The application of machine learning algorithms to the detection of fraudulent credit card transactions is a challenging problem domain due to the high imbalance in the datasets and confidentiality of financial data. This implies that legitimate transactions make up a high majority of the datasets such that a weak model with 99% accuracy and faulty predictions may still be assessed as high-performing. To build optimal models, four techniques were used in this research to sample the datasets including the baseline train test split method, the class weighted hyperparameter approach, and the undersampling and oversampling techniques. Three machine learning algorithms were implemented for the development of the models including the Random Forest, XGBoost and TensorFlow Deep Neural Network (DNN). Our observation is that the DNN is more effcient than the other 2 algorithms in modelling the under-sampled dataset while overall, the three algorithms had a better performance in the oversampling technique than in the undersampling technique. However, the Random Forest performed better than the other algorithms in the baseline approach. After comparing our results with some existing state-of-the-art works, we achieved an improved performance using real-world datasets.
This paper presents the development of a web-based examination system that focuses on automated resolution of faults such as power, network, or component failure that may occur when an e-learning system is used to conduct an examination. This system can withstand various challenges that hinder the adoption of e-learning technologies in developing countries. This is important because it will reduce the time and cost involved in conducting large scale examinations by tertiary institutions without the need to upgrade existing infrastructures. These institutions will not necessarily require uninterrupted power or network connection to conduct web-based examinations as the system can easily resume if such an incident occurs. The architecture of the proposed web-based online examination system provides for integrated management of functions such as question pool creation and update, examination monitoring, failure toleration and recovery, automated grading, and randomization. The system also eliminates the need for manual scheduling of examinations which requires much planning and is error-prone. Different examinations can be scheduled to run simultaneously. The design technology adopted for the implementation is a client/server technology. The incremental software development model in conjunction with prototyping technique was adopted in the development of the web-based examination system due to the iterative nature of the developed software. The system was developed using PHP, JavaScript, Ajax and MySQL. The system has been applied to conduct an examination involving more than 20,000 students per semester at University of Calabar. It has been proved to save efforts of teachers and students.
Precision Agriculture which includes the implementation of smart farms is gradually becoming commonplace in our present world. The Internet of Things (IoT) and also Analytics techniques are useful tools for the actualization of smart farms as they allow for information dissemination to rural farmers and also serve as a platform for monitoring farm activities. When farm activities are properly monitored, food production is optimized. As the world’s population grows, there is a greater challenge of the availability of food. The combination of IoT and data analytics has not been fully explored for Smart farming especially in developing economies. This paper proposes a FarmSmart Application using an IoT-based mobile monitoring system that combines sensors, and data analytics to manage irrigation processes and broadcast Agricultural information to farmers. The FarmSmartApp was implemented on the IntelliJ IDE using C++ and MongoDB.Python and Excel were used for the data analytics. The effectiveness of the proposed system is examined on a real-world dataset harvested from the mounted sensors. Also an initial evaluation of the system is done by stakeholders. Simple Analysis of Variance of light, moisture and temperature led to the rejection of the null hypothesis of no significance difference in mean effect among the variables since fcalc is greater than fcrit justified by p value less than 0.05. On the system evaluation, 97 % of the examined stakeholders agreed that the system delivered on the agreed functionality .The system therefore has the capacity to provide farmers with useful Agricultural information to guide irrigation procedures and Agricultural decision making
The emergence of the Service Oriented computing paradigm with its implicit inclusion of web services has caused a precipitous revolution in software engineering, e-service compositions, and optimization of e-services. Web service composition requests are usually combined with end-to-end Quality of Service (QoS) requirements, which are specified in terms of non-functional properties e.g. response time, throughput, and price. This chapter describes what web services are; not just to the web but to the end users. The state of the art approaches for composing web services are briefly described and a novel game theoretic approach using genetic programming for composing web services in order to optimize service performance, bearing in mind the Quality of Service (QoS) of these web services, is presented. The implication of this approach to cloud computing and economic development of developing economies is discussed.
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.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.