Prolonged sitting with poor posture can lead to various health problems, including upper back pain, lower back pain, and cervical pain. Maintaining proper sitting posture is crucial for individuals while working or studying. Existing pressure sensor-based systems have been proposed to recognize sitting postures, but their accuracy ranges from 80% to 90%, leaving room for improvement. In this study, we developed a sitting posture recognition system called SPRS. We identified key areas on the chair surface that capture essential characteristics of sitting postures and employed diverse machine learning technologies to recognize ten common sitting postures. To evaluate the accuracy and usability of SPRS, we conducted a ten-minute sitting session with arbitrary postures involving 20 volunteers. The experimental results demonstrated that SPRS achieved an impressive accuracy rate of up to 99.1% in recognizing sitting postures. Additionally, we performed a usability survey using two standard questionnaires, the System Usability Scale (SUS) and the Questionnaire for User Interface Satisfaction (QUIS). The analysis of survey results indicated that SPRS is user-friendly, easy to use, and responsive.
Porters play an important role in supporting hospital operations. Their responsibilities include transporting patients and medical equipment between wards and departments. They also need to deliver specimens, drugs, and patients’ notes to the correct place at the right time. Therefore, maintaining a trustworthy and reliable porter team is crucial for hospitals to ensure the quality of patient care and smooth the flow of daily operations. However, most existing porter systems lack detailed information about the porter movement process. For example, the location of porters is not transparent to the dispatch center. Thus, the dispatcher does not know if porters are spending all their time providing services. The invisibility makes it difficult for hospitals to assess and improve the efficiency of porter operations. In this work, we first developed an indoor location-based porter management system (LOPS) on top of the infrastructure of indoor positioning services in the hospital National Taiwan University Hospital YunLin Branch. The LOPS provides real-time location information of porters for the dispatcher to prioritize tasks and manage assignments. We then conducted a 5-month field trial to collect porters’ traces. Finally, a series of quantitative analyses were performed to assess the efficiency of porter operations, such as the movement distribution of porters in different time periods and areas, workload distribution among porters, and possible bottlenecks of delivering services. Based on the analysis results, recommendations were given to improve the efficiency of the porter team.
Providing a safe and secure living environment for residents that is supported by a dedicated healthcare team is one of the core values of nursing homes. Nursing homes must protect residents from the risk of going missing, track quarantined residents and visitors to control the spread of infection, and maintain proactive nursing rounds. However, recruiting and retaining qualified caregivers and medical staff has long been a challenge. Therefore, using advanced technology to ensure the safety and security of residents is highly desirable. In this work, we first demonstrate the applicability of indoor tracking applications in a nursing home, such as resident and asset tracking, nursing assistant management, visitor tracking, infection control, and vital-sign monitoring. To monitor the locations of residents and staff, Bluetooth tags were used, providing real-time data for location tracking. We then conduct a series of quantitative analyses to illustrate how indoor tracking data can support the management of nursing homes, including characterizing residents’ activities in daily living and assessing the performance and workload of nursing assistants. Finally, we use qualitative research to evaluate the acceptability of an indoor positioning system in the nursing home. The results show that the implemented indoor positioning applications can improve the quality of healthcare and working efficiency, thereby providing a safer and more secure living environment for residents.
The popularity of keeping ornamental fish has grown increasingly, as their vibrant presence can provide a calming influence. Accurately assessing the health of ornamental fish is important but challenging. For this, researchers have focused on developing fish tracking methods that provide trajectories for health assessment. However, issues such as mirror images, occlusion, and motion prediction errors can significantly reduce the accuracy of existing algorithms. To address these problems, we propose a novel ornamental fish tracking method based on deep learning techniques. We first utilize the You Only Look Once (YOLO) v5 deep convolutional neural network algorithm with Distance Intersection over Union–Non Maximum Suppression (DIoU-NMS) to handle occlusion problems. We then design an object removal algorithm to eliminate fish mirror image coordinates. Finally, we adopt an improved DeepSORT algorithm, replacing the original Kalman Filter with an advanced Noise Scale Adaptive (NSA) Kalman Filter to enhance tracking accuracy. In our experiment, we evaluated our method in three simulated real-world fish tank environments, comparing it with the YOLOv5 and YOLOv7 methods. The results show that our method can increase Multiple Object Tracking Accuracy (MOTA) by up to 13.3%, Higher Order Tracking Accuracy (HOTA) by up to 10.0%, and Identification F1 Score by up to 14.5%. These findings confirm that our object removal algorithm effectively improves Multiple Object Tracking Accuracy, which facilitates early disease detection, reduces mortality, and mitigates economic losses—an important consideration given many owners’ limited ability to recognize common diseases.