A multi-label classification approach for detecting test smells over java projects

Software quality depends not only on production code but also on the quality of test code. Among the factors that compromise this quality, test smells stand out, poor implementation patterns in tests that negatively affect the readability, maintainability, and reliability of the test suite. Although tools such as tsDetect and JNose support test smell detection, they operate post-hoc, requiring the code to be complete and analyzed outside the development environment. Other tools, like RAIDE, offer detection within the IDE via plugins; however, the analysis is not instantaneous and still occurs after the code is written. These reactive approaches result in delayed feedback and significantly increase the refactoring effort. In this context, we propose AriesLinter, a static analysis tool that can be integrated into major development environments and is capable of detecting test smells in real time, as the test code is being written. Built on top of the Checkstyle infrastructure, AriesLinter automatically detects 10 of the most recurrent test smells reported in the literature and commonly found in Java projects. The tool is cross-platform and compatible with multiple IDEs. By anticipating the detection of poor patterns and embedding it into the natural workflow of developers, AriesLinter acts proactively, reducing the likelihood of test smells being introduced into the codebase and fostering a culture of continuous attention to test quality. Demo video: https://youtu.be/Cj6mQGGHlvk

As a fine-grained defect detection technique, unit testing introduces a strong dependency on the structure of the code. Accordingly, test coevolution forms an additional burden on the software developer which can be tempered by writing tests in a manner that makes them easier to change. Fortunately, we are able to concretely express what a good test is by exploiting the specific principles underlying unit testing. Analogous to the concept of code smells, violations of these principles are termed test smells. In this paper, we clarify the structural deficiencies encapsulated in test smells by formalizing core test concepts and their characteristics. To support the detection of two such test smells, General Fixture and Eager Test, we propose a set of metrics defined in terms of unit test concepts. We compare their detection effectiveness using manual inspection and through a comparison with human reviewing. Although the latter is the traditional means for test quality assurance, our results indicate it is not a reliable means for test smell detection. This work thus stresses the need for a more reliable detection mechanism and provides an initial contribution through the validation of test smell metrics.

Prediction of software defects using machine learning techniques has attracted more attention from researchers due to its importance in producing successful software. On the other side, it reduces the cost of software development and facilitates procedures to identify the reasons for determining the percentage of defect-prone software in the future. There is no conclusive evidence for specific types of machine learning that will be more efficient and accurate in predicting software defects. However, some of the previous related work proposes ensemble learning techniques as a more accurate alternative. The paper presents the resample technique with three types of ensemble learners; Boosting, Bagging, and Rotation Forest, using eight base learners tested on seven types of benchmark datasets provided in the PROMISE repository. Results indicate that accuracy has been improved using ensemble techniques more than single leaners especially in conjunction with Rotation Forest with the resample technique in most of the algorithms used in the experimental results.

Internet of Things (IoT) plays an increasingly significant role in our daily activities, connecting physical objects around us into digital services. In other words, IoT is the driving force behind home automation, smart cities, modern health systems, and advanced manufacturing. This also increases the likelihood of cyber threats against IoT devices and services. Attackers may attempt to exploit vulnerabilities in application protocols, including Domain Name System (DNS), Hyper Text Transfer Protocol (HTTP) and Message Queue Telemetry Transport (MQTT) that interact directly with backend database systems and client-server applications to store data of IoT services. Successful exploitation of one or more of these protocols can result in data leakage and security breaches. In this paper, an ensemble intrusion detection technique is proposed to mitigate malicious events, in particular botnet attacks against DNS, HTTP, and MQTT protocols utilized in IoT networks. New statistical flow features are generated from the protocols based on an analysis of their potential properties. Then, an AdaBoost ensemble learning method is developed using three machine learning techniques, namely decision tree, Naive Bayes (NB), and artificial neural network, to evaluate the effect of these features and detect malicious events effectively. The UNSW-NB15 and NIMS botnet datasets with simulated IoT sensors' data are used to extract the proposed features and evaluate the ensemble technique. The experimental results show that the proposed features have the potential characteristics of normal and malicious activity using the correntropy and correlation coefficient measures. Moreover, the proposed ensemble technique provides a higher detection rate and a lower false positive rate compared with each classification technique included in the framework and three other state-of-the-art techniques.

The present paperreports an optimal machine learning model for an effective prediction of cardiovascular diseases that uses the ensemble learning technique. The present research work gives an insight about the coherent way of combining Naive Bayes and Random Forest algorithm using ensemble technique. It also discusses how the present model is different from other traditional approaches. The present experimental results manifest that the present optimal machine learning model is more efficient than the other models.

In this paper, we present a new ensemble approach for semi-supervised multi-label classification which exploits both the dependencies between the class labels and the unlabeled instances to enhance the multi-label classification performance. Our approach combines both data resampling (bagging) and label random subspace strategies for generating a committee of multi-label models in a co-training style algorithm. The key ideas behind this approach are to i) promote and maintain diversity in the multi-label base-classifiers committee, ii) define a new cost oriented metric to estimate the prediction confidence for each label, and iii) use a new multi-label out-of-bag feature importance measure that makes full use of labeled and unlabeled in the semi-supervised setting. Experimental results on various benchmark data sets approved that the proposed approach outperforms recent state-of-the-art supervised and semi-supervised multi-label algorithms over different multi-label metrics.

Digital breast tomosynthesis (DBT) is a pseudo-3D breast image, which is a collection of 2D slice images. It is increasingly being used for detection and diagnosis of breast cancer. In comparison to mammography (2D breast image), DBT provides higher sensitivity (true-positive rate). Recently, there have been many state-of-the-art methods for the detection of masses and calcifications in DBT. However, these previous studies can identify just only one type of breast lesions (abnormality class), while there can be multiple breast lesions simultaneously (multi-label classification); each of them requires different treatment procedures. In this paper, we present an end-to-end multi-label classification approach that takes into account the pseudo-3D nature of DBT and able to automatically detect two major types of malignant lesions: soft tissue and calcifications. The proposed network is a real 3D convolutional network (ConvNet) with two additional strategies: global kernel and global average pooling. Also, an inversion augmentation is invented; it does not only alleviate a small size of training data, but also help an occlusion overlapping issue. Such system can be used to support radiologists in DBT analysis by prompting suspicious locations. Our in-house dataset consists of 115 DBT volumes, including 91 volumes of cancer detected cases (contained biopsy-proven malignant lesions) and 24 volumes of normal cases. The experimental results show that our approach yields a promising result for the classification of malignant lesions: 72% accuracy with f1-score at 0.842. Moreover, a multi-label classification network is able to detect concurrent lesions in 3 of 6 volumes in the testing set.

Many computer vision applications, such as image classification and video indexing, are usually multi-label classification problems in which an instance can be assigned to more than one category. In this paper, we present a novel multi-label classification approach with hypergraph regularization that addresses the correlations among different categories. First, a hypergraph is constructed to capture the correlations among different categories, in which each vertex represents one training instance and each hyperedge for one category contains all the instances belonging to the same category. Then, an improved SVM like learning system incorporating the hypergraph regularization, called Rank-HLapSVM, is proposed to handle the multi-label classification problems. We find that the corresponding optimization problem can be efficiently solved by the dual coordinate descent method. Many promising experimental results on the real datasets including ImageCLEF and MediaMill demonstrate the effectiveness and efficiency of the proposed algorithm.

Most effective particular object and image retrieval approaches are based on the bag-of-words (BoW) model, and all state-of-the-art performance mainly involves a query expansion procedure, which is able to significantly improve retrieval results. Nowadays, Convolutional Neural Network(CNN) is widely applied in computer vision field, including image classification, caption, recognition and retrieval, etc. We introduce an extension to query expansion: an automatic method to select good candidate samples for interactive annotation which is used in query expansion using both BoW method and CNN feature. In this work, we address the query expansion framework using active learning, where the main focus is on the sample selection step in the process of query expansion. More specifically, we propose an active sample selection algorithm based on binary relevance classification, based on the assumption that most confusing samples of the classifiers have high probability to contain helpful true positives for query expansion, which significantly improves the retrieval performance. It takes full use of the multimodal information of the shortlist obtained from the basic retrieval to train a binary relevance classifier, which is used to pick up the most confusing samples for human annotation, with top list as unlabeled data and bottom list as fake negatives. And it can achieve a faster and better retrieval than naive top sample selection method. We also fuse BoW vector and CNN prediction in the retrieval system for a better performance. To evaluate the performance of our proposed method, experiments are conducted on Standard Oxford (5K and 105K) and Paris (6K) datasets, and experimental results and comparison with the state-of-the-art methods demonstrate the effectiveness of the proposed method.

Code clones are similar code fragments at the syntactic or semantic level, commonly seen in software development. Excessive cloning harms maintainability and may introduce persistent bugs. We analyze cross-language code clone detection at the accurate semantic level. Most existing clone detection approaches target single-language environments and focus mainly on syntactic similarity. However, complex software systems are often developed using multiple programming languages, resulting in semantically similar cross-language code clones. These clones pose challenges beyond the capabilities of current detection tools. In this paper, we propose a novel flow-enhanced graph attention network approach, called FEGAT, to effectively detect cross-language code clones at the semantic level. First, we design a flow-enhanced code graph using abstract syntax tree along with the added control and data flow edges. Then, we input this code graph into the pre-trained model CodeBERT to learn the initial flow-enhanced node representation with semantic information. Third, we design FEGAT to learn flow-enhanced graph representation of cross-language codes from their semantic information and detect clones by computing the similarity score. Finally, we conduct experiments on the AtCoder and CodeChef datasets to evaluate the performance of FEGAT in terms of precision, recall, and F1-score. The experimental results demonstrate that FEGAT outperforms existing cross-language code clone detection tools.

The use of magnetic Barkhausen Noise Analysis (BNA) has been proven to be an effective tool for the non-destructive detection of microstructural anomalies in ferrous materials. Used as an in-process tool for the detection of grinding burn, heat treat defects and stresses, BNA is a quick comparative and quantitative alternative to traditional destructive methods. Applications of BNA as a quality control tool in gear production have existed for nearly two decades. This paper presents examples that demonstrate how BNA is used to evaluate changes in microstructural properties. Quantitative results correlate BNA test values to X-Ray diffraction values for the detection of changes in surface residual stress. Other quantitative analysis correlates BNA test values to surface hardness values for the detection of re-tempering burn. Qualitative results correlate BNA test values to acid etch patterns/colors for the detection of grinding burn defects. Robotically automated systems can test gear teeth and provide immediate feedback for process control and quality assurance.

Prediction of protein subcellular localization is an important but challenging problem, particularly when proteins may simultaneously exist at, or move between, two or more different subcellular location sites. Most of the existing protein subcellular localization methods are only used to deal with the single-location proteins. In the past few years, only a few methods have been proposed to tackle proteins with multiple locations. However, they only adopt a simple strategy, that is, transforming the multilocation proteins to multiple proteins with single location, which does not take correlations among different subcellular locations into account. In this paper, a novel method named random label selection (RALS) (multilabel learning via RALS), which extends the simple binary relevance (BR) method, is proposed to learn from multilocation proteins in an effective and efficient way. RALS does not explicitly find the correlations among labels, but rather implicitly attempts to learn the label correlations from data by augmenting original feature space with randomly selected labels as its additional input features. Through the fivefold cross-validation test on a benchmark data set, we demonstrate our proposed method with consideration of label correlations obviously outperforms the baseline BR method without consideration of label correlations, indicating correlations among different subcellular locations really exist and contribute to improvement of prediction performance. Experimental results on two benchmark data sets also show that our proposed methods achieve significantly higher performance than some other state-of-the-art methods in predicting subcellular multilocations of proteins. The prediction web server is available at http://levis.tongji.edu.cn:8080/bioinfo/MLPred-Euk/ for the public usage.

Web services are being embraced by IT industry in the recent past to enable rapid development of distributed systems with optimal cost. Web services in SOA are self-adaptable to context, which makes SOA widely recognized in IT system as the technology, which has the potential of improving the receptiveness of both business and IT organizations. Web services help in building Service Based Systems (SBS) like Paytm, Amazon, Paypal, e-bay etc. which evolves frequently to fit the new user requirements which impacts the evolvability and quality of software design. Similar to software systems built using other paradigms, Service based systems also suffer from bad or poor design choices as in anti-pattern, code smells etc. Anti-patterns are explicit structures in the design that indicates violation of fundamental design principles and negatively impact the design quality. Anti-patterns have obstructive influence on the maintainability and perception of software systems. Thus there is a rising need for the early prediction of anti-patterns and refactoring them to improve the software quality in terms of execution cost, maintenance cost and memory consumption. In this work, a frame work is proposed for significant feature selection from source code metrics which includes Wilcoxon signed rank test, Univariate logistic regression analysis and Cross-correlation analysis. Then the different sets of features from various steps along with the original source code metrics are considered and are used for anti-pattern detection using 13 machine learning algorithms. Experimental results show the approximation capability of different classifiers and data balancing techniques with the features selected from the various steps of feature validation framework in addition to the original features for developing anti-pattern prediction model. The results also shows that the prediction model built with by the ensemble techniques using the features obtained from proposed feature selection framework outperforms other techniques.KeywordsSoftware engineeringAnti-patternWeb serviceImbalanced dataService oriented architectureMachine learningPredictionSource code metric

Ensemble learning strategies, especially boosting and bagging decision trees, have demonstrated impressive capacities to improve the prediction accuracy of base learning algorithms. Further gains have been demonstrated by strategies that combine simple ensemble formation approaches. We investigate the hypothesis that the improvement in accuracy of multistrategy approaches to ensemble learning is due to an increase in the diversity of ensemble members that are formed. In addition, guided by this hypothesis, we develop three new multistrategy ensemble learning techniques. Experimental results in a wide variety of natural domains suggest that these multistrategy ensemble learning techniques are, on average, more accurate than their component ensemble learning techniques.

Code refactoring is the modification of structure without altering its functionality. The refactoring task is critical for enhancing the qualities for non-functional attributes, such as efficiency, understandability, reusability, and flexibility. The research aims to build an optimized model for refactoring prediction at the method level with seven ensemble techniques and varieties of SMOTE techniques. This research has considered five open source java projects to investigate the accuracy of the proposed model, which forecasts refactoring applicants by the use of ensemble techniques (BAG-KNN, BAG-DT, BAG-LOGR, ADABST, EXTC, RANF, GRDBST). Data imbalance issues are handled using three sampling techniques (SMOTE, BLSMOTE, SVSMOTE) to improve refactoring prediction efficiency and also focused all features and significant features. The mean accuracy of the classifiers like BAG-DT is 99.53%, RANF is 99.55%, and EXTC is 99.59%. The mean accuracy of the BLSMOTE is 97.21%. The performance of classifiers and sampling techniques are shown in terms of the box-plot diagram.