Boosting Commit Classification Based on Multivariate Mixed Features and Heterogeneous Classifier Selection

Code review is of primary importance in modern software development. It is widely recognized that peer review is an efficient and effective practice for improving software quality and reducing defect proneness. For successful review process, peer reviewers should have a deep experience and knowledge with the code being reviewed, and familiar to work and collaborate together. However, one of the main challenging tasks in modern code review is to find the most appropriate reviewers for submitted code changes. So far, reviewers assignment is still a manual, costly and time-consuming task. In this paper, we introduce a search-based approach, namely RevRec, to provide decision-making support for code change submitters and/or reviewers assigners to identify most appropriate peer reviewers for their code changes. RevRec aims at finding reviewers to be assigned for a code change based on their expertise and collaboration in past reviews using genetic algorithm (GA). We evaluated our approach on a benchmark of three open-source software systems, Android, OpenStack, and Qt. Results indicate that RevRec accurately recommends code reviewers with up to 59% of precision and 74% of recall. Our experiments provide evidence that leveraging reviewers expertise from their prior reviews and the socio-technical aspects of the team work and collaboration is relevant in improving the performance of peer reviewers recommendation in modern code review.

Early prediction for merged vs abandoned code changes in modern code reviews

Sub-Saharan Africa continues to shoulder the heaviest burden of malaria. The 2024 World Health Organisation (WHO) malaria report highlighted that Africa contributed an alarming 94% of the global cases and 95% of the deaths. In the WHO African region, progress towards elimination and management of malaria is hindered by weak health systems and a lack of traditional diagnostic methods such as microscopy and malaria Rapid Diagnostic Tests (mRDTs). The primary aim of this paper is to develop a machine learning (ML) ensemble model for malaria diagnosis using clinical and demographic data, tailored for resource-limited settings. A retrospective study was conducted using 637 patient records from Gutu Mission Hospital and Gweru Provincial Hospital in Zimbabwe. Clinical symptoms (fever, chills, abdominal pain, headache and diarrhea) and demographic features (age, gender, residence and travel history) were analysed. Data preprocessing included handling class imbalance using the Synthetic Minority Oversampling Technique (SMOTE) and feature selection using Recursive Feature Elimination (RFE). Seven individual ML models, including Logistic regression (LR), Random Forest (RF), Decision Trees (DT), Gradient Boosting (GB), K-Nearest Neighbour (KNN), Naive Bayes (NB) and XGBoost were trained and evaluated on the malaria dataset. The individual models were further combined to build, train and evaluate ensemble models such as Bagging, Stacking, Soft Voting and AdaBoost. Model performance was assessed using accuracy, precision, confusion matrices, recall, F1 score, and AUC-ROC metrics. Clinical symptoms (chills: p-value=0.001, fever: p=0.003, diarrhea: p=0.01, abdominal pain: p< 0.001) were statistically significant predictors of malaria. Of the demographic factors, only travel history (p=0.02) showed a significant association with malaria. Among the seven individual ML models, GB achieved the highest predictive performance (Accuracy =0.94), followed by RF (Accuracy =0.94) and XGBoost (Accuracy =0.93). The stacking ensemble model outperformed all individual ML models and other ensemble models (bagging, soft voting and AdaBoost), achieving accuracy =0.96, precision =0.95, recall =0.98, F1 score =0.96 and AUC-ROC =0.98. This study demonstrates that ML, particularly ensemble models, can be used to improve malaria diagnosis significantly. The integration of these models into a web-based application could provide a scalable and accessible diagnostic tool for healthcare workers in resource-limited settings.

Identification of the sensitive regions to soil erosion can be the foremost step in controlling the vigorous pace of soil degradation in agricultural lands. This study employs individual and ensemble models including compound factor (CF), analytical hierarchy process (AHP), and technique for order preference by similarity to ideal solution-analytical hierarchy process (TOPSIS-AHP) for identifying the regions susceptible to soil erosion in Dnyanganga watershed of India using morphometric attributes (MAs). Thirteen MAs were computed using the newly released TanDEM-X data, which is a bi-static X-band interferometric Synthetic Aperture Radar (SAR) acquisition. Weights for each of the MAs were calculated using AHP, which was employed in both AHP and TOPSIS-AHP models. The outcome of the AHP model displays that watershed slope (Sw), stream frequency (Fu), ruggedness number (Rn), and relative relief (Rr) greatly influences soil erosion in the study area. The priority ranking outcome of individual and ensemble models are compared using the Spearman correlation coefficient test (SCCT) and Kendall tau correlation coefficient test (KTCCT) to select the best model for soil erosion susceptibility mapping. The result of the non-parametric tests reveals that TOPSIS-AHP ensemble model is better in ranking alternatives than the individual models. According to TOPSIS-AHP ensemble model, the sub-watershed DNY16 is highly susceptibility to erosion, whereas DNY1 is least susceptible. Based on the ensemble model, 14.54%, 41.02%, and 44.43% of the area in Dnyanganga watershed fall under high, medium and low soil erosion susceptible classes, respectively. The results from this study will aid decision makers in better conservation planning of soil and water resources.

Modern code review is a common practice used by software developers to ensure high software quality in open source and industrial projects. During code review, developers submit their code changes which should be reviewed, via tool-based code review platforms, before being integrated into the codebase. Then, reviewers provide their feedback to developers, and may request further modifications before finally accepting or rejecting the submitted code changes. However, the identification of appropriate reviewers is still a tedious task as the number of code reviews to be performed is inflated with the increasing number of code changes and the increasing size of software development teams in today's large and active software projects. To help developers with the review process, we introduce a multi-objective search-based approach to find the appropriate set of reviewers. We use the Non-dominated Sorting Genetic Algorithm (NSGA-II) to optimize two conflicting objectives (i) maximize reviewers expertise with the changed files, and (ii) minimize reviewers workload in terms of their current open code reviews. We conduct a preliminary evaluation on two open source projects to evaluate our approach. Results indicate that our approach is efficient as compared to state-of-the-art approaches.

Development of a parsimonious GA–NN ensemble model with a case study for Charpy impact energy prediction

Background: Feature selection techniques are important factors for improving machine learning models because they increase prediction accuracy and decrease the time to create a model. Recently, feature selection techniques have been employed on software quality prediction problems with different results and no clear indication of which techniques are frequently used.Objective: This study aims to conduct a systematic review of the application of feature selection techniques in software quality prediction and answers eight research questions.Method: The review evaluates 15 papers in 9 journals and 6 conference proceedings from 2007 to 2017 using the standard systematic literature review method.Results: The results obtained from this study reveal that the filter feature selection method was the most commonly used in the studies (60%) and RELIEF was the most employed among this method, and a limited number of studies employed an ensemble method. Several studies used public datasets available in the PROMISE software project repository (60%). Most studies focused on software defect prediction (classification problem) using area under curve (AUC) as a primary evaluation measure, whereas only two studies focused on software maintainability prediction (regression problem) using mean magnitude of relative error (MMRE) as a primary evaluation measure. All selected studies performed k-fold cross-validation to evaluate model accuracy. Individual prediction models were mostly employed and ensemble models appeared only in three studies. Naive Bayes was the most investigated among individual models, whereas Random forest was the most investigated among ensemble models.Conclusion: Feature selection techniques used by selected primary studies have a positive impact on the performance of the prediction models. Further, both ensemble feature selection method and ensemble models have the ability for increasing prediction accuracy over single methods or individual models and have reported improvement in the prediction accuracy; however, the application of these techniques in software quality prediction is still limited.

A fire accident is the most tragic incident in human life. Particularly environmental hazards such as forest fires lead loss of wildlife, economy, wealth, human lives and pollution. our research purpose of predict the occurrence of fire incidents using ensemble machine learning models. The goal is to develop an accurate and reliable model that can forecast the occurrence of forest fires based on various environmental factors. The best performance is obtained by the ensemble machine learning model for this work. Comparative study of individual model and ensemble model. If you check all models Decision tree predicts 75.4%, the Random Forest tree predicts 83.2%, the Support Vector Machine predicts 71.8%, and the K nearest neighbour predicts 82.1%. Ensemble models with two combinations of decision tree and random forest tree predicts accuracy is 80.8%. Support vector machine and KNN predicts the accuracy rate is 73.4%. The individual model predicts more accuracy compared to ensemble learning model.

Machine learning algorithms aim to improve the power of predictors over conventional regression models. This study aims to tap the predictive potential of crash mechanism-related variables using ensemble machine learning models. The results demonstrate selected models can predict severity at a high level of accuracy. The stacking model with a linear blender is preferred for the designed ensemble combination. Most bagging, boosting, and stacking algorithms perform well, indicating ensemble models are capable of improving upon individual models.

BackgroundCerebral arteriovenous malformation (AVM) is a cerebrovascular disorder posing a risk for intracranial hemorrhage. However, there are few reliable quantitative indices to predict hemorrhage risk accurately. This study aimed to...

Sign language (SL) is the linguistics of speech and hearing-impaired individuals. The hand gesture is the primary model employed in SL by speech and hearing-challenged people to talk with themselves and ordinary persons. At present, hand gesture detection plays a vital part, and it is commonly employed in numerous applications worldwide. Hand gesture detection systems can aid in transmission between machines and humans by aiding these sets of people. Machine learning (ML) is a subdivision of artificial intelligence (AI), which concentrates on the growth of a method. The main challenge in hand gesture detection is that machines do not directly understand human language. A standard medium is required to facilitate communication between humans and machines. Hand gesture recognition (GR) serves as this medium, enabling commands for computer interaction that specifically benefit hearing-impaired and elderly individuals. This study proposes a Gesture Recognition for Hearing Impaired People Using an Ensemble of Deep Learning Models with Improving Beluga Whale Optimization (GRHIP-EDLIBWO) model. The main intention of the GRHIP-EDLIBWO model framework for GR is to assist as a valuable tool for developing accessible communication systems for hearing-impaired individuals. To accomplish that, the GRHIP-EDLIBWO method initially performs image preprocessing using a Sobel filter (SF) to enhance edge detection and extract critical gesture features. For the feature extraction process, the squeeze-and-excitation capsule network (SE-CapsNet) effectively captures spatial hierarchies and complex relationships within gesture patterns. In addition, an ensemble of classification processes, such as bidirectional gated recurrent unit (BiGRU), Variational Autoencoder (VAE), and bidirectional long short-term memory (BiLSTM) technique, is employed. Finally, the improved beluga whale optimization (IBWO) method is implemented for the hyperparameter tuning of the three ensemble models. To achieve a robust classification result with the GRHIP-EDLIBWO approach, extensive simulations are conducted on an Indian SL (ISL) dataset. The performance validation of the GRHIP-EDLIBWO approach portrayed a superior accuracy value of 98.72% over existing models.

The purpose of this study is to develop predictive and optimization models to reduce patients' waiting time for diagnostic tests and medical treatments. Long wait times for receiving medical care is a pressing issue in the Canadian healthcare system. These wait times are spread over different phases of treatment, such as diagnostic tests, physicians' treatments, and appointments with specialists and surgeons. An integrated system to monitor all the phases of treatment along with efficient workload distribution in each phase can reduce patients' waiting time at each of these phases. This study investigates the impact of efficient resource allocation and workload distribution in the medical system. This research also explores the effect of optimized resource allocation on the patients' waiting time in Medicare settings. Resource allocation planning is directly related to the number of patient-arrival, and it is hard to predict such uncertain parameters in the future time frame. The number of patient-arrival also varies across different medical departments and different timeframes which makes the patient-arrival prediction challenging. The goal of this study is to investigate the forecasting effect on patients' waiting time and physicians' workload. To achieve this goal, advanced machine learning technique is integrated with the optimization model. The machine learning technique is used to predict the uncertain parameters of the optimization model for a shorter time span. To predict time-dependent uncertain parameters, such as patient arrival is a major issue, as the prediction may suffer from the concept drift problem. Besides, real-time data are commonly prone to errors due to irregular fluctuations, seasonal biases, and missing values in the data. On the other hand, predicting for shorter intervals requires lower execution time combined with higher accuracy. The developed predictive ensemble model in this research has addressed these issues legitimately with four research contributions. In the first contribution (Chapter 2), we have investigated methodologies for predicting Radiologists’ workload in a short time interval by adopting a machine learning technique. An ensemble model is proposed with the fixed batch training method in this part. To excel in the execution time, a fixed batch training method is used. Secondly, in Chapter 3, an Adaptive Batched-Ranked Ensemble (ABRE) model that reduces the effect of fluctuation using the time-variant windowing technique. Besides, a data aggregation technique is developed and integrated with the offline training phase of the proposed model to tackle the concept drift problem. In the third contribution (Chapter 4), a novel Ensemble of Pruned Regressor Chain (EPRC) method is developed and trained offline to predict uncertain parameters, such as patients’ arrival. Finally, the fourth contribution in Chapter 4, the EPRC method is integrated with a novel multi-objective optimization model to reduce patients’ waiting time, and to determine workload allocation for future timespan. This research enables enhanced decision-making with effective resource allocation and workload scheduling, as well as assists in reducing healthcare expenditure.

Software design is a key concern in code review through which developers actively discuss and improve each code change. Nevertheless, code review is predominantly a cooperative task influenced by both technical and social aspects. Consequently, these aspects can play a key role in how software design degrades as well as contributing to accelerating or reversing the degradation during the process of each single code change’s review. However, there is little understanding about such social and technical aspects relates to either the reduction or the increase of design degradation as the project evolves. Consequently, the scarce knowledge on this topic helps little in properly guiding developers along design-driven code reviews. Our goal in this Doctoral research is three-fold: (1) to characterize the impact of code review and their practices on design degradation over time; (2) to understand the contribution of technical and social aspects to design degradation; and (3) to propose a conceptual framework to support design-decision making during code review. Our preliminary results show that the majority of code reviews had little to no design degradation impact, and that technical and social aspects contribute to distinguishing and predicting design impactful changes.

Code ownership establishes a chain of responsibility for modules in large software systems. Although prior work uncovers a link between code ownership heuristics and software quality, these heuristics rely solely on the authorship of code changes. In addition to authoring code changes, developers also make important contributions to a module by reviewing code changes. Indeed, recent work shows that reviewers are highly active in modern code review processes, often suggesting alternative solutions or providing updates to the code changes. In this paper, we complement traditional code ownership heuristics using code review activity. Through a case study of six releases of the large Qt and OpenStack systems, we find that: (1) 67%--86% of developers did not author any code changes for a module, but still actively contributed by reviewing 21%--39% of the code changes, (2) code ownership heuristics that are aware of reviewing activity share a relationship with software quality, and (3) the proportion of reviewers without expertise shares a strong, increasing relationship with the likelihood of having post-release defects. Our results suggest that reviewing activity captures an important aspect of code ownership, and should be included in approximations of it in future studies.

Background: Breast cancer is one of the leading causes of death in women, making early detection through mammography crucial for improving survival rates. However, human interpretation of mammograms is often prone to diagnostic errors. This study addresses the challenge of improving the accuracy of breast cancer detection by leveraging advanced machine learning techniques. Methods: We propose an extended ensemble deep learning model that integrates three state-of-the-art convolutional neural network (CNN) architectures: VGG16, DenseNet121, and InceptionV3. The model utilizes multi-scale feature extraction to enhance the detection of both benign and malignant masses in mammograms. This ensemble approach is evaluated on two benchmark datasets: INbreast and CBIS-DDSM. Results: The proposed ensemble model achieved significant performance improvements. On the INbreast dataset, the ensemble model attained an accuracy of 90.1%, recall of 88.3%, and an F1-score of 89.1%. For the CBIS-DDSM dataset, the model reached 89.5% accuracy and 90.2% specificity. The ensemble method outperformed each individual CNN model, reducing both false positives and false negatives, thereby providing more reliable diagnostic results. Conclusions: The ensemble deep learning model demonstrated strong potential as a decision support tool for radiologists, offering more accurate and earlier detection of breast cancer. By leveraging the complementary strengths of multiple CNN architectures, this approach can improve clinical decision making and enhance the accessibility of high-quality breast cancer screening.