A Framework for Maternal Physical Activities and Health Monitoring Using Wearable Sensors

Abstract

We propose a physical activity recognition and monitoring framework based on wearable sensors during maternity. A physical activity can either create or prevent health issues during a given stage of pregnancy depending on its intensity. Thus, it becomes very important to provide continuous feedback by recognizing a physical activity and its intensity. However, such continuous monitoring is very challenging during the whole period of maternity. In addition, maintaining a record of each physical activity, and the time for which it was performed, is also a non-trivial task. We aim at such problems by first recognizing a physical activity via the data of wearable sensors that are put on various parts of body. We avoid the use of smartphones for such task due to the inconvenience caused by wearing it for activities such as “eating”. In our proposed framework, a module worn on body consists of three sensors: a 3-axis accelerometer, 3-axis gyroscope, and temperature sensor. The time-series data from these sensors are sent to a Raspberry-PI via Bluetooth Low Energy (BLE). Various statistical measures (features) of this data are then calculated and represented in features vectors. These feature vectors are then used to train a supervised machine learning algorithm called classifier for the recognition of physical activity from the sensors data. Based on such recognition, the proposed framework sends a message to the care-taker in case of unfavorable situation. We evaluated a number of well-known classifiers on various features developed from overlapped and non-overlapped window size of time-series data. Our novel dataset consists of 10 physical activities performed by 61 subjects at various stages of maternity. On the current dataset, we achieve the highest recognition rate of 89% which is encouraging for a monitoring and feedback system.

Motion Tracking of Daily Living and Physical Activities in Health Care: Systematic Review From Designers’ Perspective

“…The findings ( Figure 2 ) revealed that 54 articles used motion tracking data in health care and physical wellness applications, of which 42 (78%) articles used motion-tracking sensors [ 75 - 81 , 84 - 86 , 88 - 97 , 101 , 103 - 116 , 119 , 121 - 123 , 125 , 126 ]. Overall, 70% (38/54) of the articles used AI technology combined with motion tracking data [ 75 , 77 , 79 , 82 - 85 , 87 , 89 - 91 , 93 , 94 , 97 , 99 - 101 , 103 , 105 , 106 , 108 , 109 , 111 - 113 , 117 - 128 ]. The role of AI mainly functions for data classification, monitoring, and visualization among the included studies.…”

Wearable devices for Health Remote Monitor System

“…1 Commercial grown of the Wearable Technology in the health care sector between 2015-2021 by [8] 2 DSR Methodology by [21] 3 Remote health monitoring system architecture proposed by [9] 4 Structure of body sensor nodes and the communication pathway by [13] 5 Design of an intelligent medical monitoring system by [13] 6 Framework Architecture by [15] 7 System Architecture by [17] 8 Examples of wearable devices used in health and cardiovascular disease by [45] 9 System Architecture and Structure 10 Hardware : Equipment used in this System 11 Data transfer/Message Protocols by [61] 12 MQTT Publish/Subscribe Model by [65] 13 Cluster Overview 14 Inserting times by [70] 15 Updating times by [70] 16 Deleting times by [70] 17 Command to run the program 18 Publish/Subscribe Methods 19 Average Velocity when walking and/or running by [74] 20 Speed distributions at different prescribed average speeds by [74]…”

“…In more detail, a Python script with open-source code was used to establish communication between the shimmer sensors and the raspberry pi, allowing all sensor data to be sent to and stored on the raspberry pi local database . Like this study, there are other studies, such as [13] [14] [15] [16] [17], that employed different types of devices and approaches to achieve the similar goal of developing a healthcare remote system.…”

“…F. Ullah, A. Iqbal, et al [15] had a similar concept to [14], but instead of elders and disabled people, the authors built a framework for physical activities and health monitoring for pregnant women. Their framework consisted of only three sensors, a three-axis accelerometer, a three-axis gyroscope, and a temperature sensor, as well as a Raspberry Pi, same to [9], and a mobile phone, Figure 6.…”

Preterm Birth Risk Stratification through Longitudinal Heart Rate and HRV Monitoring in Daily Life

“…The continuous monitoring of pregnant women using wearable devices allows for the exploration of various pregnancy issues, such as stress 28,41 , hypertension 42 , mental problems 43 , and obesity 44 . Moreover, it enables the assessments of maternal sleep 45 , physical activity 46,47 , and fetal parameters, including heart activity [48][49][50] and movement 51,52 .…”