With the widespread availability of free AI-powered mobile applications, the creation of realistic and deceptive videos known as "DeepFakes" has become increasingly effortless. Detecting the authenticity of such videos poses a formidable challenge due to the scarcity of discernible traces. In this study, we delve into the application of an image processing algorithm, specifically InceptionResNetV2, for deepfake detection in videos. The amalgamation of ResNet and Inception models in InceptionResNetV2 yields superior accuracy, making it an ideal choice for our investigation. Our research entails the development of an Android-based application employing the proposed algorithm, with MIT App Inventor for application creation and Google Colab for the prediction model. Furthermore, we conduct a thorough evaluation of the application's performance in detecting deepfake videos, employing three models-InceptionResNetV2, EfficientNetB0, and ResNet50-across two datasets: DFDC and CelebDF, totalling 400 datasets. Notably, InceptionResNetV2 outperformed the other models, achieving an accuracy of 93.20% for the DFDC dataset and an impressive accuracy of 97.72% for the CelebDF dataset. Conversely, ResNet50 exhibited the lowest accuracy for the DFDC dataset, at a mere 52.28%, while EfficientNetB0 displayed the lowest accuracy for the CelebDF dataset, measuring 30.81%. This journal publication sheds light on the advancements in deepfake detection, focusing on the efficacy of InceptionResNetV2 as a powerful tool for reliable video authentication and providing valuable insights into the comparative performance of different models in tackling this complex issue.

This paper explores the development and implementation of an agility monitoring system, aiming to provide real-time assessment of an athlete's agility. The need for such technology to facilitate instant and remote agility assessment has become increasingly apparent in the field of sports science. Unfortunately, progress in this area has been relatively slow until the emergence of IoT (Internet of Things) technology, which presents a promising avenue for athlete agility monitoring through telemetering. The core of this innovative system consists of an agility pad and a real-time monitoring module, with communication facilitated by LabVIEW software. Our approach involves rigorous testing, including unit testing of the agility pad, which serves as an MQTT publisher, the server, which functions as an MQTT broker, and the monitoring module, acting as an MQTT subscriber. In addition to these technical aspects, this article showcases various outcomes of our research. These include the designs of two activity diagrams, a comprehensive conceptual framework for agility monitoring, the database structure, communication designs for the agility pad, a wiring schematic, a 3D model of the agility pad, and the corresponding wiring configuration. We have successfully constructed two sets of agility pads, each integrated with an MCU system (ESP8266) and a dedicated database architecture designed for agile monitoring. One significant achievement of our work is the identification of the optimal delay interval required on the agility pad to prevent data loss on the MQTT broker. Furthermore, we have effectively developed a mechanism for detecting and addressing abnormal data during each testing phase, which contributes to the robustness and reliability of the system. This paper not only highlights the innovative technology behind the IOT-Infused Agility-Pad but also underscores its potential to revolutionize the assessment of athletic performance, offering coaches and athletes real-time insights into agility progress.

Running is a common and easily accessible physical activity that greatly enhances mental and cardiovascular health. The development of technology has completely changed the way we think about fitness. However, the absence of a sophisticated and intelligent running tracking system poses several problems. Among the problems running enthusiasts face is recording the data and analysing the runner for coaches to monitor their health in field paces, heart rate, and distances using wearable devices. In the absence of monitoring, the runner is incautious about their condition while running to avoid injury. The objectives are: to design the implementation of wearable devices equipped with sensors to record comprehensive data during a runner's activity; to develop a system for coaches to monitor and track the health and performance of runners in real-time; and to test the effectiveness of the sensor monitoring system in promoting runner awareness and preventing injuries during running. The methodology is to create a wearable device sensor using IoT components that can easily attach and detect the runner’s health accurately. In this project we can expect that the system should seamlessly function once installed on the runners, the data will be forwarded to the server attached to the laptop where the coaches and admin can view the runner's health status. Also, the device can trace and record the data without causing any problems. Hence, the objective of the result is to study a better-running tracking system by analysing its limitations, especially concerning accurate data storage, real-time performance analysis, and personalized insights. The embedded device can record the health status and able to be monitored by the coach. The combination of embedded technology and monitoring systems will effectively prevent injuries among runners. The technologies/tools used are MKR1010, Arduino IDE, Laravel, Firebase, PHP, and Processing IDE.

Running is a common and easily accessible physical activity that greatly enhances mental and cardiovascular health. The development of technology has completely changed the way we think about fitness. However, the absence of a sophisticated and intelligent running tracking system poses several problems. Among the problems running enthusiasts face is recording the data and analysing the runner for coaches to monitor their health in field paces, heart rate, and distances using wearable devices. In the absence of monitoring, the runner is incautious about their condition while running to avoid injury. The objectives are: to design the implementation of wearable devices equipped with sensors to record comprehensive data during a runner's activity; to develop a system for coaches to monitor and track the health and performance of runners in real-time; and to test the effectiveness of the sensor monitoring system in promoting runner awareness and preventing injuries during running. The methodology is to create a wearable device sensor using IoT components that can easily attach and detect the runner’s health accurately. In this project we can expect that the system should seamlessly function once installed on the runners, the data will be forwarded to the server attached to the laptop where the coaches and admin can view the runner's health status. Also, the device can trace and record the data without causing any problems. Hence, the objective of the result is to study a better-running tracking system by analysing its limitations, especially concerning accurate data storage, real-time performance analysis, and personalized insights. The embedded device can record the health status and able to be monitored by the coach. The combination of embedded technology and monitoring systems will effectively prevent injuries among runners. The technologies/tools used are MKR1010, Arduino IDE, Laravel, Firebase, PHP, and Processing IDE.

Wireless Body Area Networks (WBANs) have gained attention as a promising technology for healthcare applications. However, one of the key challenges in WBANs is the reliability of the gateway device which serves as a bridge between the WBAN and the external network. This research has proposed a technique for the gateway failure problem which occurs when a default gateway fails to transmit packets to the medical server due to unforeseen circumstances such as loss of network, and power interruption during continuous packet transmission. This research has proposed a method called redundant gateway architecture (RGA) in which a backup gateway is introduced as an aide for the default gateway and automatically continues the task of packet transmission whenever the default gateway is out of service until it’s back to function. RGA uses a failover mechanism to detect gateway failures. We evaluate the RGA in real-time with ECG, temperature sensor, pulse sensor, ESP8266, and ESP37 microcontrollers and the results show that the proposed architecture can effectively handle gateway failures in WBANs with a high delivery ratio and low latency. The RGA architecture demonstrated superior performance compared to other methods, particularly in terms of packet delivery ratio, attributed to its ability to minimize packet loss throughout the routing process. This has enhanced the reliability of WBAN data and enabled the seamless delivery of healthcare services.