Abstract-Software Bug Prediction (SBP) is an important issue in software development and maintenance processes, which concerns with the overall of software successes. This is because predicting the software faults in earlier phase improves the software quality, reliability, efficiency and reduces the software cost. However, developing robust bug prediction model is a challenging task and many techniques have been proposed in the literature. This paper presents a software bug prediction model based on machine learning (ML) algorithms. Three supervised ML algorithms have been used to predict future software faults based on historical data. These classifiers are Naïve Bayes (NB), Decision Tree (DT) and Artificial Neural Networks (ANNs). The evaluation process showed that ML algorithms can be used effectively with high accuracy rate. Furthermore, a comparison measure is applied to compare the proposed prediction model with other approaches. The collected results showed that the ML approach has a better performance.
Last mile logistics represent one of the most important challenging issues in online grocery shopping. Online customers are expecting high logistical services, demanding convenience, high reliable and on-time delivery services. As such, online retailers have to respond to these expectations by providing convenient logistical services while keeping this process cost efficient as much as possible. This research aims to design an e-commerce logistical decision support system for online grocery shopping in Jordan as a case study from the developing countries. Online grocery retailers are supposed to use this model in order to select the most suitable delivery operating system in the future. To implement and evaluate this model, one of the available routing and scheduling online solutions (i.e. “My Route Online”) is used to identify, analyse, and compare the cost efficiencies of the available alternative delivery solutions. The system is tested using real data over three different delivery alternatives (i.e. home delivery, delivery point and pickup point) in order to evaluate and compare their cost efficiencies. The findings from the experiments show that there are significant differences amongst the three delivery alternatives on the basis of three KPIs: cost, distance and time. The findings also indicate that the time indicator has more powerful change effect on cost than distance for all delivery alternatives. According to the level of investments online grocery retailers are willing to offer, customer preferences, and the experimental results, it is concluded that pickup point solution is the best logistical strategy for online grocery retailers to start with.
Quality has become a fundamental requirement for success and sustainability of websites. This study discusses the evaluation of some e-Learning websites as one of the main sources of information to administrators, students and teachers in the educational systems. This article investigates the quality of e-learning websites in the Middle East in term of usability and content accessibility. Eleven websites from eleven countries were selected for this study. Evaluations process is done based on different web diagnostic tools and measures. The experimental results show several issues on usability and content accessibility of the selected e-learning websites. Many usability problems with respect of speed and number of broken links were found. Moreover, the design of the selected websites is not fit with the content accessibility standards.
Abstract-Mobile Ad hoc Networks (MANETs) are considered as a reunion of wireless mobile devices (nodes) that form a temporary wireless network. In order to facilitate communication in MANET, every node has to participate in the routing process. Reaching an optimal route is a fundamental task in MANET, because routes are multi-hoped and susceptible. Several routing protocols exist and can be categorized to; topology-based and position-based routing protocols. However, the efficiency of these protocols in highly dynamic and dense environments is a challenging task to be considered for increasing perceived Quality of Service (QoS) in MANET. This paper focuses on the presentation and basic operation of each category. A performance evaluation study was conducted comparing between both categories in terms of End-to End delay, packet-delivery ratio and routing overhead. Results analysis show that position-based protocols outperforms topology-based protocols in dense and high dynamic environments. Recommendations for implementing future efficient position-based protocols were presented.
Abstract-This work investigates university students' acceptance and readiness for adopting collaborative and context-aware mobile learning services. An acceptance evaluation study was conducted to identify challenges affecting successful implementation and adoption of collaborative mlearning system. The acceptance study has focused on learning contextual factors and learners requirements available at developing countries, where Jordan was considered as the case of this research. Results have confirmed that learning style, mobile device capability and perceived ease of use are having the most positive contribution towards learners' behavior to use collaborative m-learning services. In light of the achieved results, this work provides a new user acceptance model focused toward the adoption of collaborative m-learning services. Finally, this research draws fundamental recommendations allowing for learning context adaptation and successful collaborative m-learning services implementation.
This research utilizes metaheuristic optimization inspired by the Egyptian Vulture Optimization (EVO) technique. Biomedical image segregation is developed to reduce the complex association of hyperparameters of Convolutional Neural networks (CNN). The complex attributes of CNN include the type of kernel, size of the kernel, size of the batch, epoch counts, momentum, learning rate, activation function, convolution layer, and dropout. However, the life cycle of an Egyptian vulture influences the optimization technique to resolve complexity and increase the accuracy of CNN. The proposed CNN-based EVO model was evaluated in comparison to ANN-based and deep learning-based classifiers utilizing brain MRI image datasets. The results achieved have confirmed the efficiency and performance of the proposed CNN-based EVO model, in which the average detection accuracy and precision were 93% and 95%, respectively.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.