Software Defect Prediction with Naïve Bayes Classifier

Rahim, Aqsa; Hayat, Zara; Abbas, Muhammad; Rahim, Amna; Rahim, Muhammad Abdul

doi:10.1109/ibcast51254.2021.9393250

Cited by 14 publications

(8 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The KNN algorithm achieves very high accuracy [51] for uncovered faces but for covered faces, the accuracy drops down below 10% [50]. Rahim et al [52] used the NB algorithm to predict the errors which can happen from certain software and proposed three steps which when applied show high accuracy in detecting those errors [52]. Another paper discussed increasing the accuracy of the Naive Bayes algorithm when applied to artificial intelligence classification problems.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Design and analysis of a new brake-by-wire system using machine learning

Hassanein

Dawod

Hassan

2023

IJECE

View full text Add to dashboard Cite

One of the main aims of the recent research on brake-by-wire systems is to decrease mechanical components. In this paper, we propose replacing the brake pedal with a driving wheel that is fully covered by pressure braking batch sensors. The new mechanism for braking translates pressure exerted through the driver’s hands on the driving wheel to a corresponding electrical signal. A proposed design for the pressure braking batch (PBB) is made out of a mesh of conducting threads separated by a resistive sheet. To the best of our knowledge, this idea has not been raised before in other research papers. Different people have different muscle strengths and so the problem of identifying the intention of the user when pressing the PBB is tackled. For this aim, a new dataset of its kind is created by several volunteers. From each volunteer, age, gender, body mass index (BMI), and maximum pressure exerted on the driving wheel are collected. Using Weka software, the detection accuracy is calculated for a new volunteer to know the intention of his/her pressure on PBB. Among the three algorithms tried, the regression tree gives the best results in predicting the class of the pressure exerted by the volunteers.

show abstract

Section: Resultsmentioning

confidence: 99%

“…Carrizosa et al [54] aimed at decreasing its time consumption and the processing power required for running it. For interested readers in the equations of the three algorithms KNN, NB and RT kindly refer to [50], [52], [54], respectively. We use the Weka software [56] to solve the classification problem.…”

Section: Resultsmentioning

confidence: 99%

Design and analysis of a new brake-by-wire system using machine learning

Hassanein

Dawod

Hassan

2023

IJECE

View full text Add to dashboard Cite

show abstract

“…These metrics provide insights into the structure and complexity of the code, which can be correlated with the likelihood of defects. It is widely used, as can be seen in [ 18 ], where Rahim et al proposed a Naïve Bayes Classifier for the identification of software application defects with a high accuracy, reaching 98.7%. The early detection of these defects in software systems can help developers remove them and, thus, improve the software quality before the deployment phase.…”

Section: Related Workmentioning

confidence: 99%

Design and Implementation of an AI-Enabled Sensor for the Prediction of the Behaviour of Software Applications in Industrial Scenarios

Gama Garcia,

Alcaraz Calero,

Mora Mora

et al. 2024

Sensors

View full text Add to dashboard Cite

In the era of Industry 4.0 and 5.0, a transformative wave of softwarisation has surged. This shift towards software-centric frameworks has been a cornerstone and has highlighted the need to comprehend software applications. This research introduces a novel agent-based architecture designed to sense and predict software application metrics in industrial scenarios using AI techniques. It comprises interconnected agents that aim to enhance operational insights and decision-making processes. The forecaster component uses a random forest regressor to predict known and aggregated metrics. Further analysis demonstrates overall robust predictive capabilities. Visual representations and an error analysis underscore the forecasting accuracy and limitations. This work establishes a foundational understanding and predictive architecture for software behaviours, charting a course for future advancements in decision-making components within evolving industrial landscapes.

show abstract

“…Software defect prediction(SDP) has emerged as a popular research topic over the last several decades [3], [6], [7]. Researchers have utilized various classification techniques to build these models including Logistic Regression [8], Na¨ıve Bayes classifier [9], Support Vector Machine [8], Artificial Neural Networks [10], Decision Tree Classifiers [11], Random Forest Algorithms [12], kernel PCA [13], Deep Learning [14], combination of Kernel PCA and Deep Learning [15] [16] and ensemble learning techniques [17] etc. Aleem et al [3] explored different machine learning techniques for software bug detection and provided a comparative performance analysis of these algorithms.…”

Section: Background and Related Workmentioning

confidence: 99%

Explainable Software Defect Prediction from Cross Company Project Metrics using Machine Learning

Haldar

Capretz

2023

2023 7th International Conference on Intelligent Computing and Control Systems (ICICCS)

View full text Add to dashboard Cite

Predicting the number of defects in a project is critical for project test managers to allocate budget, resources, and schedule for testing, support and maintenance efforts. Software Defect Prediction models predict the number of defects in given projects after training the model with historical defect related information. The majority of defect prediction studies focused on predicting defect-prone modules from methods, and class-level static information, whereas this study predicts defects from project-level information based on a cross-company project dataset. This study utilizes software sizing metrics, effort metrics, and defect density information, and focuses on developing defect prediction models that apply various machine learning algorithms. One notable issue in existing defect prediction studies is the lack of transparency in the developed models. Consequently, the explain-ability of the developed model has been demonstrated using the state-of-the-art post-hoc model-agnostic method called Shapley Additive exPlanations (SHAP). Finally, important features for predicting defects from cross-company project information were identified.

show abstract

Software Defect Prediction with Naïve Bayes Classifier

Cited by 14 publications

References 14 publications

Design and analysis of a new brake-by-wire system using machine learning

Design and analysis of a new brake-by-wire system using machine learning

Design and Implementation of an AI-Enabled Sensor for the Prediction of the Behaviour of Software Applications in Industrial Scenarios

Explainable Software Defect Prediction from Cross Company Project Metrics using Machine Learning

Contact Info

Product

Resources

About