This research work focused on transmission channel characterization of Free-Space-Optical (FSO) communications technology for deploying in the developing country like Bangladesh. To meet the tremendous amount of data traffic, mobile operators and ISPs need better solution than the existing RF and fiber optic communications. Moreover, Bangladesh is entering in the era of satellite communications by launching its own satellite. So, Bangladesh needs such communication technology that provides higher channel bandwidth, sophisticated transmission security and can cope channel dispersion. FSO is a good candidate that can meet all these features. The transmission channel characterization plays a significant role in optimizing the performance of FSO link. In this work, the channel characterization of FSO technology from the weather perspective of Bangladesh has been investigated thoroughly. The obtained results show that the atmospheric scattering effect does not hamper the short range FSO link performance, whereas, the atmospheric turbulence effect is not favorable to deploy FSO technology with reasonable quality signal unless it is optimized properly using antenna aperture averaging technique.
8 December 2025 in Engineering, Technology & Applied Science Research
Falls are a major concern among the elderly, as they can cause serious injuries and even death. Therefore, the development of an effective and reliable fall detection system for the elderly is a critical area of research that can significantly improve their safety and quality of life. This paper presents a user-centric Human Activity Recognition (uHAR) model that integrates machine learning algorithms and advanced sensor technology to analyze and classify the various activities and movements. The proposed model, called uActivity, aims to significantly improve the safety and well-being of elderly people, using a uHAR model that integrates multiple sensor data streams and machine learning algorithms. In the performance analysis of daily activity and fall classification, the uActivity algorithm demonstrates satisfactory results in accurately classifying activities and detecting falls among elderly individuals, achieving an accuracy of more than 99% in detecting falls. The proposed uHAR architecture with the uActivity algorithm can significantly improve the accuracy and reliability of fall detection and daily activity classification systems for elderly people.
1 August 2023 in International Journal of Electrical and Computer Engineering (IJECE)
Elder citizens face sudden fall, which can lead to injuries of both destructive and non-virulent. These sudden falls are later more precarious than diseases like heart attack, blood sugar, blood pressure because these can be untreated for a lengthy time which can lead to death. Elder citizen who experiences a precipitous fall, carry out their communal life narrowed. Therefore, a shrewd and adequate anti-fallen system is required for aiding elderly health care, specifically to those who live individually. So, it can identify and anticipate a precipitous fall through appropriate human activity recognition. In this study, we have suggested an end-edge-cloud based wearable EdgeFall architecture for elderly care. We have performed simulation setups to clarify the query of why we need such a strategy, and its validity. We have achieved maximum 91.87% accuracy with 1.6% false alarm rate (FAR). These empirical results indicate the superiority of using tightly couple multiple information for recognizing human activity. We can accomplish a low FAR with an enhanced accuracy. We can observe that our proposed end-edge-cloud based architecture can reduce the execution time to millisecond range (ms) of 14.16 to 15.74. This work serves as the starting mark for future related research activities.
Elder citizens face sudden fall which can cause injuries of both fatal and non-fatal type. These sudden falls are sometime more dangerous than diseases heart attract, blood sugar, blood pressure because these can be untreated for a long period of time which can lead to death. An elder citizen who faces an sudden fall, make his or her social life limited. This is why a smart and effective anti-fallen system needed to be developed to support elderly health care, especially to those who lives independently, which can detect and predict a sudden fall through proper human activity recognition. In this paper, we have introduced an end-edge-cloud based wearable smarachFALL (smart activity recognition architecture for fall detection and prediction) architecture for elderly care. We have designed simulation setups to answer the question of why we need such system and the effectiveness. These experimental results also shows the advantage of using tightly couple multiple information for recognizing human activity. We are able to achieve a low false alarm rate (FAR) with an improved accuracy. These work serves as the starting point for future related research activities.
Human activity recognition (HAR) remains a pivotal research domain with extensive applications in healthcare, elderly care, and assistive technology. However, traditional systems relying solely on inertial measurement units (IMUs) face significant limitations, particularly regarding precision and vulnerability to varying device orientations. To address this urgent need, this study introduces visual inertial odometry based human activity recognition (vioHAR), a novel methodology and public dataset that seamlessly fuses visual and inertial data. By leveraging the visual-inertial odometry system for monocular cameras (VINS-Mono) state estimator, the proposed system generates precise, orientation-independent trajectories, facilitating robust classification across eight distinct daily behaviors and fall scenarios. Extensive evaluation using leave-one-subject-out (LOSO) cross-validation demonstrates that the vioHAR method achieves a robust average accuracy of 73.96%. This represents a substantial improvement over the standard IMU-only baseline (43.35%), yielding specific accuracy gains of +27.60% for the random forest (RF) model and +41.11% for the long short-term memory (LSTM) model. Furthermore, comparing computational efficiency, the LSTM network trained nearly ten times faster than the RF model (44.79 vs 415.81 s) while maintaining a minimal false alarm rate of 0.038, highlighting its superior potential for edge computing applications. Despite hardware challenges such as asynchronous sensor clocks, vioHAR establishes a rigorous and efficient foundation for real-world HAR deployment on emerging head-worn devices.