Pub Date : 2020-10-25DOI: 10.1109/SENSORS47125.2020.9278639
R. Cheng, Jianyong Zhang, B. Zhou
The cross-correlation method plays a very important role in velocity measurement of pneumatically conveyed particles. There are still gaps in understanding of the mechanism and significance of sensor’s spatial sensitivity on this method, which is the focus of this paper. Quantitative evaluations were conducted on a 330.2mm diameter electrostatic sensor under different velocity profiles based on the spatial sensitivity obtained through experiments. From this investigation, it is apparent that the difference between the theoretical velocity and measured velocity can be significant.
{"title":"Effect of Spatial Sensitivity of Sensor on Particulate Velocity Measurement Derived Based on Cross Correlation Techniques","authors":"R. Cheng, Jianyong Zhang, B. Zhou","doi":"10.1109/SENSORS47125.2020.9278639","DOIUrl":"https://doi.org/10.1109/SENSORS47125.2020.9278639","url":null,"abstract":"The cross-correlation method plays a very important role in velocity measurement of pneumatically conveyed particles. There are still gaps in understanding of the mechanism and significance of sensor’s spatial sensitivity on this method, which is the focus of this paper. Quantitative evaluations were conducted on a 330.2mm diameter electrostatic sensor under different velocity profiles based on the spatial sensitivity obtained through experiments. From this investigation, it is apparent that the difference between the theoretical velocity and measured velocity can be significant.","PeriodicalId":338240,"journal":{"name":"2020 IEEE Sensors","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121095845","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-25DOI: 10.1109/SENSORS47125.2020.9278805
M. Imtiaz, D. Hossain, V. Senyurek, Prajakta Belsare, E. Sazonov
Recently, body-worn sensor systems have extensively been studied to assess the manifestations of cigarette smoking in the free-living. This paper provides a detailed description of a camera-based wearable sensor system, PACT CAM, that can capture the most relevant images of cigarette smoking at every second from the eye level. Along with a 5MP camera, PACT CAM includes inertial sensors to detect the wearer’s motion, a micro-SD card capable of storing ~1 million images, a rechargeable LiPo battery to support the image capture for ~32 hours with a single charge, etc. This circuitry was enclosed within a plastic enclosure with a provision to facilitate attachment to the eye-glass temple of the wearer. To support multi-day data collection, imaging was configured to pause while the sensor system was stationary or put to charge, and resume while out of inactivity or removed from the charger. During this inactivity state, the system was configured to enter into the low power sleep mode with ~0.05mA power consumption. The EXIF header of the captured images contained detailed information on the image capture timestamp, inactivity time, the wearer’s walking steps at the moment of image capture, etc. This EXIF information can be accessed from a computer application without requiring the manual image review. The smoking context, as captured objectively by PACT CAM for multiple days, is critical to infer the overall smoking behavior of a person and select proper cessation intervention methods. The performance of PACT CAM was also validated involving two volunteer smokers wearing it for multiple days.
{"title":"PACT CAM: Wearable Sensor System to Capture the Details of Cigarette Smoking in Free-Living","authors":"M. Imtiaz, D. Hossain, V. Senyurek, Prajakta Belsare, E. Sazonov","doi":"10.1109/SENSORS47125.2020.9278805","DOIUrl":"https://doi.org/10.1109/SENSORS47125.2020.9278805","url":null,"abstract":"Recently, body-worn sensor systems have extensively been studied to assess the manifestations of cigarette smoking in the free-living. This paper provides a detailed description of a camera-based wearable sensor system, PACT CAM, that can capture the most relevant images of cigarette smoking at every second from the eye level. Along with a 5MP camera, PACT CAM includes inertial sensors to detect the wearer’s motion, a micro-SD card capable of storing ~1 million images, a rechargeable LiPo battery to support the image capture for ~32 hours with a single charge, etc. This circuitry was enclosed within a plastic enclosure with a provision to facilitate attachment to the eye-glass temple of the wearer. To support multi-day data collection, imaging was configured to pause while the sensor system was stationary or put to charge, and resume while out of inactivity or removed from the charger. During this inactivity state, the system was configured to enter into the low power sleep mode with ~0.05mA power consumption. The EXIF header of the captured images contained detailed information on the image capture timestamp, inactivity time, the wearer’s walking steps at the moment of image capture, etc. This EXIF information can be accessed from a computer application without requiring the manual image review. The smoking context, as captured objectively by PACT CAM for multiple days, is critical to infer the overall smoking behavior of a person and select proper cessation intervention methods. The performance of PACT CAM was also validated involving two volunteer smokers wearing it for multiple days.","PeriodicalId":338240,"journal":{"name":"2020 IEEE Sensors","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121108629","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Since the atmosphere has been highly polluted over the recent years, more and more people start to take this subject seriously. The toxic substances adhering to the particulate particles can enter the human bodies as they breathe, and thus cause the body health damage, especially for the particulate particles with a diameter less than 2.5um (PM2.5). Many gas sensor systems are therefore proposed to monitor air quality recently. Although these existing PM2.5 sensor systems can be deployed and acquire PM data correctly, they lack of the portability due to usages of the external power supply or an external battery. Currently, there are no PM2.5 sensor systems that can support the interfaces of micro-USB and Apple lightning with mobile phone since the PM2.5 sensor system usually consumes more power than that the mobile phone can provide. In this paper, we propose a PM2.5 sensor system named PaS-PM2.5 that can support the micro-USB and lightning interfaces for the mobile phone. The PaS-PM2.5 adopts the energy storage hardware mechanism and a low power firmware technique to enable the use of mobile phone power, while a sensor calibration method can acquire the accurate PM2.5 concentration. With the low power support of hardware and firmware mechanism, the sensor system can achieve 32% reduction of power consumption and thus meet the limitation of the mobile phone power supply. Furthermore, the PM2.5 mass concentration of our proposed low power sensor system has 98.04% of R-squared (R2) as compared to the sensor system without the low power mechanism.
{"title":"A Portable Power-efficient PM2.5 Sensor System","authors":"Chih-Chyau Yang, Yi-Jie Hsieh, Wei-Lin Lai, Chun-Yu Chen, Jin-Ju Chue, Chien‐Ming Wu, Chun-Ming Huang","doi":"10.1109/SENSORS47125.2020.9278763","DOIUrl":"https://doi.org/10.1109/SENSORS47125.2020.9278763","url":null,"abstract":"Since the atmosphere has been highly polluted over the recent years, more and more people start to take this subject seriously. The toxic substances adhering to the particulate particles can enter the human bodies as they breathe, and thus cause the body health damage, especially for the particulate particles with a diameter less than 2.5um (PM2.5). Many gas sensor systems are therefore proposed to monitor air quality recently. Although these existing PM2.5 sensor systems can be deployed and acquire PM data correctly, they lack of the portability due to usages of the external power supply or an external battery. Currently, there are no PM2.5 sensor systems that can support the interfaces of micro-USB and Apple lightning with mobile phone since the PM2.5 sensor system usually consumes more power than that the mobile phone can provide. In this paper, we propose a PM2.5 sensor system named PaS-PM2.5 that can support the micro-USB and lightning interfaces for the mobile phone. The PaS-PM2.5 adopts the energy storage hardware mechanism and a low power firmware technique to enable the use of mobile phone power, while a sensor calibration method can acquire the accurate PM2.5 concentration. With the low power support of hardware and firmware mechanism, the sensor system can achieve 32% reduction of power consumption and thus meet the limitation of the mobile phone power supply. Furthermore, the PM2.5 mass concentration of our proposed low power sensor system has 98.04% of R-squared (R2) as compared to the sensor system without the low power mechanism.","PeriodicalId":338240,"journal":{"name":"2020 IEEE Sensors","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125245641","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-25DOI: 10.1109/SENSORS47125.2020.9278936
G. Mussi, P. Frigerio, G. Langfelder, G. Gattere
The purpose of this paper is to assess the feasibility of MEMS-based real-time clocks (RTCs) using conventional polysilicon, without correcting the temperature coefficient of frequency (TCf) through dedicated technological steps. The paper first shows how such a large TCf (-30 ppm/K) is not an issue in terms of maximum frequency correction to achieve with a dedicated electronics: indeed, whatever the TCf, the dominant part of the frequency correction, required to match the 32-kHz RTC target value, is always demanded by the native frequency offset due to etching nonuniformities, and not by temperature changes. This sets the required number of bits of the modulator used to drive a fractional frequency divider that performs the compensation. Instead, requirements in the bit number and refresh rate of the temperature sensor are affected by a large TCf. Nevertheless, the paper shows the possibility to achieve few ppm frequency stability using a 9-bit temperature sensor with a 4-Hz refresh rate. This makes the approach quite competitive against more sophisticated MEMS processes, especially in terms of final cost. Experimental measurements on a MEMS-based resonator coupled to a dedicated integrated circuit are used to support the discussion.
{"title":"MEMS real-time clocks based on epitaxial polysilicon: system-level requirements and experimental characterization","authors":"G. Mussi, P. Frigerio, G. Langfelder, G. Gattere","doi":"10.1109/SENSORS47125.2020.9278936","DOIUrl":"https://doi.org/10.1109/SENSORS47125.2020.9278936","url":null,"abstract":"The purpose of this paper is to assess the feasibility of MEMS-based real-time clocks (RTCs) using conventional polysilicon, without correcting the temperature coefficient of frequency (TCf) through dedicated technological steps. The paper first shows how such a large TCf (-30 ppm/K) is not an issue in terms of maximum frequency correction to achieve with a dedicated electronics: indeed, whatever the TCf, the dominant part of the frequency correction, required to match the 32-kHz RTC target value, is always demanded by the native frequency offset due to etching nonuniformities, and not by temperature changes. This sets the required number of bits of the modulator used to drive a fractional frequency divider that performs the compensation. Instead, requirements in the bit number and refresh rate of the temperature sensor are affected by a large TCf. Nevertheless, the paper shows the possibility to achieve few ppm frequency stability using a 9-bit temperature sensor with a 4-Hz refresh rate. This makes the approach quite competitive against more sophisticated MEMS processes, especially in terms of final cost. Experimental measurements on a MEMS-based resonator coupled to a dedicated integrated circuit are used to support the discussion.","PeriodicalId":338240,"journal":{"name":"2020 IEEE Sensors","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126632867","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-25DOI: 10.1109/SENSORS47125.2020.9278828
Kohei Semasa, F. Sassa, K. Hayashi
LSPR (Localized Surface Plasmon Resonance) based 2D (Two-dimensional) gas sensor system which can measure and identify multi-gases with high spatial resolution have been developed. The gas sensor detects optical changes promoted by the gas on the LSPR substrate with hyperspectral camera. Basically, LSPR gas sensor does not have a molecular selectivity, then the identification of gas species is difficult. To overcome the disadvantage, LSPR substrates based on Au/Ag core-shell structure with spectral gas-discriminating ability through optical interaction were fabricated by spin coating fluorescent dyes. Using the LSPR coupled with fluorescent dyes, this sensor provides rich spectral information about the detecting molecules and can discriminates gas species.
{"title":"2D LSPR gas sensor with Au/Ag core-shell structure coated by fluorescent dyes","authors":"Kohei Semasa, F. Sassa, K. Hayashi","doi":"10.1109/SENSORS47125.2020.9278828","DOIUrl":"https://doi.org/10.1109/SENSORS47125.2020.9278828","url":null,"abstract":"LSPR (Localized Surface Plasmon Resonance) based 2D (Two-dimensional) gas sensor system which can measure and identify multi-gases with high spatial resolution have been developed. The gas sensor detects optical changes promoted by the gas on the LSPR substrate with hyperspectral camera. Basically, LSPR gas sensor does not have a molecular selectivity, then the identification of gas species is difficult. To overcome the disadvantage, LSPR substrates based on Au/Ag core-shell structure with spectral gas-discriminating ability through optical interaction were fabricated by spin coating fluorescent dyes. Using the LSPR coupled with fluorescent dyes, this sensor provides rich spectral information about the detecting molecules and can discriminates gas species.","PeriodicalId":338240,"journal":{"name":"2020 IEEE Sensors","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122519925","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-25DOI: 10.1109/SENSORS47125.2020.9278908
Kai Wu, Kuo Lu, Qingsong Li, Yi Xu, D. Xiao, Xuezhong Wu
The push-pull driven method for symmetric MEMS resonator is of great efficiency and can suppress the structure asymmetry caused by manufacturing errors. However, the parametric excitation applied to these symmetrical gyroscopes is coincidentally driven by only a single excitation signal to achieve parametric amplification in previous studies, which is inefficient. For theoretical analysis, we find that the valid terms for parametric amplification are eliminated when applied in push-pull driven resonators. Therefore, in order to take advantage of both parametric excitation and push-pull driving, two modified methods are proposed in this paper and have been experimentally demonstrated.
{"title":"Analysis and experiment on the parametrically amplified and push-pull driven resonators","authors":"Kai Wu, Kuo Lu, Qingsong Li, Yi Xu, D. Xiao, Xuezhong Wu","doi":"10.1109/SENSORS47125.2020.9278908","DOIUrl":"https://doi.org/10.1109/SENSORS47125.2020.9278908","url":null,"abstract":"The push-pull driven method for symmetric MEMS resonator is of great efficiency and can suppress the structure asymmetry caused by manufacturing errors. However, the parametric excitation applied to these symmetrical gyroscopes is coincidentally driven by only a single excitation signal to achieve parametric amplification in previous studies, which is inefficient. For theoretical analysis, we find that the valid terms for parametric amplification are eliminated when applied in push-pull driven resonators. Therefore, in order to take advantage of both parametric excitation and push-pull driving, two modified methods are proposed in this paper and have been experimentally demonstrated.","PeriodicalId":338240,"journal":{"name":"2020 IEEE Sensors","volume":"307 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122639226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-25DOI: 10.1109/SENSORS47125.2020.9278831
N. Raja, Krishnan Balasubramanian
This paper reports a novel ultrasonic guided wave-based waveguide sensor for liquid level measurement which is critical for process controls in industries. A thin stainless wire with a varying cross-section (cylinder and rectangular end) is selected as the waveguide sensor in which all three fundamental wavemode L (0,1), T (0,1), and F (1,1) are excited and received by a single shear transducer. We validated the suitability of this waveguide for continuous level measurement experiments in the laboratory conditions. Level measurement experiments were carried out in inviscid fluid (water) and the fluid level is monitored/extracted by tracking the change in time of flight ((δTOF) of the excited torsional wavemode T(0,1) and flexural wavemode F(1,1) in the waveguide that is directly related to the fluid level in the probed media. The presented technique is suitable for enhanced level measurement using two wavemodes simultaneously. The versatility of this technique enables its application for remote measurements in a wide range of applications Keywords: Guided wave, Waveguide, Sensor, Level Measurement
{"title":"Phase Shift Based Level Sensing using two guided Wave Mode T (0, 1) and F(1,1) on a thin Waveguide","authors":"N. Raja, Krishnan Balasubramanian","doi":"10.1109/SENSORS47125.2020.9278831","DOIUrl":"https://doi.org/10.1109/SENSORS47125.2020.9278831","url":null,"abstract":"This paper reports a novel ultrasonic guided wave-based waveguide sensor for liquid level measurement which is critical for process controls in industries. A thin stainless wire with a varying cross-section (cylinder and rectangular end) is selected as the waveguide sensor in which all three fundamental wavemode L (0,1), T (0,1), and F (1,1) are excited and received by a single shear transducer. We validated the suitability of this waveguide for continuous level measurement experiments in the laboratory conditions. Level measurement experiments were carried out in inviscid fluid (water) and the fluid level is monitored/extracted by tracking the change in time of flight ((δTOF) of the excited torsional wavemode T(0,1) and flexural wavemode F(1,1) in the waveguide that is directly related to the fluid level in the probed media. The presented technique is suitable for enhanced level measurement using two wavemodes simultaneously. The versatility of this technique enables its application for remote measurements in a wide range of applications Keywords: Guided wave, Waveguide, Sensor, Level Measurement","PeriodicalId":338240,"journal":{"name":"2020 IEEE Sensors","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128322982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-25DOI: 10.1109/SENSORS47125.2020.9278597
Zhiqiang Feng, Xuefeng He, Junru Li, Shen Li, Z. Shang
Ultra-low power sensors attract increasing attention as the requisite building blocks of long-life wireless sensor nodes. This work developed a proof-of-concept device to evaluate the feasibility of ultra-low power stress sensing by the leakage current of p-n junctions. Experimental results show that the variation of the leakage current of p-n junctions demonstrates excellent linearity and stability with the stress in the range from 0 to 90 MPa. When the reverse bias voltage decreases from 2.5 to 0.5 V, there is almost no deterioration of the stress sensitivity but the maximum power consumption greatly decreases from to 705 pW to 156 pW. By using the published circuit for temperature sensors, the power consumption of the stress/strain sensors based on the detection of the leakage current of p-n junctions may be decreased to lower than 1 nW. Therefore, the piezojunction effect of p-n junctions is an attractive sensing mechanism for ultra-low power stress/strain sensors.
{"title":"Ultra-Low Power Stress Sensing By Leakage Current of P-N Junctions","authors":"Zhiqiang Feng, Xuefeng He, Junru Li, Shen Li, Z. Shang","doi":"10.1109/SENSORS47125.2020.9278597","DOIUrl":"https://doi.org/10.1109/SENSORS47125.2020.9278597","url":null,"abstract":"Ultra-low power sensors attract increasing attention as the requisite building blocks of long-life wireless sensor nodes. This work developed a proof-of-concept device to evaluate the feasibility of ultra-low power stress sensing by the leakage current of p-n junctions. Experimental results show that the variation of the leakage current of p-n junctions demonstrates excellent linearity and stability with the stress in the range from 0 to 90 MPa. When the reverse bias voltage decreases from 2.5 to 0.5 V, there is almost no deterioration of the stress sensitivity but the maximum power consumption greatly decreases from to 705 pW to 156 pW. By using the published circuit for temperature sensors, the power consumption of the stress/strain sensors based on the detection of the leakage current of p-n junctions may be decreased to lower than 1 nW. Therefore, the piezojunction effect of p-n junctions is an attractive sensing mechanism for ultra-low power stress/strain sensors.","PeriodicalId":338240,"journal":{"name":"2020 IEEE Sensors","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128363557","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-25DOI: 10.1109/SENSORS47125.2020.9278629
Tomoki Uno, Maki Sawano, H. Matsukura, H. Ishida
We report a mobile robot that can effectively follow a chemical trail laid on the floor. Three metal-oxide gas sensors are mounted on the robot to detect its position with respect to the chemical trail, and four fans are aligned around each gas sensor. The effects of the airflows generated by the fans are two-fold. First, the airflows that impinge on the ground help bring the chemical vapor from a chemical trail to the gas sensors. Second, they serve as air curtains and prevent the gas sensors from responding to chemical vapor straying off to the side from the trail.
{"title":"Detection of Chemical Trail on the Floor by Mobile Robot: : Using Fans to Enhance Chemical Reception at Gas Sensors","authors":"Tomoki Uno, Maki Sawano, H. Matsukura, H. Ishida","doi":"10.1109/SENSORS47125.2020.9278629","DOIUrl":"https://doi.org/10.1109/SENSORS47125.2020.9278629","url":null,"abstract":"We report a mobile robot that can effectively follow a chemical trail laid on the floor. Three metal-oxide gas sensors are mounted on the robot to detect its position with respect to the chemical trail, and four fans are aligned around each gas sensor. The effects of the airflows generated by the fans are two-fold. First, the airflows that impinge on the ground help bring the chemical vapor from a chemical trail to the gas sensors. Second, they serve as air curtains and prevent the gas sensors from responding to chemical vapor straying off to the side from the trail.","PeriodicalId":338240,"journal":{"name":"2020 IEEE Sensors","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128680067","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-10-25DOI: 10.1109/SENSORS47125.2020.9278625
Xiaoshuai Chen, Shuo Jiang, Benny P. L. Lo
One of the major healthcare challenges is elderly fallers. A fall can lead to disabilities and even mortality. With the current Covid-19 pandemic, insufficient resources could be provided for the care of elderlies, and care workers often may not be able to visit them. Therefore, a fall may get undetected or delayed leading to serious harm or consequences. Automatic fall detection systems could provide the necessary detection and warnings for timely intervention. Although many sensor-based fall detection systems have been proposed, most systems focus on the sudden fall and have not considered the slow fall scenario, a typical fall instance for elderly fallers. In this paper, a robust activity (RA) and slow fall detection system is proposed. The system consists of a waist-worn wearable sensor embedded with an inertial measurement unit (IMU) and a barometer, and a reference ambient barometer. A deep neural network (DNN) is developed for fusing the sensor data and classifying fall events. The results have shown that the IMU-barometer design yield better detection of fall events and the DNN approach (90.33% accuracy) outperforms traditional machine learning algorithms.
{"title":"Subject-Independent Slow Fall Detection with Wearable Sensors via Deep Learning","authors":"Xiaoshuai Chen, Shuo Jiang, Benny P. L. Lo","doi":"10.1109/SENSORS47125.2020.9278625","DOIUrl":"https://doi.org/10.1109/SENSORS47125.2020.9278625","url":null,"abstract":"One of the major healthcare challenges is elderly fallers. A fall can lead to disabilities and even mortality. With the current Covid-19 pandemic, insufficient resources could be provided for the care of elderlies, and care workers often may not be able to visit them. Therefore, a fall may get undetected or delayed leading to serious harm or consequences. Automatic fall detection systems could provide the necessary detection and warnings for timely intervention. Although many sensor-based fall detection systems have been proposed, most systems focus on the sudden fall and have not considered the slow fall scenario, a typical fall instance for elderly fallers. In this paper, a robust activity (RA) and slow fall detection system is proposed. The system consists of a waist-worn wearable sensor embedded with an inertial measurement unit (IMU) and a barometer, and a reference ambient barometer. A deep neural network (DNN) is developed for fusing the sensor data and classifying fall events. The results have shown that the IMU-barometer design yield better detection of fall events and the DNN approach (90.33% accuracy) outperforms traditional machine learning algorithms.","PeriodicalId":338240,"journal":{"name":"2020 IEEE Sensors","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129855799","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：