Wireless Body Area Network Control Policies for Energy-Efficient Health Monitoring
Wireless body area networks (WBANs) have strong potential in the field of health monitoring. However, the energy consumption required for accurate monitoring determines the time between battery charges of the wearable sensors, which is a key performance factor (and can be critical in the case of imp...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/12/4245 |
| _version_ | 1797529330053545984 |
|---|---|
| author | Yair Bar David Tal Geller Ilai Bistritz Irad Ben-Gal Nicholas Bambos Evgeni Khmelnitsky |
| author_facet | Yair Bar David Tal Geller Ilai Bistritz Irad Ben-Gal Nicholas Bambos Evgeni Khmelnitsky |
| author_sort | Yair Bar David |
| collection | DOAJ |
| description | Wireless body area networks (WBANs) have strong potential in the field of health monitoring. However, the energy consumption required for accurate monitoring determines the time between battery charges of the wearable sensors, which is a key performance factor (and can be critical in the case of implantable devices). In this paper, we study the inherent trade-off between the power consumption of the sensors and the probability of misclassifying a patient’s health state. We formulate this trade-off as a dynamic problem, in which at each step, we can choose to activate a subset of sensors that provide noisy measurements of the patient’s health state. We assume that the (unknown) health state follows a Markov chain, so our problem is formulated as a partially observable Markov decision problem (POMDP). We show that all the past measurements can be summarized as a belief state on the true health state of the patient, which allows tackling the POMDP problem as an MDP on the belief state. Then, we empirically study the performance of a greedy one-step look-ahead policy compared to the optimal policy obtained by solving the dynamic program. For that purpose, we use an open-source Continuous Glucose Monitoring (CGM) dataset of 232 patients over six months and extract the transition matrix and sensor accuracies from the data. We find that the greedy policy saves ≈50% of the energy costs while reducing the misclassification costs by less than 2% compared to the most accurate policy possible that always activates all sensors. Our sensitivity analysis reveals that the greedy policy remains nearly optimal across different cost parameters and a varying number of sensors. The results also have practical importance, because while the optimal policy is too complicated, a greedy one-step look-ahead policy can be easily implemented in WBAN systems. |
| first_indexed | 2024-03-10T10:12:17Z |
| format | Article |
| id | doaj.art-03ab19e8b5654c13b625884011f8273a |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T10:12:17Z |
| publishDate | 2021-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-03ab19e8b5654c13b625884011f8273a2023-11-22T01:04:40ZengMDPI AGSensors1424-82202021-06-012112424510.3390/s21124245Wireless Body Area Network Control Policies for Energy-Efficient Health MonitoringYair Bar David0Tal Geller1Ilai Bistritz2Irad Ben-Gal3Nicholas Bambos4Evgeni Khmelnitsky5Department of Industrial Engineering, Tel Aviv University, Tel-Aviv 69978, IsraelDepartment of Industrial Engineering, Tel Aviv University, Tel-Aviv 69978, IsraelDepartment of Electrical Engineering, Stanford University, Stanford, CA 94305, USADepartment of Industrial Engineering, Tel Aviv University, Tel-Aviv 69978, IsraelDepartment of Electrical Engineering, Stanford University, Stanford, CA 94305, USADepartment of Industrial Engineering, Tel Aviv University, Tel-Aviv 69978, IsraelWireless body area networks (WBANs) have strong potential in the field of health monitoring. However, the energy consumption required for accurate monitoring determines the time between battery charges of the wearable sensors, which is a key performance factor (and can be critical in the case of implantable devices). In this paper, we study the inherent trade-off between the power consumption of the sensors and the probability of misclassifying a patient’s health state. We formulate this trade-off as a dynamic problem, in which at each step, we can choose to activate a subset of sensors that provide noisy measurements of the patient’s health state. We assume that the (unknown) health state follows a Markov chain, so our problem is formulated as a partially observable Markov decision problem (POMDP). We show that all the past measurements can be summarized as a belief state on the true health state of the patient, which allows tackling the POMDP problem as an MDP on the belief state. Then, we empirically study the performance of a greedy one-step look-ahead policy compared to the optimal policy obtained by solving the dynamic program. For that purpose, we use an open-source Continuous Glucose Monitoring (CGM) dataset of 232 patients over six months and extract the transition matrix and sensor accuracies from the data. We find that the greedy policy saves ≈50% of the energy costs while reducing the misclassification costs by less than 2% compared to the most accurate policy possible that always activates all sensors. Our sensitivity analysis reveals that the greedy policy remains nearly optimal across different cost parameters and a varying number of sensors. The results also have practical importance, because while the optimal policy is too complicated, a greedy one-step look-ahead policy can be easily implemented in WBAN systems.https://www.mdpi.com/1424-8220/21/12/4245wireless body area networkscontrolled sensingenergy efficiencypartially observable Markov decision processes (POMDPs)remote health monitoring |
| spellingShingle | Yair Bar David Tal Geller Ilai Bistritz Irad Ben-Gal Nicholas Bambos Evgeni Khmelnitsky Wireless Body Area Network Control Policies for Energy-Efficient Health Monitoring Sensors wireless body area networks controlled sensing energy efficiency partially observable Markov decision processes (POMDPs) remote health monitoring |
| title | Wireless Body Area Network Control Policies for Energy-Efficient Health Monitoring |
| title_full | Wireless Body Area Network Control Policies for Energy-Efficient Health Monitoring |
| title_fullStr | Wireless Body Area Network Control Policies for Energy-Efficient Health Monitoring |
| title_full_unstemmed | Wireless Body Area Network Control Policies for Energy-Efficient Health Monitoring |
| title_short | Wireless Body Area Network Control Policies for Energy-Efficient Health Monitoring |
| title_sort | wireless body area network control policies for energy efficient health monitoring |
| topic | wireless body area networks controlled sensing energy efficiency partially observable Markov decision processes (POMDPs) remote health monitoring |
| url | https://www.mdpi.com/1424-8220/21/12/4245 |
| work_keys_str_mv | AT yairbardavid wirelessbodyareanetworkcontrolpoliciesforenergyefficienthealthmonitoring AT talgeller wirelessbodyareanetworkcontrolpoliciesforenergyefficienthealthmonitoring AT ilaibistritz wirelessbodyareanetworkcontrolpoliciesforenergyefficienthealthmonitoring AT iradbengal wirelessbodyareanetworkcontrolpoliciesforenergyefficienthealthmonitoring AT nicholasbambos wirelessbodyareanetworkcontrolpoliciesforenergyefficienthealthmonitoring AT evgenikhmelnitsky wirelessbodyareanetworkcontrolpoliciesforenergyefficienthealthmonitoring |