Search

The goal of defect specificity is to pinpoint defective program components (such as faulty files, problematic procedures, or troublesome lines of code) based on defect symptoms, such as event logs or program spectrum. However, the problem is revealed and adverse effects are introduced when one experiences the defect indications. Consequently, one difficult task is to determine whether one can find buggy program before the signs of the defect manifests itself. Just-in-time defect prediction (JIT-DP) is a particular category of Software Defect Prediction (SDP) that includes this type of early detection of flawed changes to a software programs. This paper presents a novel five-phase JIT-DP framework that classifies the newly committed change as either a buggy change or a clean change relying on the project's historical data regarding the executed changes. The distinctive aspect of the model is that it uses the Chunk Balancing Algorithm (CBA) as a novel way of handling the Class Imbalance Problem (CIP) rather than utilizing conventional data re-sampling techniques. The experimental study uses 10 open-source projects with an average of 23,989 modifications to train the JIT-DP model. The research study examines the JIT-DP model's prediction abilities from both Within Project (WP) and Cross Project (CP) scenarios. The findings show that for within project setup, Logistic Regression (LR) outperforms among all other classifiers with the highest accuracy, TPR, and FPR as 0.85, 0.847, and 0.207, respectively. The model provides comparable prediction findings with an average accuracy of 0.90 for all seven testing samples when it was trained using commit logs from related six Java projects under CP context. However, taking into account the larger training pool of commit records in the former scenario, the model in the CP context (3.740 s) lags behind in terms of training and classification time periods when compared to the results of WI (0.984 s).

Machine learning (ML) has been instrumental in optimal decision making through relevant historical data, including the domain of bioinformatics. In bioinformatics classification of natural genes and the genes that are infected by disease called invalid gene is a very complex task. In order to find the applicability of a fresh protein through genomic research, DNA sequences need to be classified. The current work identifies classes of DNA sequence using machine learning algorithm. These classes are basically dependent on the sequence of nucleotides. With a fractional mutation in sequence, there is a corresponding change in the class. Each numeric instance representing a class is linked to a gene family including G protein coupled receptors, tyrosine kinase, synthase, etc. In this paper, the authors applied the classification algorithm on three types of datasets to identify which gene class they belong to. They converted sequences into substrings with a defined length. That ‘k value' defines the length of substring which is one of the ways to analyze the sequence.

Medical data analysis is being recognized as a field of enormous research possibilities due to the fact there is a huge amount of data available and prediction in initial stage may save patient lives with timely intervention. With machine learning, a particular algorithm may be created through which any disease may be predicted well in advance on the basis of its feature sets or its symptoms can be detected. With respect to this research work, heart disease will be predicted with support vector machine that falls under the category of supervised machine learning algorithm. The main idea of this study is to focus on the significance of parameter tuning to elevate the performance of classifier. The results achieved were then compared with normal classifier SVM before tuning the parameters. Results depict that the hyperparameters tuning enhances the performance of the model. Finally, results were calculated by using various validation metrics.

There is an unprecedented growth of internet and internet-based technologies in the recent times. We are now switching to 5G as the most recent wireless communication technology. The internet of things has become a blessing for Industry 4.0 by challenging all the existing technologies in its utility for contributing to the industrial growth. There are a lot of wireless communication technologies for IoT, and it becomes difficult choice to select one suitable for an application. Authors have presented multi-criteria decision-making techniques which are very instrumental in making a confirmed decision on the choice of appropriate technology. This choice is done based on a number of deciding parameter which are used to differentiate between all the available options. The authors have identified 11 wireless communication technologies and seven parameters to evaluate the performance of the WCT's. All the seven parameters are considered in ranking and rank matrix is obtained. This technique can be very helpful for application designers so as to choose the right platform for their applications.