An efficient monitoring of eclamptic seizures in wireless sensors networks. (May 2019)

• Record Type: Journal Article
• Authors: Haider, Daniyal; Ren, Aifeng; Fan, Dou; Zhao, Nan; Yang, Xiaodong; Shah, Syed Aziz; Hu, Fangming; Abbasi, Qammer H.
• Is Part Of: Computers & electrical engineering. Volume 75(2019)
• Page Start: 16
• Page End: 30
• Publication Date: 2019-05
• Subjects: C-band -- Wireless channel information (WCI) -- Internet of thing (IoT) -- Support vector machine (SVM) -- K-nearest neighbor (KNN) -- Random forest (RF) and K-mean; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2019.02.011
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: This paper presents the application of wireless sensing at C-band operating at 4.8 GHz technology (a potential Chinese 5G band). A wireless transceiver is used in the indoor environment to monitor different body motions of a woman experiencing an eclamptic seizure. The body movement shows unique wireless data which carries the wireless channel information. The results indicate that using higher features increases the accuracy from 3% to 4% for classifying data from different body motions. All of the four classifiers are compared by using six performance metrics such as accuracy, recall, precession, specificity, F-measure and Kappa. The values from these metrics indicate the better performance of SVM as compared to other three classifiers, the results indicate that the eclamptic seizures are easily differentiated from other body movements by applying the aforementioned classifiers.