Abstract : In the past few years, the integration of technology within education has been emerging intensively. It has become conventional for higher educators to implement learning management systems (LMS) in several ways that had been formerly seen in a few educational institutes. This article collects data from LMS to see how data analytics can play a role in education by focusing on the success opportunities and restrictions of graduates. In the framework of LMS utilization, students have gained insights throughout their registrations. The aim is to explore the role of data analytics in the field of education. By implementing the LMS, students have gained informative knowledge during their enrollment. Within this specific context, the data pertaining to the learners' footprints, enrollment patterns, and degree of accomplishment has been systematically documented in an electronic fashion. By employing survival analysis on this dataset, we may predict the future accomplishments of the students and anticipate their progress. The results show that psychology is one of the areas that the institution should provide as a remedial class for all master students in order to increase their success rate. Besides, the findings can aid educators in enhancing the standard of instruction and learning by reinforcing extracurricular activities that are specifically designed to assist and rectify graduates who are underperforming. The analytical results can be utilized to bolster the development of a forward-thinking curriculum, aimed at improving the quality of education by creating essential introductory courses. Ultimately, educators possess the capacity to align their teaching methods with all available analytical data in order to enhance their instructional tactics.. Full article
Abstract : One of the core tasks in computer vision with many applications is object detection. As a result of recent developments, strong object detection architectures like YOLOv8 and EfficientDet have emerged, each with special benefits. In this paper, we integrate the advantages of both architectures to present a revolutionary unified object identification system. We achieve state-of-the-art performance across multiple benchmarks by utilizing the superior accuracy of EfficientDet and the real-time capability of YOLOv8. We offer thorough experiments proving the efficiency of our method and shed light on how well the two architectures work together. Our cohesive architecture, which strikes a compromise between speed and precision for realistic deployment in real-world scenarios, raises the bar for object detection systems.. Full article
Abstract : Cardiovascular diseases have long been a significant medical concern, and early and accurate identification is crucial for effective rehabilitation and treatment. Predicting heart disease promptly enables informed decision-making, reducing patient risks. We utilized the MIT-BIH Database to facilitate this process, containing 48 half-hour excerpts of two-channel ambulatory ECG recordings digitized at 360 samples per second per channel. Before further analysis, the data underwent preprocessing steps, including Wavelet Transformation for Baseline Correction and normalization. Additionally, we detected a PQRST waveform consisting of 290 samples, which was extracted and then converted to 360 Hz after peak detection. Next, we performed a Hybrid Time-Frequency analysis using Short Time Fourier Transformation (STFT) and Wigner-Ville distribution (WVD). This transformation process turned the 1D ECG recordings into a 2D time-frequency spectrum, providing a more comprehensive signal representation. We employed a ResNet50 classifier with a 2D architecture to classify the ECG signals. Three distinct cases were considered: normal (non-ectopic cardiac beat), arrhythmia (ventricular ectopic beat), and abnormal (unknown beat). Remarkably, the ResNet50 classifier achieved an impressive accuracy of 97.96% in accurately identifying the different ECG signal categories.. Full article