Pub Date : 2022-08-01DOI: 10.1109/SAS54819.2022.9881378
Gernot Fiala, Zhenyu Ye, C. Steger
For future augmented reality (AR) and virtual reality (VR) applications, several different kinds of sensors will be used. These sensors, to give some examples, are used for gesture recognition, head pose tracking and pupil tracking. All these sensors send data to a host platform, where the data must be processed in real-time. This requires high processing power which leads to higher energy consumption. To lower the energy consumption, optimizations of the image processing system are necessary. This paper investigates pupil detection for AR/VR applications based on images with reduced bit depths. It shows that images with reduced bit depths even down to 3 or 2 bits can be used for pupil detection, with almost the same average detection rate. Reduced bit depths of an image reduces the memory foot-print, which allows to perform in-sensor processing for future image sensors and provides the foundation for future in-sensor processing architectures.
{"title":"Pupil Detection for Augmented and Virtual Reality based on Images with Reduced Bit Depths","authors":"Gernot Fiala, Zhenyu Ye, C. Steger","doi":"10.1109/SAS54819.2022.9881378","DOIUrl":"https://doi.org/10.1109/SAS54819.2022.9881378","url":null,"abstract":"For future augmented reality (AR) and virtual reality (VR) applications, several different kinds of sensors will be used. These sensors, to give some examples, are used for gesture recognition, head pose tracking and pupil tracking. All these sensors send data to a host platform, where the data must be processed in real-time. This requires high processing power which leads to higher energy consumption. To lower the energy consumption, optimizations of the image processing system are necessary. This paper investigates pupil detection for AR/VR applications based on images with reduced bit depths. It shows that images with reduced bit depths even down to 3 or 2 bits can be used for pupil detection, with almost the same average detection rate. Reduced bit depths of an image reduces the memory foot-print, which allows to perform in-sensor processing for future image sensors and provides the foundation for future in-sensor processing architectures.","PeriodicalId":129732,"journal":{"name":"2022 IEEE Sensors Applications Symposium (SAS)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125969028","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 : 2022-08-01DOI: 10.1109/SAS54819.2022.9881354
K. Husby, A. Saasen, J. D. Ytrehus, M. Hjelstuen, T. Eriksen, A. Liberale
Active magnetic ranging (AMR) while drilling is an electromagnetic method used to map subsurface ground by its conductivity. Subsurface mapping is needed both in the oil and gas industry and in the geothermal drilling industry. In both cases, several wells are drilled close to each other to exploit the full potential of either an oil reservoir or a geothermal reservoir. The challenge however with subsurface mapping compared to thin air radar mapping is the very low skin depth given by the high conductivity of the ground. For that reason, existing systems are often limited to very short range operations.In this paper methods for range improvement are presented. To maximize the range potential the frequency of operation is reduced, and the efficiency and size of the antennas are increased as much as possible.
{"title":"Active magnetic ranging while drilling: A down-hole surroundings mapping","authors":"K. Husby, A. Saasen, J. D. Ytrehus, M. Hjelstuen, T. Eriksen, A. Liberale","doi":"10.1109/SAS54819.2022.9881354","DOIUrl":"https://doi.org/10.1109/SAS54819.2022.9881354","url":null,"abstract":"Active magnetic ranging (AMR) while drilling is an electromagnetic method used to map subsurface ground by its conductivity. Subsurface mapping is needed both in the oil and gas industry and in the geothermal drilling industry. In both cases, several wells are drilled close to each other to exploit the full potential of either an oil reservoir or a geothermal reservoir. The challenge however with subsurface mapping compared to thin air radar mapping is the very low skin depth given by the high conductivity of the ground. For that reason, existing systems are often limited to very short range operations.In this paper methods for range improvement are presented. To maximize the range potential the frequency of operation is reduced, and the efficiency and size of the antennas are increased as much as possible.","PeriodicalId":129732,"journal":{"name":"2022 IEEE Sensors Applications Symposium (SAS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129365489","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 : 2022-08-01DOI: 10.1109/SAS54819.2022.9881347
L. Kassab, Andrew J. Law, Bruce Wallace, J. Larivière-Chartier, R. Goubran, F. Knoefel
Screening people for signs of illness through contactless measurement of vital signs could be beneficial in public transportation settings or long-term care facilities. To achieve this goal, one solution could utilize Red/Green/Blue (RGB) video cameras to measure heart rate. In this work, we present results for the assessment of heart rate through Video Magnification (VM) techniques applied to RGB face video recordings from 19 subjects. The work specifically explores (1) the effect of two lighting illumination levels and (2) the effect of window length on the accuracy of heart rate extraction via Video Magnification. The results show that higher illumination, as a result of combining halogen light with LED, yielded lower average errors in heart rate measured through Video Magnification. Additionally, the results show that increasing the window length from 10 seconds up to 30 seconds improves VM heart rate accuracy when there are small frequent head movements in the video but decreases heart rate accuracy in the absence of head motion.
{"title":"Effects of Lighting and Window Length on Heart Rate Assessment through Video Magnification","authors":"L. Kassab, Andrew J. Law, Bruce Wallace, J. Larivière-Chartier, R. Goubran, F. Knoefel","doi":"10.1109/SAS54819.2022.9881347","DOIUrl":"https://doi.org/10.1109/SAS54819.2022.9881347","url":null,"abstract":"Screening people for signs of illness through contactless measurement of vital signs could be beneficial in public transportation settings or long-term care facilities. To achieve this goal, one solution could utilize Red/Green/Blue (RGB) video cameras to measure heart rate. In this work, we present results for the assessment of heart rate through Video Magnification (VM) techniques applied to RGB face video recordings from 19 subjects. The work specifically explores (1) the effect of two lighting illumination levels and (2) the effect of window length on the accuracy of heart rate extraction via Video Magnification. The results show that higher illumination, as a result of combining halogen light with LED, yielded lower average errors in heart rate measured through Video Magnification. Additionally, the results show that increasing the window length from 10 seconds up to 30 seconds improves VM heart rate accuracy when there are small frequent head movements in the video but decreases heart rate accuracy in the absence of head motion.","PeriodicalId":129732,"journal":{"name":"2022 IEEE Sensors Applications Symposium (SAS)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132137552","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 : 2022-08-01DOI: 10.1109/SAS54819.2022.9881382
Pengwei Du, T. Polonelli, M. Magno, Zhiyuan Cheng
Agriculture is the pillar industry for human survival. However, various diseases threaten the health of crops and lead to a decrease in yield. Industry 4.0 is making strides in plant illness prevention and detection, other than supporting farmers to improve plantations’ income. To prevent crop diseases in time, this paper proposes, implements, and evaluates a low-power smart camera. It features a lightweight neural network to verify and monitor the growth status of crops. The proposed tiny model features optimized complexity, to be deployed in milliwatt power microcontrollers, and high accuracy. Experimental results show that our work reaches 99% accuracy on a 4-classes dataset and more than 96% for a 10 classes dataset. The compact model size (139 kB) and low complexity enable ultra-low power consumption (2.63 mW per hour) on the battery-powered Sony Spresense platform, which features a six-core ARM Cortex-M4F.
{"title":"Towards lightweight deep neural network for smart agriculture on embedded systems","authors":"Pengwei Du, T. Polonelli, M. Magno, Zhiyuan Cheng","doi":"10.1109/SAS54819.2022.9881382","DOIUrl":"https://doi.org/10.1109/SAS54819.2022.9881382","url":null,"abstract":"Agriculture is the pillar industry for human survival. However, various diseases threaten the health of crops and lead to a decrease in yield. Industry 4.0 is making strides in plant illness prevention and detection, other than supporting farmers to improve plantations’ income. To prevent crop diseases in time, this paper proposes, implements, and evaluates a low-power smart camera. It features a lightweight neural network to verify and monitor the growth status of crops. The proposed tiny model features optimized complexity, to be deployed in milliwatt power microcontrollers, and high accuracy. Experimental results show that our work reaches 99% accuracy on a 4-classes dataset and more than 96% for a 10 classes dataset. The compact model size (139 kB) and low complexity enable ultra-low power consumption (2.63 mW per hour) on the battery-powered Sony Spresense platform, which features a six-core ARM Cortex-M4F.","PeriodicalId":129732,"journal":{"name":"2022 IEEE Sensors Applications Symposium (SAS)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125414359","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 : 2022-08-01DOI: 10.1109/SAS54819.2022.9881346
N. Cennamo, F. Arcadio, V. Marletta, D. D. Prete, B. Andò, L. Zeni, Mario Cesaro, Alfredo De Matteis
In this work, a force sensor based on plastic optical fibers (POFs) is realized and tested. More specifically, the optical sensor system is composed of a cantilever obtained by a spring-steel beam and a modified POF glued on the underside of the cantilever. One end of the cantilever is fixed to the optical desk using a developed support, while on the other end, a weight is applied to realize an applied force. The POF is modified by notches in order to improve the optical performance of the force sensor. An analysis is carried out to characterize the sensor system. In particular, it has a linear behaviour ranging from 50 mN to 300 mN with a sensitivity of 53.43 mV/N and a resolution of 0.01 N.
{"title":"A simple and highly sensitive Force Sensor based on modified plastic optical fibers and cantilevers","authors":"N. Cennamo, F. Arcadio, V. Marletta, D. D. Prete, B. Andò, L. Zeni, Mario Cesaro, Alfredo De Matteis","doi":"10.1109/SAS54819.2022.9881346","DOIUrl":"https://doi.org/10.1109/SAS54819.2022.9881346","url":null,"abstract":"In this work, a force sensor based on plastic optical fibers (POFs) is realized and tested. More specifically, the optical sensor system is composed of a cantilever obtained by a spring-steel beam and a modified POF glued on the underside of the cantilever. One end of the cantilever is fixed to the optical desk using a developed support, while on the other end, a weight is applied to realize an applied force. The POF is modified by notches in order to improve the optical performance of the force sensor. An analysis is carried out to characterize the sensor system. In particular, it has a linear behaviour ranging from 50 mN to 300 mN with a sensitivity of 53.43 mV/N and a resolution of 0.01 N.","PeriodicalId":129732,"journal":{"name":"2022 IEEE Sensors Applications Symposium (SAS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131105715","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 : 2022-08-01DOI: 10.1109/SAS54819.2022.9881376
P. Bellagente
According to statistics, the construction market is one of the most dangerous economic sector all around the world. Construction workers are continuously exposed to moving materials and machinery, often in constrained spaces, rising the risk of collision accidents. In this paper an Ultra-Wide Band (UWB) Real Time Location System (RTLS) designed in a previous work for proximity hazards management in construction sites is described in detail. An extensive measurement campaign have been carried out outdoor, using a square grid (15 m x 15 m) and 1 m step, for a total of 225 positions. For each position, 1000 location measures have been collected and the bidimensional localization resolution has been estimated. Results show that location resolution remains similar across the considered area and that it could be manually verified by construction workers. In optimal conditions, the resolution ranges are within 0.01 m and 0.05 m . The results highlight a major error contribution due to radio-frequency reflection interference, which makes impossible to measure positions under some conditions.
据统计，建筑市场是世界上最危险的经济部门之一。建筑工人经常在有限的空间里不断接触移动的材料和机械，这增加了发生碰撞事故的风险。本文详细介绍了前人设计的一种用于建筑工地近距离危险管理的超宽带实时定位系统。在室外进行了广泛的测量活动，使用方形网格(15米× 15米)和1米的台阶，总共225个位置。对于每个位置，收集了1000个位置测量，并估计了二维定位分辨率。结果表明，在考虑的区域内，位置分辨率保持相似，并且可以由建筑工人手动验证。在最佳条件下，分辨率范围在0.01 m ~ 0.05 m之间。结果强调了射频反射干扰对误差的主要贡献，这使得在某些条件下无法测量位置。
{"title":"Assessment of UWB RTLS for Proximity Hazards Management in Construction Sites","authors":"P. Bellagente","doi":"10.1109/SAS54819.2022.9881376","DOIUrl":"https://doi.org/10.1109/SAS54819.2022.9881376","url":null,"abstract":"According to statistics, the construction market is one of the most dangerous economic sector all around the world. Construction workers are continuously exposed to moving materials and machinery, often in constrained spaces, rising the risk of collision accidents. In this paper an Ultra-Wide Band (UWB) Real Time Location System (RTLS) designed in a previous work for proximity hazards management in construction sites is described in detail. An extensive measurement campaign have been carried out outdoor, using a square grid (15 m x 15 m) and 1 m step, for a total of 225 positions. For each position, 1000 location measures have been collected and the bidimensional localization resolution has been estimated. Results show that location resolution remains similar across the considered area and that it could be manually verified by construction workers. In optimal conditions, the resolution ranges are within 0.01 m and 0.05 m . The results highlight a major error contribution due to radio-frequency reflection interference, which makes impossible to measure positions under some conditions.","PeriodicalId":129732,"journal":{"name":"2022 IEEE Sensors Applications Symposium (SAS)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132347284","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 : 2022-08-01DOI: 10.1109/SAS54819.2022.9881246
O. Makeyev, Y. Ye-Lin, G. Prats-Boluda, J. Garcia-Casado
While finite element method modeling has been used to compare bipolar and tripolar concentric ring electrode configurations in the past it was based on the simplistic negligible dimensions model of the electrode. This study uses realistic finite dimensions models including novel optimal bipolar and tripolar configurations and directly compares them to bipolar configurations of the same size with dimensions corresponding to the commercially available CoDe® electrodes manufactured by Spes Medica. Moreover, it also compares bipolar and tripolar configurations of different sizes. In particular, optimal tripolar concentric ring electrode configuration is compared to a bipolar configuration consisting out of its central disc and middle ring only. Obtained results include relative and normalized maximum errors of Laplacian estimation. Compared to the optimal tripolar concentric ring electrode configuration, commercially available bipolar electrode of the same size corresponds to a median increase in Laplacian estimation errors of 120-146 times while its counterpart one third of its size corresponds to an increase of 15-18 times. Compared to the optimal bipolar configuration, commercially available bipolar electrode of the same size corresponds to a median increase in Laplacian estimation errors of 1.2 times. These results are consistent with previously obtained results based on the negligible dimensions models.
{"title":"Comparing Optimal and Commercially Available Bipolar and Tripolar Concentric Ring Electrode Configurations Using Finite Element Method Modeling Based on Their Finite Dimensions Models","authors":"O. Makeyev, Y. Ye-Lin, G. Prats-Boluda, J. Garcia-Casado","doi":"10.1109/SAS54819.2022.9881246","DOIUrl":"https://doi.org/10.1109/SAS54819.2022.9881246","url":null,"abstract":"While finite element method modeling has been used to compare bipolar and tripolar concentric ring electrode configurations in the past it was based on the simplistic negligible dimensions model of the electrode. This study uses realistic finite dimensions models including novel optimal bipolar and tripolar configurations and directly compares them to bipolar configurations of the same size with dimensions corresponding to the commercially available CoDe® electrodes manufactured by Spes Medica. Moreover, it also compares bipolar and tripolar configurations of different sizes. In particular, optimal tripolar concentric ring electrode configuration is compared to a bipolar configuration consisting out of its central disc and middle ring only. Obtained results include relative and normalized maximum errors of Laplacian estimation. Compared to the optimal tripolar concentric ring electrode configuration, commercially available bipolar electrode of the same size corresponds to a median increase in Laplacian estimation errors of 120-146 times while its counterpart one third of its size corresponds to an increase of 15-18 times. Compared to the optimal bipolar configuration, commercially available bipolar electrode of the same size corresponds to a median increase in Laplacian estimation errors of 1.2 times. These results are consistent with previously obtained results based on the negligible dimensions models.","PeriodicalId":129732,"journal":{"name":"2022 IEEE Sensors Applications Symposium (SAS)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132435412","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 : 2022-08-01DOI: 10.1109/SAS54819.2022.9881336
B. Andò, S. Baglio, V. Dibilio, V. Marletta, Michele Marella, G. Mostile, S. Rajan, M. Zappia
Assistive Technology helps to assess the daily living of frail people, and aid to detect and prevent falls. In this paper, a novel Neuro-Fuzzy paradigm is proposed that can perform the assessment of postural sway behaviors based on inertial measurements of the user dynamics. A suitable set of features is obtained from the measurements and is used to feed the assessment methodology. The proposed assessment approach provides superior results, in terms of reliability, when compared to the traditional threshold-based assessment algorithms, showing a mean reliability index in the order of 95%.
{"title":"A Neuro-Fuzzy Approach to Assess Postural Sway","authors":"B. Andò, S. Baglio, V. Dibilio, V. Marletta, Michele Marella, G. Mostile, S. Rajan, M. Zappia","doi":"10.1109/SAS54819.2022.9881336","DOIUrl":"https://doi.org/10.1109/SAS54819.2022.9881336","url":null,"abstract":"Assistive Technology helps to assess the daily living of frail people, and aid to detect and prevent falls. In this paper, a novel Neuro-Fuzzy paradigm is proposed that can perform the assessment of postural sway behaviors based on inertial measurements of the user dynamics. A suitable set of features is obtained from the measurements and is used to feed the assessment methodology. The proposed assessment approach provides superior results, in terms of reliability, when compared to the traditional threshold-based assessment algorithms, showing a mean reliability index in the order of 95%.","PeriodicalId":129732,"journal":{"name":"2022 IEEE Sensors Applications Symposium (SAS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132081500","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 : 2022-08-01DOI: 10.1109/SAS54819.2022.9881361
Saif Almhairat, Bruce Wallace, J. Larivière-Chartier, A. El-Haraki, R. Goubran, F. Knoefel
Smart home systems have shown potential to enable older adults to age-in-place, delaying entry to care. However, previous work has revealed network inefficiencies in these systems. For telecom carriers, these findings become more significant with the wide-scale deployment of smart home systems and, more generally, Wireless Sensor Networks (WSNs). Subsequently, research applied Dual Machine Learning to reduce network traffic leaving the residence to cloud processing. However, the dual model was shown to be impacted by network effects such as latency, jitter, and packet loss, whereby as much as half of sensor data stored in the cloud was incorrect. This report proposes a 2-stage Phase-Locked Loop (PLL) based solution to mitigate the impact of network latency and jitter on Dual Machine Learning and improve the accuracy of data stored in the cloud; the proposed solution increased the worst-case accuracy rate from 71.4% to 94.6% for latency and from 64.1% to 90.3% for jitter.
{"title":"Maintaining Synchrony of Dual Machine Learning: A Phase-Locked Loop Approach","authors":"Saif Almhairat, Bruce Wallace, J. Larivière-Chartier, A. El-Haraki, R. Goubran, F. Knoefel","doi":"10.1109/SAS54819.2022.9881361","DOIUrl":"https://doi.org/10.1109/SAS54819.2022.9881361","url":null,"abstract":"Smart home systems have shown potential to enable older adults to age-in-place, delaying entry to care. However, previous work has revealed network inefficiencies in these systems. For telecom carriers, these findings become more significant with the wide-scale deployment of smart home systems and, more generally, Wireless Sensor Networks (WSNs). Subsequently, research applied Dual Machine Learning to reduce network traffic leaving the residence to cloud processing. However, the dual model was shown to be impacted by network effects such as latency, jitter, and packet loss, whereby as much as half of sensor data stored in the cloud was incorrect. This report proposes a 2-stage Phase-Locked Loop (PLL) based solution to mitigate the impact of network latency and jitter on Dual Machine Learning and improve the accuracy of data stored in the cloud; the proposed solution increased the worst-case accuracy rate from 71.4% to 94.6% for latency and from 64.1% to 90.3% for jitter.","PeriodicalId":129732,"journal":{"name":"2022 IEEE Sensors Applications Symposium (SAS)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133318746","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 : 2022-08-01DOI: 10.1109/SAS54819.2022.9881365
Mazhar Hussain, M. O’nils, J. Lundgren, M. Carratù, Irida Shallari
The study aims to explore the fuel consumption of city buses with data fusion using a dataset with multiple parameters such as travelled distance, weekday, hour of the day, drivers, buses, and routes, that influence the trip fuel consumption. In this study, manipulated parameters such as modified driver, bus and route identification numbers are used together with original parameters to identify the optimal combination of parameters that can be used to enhance the accuracy of the prediction model. Two regression methods, i.e. cubic SVM and artificial neural networks (ANN), are used to demonstrate the performance of the proposed approach. Results shows that a combination of original parameters and processed parameters increases the performance.
{"title":"Selection of optimal parameters to predict fuel consumption of city buses using data fusion","authors":"Mazhar Hussain, M. O’nils, J. Lundgren, M. Carratù, Irida Shallari","doi":"10.1109/SAS54819.2022.9881365","DOIUrl":"https://doi.org/10.1109/SAS54819.2022.9881365","url":null,"abstract":"The study aims to explore the fuel consumption of city buses with data fusion using a dataset with multiple parameters such as travelled distance, weekday, hour of the day, drivers, buses, and routes, that influence the trip fuel consumption. In this study, manipulated parameters such as modified driver, bus and route identification numbers are used together with original parameters to identify the optimal combination of parameters that can be used to enhance the accuracy of the prediction model. Two regression methods, i.e. cubic SVM and artificial neural networks (ANN), are used to demonstrate the performance of the proposed approach. Results shows that a combination of original parameters and processed parameters increases the performance.","PeriodicalId":129732,"journal":{"name":"2022 IEEE Sensors Applications Symposium (SAS)","volume":" 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132125376","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：