A Device-Independent Efficient Actigraphy Signal-Encoding System for Applications in Monitoring Daily Human Activities and Health

Abstract

Actigraphs for personalized health and fitness monitoring is a trending niche market and fit aptly in the Internet of Medical Things (IoMT) paradigm. Conventionally, actigraphy is acquired and digitized using standard low pass filtering and quantization techniques. High sampling frequencies and quantization resolution of various actigraphs can lead to memory leakage and unwanted battery usage. Our systematic investigation on different types of actigraphy signals yields that lower levels of quantization are sufficient for acquiring and storing vital movement information while ensuring an increase in SNR, higher space savings, and in faster time. The objective of this study is to propose a low-level signal encoding method which could improve data acquisition and storage in actigraphs, as well as enhance signal clarity for pattern classification. To further verify this study, we have used a machine learning approach which suggests that signal encoding also improves pattern recognition accuracy. Our experiments indicate that signal encoding at the source results in an increase in SNR (signal-to-noise ratio) by at least 50–90%, coupled with a bit rate reduction by 50–80%, and an overall space savings in the range of 68–92%, depending on the type of actigraph and application used in our study. Consistent improvements by lowering the quantization factor also indicates that a 3-bit encoding of actigraphy data retains most prominent movement information, and also results in an increase of the pattern recognition accuracy by at least 10%.

Actigraphy Signal Analysis System for Sleep and Wake Studies

“…Figure 1.2 illustrates the overall structure of an IoT model. Figure 1.2: IoT -The Big Picture [10] In order to understand the IoT framework, two main aspects of this internet-connectivity model along with the functioning of its layered have been covered. Figure 1.3 depicts two aspects of the IoT architecture, namely -hardware and software.…”

“…Figure 1.5: User data handling in IoT [9] It is evident that for a seamless functioning of the IoT framework, its three components, namelyhardware, software and supporting architecture layers must coordinate and function in synchronization with each other. This being said, current niche markets retailing smart devices for IoT environments pose one or many of the following challenges in order to ensure the robustness and integrity of a connected environment [10]:…”

Data Analytics and Applications of the Wearable Sensors in Healthcare: An Overview

“…Because of the versatility of the QCA approach, the authors suggested that it can provide useful analytical tools for data in multi-modal monitoring. By explaining the role of actigraphs in personalized health, fitness monitoring and Internet of Medical Things (IoMT) paradigm, Athavale [26] presented a study utilizing wearable devices to capture and analyze physiological data at home-based health monitoring in an IoMT environment, and proposed a low level encoding scheme to improve actigraphy analysis. In order to ensure that there was no loss of information in encoding process, ML approach was used for the study validation.…”

Nanosystems, Edge Computing, and the Next Generation Computing Systems

“…Similarly, traffic lights augmented with hyperspectral imaging and chem-bio sensors can be made locally smart when combined with weather sensors and the unique local population and infrastructure signatures. More concrete EC applications include scalable framework for early fire detection [99], disaster management services [100], accelerometers for structural health monitoring [101], micro-seismic monitoring platform for hydraulic fracture [102], a framework for searchable personal health records [75,76,103], smart health monitoring [76,104] and healthcare framework [105], improved multimedia traffic [106], a field-programmable gate array (FPGA)-based system for cyber-physical systems [107] and for space applications [108], biomedical wearables for IoMT [73,76,109], air pollution monitoring systems [110], precision agriculture [111,112], diabetes [74] and ECG [109] devices, and marine sensor networks [113].…”