According to the World Health Organization and other authorities, falls are one of the main causes of accidental injuries among the elderly population. Therefore, it is essential to detect and predict the fall activities of older persons in indoor environments such as homes, nursing, senior residential centers, and care facilities. Due to non-contact and signal confidentiality characteristics, radar equipment is widely used in indoor care, detection, and rescue. This paper proposes an adaptive channel selection algorithm to separate the activity signals from the background using an ultra-wideband radar and to generalize fused features of frequency- and time-domain images which will be sent to a lightweight convolutional neural network to detect and recognize fall activities. The experimental results show that the method is able to distinguish three types of fall activities (i.e., stand to fall, bow to fall, and squat to fall) and obtain a high recognition accuracy up to 95.7%.

The healthcare industry faces challenges due to rising treatment costs, an aging population, and limited medical resources. Remote monitoring technology offers a promising solution to these issues. This article introduces an innovative adaptive method that deploys an ultrawideband (UWB) radar-based Internet of Medical Things (IoMT) system to remotely monitor elderly individuals’ vital signs and fall events during their daily routines. The system employs edge computing for prioritizing critical tasks and a combined cloud infrastructure for further processing and storage. This approach enables monitoring and telehealth services for elderly individuals. A case study demonstrates the system’s effectiveness in accurately recognizing high-risk conditions and abnormal activities, such as sleep apnea and falls. The experimental results show that the proposed system achieved high accuracy levels, with a mean absolute error (MAE) ± standard deviation of absolute error (SDAE) of 1.23± 1.16 bpm for heart rate (HR) detection and 0.22 ± 0.27 bpm for respiratory rate (RR) detection. Moreover, the system demonstrated a recognition accuracy of 90.60% for three types of falls (i.e., stand, bow, squat to fall), one daily activity, and No Activity Background. These findings indicate that the radar sensor provides a high degree of accuracy suitable for various remote monitoring applications, thus enhancing the safety and well-being of elderly individuals in their homes.

As a sedentary lifestyle leads to numerous health problems, it is important to keep constant motivation for a more active lifestyle. A large majority of the worldwide population, such as office workers, long journey vehicle drivers and wheelchair users, spends several hours every day in sedentary activities. The postures that sedentary lifestyle users assume during daily activities hide valuable information that can reveal their wellness and general health condition. Aiming at mining such underlying information, we developed a cushion-based system to assess their activity levels and recognize the activity from the information hidden in sitting postures. By placing the smart cushion on the chair, we can monitor users’ postures and body swings, using the sensors deployed in the cushion. Specifically, we construct a body posture analysis model to recognize sitting behaviors. In addition, we provided a smart cushion that effectively combine pressure and inertial sensors. Finally, we propose a method to assess the activity levels based on the evaluation of the activity assessment index (AAI) in time sliding windows. Activity level assessment can be used to provide statistical results in a defined period and deliver recommendation exercise to the users. For practical implications and actual significance of results, we selected wheelchair users among the participants to our experiments. Features in terms of standard deviation and approximate entropy were compared to recognize the activities and activity levels. The results showed that, using the novel designed smart cushion and the standard deviation features, we are able to achieve an accuracy of (>89%) for activity recognition and (>98%) for activity level recognition.