Résumé
With the advent of Bluetooth Low Energy (BLE)-enabled smartphones, there has been considerable interest in investigating BLE-based distancing/positioning methods (e.g., for social distancing applications). In this paper, we present a novel hybrid learning method to support Mobile Ad-hoc Distancing (MAD) / Positioning (MAP) using BLE-enabled smartphones. Compared to traditional BLE-based distancing/positioning methods, the hybrid learning method provides the following unique features and contributions. First, it combines unsupervised learning, supervised learning and genetic algorithms for enhancing distance estimation accuracy. Second, unsupervised learning is employed to identify three pseudo channels/clusters for enhanced RSSI data processing. Third, its underlying mechanism is based on a new pattern-inspired approach to enhance the machine learning process. Fourth, it provides a flagging mechanism to alert users if a predicted distance is accurate or not. Fifth, it provides a model aggregation scheme with an innovative two-dimensional genetic algorithm to aggregate the distance estimation results of different machine learning models. As an application of hybrid learning for distance estimation, we also present a new MAP scenario with an iterative algorithm to estimate mobile positions in an ad-hoc environment. Experimental results show the effectiveness of the hybrid learning method. In particular, hybrid learning without flagging and with flagging outperform the baseline by 57 and 65 percent respectively in terms of mean absolute error. By means of model aggregation, a further 4 percent improvement can be realized. The hybrid learning approach can also be applied to previous work to enhance distance estimation accuracy and provide valuable insights for further research. IEEE
Résumé
Disease surveillance is essential for the control of flu and respiratory infectious diseases including the novel coronavirus disease (COVID-19). Indoor air quality monitoring has been shown effective in understanding the effectiveness of airflow and circulation indoors to reduce the risk of infectious diseases. In this project, we developed low-cost indoor air quality monitoring devices and systems to tackle the disease surveillance problem. The monitoring device consists of a set of air quality sensors. By strategic deployment and real-time data analysis, the system is able to yield insightful air circulation information indoors. The real-time data analysis is performed on air quality for the indoor ventilation using Long Short-Term Memory (LSTM) on sensed data. A series of user-friendly visualization interfaces and chatbot applications are designed to interact with users and ensure the successful delivery of infection control information. Finally, we work closely with the Taiwan Centers for Disease Control (CDC) and conduct field experiments in 15 locations including hospitals, long-term care centers, schools with total of 144 IAQ devices. © 2020 ACM.