An efficient priority‐based convolutional auto‐encoder approach for electrocardiogram signal compression in Internet of Things based healthcare system

Abstract

Due to advancements in healthcare monitoring systems, the Internet of Things concepts are proficiently utilized in the medical field to detect and diagnose the physical health problems. The compression of more substantial medical information is a significant issue that requires ample data storage space and takes longer transmission time. Though several compression algorithms are actualized in past cases, there is an absence of an upgraded approach to achieve improved signal compression without influencing signal quality. Hence a proficient signal compression algorithm is proposed in our work to provide an enhanced electrocardiogram (ECG) signal compression without any data loss and to acquire increased compression ratio (CR) and zero construction error. In this proposed approach, the input ECG signal dataset from the MIT‐BIH arrhythmia database gets influenced by noise because of the electrical measuring gadget. Hence, preprocessing is done by the proposed multi‐scoop notch filter (MSNF) to denoise this signal by removing the specified noise frequency range of around (1‐50) Hz. This proposed MSNF is designed with adaptiveness that has achieved the enhanced denoising by adjusting the notch frequency. In addition, to extricate the sophisticated ECG signal features, Fast Fourier Transform is being utilized, and that performs and decomposes the signal elegantly and obtains characteristics of the signal in the frequency domain. After feature extraction, optimal signal compression is performed by our proposed priority‐based convolutional auto‐encoder (PCAE) that provides better compression with almost zero reconstruction error by encoding the signals into lower‐dimensional vectors in convolutional layers which are again reconstructed using a decoding approach. The experimental results are then assessed using the performance metrics that include signal to noise ratio (SNR), CR, and percentage root‐mean‐square difference (PRD). The attained results are 1.83% as average PRD value, average SNR is about 33 dB, and average CR is about 35.2% whereas the traditional CAE approach has average values of 2.05% PRD, 23.45 dB SNR, and 32.2% CR.

Federated Learning for Privacy-Preserved Medical Internet of Things

“…Examples include using wearable medical devices to predict emergency medical events, such as the risk of a heart attack. Wearable medical devices and other nonmedical IoT devices, such as self-driving cars, may have multiple sensors that allow them to acquire, aggregate, react, and adapt to incoming data in real time [33][34][35][36]. For example, when predicting the risk of cardiovascular disease, medical equipment may require the latest models of various pathological information to safely operate and predict risks in real time, and building aggregate models in these scenarios may fail due to the privacy of highly sensitive patient medical data concerns and limited connectivity of devices.…”

“…On the other hand, with the more effective expansion of IoT networks and the increasing privacy issues in typical IoT environments over a long period of time, typical AI technologies that rely on collecting and accumulating all data in one place for further analysis may become endanger the privacy of aggregated data [16][17][18][19][20][21][22]. In this case, this kind of FL manifests itself as a collaborative and distributed AI method [22][23][24][25][26][27][28] that allows training of decentralized IoT devices without data sharing [28][29][30], thereby protecting data privacy [8,[30][31][32][33][34][35].…”

Internet of Things for Managing Global Pandemics: Lessons from COVID-19 Pandemic

“…In order to increase the performance, communication latency, security and quality of service, the IoT in healthcare would incorporate with innovative and intelligent enabling technologies like AI, VR, Blockchain, Fog, Edge computing and so on, which are are only a few of the enabling technologies that will further fuel and expand the usage of IoT in healthcare that could use to subside the strain on healthcare during pandemics [3], [5]- [10].  Rise of AI based IoT solutions AI-based, machine-learning, and deep-learning technologies are increasingly being employed in the pharmaceutical business in the development of effective medications and clinical trials [13], [39]. Furthermore, by combining satellite and geographical data, these AI-based technologies will be utilized to track and predict epidemics around the world [3].…”

An Internet‐of‐Disease System for COVID‐19 Testing Using Saliva by an AI‐Controlled Microfluidic ELISA Device

“…The name IoD has been introduced as its core concept is developing a comprehensive system for the surveillance of infectious disease transmission rather than conventional IoT‐based platforms used for remote health monitoring. [ 37 , 38 , 39 , 40 ]…”