Smart healthcare and quality of service in IoT using grey filter convolutional based cyber physical system. (August 2020)

• Record Type: Journal Article
• Authors: Patan, Rizwan; Pradeep Ghantasala, G S; Sekaran, Ramesh; Gupta, Deepak; Ramachandran, Manikandan
• Is Part Of: Sustainable cities and society. Volume 59(2020)
• Publication Date: 2020-08
• Subjects: Internet of Things (IoT) -- Deep Neural Networks -- Grey Filter -- Bayesian -- Convolution Neural Network; Sustainable urban development -- Periodicals; Sustainable buildings -- Periodicals; Urban ecology (Sociology) -- Periodicals; 307.76
• DOI: 10.1016/j.scs.2020.102141
• Languages: English
• ISSNs: 2210-6707

Abstract

Highlights: To minimize the communication overhead and response time, the proposed Grey Filter Bayesian Convolution Neural Network method is introduced. The proposed method utilizes the grey filter for obtaining computationally efficient features with the help of AGO. With pre-processed features, the Bayesian Logistic Sigmoid Activation function is used to either record/not record the sensing modalities based on the sampling rate measurement. In this way, minimum overhead and response time is achieved in the medical data analysis. To enhance the accuracy rate of medical data analysis, the Volume Aligned Softmax CNN technique is used in the proposed GFB-CNN method to classify the healthy and unhealthy heart signals by measuring max pooling function. Abstract: The relationship between technology and healthcare society rises due to the intelligent Internet of Things (IoT) with endless networking capabilities for medical data analysis. Deep Neural Networks and the swift public embracement of medical wearable have been productively metamorphosed in the recent few years. Deep Neural Network-powered IoT allowed innovative developments for medical society and distinctive probabilities to the medical data analysis in the healthcare industry (Yin, Yang, Zhang, & Oki, 2016 ). Despite this progress, several issues still required to be handled while concerning the quality of service. The key to flourishing in the shift from client-oriented to patient-oriented medical data analysis for healthcare society is applying deep networks to provide a high level of quality in key attributes such as end-to-end response time, overhead and accuracy. In this paper, we propose a holistic Deep Neural Network-driven IoT smart health care method called, Grey Filter Bayesian Convolution Neural Network (GFB-CNN) based on real-time analytics. In this paper, we propose a holistic AI-driven IoT eHealth architecture based on the Grey Filter Bayesian Convolution Neural Network in which the key quality of service parameters like, time and overhead is reduced with a higher rate of accuracy. The feasibility of the method is investigated using a comprehensive Mobile HEALTH (MHEALTH) dataset. This illustrative example discusses and addresses all important aspects of the proposed method from design suggestions such as corresponding overheads, time, accuracy compared to state-of-the-art methods. By simulation, the performance of GFB-CNN method is compared to the state-of-the-art methods with various synthetically generated scenarios. Results show that with minimal time and overhead incurred for sensing and data collection, our method accurately evaluates medical data analysis for heart signals by efficient differentiation between healthy and unhealthy heart signals.