Pub Date : 2017-07-17DOI: 10.1109/HSI.2017.8004993
A. Kwaśniewska, J. Rumiński, P. Rad
Recently, capabilities of many computer vision tasks have significantly improved due to advances in Convolutional Neural Networks. In our research, we demonstrate that it can be also used for face detection from low resolution thermal images, acquired with a portable camera. The physical size of the camera used in our research allows for embedding it in a wearable device or indoor remote monitoring solution for elderly and disabled people. The benefits of the proposed architecture were experimentally verified on the thermal video sequences, acquired in various scenarios to address possible limitations of remote diagnostics: movements of the person performing a diagnose and movements of the examined person. The achieved short processing time (42.05±0.21ms) along with high model accuracy (false positives - 0.43%; true positives for the patient focused on a certain task - 89.2%) clearly indicates that the current state of the art in the area of image classification and face tracking in thermography was significantly outperformed.
{"title":"Deep features class activation map for thermal face detection and tracking","authors":"A. Kwaśniewska, J. Rumiński, P. Rad","doi":"10.1109/HSI.2017.8004993","DOIUrl":"https://doi.org/10.1109/HSI.2017.8004993","url":null,"abstract":"Recently, capabilities of many computer vision tasks have significantly improved due to advances in Convolutional Neural Networks. In our research, we demonstrate that it can be also used for face detection from low resolution thermal images, acquired with a portable camera. The physical size of the camera used in our research allows for embedding it in a wearable device or indoor remote monitoring solution for elderly and disabled people. The benefits of the proposed architecture were experimentally verified on the thermal video sequences, acquired in various scenarios to address possible limitations of remote diagnostics: movements of the person performing a diagnose and movements of the examined person. The achieved short processing time (42.05±0.21ms) along with high model accuracy (false positives - 0.43%; true positives for the patient focused on a certain task - 89.2%) clearly indicates that the current state of the art in the area of image classification and face tracking in thermography was significantly outperformed.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132710714","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 : 2017-07-17DOI: 10.1109/HSI.2017.8005002
Donggil Song, E. Oh, Marilyn Rice
Since distance education creates new opportunities for learners, the enrollment in online courses has been sharply increasing in higher education. However, the higher attrition rate is one of the more significant concerns in this field. Educational researchers have found that meaningful interactions play a significant role in learner persistence in online courses. Still, it is challenging for an individual instructor to promote learners' positive interaction experiences. The expectation of improved learners' interaction with conversational agent systems has received attention in the distance education field. Few conversational agent systems have been developed for educational purposes, and few systems are used in real online learning settings. This study aims at designing and developing a conversational agent system to promote the learner's meaningful interaction in online courses, and also exploring the feasibility of human interaction with the conversational agent system, or chatbot, in online courses in higher education. The primary findings of this study show that instant, content-related, and quality interactions between the learner and the conversational agent system is applicable to graduate-level online courses. Implications and future research are discussed.
{"title":"Interacting with a conversational agent system for educational purposes in online courses","authors":"Donggil Song, E. Oh, Marilyn Rice","doi":"10.1109/HSI.2017.8005002","DOIUrl":"https://doi.org/10.1109/HSI.2017.8005002","url":null,"abstract":"Since distance education creates new opportunities for learners, the enrollment in online courses has been sharply increasing in higher education. However, the higher attrition rate is one of the more significant concerns in this field. Educational researchers have found that meaningful interactions play a significant role in learner persistence in online courses. Still, it is challenging for an individual instructor to promote learners' positive interaction experiences. The expectation of improved learners' interaction with conversational agent systems has received attention in the distance education field. Few conversational agent systems have been developed for educational purposes, and few systems are used in real online learning settings. This study aims at designing and developing a conversational agent system to promote the learner's meaningful interaction in online courses, and also exploring the feasibility of human interaction with the conversational agent system, or chatbot, in online courses in higher education. The primary findings of this study show that instant, content-related, and quality interactions between the learner and the conversational agent system is applicable to graduate-level online courses. Implications and future research are discussed.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116361299","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 : 2017-07-01DOI: 10.1109/HSI.2017.8005036
Danilo Cáceres Hernández, A. Filonenko, Ajmal Shahbaz, K. Jo
The lane marking detection task is an essential process in the field of semi-autonomous and autonomous navigation. This paper proposes a method that combines the color and edge information to robustly detect the lane marking within the image either located far on near to the vehicle. Firstly, the region of interest is extracted from the image. Secondly, the set of lane marking features are extracted. To do that, the change in color between road and marking surface is used along a probability density function to extract the set of candidates. Finally, a clustering method along a line fitting model is implemented. Preliminary results were performed and tested on a group of consecutive frames to prove the effectiveness of the proposed method.
{"title":"Lane marking detection using image features and line fitting model","authors":"Danilo Cáceres Hernández, A. Filonenko, Ajmal Shahbaz, K. Jo","doi":"10.1109/HSI.2017.8005036","DOIUrl":"https://doi.org/10.1109/HSI.2017.8005036","url":null,"abstract":"The lane marking detection task is an essential process in the field of semi-autonomous and autonomous navigation. This paper proposes a method that combines the color and edge information to robustly detect the lane marking within the image either located far on near to the vehicle. Firstly, the region of interest is extracted from the image. Secondly, the set of lane marking features are extracted. To do that, the change in color between road and marking surface is used along a probability density function to extract the set of candidates. Finally, a clustering method along a line fitting model is implemented. Preliminary results were performed and tested on a group of consecutive frames to prove the effectiveness of the proposed method.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125467093","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 : 2017-07-01DOI: 10.1109/HSI.2017.8005031
Sanghee Lee, K. Jo
The needs for automatic semantic information indexing and retrieval systems have raised owing to the rapid growth of video content. Above all, in the information sources of the video, textual information has an important role in high level semantics. This paper presents the strategy for automatic person indexing and retrieval system using overlay text in the television news interview video sequences. For recognition the overlay text and extraction the information, the proposed methods are based on many of the accepted production rules of the television news and the temporality of the video sequences. The experimental results on Korean television news video show that the proposed method efficiently realizes the automatic indexing and retrieval system.
{"title":"Strategy for automatic person indexing and retrieval system in news interview video sequences","authors":"Sanghee Lee, K. Jo","doi":"10.1109/HSI.2017.8005031","DOIUrl":"https://doi.org/10.1109/HSI.2017.8005031","url":null,"abstract":"The needs for automatic semantic information indexing and retrieval systems have raised owing to the rapid growth of video content. Above all, in the information sources of the video, textual information has an important role in high level semantics. This paper presents the strategy for automatic person indexing and retrieval system using overlay text in the television news interview video sequences. For recognition the overlay text and extraction the information, the proposed methods are based on many of the accepted production rules of the television news and the temporality of the video sequences. The experimental results on Korean television news video show that the proposed method efficiently realizes the automatic indexing and retrieval system.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122407300","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 : 2017-07-01DOI: 10.1109/HSI.2017.8005012
Shaona Cheng, Dingguo Zhang
Electroactile feedback is crucial to close the loop systems of the teleoperation system, virtual reality system, and prosthetic system. Feedback devices are always limited in application due to large size for their inconvenience. In the present study, a wearable armband named “iFeel” is developed, which includes five pairs of electrodes for electrotactile stimulation is introduced for feedback to close the loop in the systems above. The armband also includes a custom-designed stimulator for generating pulses. The stimulator consists of power module, voltage converting module, Bluetooth module, the microcontroller Unit, constant-current power supply module and multiplexing module. Two experiments including position discrimination and frequency discrimination are conducted to validate the armband. We use the success rate to evaluate feasibility of armband. Our preliminary results show a high accuracy of position discrimination (success rate > 90%) and frequency levels discrimination (success rate > 90%). The sensory substitute feedback has the potential to be applied for feedback to achieve more information with high resolution and accuracy after minimal training.
{"title":"A wearable armband “iFeel” for electrotactile stimulation","authors":"Shaona Cheng, Dingguo Zhang","doi":"10.1109/HSI.2017.8005012","DOIUrl":"https://doi.org/10.1109/HSI.2017.8005012","url":null,"abstract":"Electroactile feedback is crucial to close the loop systems of the teleoperation system, virtual reality system, and prosthetic system. Feedback devices are always limited in application due to large size for their inconvenience. In the present study, a wearable armband named “iFeel” is developed, which includes five pairs of electrodes for electrotactile stimulation is introduced for feedback to close the loop in the systems above. The armband also includes a custom-designed stimulator for generating pulses. The stimulator consists of power module, voltage converting module, Bluetooth module, the microcontroller Unit, constant-current power supply module and multiplexing module. Two experiments including position discrimination and frequency discrimination are conducted to validate the armband. We use the success rate to evaluate feasibility of armband. Our preliminary results show a high accuracy of position discrimination (success rate > 90%) and frequency levels discrimination (success rate > 90%). The sensory substitute feedback has the potential to be applied for feedback to achieve more information with high resolution and accuracy after minimal training.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124464126","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 : 2017-07-01DOI: 10.1109/HSI.2017.8005001
A. Masrukhin, A. Yusuf
Indonesia emergency drugs, this is the news we often hear and see these days on various media. How it is not emergency drugs because about 4.5 youth are not be rehabilitated, even drugs are not only damage the environment to young people but also entered in the institutions. The government and society so heavily sought tackling drug addicts, but still so many victims of drugs. This study tried to determine the influence of facility design differentiation and human resource management on mental health rehabilitation in Babesrehab BNN Lido and Islamic Boarding School Inabah xx Suryalaya and determine the factors that influence to effectiveness of mental health rehabilitation both institutions. The type of this research is qualitative descriftive. Researchers will conduct direct field observation at the sites. Data analysis methods used by the author is the method of discourse analysis and swot analysis of the two organizers subject fostering mental health of drug addicts. With the hope of finding the most effective methods of rehabilitation.
印尼紧急药品，这是我们这几天在各种媒体上经常听到和看到的新闻。怎么也不紧急吸毒，因为大约有4.5名青少年是得不到康复的，甚至吸毒不仅破坏了青少年的环境，而且还进入了机构。政府和社会如此大力地寻求解决吸毒成瘾者，但仍然有如此多的毒品受害者。本研究试图确定设施设计差异化和人力资源管理对Babesrehab BNN Lido和Inabah xx Suryalaya伊斯兰寄宿学校心理健康康复的影响，并确定影响两所机构心理健康康复效果的因素。本研究的类型是定性描述。研究人员将在这些地点进行直接的实地观察。作者使用的数据分析方法是话语分析法和swot分析法，对两个组织者的主题培养吸毒成瘾者的心理健康。希望能找到最有效的康复方法。
{"title":"The influence of facility design differentiation and human resource management on mental health rehabilitation","authors":"A. Masrukhin, A. Yusuf","doi":"10.1109/HSI.2017.8005001","DOIUrl":"https://doi.org/10.1109/HSI.2017.8005001","url":null,"abstract":"Indonesia emergency drugs, this is the news we often hear and see these days on various media. How it is not emergency drugs because about 4.5 youth are not be rehabilitated, even drugs are not only damage the environment to young people but also entered in the institutions. The government and society so heavily sought tackling drug addicts, but still so many victims of drugs. This study tried to determine the influence of facility design differentiation and human resource management on mental health rehabilitation in Babesrehab BNN Lido and Islamic Boarding School Inabah xx Suryalaya and determine the factors that influence to effectiveness of mental health rehabilitation both institutions. The type of this research is qualitative descriftive. Researchers will conduct direct field observation at the sites. Data analysis methods used by the author is the method of discourse analysis and swot analysis of the two organizers subject fostering mental health of drug addicts. With the hope of finding the most effective methods of rehabilitation.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130237164","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 : 2017-07-01DOI: 10.1109/HSI.2017.8005013
Muhammad Jawad Khan, A. Zafar, K. Hong
In this paper, we investigate active brain regions for motor execution and motor imagination tasks after training with a rehabilitation robot. Functional near-infrared spectroscopy (fNIRS) is used to measure the hemodynamic responses in the motor cortices of five subjects. An assistive robot (IMT 2.0, connected to the right hand) is used during the training session to make the subject to reach a target point displayed on a computer screen. During the training, the subjects have to reach the target point in two directions (left and right) using right arm movement. Our intention is to investigate the differences between brain signals generated from left and right movements of the right hand. It was found that the same brain region was activated for both left- and right-directional motions. During the testing, we asked the subjects to imagine the executed movement. We found that although the imagined movement activity is weak but it appears in the same region as that of motor execution during the reach task. The results show that executed and imagined movements can be discriminated using fNIRS. However, for brain-computer interface it is difficult to generate two commands using only one arm movement signals.
{"title":"Comparison of brain areas for executed and imagined movements after motor training: An fNIRS study","authors":"Muhammad Jawad Khan, A. Zafar, K. Hong","doi":"10.1109/HSI.2017.8005013","DOIUrl":"https://doi.org/10.1109/HSI.2017.8005013","url":null,"abstract":"In this paper, we investigate active brain regions for motor execution and motor imagination tasks after training with a rehabilitation robot. Functional near-infrared spectroscopy (fNIRS) is used to measure the hemodynamic responses in the motor cortices of five subjects. An assistive robot (IMT 2.0, connected to the right hand) is used during the training session to make the subject to reach a target point displayed on a computer screen. During the training, the subjects have to reach the target point in two directions (left and right) using right arm movement. Our intention is to investigate the differences between brain signals generated from left and right movements of the right hand. It was found that the same brain region was activated for both left- and right-directional motions. During the testing, we asked the subjects to imagine the executed movement. We found that although the imagined movement activity is weak but it appears in the same region as that of motor execution during the reach task. The results show that executed and imagined movements can be discriminated using fNIRS. However, for brain-computer interface it is difficult to generate two commands using only one arm movement signals.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134228216","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 : 2017-07-01DOI: 10.1109/HSI.2017.8005042
A. Ebrahimi
This paper describes the methodic for reduction of load peaks in assembly and logistic tasks using powered exoskeletons. The functional principal of the exoskeleton is explained using an industrial upper body assembly show case. The kinematics, drive and control requirements for these kind of wearable robots are discussed and the technical approaches to the interdisciplinary design of the exoskeleton are briefly explained. The Stuttgart Exo-Jacket is an actively powered exoskeleton basically developed to reduce the musculoskeletal injuries of industrial logistics and montage applications with either stabilizing the arm for upper body assembly tasks or force boosting in logistics by empowering the human joints.
{"title":"Stuttgart Exo-Jacket: An exoskeleton for industrial upper body applications","authors":"A. Ebrahimi","doi":"10.1109/HSI.2017.8005042","DOIUrl":"https://doi.org/10.1109/HSI.2017.8005042","url":null,"abstract":"This paper describes the methodic for reduction of load peaks in assembly and logistic tasks using powered exoskeletons. The functional principal of the exoskeleton is explained using an industrial upper body assembly show case. The kinematics, drive and control requirements for these kind of wearable robots are discussed and the technical approaches to the interdisciplinary design of the exoskeleton are briefly explained. The Stuttgart Exo-Jacket is an actively powered exoskeleton basically developed to reduce the musculoskeletal injuries of industrial logistics and montage applications with either stabilizing the arm for upper body assembly tasks or force boosting in logistics by empowering the human joints.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116030829","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 : 2017-07-01DOI: 10.1109/HSI.2017.8005007
Wella, V. U. Tjhin
Learning Management System (LMS) is one of the online learning tool that used by one of private university in Indonesia. The private university began venturing into online learning, which more flexible for users, especially teachers and students. Online learning was implemented to build mutual knowledge, motivation, and communication for the sake of creating a collaborative and efficient learning environment and [1]–[6]. There were many perceptions about the form of effective online learning resources, which create an interesting teaching and learning process that engage and motivate students to learn. Currently, the most effective learning resources for students in online learning is still being debated. The contribution of this research was to discover the pattern of online learning users' behavior in Indonesia, especially students, find the most suitable and motivating learning resource for students, also improving the ease of learning material understanding. The research data was collected quantitatively using 730 students as a sample of the total 3870 students throughout the participants of online program, at one of a private university in Indonesia. Learning resources packaged in this among others: Lecture Note pdf-text, PowerPoints, Videos and Quizzes. In this paper, text-based has been found has a high role in motivating and facilitating for students to understand the material. The students believed both the learning resources have a relevance to the topics that covered in their courses, so that both learning resources become the main source of learning for students. Students regarded videos as additional resources, because it takes longer to understand the material in this type of sources.
{"title":"Exploring effective learning resources affecting student behavior on distance education","authors":"Wella, V. U. Tjhin","doi":"10.1109/HSI.2017.8005007","DOIUrl":"https://doi.org/10.1109/HSI.2017.8005007","url":null,"abstract":"Learning Management System (LMS) is one of the online learning tool that used by one of private university in Indonesia. The private university began venturing into online learning, which more flexible for users, especially teachers and students. Online learning was implemented to build mutual knowledge, motivation, and communication for the sake of creating a collaborative and efficient learning environment and [1]–[6]. There were many perceptions about the form of effective online learning resources, which create an interesting teaching and learning process that engage and motivate students to learn. Currently, the most effective learning resources for students in online learning is still being debated. The contribution of this research was to discover the pattern of online learning users' behavior in Indonesia, especially students, find the most suitable and motivating learning resource for students, also improving the ease of learning material understanding. The research data was collected quantitatively using 730 students as a sample of the total 3870 students throughout the participants of online program, at one of a private university in Indonesia. Learning resources packaged in this among others: Lecture Note pdf-text, PowerPoints, Videos and Quizzes. In this paper, text-based has been found has a high role in motivating and facilitating for students to understand the material. The students believed both the learning resources have a relevance to the topics that covered in their courses, so that both learning resources become the main source of learning for students. Students regarded videos as additional resources, because it takes longer to understand the material in this type of sources.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123196093","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 : 2017-07-01DOI: 10.1109/HSI.2017.8005044
Kashyap Vasudevan, Anjana P. Das, B. Sandhya, P. Subith
For a safety critical task like driving, it is very important for the driver to be vigilant at all times. In this study, we explore a driver drowsiness monitoring and early warning system, which uses machine learning techniques based on vehicle telemetry data. The proposed system can ensure safe driving by real time monitoring of driving pattern. This proves to be a very cost effective technique over biometric and camera based techniques since it doesn't involve expensive sensors. The detection of drowsy state of a driver is modeled as a binary classification issue. We outline the design methodology followed and challenges faced in developing a machine learning based classification scheme on vehicle telemetry data, which is essentially a time-series data. Even though our study is focused on an exemplary application like driver attention monitoring, the results can be equally applied for vehicle prognostics, driving style analytics and various other telematics applications in automotive industry. We have done our entire development and validation on a driver-in-loop simulation platform.
{"title":"Driver drowsiness monitoring by learning vehicle telemetry data","authors":"Kashyap Vasudevan, Anjana P. Das, B. Sandhya, P. Subith","doi":"10.1109/HSI.2017.8005044","DOIUrl":"https://doi.org/10.1109/HSI.2017.8005044","url":null,"abstract":"For a safety critical task like driving, it is very important for the driver to be vigilant at all times. In this study, we explore a driver drowsiness monitoring and early warning system, which uses machine learning techniques based on vehicle telemetry data. The proposed system can ensure safe driving by real time monitoring of driving pattern. This proves to be a very cost effective technique over biometric and camera based techniques since it doesn't involve expensive sensors. The detection of drowsy state of a driver is modeled as a binary classification issue. We outline the design methodology followed and challenges faced in developing a machine learning based classification scheme on vehicle telemetry data, which is essentially a time-series data. Even though our study is focused on an exemplary application like driver attention monitoring, the results can be equally applied for vehicle prognostics, driving style analytics and various other telematics applications in automotive industry. We have done our entire development and validation on a driver-in-loop simulation platform.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121731530","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：