Tianao Cao, Jinwei Sun, Huanhuan Guo, Jiaze Tang, Qisong Wang, Dan Liu
{"title":"Design of wearable and portable physiological parameter monitoring system for attentiveness evaluation","authors":"Tianao Cao, Jinwei Sun, Huanhuan Guo, Jiaze Tang, Qisong Wang, Dan Liu","doi":"10.1109/ICAICA52286.2021.9498201","DOIUrl":null,"url":null,"abstract":"With the rapid development of information technology, the \"human-machine collaboration\" smart education model is emerging increasingly. Aiming at addressing the problems of poor portability of the devices, single sort of physiological signals, and excessively subjective evaluation of attentiveness in current monitoring systems, this paper designed an attentiveness evaluation system based on multiple physiological information. First of all, in view of the large volume of traditional acquisition devices, we designed the miniaturized, wearable multi-physiological signal acquisition node. Based on a single-channel EEG signal analog acquisition front-end, 9-axis acceleration acquisition chip and blood oxygen (SpO2) acquisition module, we acquired the EEG, posture and SpO2 signals synchronously. Secondly, in the light of the bandwidth and power consumption of information transmission in the wireless body area network, we designed a data transmission networking based on wireless radio frequency Wi-Fi, achieving high-speed signal communication with high accuracy. The attentiveness induction experiment was designed, and an objective evaluation index of attentiveness based on reaction time and accuracy rate for regression analysis and fitting was put forward. After preprocessing the raw data, a variety of features were extracted, and the performance of the attentiveness evaluation was verified. Results show that the accuracy rate of the attentiveness is up to 77.1%, which realizes the effective evaluation of attentiveness.","PeriodicalId":121979,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICAICA52286.2021.9498201","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
With the rapid development of information technology, the "human-machine collaboration" smart education model is emerging increasingly. Aiming at addressing the problems of poor portability of the devices, single sort of physiological signals, and excessively subjective evaluation of attentiveness in current monitoring systems, this paper designed an attentiveness evaluation system based on multiple physiological information. First of all, in view of the large volume of traditional acquisition devices, we designed the miniaturized, wearable multi-physiological signal acquisition node. Based on a single-channel EEG signal analog acquisition front-end, 9-axis acceleration acquisition chip and blood oxygen (SpO2) acquisition module, we acquired the EEG, posture and SpO2 signals synchronously. Secondly, in the light of the bandwidth and power consumption of information transmission in the wireless body area network, we designed a data transmission networking based on wireless radio frequency Wi-Fi, achieving high-speed signal communication with high accuracy. The attentiveness induction experiment was designed, and an objective evaluation index of attentiveness based on reaction time and accuracy rate for regression analysis and fitting was put forward. After preprocessing the raw data, a variety of features were extracted, and the performance of the attentiveness evaluation was verified. Results show that the accuracy rate of the attentiveness is up to 77.1%, which realizes the effective evaluation of attentiveness.