Eleonora Tudora

In the context of global demographic aging, falls among the elderly remain a major public health concern, often leading to injury, hospitalization, and loss of autonomy. This study proposes a real-time fall detection system that combines a modern computer vision model, YOLOv11 with integrated pose estimation, and an Artificial Intelligence (AI)-based voice assistant designed to reduce false alarms and improve intervention efficiency and reliability. The system continuously monitors human posture via video input, detects fall events based on body dynamics and keypoint analysis, and initiates a voice-based interaction to assess the user’s condition. Depending on the user’s verbal response or the absence thereof, the system determines whether to trigger an emergency alert to caregivers or family members. All processing, including speech recognition and response generation, is performed locally to preserve user privacy and ensure low-latency performance. The approach is designed to support independent living for older adults. Evaluation of 200 simulated video sequences acquired by the development team demonstrated high precision and recall, along with a decrease in false positives when incorporating voice-based confirmation. In addition, the system was also evaluated on an external dataset to assess its robustness. Our results highlight the system’s reliability and scalability for real-world in-home elderly monitoring applications.

This study aims to enhance elderly fall detection systems by using the YOLO (You Only Look Once) object detection algorithm with pose estimation, improving both accuracy and efficiency. Utilizing YOLOv7-W6-Pose’s robust real-time object detection and pose estimation capabilities, the proposed system can effectively identify falls in video feeds by using a webcam and process them in real-time on a high-performance computer equipped with a GPU to accelerate object detection and pose estimation algorithms. YOLO’s single-stage detection mechanism enables quick processing and analysis of video frames, while pose estimation refines this process by analyzing body positions and movements to accurately distinguish falls from other activities. Initial validation was conducted using several free videos sourced online, depicting various types of falls. To ensure real-time applicability, additional tests were conducted with videos recorded live using a webcam, simulating dynamic and unpredictable conditions. The experimental results demonstrate significant advancements in detection accuracy and robustness compared to traditional methods. Furthermore, the approach ensures data privacy by processing only skeletal points derived from pose estimation, with no personal data stored. This approach, integrated into the NeuroPredict platform developed by our team, advances fall detection technology, supporting better care and safety for older adults.

Internet of Medical Things (IoMT) has already proved to support a proper evaluation of the medical status and living conditions of a patient by gathering a large variety of data. For a personalized health management of an older patient, IoMT provides the capacity for sustaining the transformation the patient-physician relationship by enabling a real-time and continuous remote monitoring of the health status, activities and well-being of the senior, especially in a residential environment. Thus, a new collaborative solution between the patient and the physician and the enhancement of their involvement and shared decision-making are provided. Health remote monitoring systems in smart environments are able to be a viable alternative to traditional healthcare solutions. The ongoing “Non-invasive monitoring and health assessment of the elderly in a smart environment (RO-SmartAgeing)” project aims to a complete and accurate solution for assessing the health condition of the seniors, improving their wellbeing and quality of life. The continuous monitoring of patient's health status together of the provision of notifications and alerts related to problems in her/his health condition can allow the physician to provide health services at a higher level of efficiency and to offer a more comprehensive perspective of proactive and preventive medical acts.

Number of people 65+ is increasing all over the word, accompanied by illness, disability, vulnerability and dependence, thus potentially putting enormous stress on healthcare and long-term care costs. Creating an enabling environment that allows people with care needs to live at their homes as long as possible remains the main challenge of the long-term care system. Our paper presents RO-SmartAgeing system, an IoT-based system for remote monitoring of older people heath. Its functions and advantages for elderly are underlined.

The Internet of Things (IoT), through portable devices and sensor networks, has the potential to transform the way in which healthcare monitoring systems collect and analyze patients' medical data. Nowadays, the IoT-based healthcare monitoring systems for the elderly require large amounts of data that needs to be transferred to a centralized database and from the database to cloud data centers, which leads to a decrease in the performance of such systems. Thus, fog computing provides innovative solutions by bringing resources closer to the user and by providing low latency and efficient solutions for data processing as against to cloud. In this paper, we present the “Non-invasive monitoring and health assessment of the elderly in a smart environment (RO-SmartAgeing)” project which supports elderly centered healthcare services in order to ensure illness prevention, personalized assistance and monitoring healthcare services. According to the current development state of the project, we propose a functional framework of the architecture of RO-SmartAgeing system based on IoT, Fog and Cloud Computing, present the hardware components of the system necessary for proper operation, the data flow chart of the RO-SmartAgeing system and an example of numerical validation and filtering of data from IoT devices.

Mild cognitive impairment (MCI) can occur while a person is getting old and it is associated with more serious cognitive deteriorations than the normal ageing-related ones. As it may involve a significant decrease in the quality of life, health status and independence of the elderly, the early diagnosis and a personalized assistance become crucial in this ageing worldwide context. Current and emerging technologies provide the needed support for implementing appropriate new models of healthcare delivery. This paper highlights how RO-SmartAgeing system, which aims to provide customized monitoring and assistance for an elderly in his home, is designed for addressing a particular health condition as MIC. The associated smart environment is presented, together with the data flow chart and architecture, with an emphasis on MIC approach.