An Automated Sitting Posture Recognition System Utilizing Pressure Sensors.

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.

DBOS: A Dialog-Based Object Query System for Hospital Nurses.

Due to the advance of indoor positioning technology, it is now possible to trace mobile medical equipment (such as electrocardiography machines, patient monitors, and so on) being moved around a hospital ward. With the support of an object tracking system, nurses can easily locate and find a device, especially when they prepare for a shift change or a medical treatment. As nurses usually face high workloads, it is highly desirable to provide nurses with a user-friendly search interface integrated into a popular mobile app that they use daily. For this, DBOS, a dialog-based object query system, is proposed, which simulates a real conversation with users via the Line messaging app's chatbot interface. A hybrid method that combines cosine similarity (CS) and term frequency-inverse document frequency (TF-IDF) is used to determine user intent. The result is returned to the user through Line's interface. To evaluate the applicability of DBOS, 70 search queries given by a head nurse were tested. DBOS was compared with CS, TF-IDF, and Facebook Wit.ai respectively. The experiment results show that DBOS outperforms the abovementioned methods and can achieve a 92.8% accuracy in identifying user intent.

ARBIN: Augmented Reality Based Indoor Navigation System.

Due to the popularity of indoor positioning technology, indoor navigation applications have been deployed in large buildings, such as hospitals, airports, and train stations, to guide visitors to their destinations. A commonly-used user interface, shown on smartphones, is a 2D floor map with a route to the destination. The navigation instructions, such as turn left, turn right, and go straight, pop up on the screen when users come to an intersection. However, owing to the restrictions of a 2D navigation map, users may face mental pressure and get confused while they are making a connection between the real environment and the 2D navigation map before moving forward. For this reason, we developed ARBIN, an augmented reality-based navigation system, which posts navigation instructions on the screen of real-world environments for ease of use. Thus, there is no need for users to make a connection between the navigation instructions and the real-world environment. In order to evaluate the applicability of ARBIN, a series of experiments were conducted in the outpatient area of the National Taiwan University Hospital YunLin Branch, which is nearly 1800 m2, with 35 destinations and points of interests, such as a cardiovascular clinic, x-ray examination room, pharmacy, and so on. Four different types of smartphone were adopted for evaluation. Our results show that ARBIN can achieve 3 to 5 m accuracy, and provide users with correct instructions on their way to the destinations. ARBIN proved to be a practical solution for indoor navigation, especially for large buildings.

Active disaster response system for a smart building.

Disaster warning and surveillance systems have been widely applied to help the public be aware of an emergency. However, existing warning systems are unable to cooperate with household appliances or embedded controllers; that is, they cannot provide enough time for preparedness and evacuation, especially for disasters like earthquakes. In addition, the existing warning and surveillance systems are not responsible for collecting sufficient information inside a building for relief workers to conduct a proper rescue action after a disaster happens. In this paper, we describe the design and implementation of a proof of concept prototype, named the active disaster response system (ADRS), which automatically performs emergency tasks when an earthquake happens. ADRS can interpret Common Alerting Protocol (CAP) messages, published by an official agency, and actuate embedded controllers to perform emergency tasks to respond to the alerts. Examples of emergency tasks include opening doors and windows and cutting off power lines and gas valves. In addition, ADRS can maintain a temporary network by utilizing the embedded controllers; hence, victims trapped inside a building are still able to post emergency messages if the original network is disconnected. We conducted a field trial to evaluate the effectiveness of ADRS after an earthquake happened. Our results show that compared to manually operating emergency tasks, ADRS can reduce the operation time by up to 15 s, which is long enough for people to get under sturdy furniture, or to evacuate from the third floor to the first floor, or to run more than 100 m.

An indoor location-based hospital Porter management system and trace analysis.

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.