consumer. Solar cell and MPPT system are been studied and analyzed individually. The system with MPPT generates 30% more energy than the system without MPPT. After simulating the household system, it is can be seen that the power which generated by the system is . per sunny day. By combining the power generated by the system and the price of the electric power, 8.42 years are need for the system to achieve a balance of income and expenditure when weather condition is considered. Table of

API directive is one of the most important knowledge in API specifications. Existing approach only relies on syntactic patterns to detect API directives and lacks a deep semantic understanding. In this study, we propose a deep learning approach DeepDir to automatically detect API directives. Experimental results show that DeepDir significantly improves the state-of-the-art approach by 20.78% on average in terms of F-measure.

Software requirements are constantly changing. Consequently, the development process is frequently under time pressure, which results in technical debt. To illustrate the symptoms of technical debt, 22 code smells have been introduced to indicate the poor design in code fragment, among which refused bequest is one of the most harmful smells and with high diffuseness. However, refused bequest is rarely taken into account because there is a lack of dataset. Moreover, it is difficult to design the detection rules for refused bequest compared with other popular smells.In this paper, we propose a machine-learning-based refused bequest smell detection framework SEADART, which features the utilization of a set of synthetic smelly instances. Specifically, SEADART comprises three components: (1) a smell generation approach, and (2) a model training strategy, and (3) an AdaBoost-based detection model. We evaluate the performance of the proposed framework. The evaluation results suggest that the generated smelly instances are reliable, and the trained AdaBoost model significantly outperforms the state-of-the-art over a real-world dataset.

In this paper, we investigate the economic dispatch problem in islanded microgrids and we propose a distributed finite-time algorithm to solve the economic dispatch problem. Different from the existing distributed algorithms which solve the economic dispatch problem asymptotically, the proposed algorithm can get the optimal solution in finite time and the bound of the convergence time only depends on the designed parameters in the proposed algorithm. The rapid convergence rate of the proposed algorithm makes it suitable for application in microgrids with penetration of large scale distributed generation resources. Numerical simulations are conducted to evaluate the performance of the proposed algorithm.