Student-Centered Group-Based Learning System

This study developed a student-centered group-based learning system. The system requirements were gathered from relevant literature on pedagogy and WebRTC. The study identified social loafing as a major drawback of most student-centered learning groups. The system was designed using block, architectural pattern, flow-chart, use-case, sequence, class and architectural-context diagrams and the system’s application logic was implemented using ASP.NET C#; HTML, JAVASCRIPT and BOOTSTRAP for the front-end and SQL for the database, HangFire and SignalR for the reminder and texting system. SendGrid API for reminders and OpenVidu Media server for video and audio-calling. The system has been tested and proven to be effective in providing different forms of communication and structure to group-learning that reduces social loafing, and can be recommended for tertiary institutions who want to promote a better student-student relationship for improved learning.

A Review of Sign Language Recognition Techniques

Sign language recognition is important for natural and convenient communication between deaf community and hearing majority. Hand gestures are a form of nonverbal communication that makes up the bulk of the communication between mute individuals, as sign language constitutes largely of hand gestures. Research works based on hand gestures have adopted many different techniques, including those based on instrumented sensor technology and computer vision. In other words, the hand sign can be classified under many headings, such as posture and gesture, as well as dynamic and static, or a hybrid of the two. This paper focuses on a review of the literature on computer based sign language recognition approaches, their motivations, techniques, observed limitations and suggestion for improvement.

Breast Cancer Detection, Diagnosis, and Prediction

The early detection, diagnosis, prediction, and treatment of breast cancer are challenginghealthcare problems. This study focuses on outlining the traditional and trending techniques used for breast cancer detection, diagnosis, and prediction, including trending noninvasive, nonionizing, and biomarker genetic techniques.In addition, a Computer Aided Detection (CAD) is introduced to classify benign and malignant tumors in mammograms. This CAD system involves three steps. First, the Region of Interest (ROI) that includesthe tumor is identified using a threshold-based method. Second, a deep learning Convolutional Neural Network (CNN) processes the ROI to extract relevant mammogram features. Finally, a Support Vector Machine (SVM) classifier is used to decode two classes of mammogram structures (i.e., Benign (B), and Malignant (M) nodules). The training processes and implementations were carried out using 2800 mammogram images taken from the Curated Breast Imaging Subset of DDSM (CBIS-DDSM). Results have shown that the accuracy of CNN-SVM system achieves 85.1% using AlexNet CNN. Comparison with related work shows the promise of the proposed CAD system

An Incremental Deep Model For Computing Electrical Power Load Forecasting Based Social Factors

Load forecasting (LF) is critical for guaranteeing adequate limit and controlling of the power business in numerous nations, which theeconomies dependingon electricity. Its production (load) and consumption (demand) have to be in equilibrium at all times since storing electricity, in a considerable quantity, results in high costs. Therefore, the forecasting of the electrical load problem in many countries become crucial and critical in the recent years. In this paper, a novel deep model architecture for LFintroduced, which integrates the features of dataset in discovering the most influent factors affecting electrical load usage. In addition, different LF strategies introduced and their interrelations just asthe intensity of neural organizations to rough the heap estimating. The deep model is based on in three terms time: Long-term (yearly), Mid-term (Monthly), and Mid-term (Weekly), which can possibly provide interrelated deep learning models. Moreover, to generating more accurate predictions based the hierarchal learning architecture. The dataset used is introduced in the case study, which is power load in Giga-watt from years 2006 to 2015. The load forecasted for the year 2016 and is validated to check its accuracy