Higher education institutions’ principal goal is to give their learners a high-quality education. The volume of research data gathered in the higher education industry has increased dramatically in recent years due to the fast development of information technologies. The Learning Management System (LMS) also appeared and is bringing courses online for an e-learning model at almost every level of education. Therefore, to ensure the highest level of excellence in the higher education system, finding information for predictions or forecasts about student performance is one of many tasks for ensuring the quality of education. Quality is vital in e-learning for several reasons: content, user experience, credibility, and effectiveness. Overall, quality is essential in e-learning because it helps ensure that learners receive a high-quality education and can effectively apply their knowledge. E-learning systems can be made more effective with machine learning, benefiting all stakeholders of the learning environment. Teachers must be of the highest caliber to get the most out of students and help them graduate as academically competent and well-rounded young adults. This research paper presents a Quality Teaching and Evaluation Framework (QTEF) to ensure teachers’ performance, especially in e-learning/distance learning courses. Teacher performance evaluation aims to support educators’ professional growth and better student learning environments. Therefore, to maintain the quality level, the QTEF presented in this research is further validated using a machine learning model that predicts the teachers’ competence. The results demonstrate that when combined with other factors particularly technical evaluation criteria, as opposed to strongly associated QTEF components, the anticipated result is more accurate. The integration and validation of this framework as well as research on student performance will be performed in the future.

At the beginning stage, the wireless module Intrusion Detection System (IDS) is used to address the networking and misuse attacks on computers. Furthermore, the attempt of IDS monitors the network traffic or user activity is malicious. The detection of intrusion contains some challenging tasks such as detection accuracy, execution time, quality of data, and error. This research designed a novel Bear Smell-based Random Forest (BSbRF) for accurate detection of intrusion by monitoring the behavior and threshold value of each user. Thus the developed electronic-based sensing processor model was implemented in the python tool and the normal and attack user dataset are collected and trained in the system. Henceforth, pre-processing is employed to remove the errors present in the dataset. Moreover, feature extraction was utilized to extract the relevant features from the dataset. Then, update bear smell fitness in the random forest classification layer which monitors the behavior and detects the intrusion accurately in the output layer. Furthermore, enhance the performance of intrusion detection accuracy by bear smell fitness. Finally developed model experimental outcomes shows better performance to detect intrusion and the attained results are validated with prevailing models in terms of accuracy, precision, recall, execution time, and F1 score for wireless sensing mechanism.

In this study, we detail the use of a small, label-free optoelectronic biosensor for the detection of anti-dengue antibodies in human serum samples. The system consists of a vertical-cavity surface-emitting laser that can be tuned, a guided-mode resonant sensor surface, and two silicon pin detectors. After showing adequate sensitivity in a clinically relevant experiment, researchers hypothesized that this cutting-edge biosensor could serve as a novel platform for the development of efficient point-of-care diagnostic techniques for the identification of infectious diseases. Humans are susceptible to one of the world’s most common and contagious diseases, dengue fever, which is spread by the Aedes albopictis mosquito. Human deaths were also a direct outcome of the widespread increase in Dengue fever cases. A shortage of medical professionals and healthcare facilities only made matters worse. In order to achieve this goal, it will be necessary to employ archaic medical technologies. Recent innovations like Fog Computing and the success of remote healthcare in real time, Cloud Computing, and the Internet of Things have opened up new frontiers in technology (IoT). In this research, we proposed a new method for diagnosing dengue disease. Information gathered from those who have been afflicted by a disease will be shared with higher authorities. Various IoT devices compile comprehensive reports on each and every patient. Once medical history is gathered, the patient’s whereabouts must be ascertained. Sensors connected to the internet are used to gather information on the weather, the location, the effectiveness of medications, the safety of the surrounding environment, and the patients’ states of health. The fog computing layer is the bridge between IoT sensors and cloud servers. Two primary functions of the fog computing layer are the creation of notifications and the categorization of users’ health conditions. Dengue fevers are diagnosed using an Artificial Neural Network (ANN) trained with the Salp Swarm Optimization method Salp swarm algorithm (SSA). The dataset will be analyzed using an Internet of Things (IoT) scenario built with the Java simulator CupCarbon U-one 3.8.2. The proposed method achieves competitive or better outcomes than the state-of-the-art alternatives.

No abstract

No abstract