A Software Defect Learning and Analysis Utilizing Regression Method for Quality Software Development

Energy supplies are expected to be expanded in order to meet the emerging demands in this modern era due to highly depends on electricity. Energy demand has been reported to increase by 2.3% in 2018 and this causes increasing in electricity price. Energy consumption in houses or factories is given more attention due to our concern on every single cent that we need to pay for the electricity bills. Consequently, the status of each appliance usage should be monitored for appropriate saving actions to be taken. However, this requires a tremendous amount of meter being clamped on the electrical appliances to monitor their status. This paper presents a non-intrusive monitoring approach using logistic regression technique to identify whether the appliances are switched on or off from the total consumption. The logistic regression estimates the parameters of a logistic model giving output in form of binary such as on or off. Individual logistic model is proposed for each appliance to give better estimation. Then, the developed logistic regression models are embedded in a web-based user interface so that user can monitor the status of appliances easily. As a result, consumers will be able to monitor their energy consumption and status of electrical appliances usage at anywhere and everywhere.

Section: Resultsmentioning

confidence: 99%

A Web-Based Non-Intrusive Appliances Monitoring System Using Logistic Regression Technique

Tan¹

2020

“…Scaling is to avoid attributes in a larger numeric range dominating attributes in a smaller numeric range [34]. To improve the efficiency and excellence of software development, he can utilize data mining techniques to analyze and predict large amounts of data [93].…”

Section: Data Preprocessingmentioning

confidence: 99%

Optimizing Software Effort Estimation Models Based On Metaheuristic Methods: A Proposed Framework

Marco¹

2019

Software effort estimation are part of the field of project management in software that is very important for development efforts. Software development planning is something very complex and serious, which determines the success of a software project. Because of the lack of good requirements and information, it causes software project failures. Although there are many studies that aim to solve the problem of noisy, irrelevant and excessive data to achieve accuracy. The purpose of this study is to combine metaheuristic optimization techniques as a framework for using Machine Learning models. By proposing a hybrid estimation model based on a combination of the Satin Bowerbird Optimizer (SBO) algorithm and Support Vector Regression (SVR) to improve the accuracy of software estimation efforts. This study is to determine the effort estimation and duration estimation. The proposed framework is based on theoretical concepts. the proposed model will be tested using a heterogeneous dataset, namely the ISBSG dataset. the results of the study are expected to be used as decision making as the initial planning of software project development.

“…As the dependency and complexity of software grows, the demands for maintainable and high-quality low-cost software grows with it. However, for reduced maintenance in software operation and software quality improvement to be actualized, there is need for a software defect prediction system [1,2,3]. Having an early detection system in place will enable fast delivery of maintainable software since it will allow for timely correction of the detected faults [4].…”

Section: Introductionmentioning

confidence: 99%

Predicting Software Defects using Machine Learning Techniques

Aquil¹,

Ishak²

2020

A huge variety of software systems are relied upon in such domains as aviation, healthcare, manufacturing and robotics, and therefore, h systems and that they are reliable. Software defect prediction helps improve software reliability by identifying potential bugs during software maintenance. Traditionally, the focus of software defect prediction was on the design of static code metrics, which help with predicting the defect probabilities of a code when input into machine learning classifiers. While machine learning techniques such as Deep Learning technique, Ensembling, Data Mining, Clustering and Classification are known to help predict the location of defects in code bases, researchers have not yet agreed on which is the best predictor model. This paper will use 13 software defect datasets in evaluating the performance of the different predictor models. The results show that consistency in high accuracy prediction was achieved using Ensembling techniques.