Pub Date : 2019-02-01DOI: 10.1109/icaiic.2019.8669001
{"title":"ICAIIC 2019 TOC","authors":"","doi":"10.1109/icaiic.2019.8669001","DOIUrl":"https://doi.org/10.1109/icaiic.2019.8669001","url":null,"abstract":"","PeriodicalId":273383,"journal":{"name":"2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129694143","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 : 2019-02-01DOI: 10.1109/ICAIIC.2019.8668993
Takuro Ebuchi, Hiroshi Yamamoto
In recent years, the number of casualties and injuries at intersections and roads has been decreasing due to wide spread of safe driving support systems, but the number of casualties and injuries due to low-speed traffic accidents in parking lots has not decreased. In the parking lot, it is necessary to drive while looking for an empty slot, which may result in contact accidents with pedestrians. Therefore, in this research, we propose a new smart parking system that prevents low-speed contact accidents by estimating availability of slots in the parking lot and the position of pedestrians. The proposed system attempts to estimate positions of user’s smartphones by deploying a small number of beacon devices on the parking lot, and by analyzing the radio wave intensity measured by the smartphones. In addition, estimation accuracy of the position of the pedestrian / driver is evaluated by experimental evaluation in a parking lot. Through the performance evaluation, estimation accuracy of the vehicle’s position to higher than 98%, and estimation accuracy of the pedestrian’s position is about 70%.
{"title":"Vehicle/Pedestrian Localization System Using Multiple Radio Beacons and Machine Learning for Smart Parking","authors":"Takuro Ebuchi, Hiroshi Yamamoto","doi":"10.1109/ICAIIC.2019.8668993","DOIUrl":"https://doi.org/10.1109/ICAIIC.2019.8668993","url":null,"abstract":"In recent years, the number of casualties and injuries at intersections and roads has been decreasing due to wide spread of safe driving support systems, but the number of casualties and injuries due to low-speed traffic accidents in parking lots has not decreased. In the parking lot, it is necessary to drive while looking for an empty slot, which may result in contact accidents with pedestrians. Therefore, in this research, we propose a new smart parking system that prevents low-speed contact accidents by estimating availability of slots in the parking lot and the position of pedestrians. The proposed system attempts to estimate positions of user’s smartphones by deploying a small number of beacon devices on the parking lot, and by analyzing the radio wave intensity measured by the smartphones. In addition, estimation accuracy of the position of the pedestrian / driver is evaluated by experimental evaluation in a parking lot. Through the performance evaluation, estimation accuracy of the vehicle’s position to higher than 98%, and estimation accuracy of the pedestrian’s position is about 70%.","PeriodicalId":273383,"journal":{"name":"2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129316506","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 : 2019-02-01DOI: 10.1109/icaiic.2019.8668994
{"title":"ICAIIC 2019 Venue","authors":"","doi":"10.1109/icaiic.2019.8668994","DOIUrl":"https://doi.org/10.1109/icaiic.2019.8668994","url":null,"abstract":"","PeriodicalId":273383,"journal":{"name":"2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127334812","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 : 2019-02-01DOI: 10.1109/ICAIIC.2019.8669070
Jongbae Kim
In this paper, we propose a method to detect a pedestrian in real time in a low illumination environment and estimate the distance from the camera using a smart phone based thermal camera. Thermal cameras use equipment that can be attached to low-cost smartphones and which use cameras for image processing in real-time. A pedestrian detector is created using a multi-stage cascade learning device to detect pedestrians in a low-illuminated environment, and the pedestrian area is detected using this detector. Then, the distance is estimated by calculating the position of the pedestrian detected in the real-world 3D environment in the 2D thermal image by calculating the parameters detected by the thermal imaging camera in advance. Experimental results show that the detection accuracy of pedestrians is about 91% and the accuracy of distance estimation is 95%. In this way, the proposed method can be applied to the image sensing system in real time in a low-illuminance environment such as nighttime.
{"title":"Pedestrian Detection and Distance Estimation Using Thermal Camera in Night Time","authors":"Jongbae Kim","doi":"10.1109/ICAIIC.2019.8669070","DOIUrl":"https://doi.org/10.1109/ICAIIC.2019.8669070","url":null,"abstract":"In this paper, we propose a method to detect a pedestrian in real time in a low illumination environment and estimate the distance from the camera using a smart phone based thermal camera. Thermal cameras use equipment that can be attached to low-cost smartphones and which use cameras for image processing in real-time. A pedestrian detector is created using a multi-stage cascade learning device to detect pedestrians in a low-illuminated environment, and the pedestrian area is detected using this detector. Then, the distance is estimated by calculating the position of the pedestrian detected in the real-world 3D environment in the 2D thermal image by calculating the parameters detected by the thermal imaging camera in advance. Experimental results show that the detection accuracy of pedestrians is about 91% and the accuracy of distance estimation is 95%. In this way, the proposed method can be applied to the image sensing system in real time in a low-illuminance environment such as nighttime.","PeriodicalId":273383,"journal":{"name":"2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"241 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132951183","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 : 2019-02-01DOI: 10.1109/ICAIIC.2019.8669082
Hyeyoung Park, Kwanyong Lee
Natural gradient learning, which is one of gradient descent learning methods, is known to have ideal convergence properties in the learning of hierarchical machines such as layered neural networks. However, there are a few limitations that degrades its practical usability: necessity of true probability density function of input variables and heavy computational cost due to matrix inversion. Though its adaptive approximation have been developed, it is basically derived for online learning mode, in which a single update is done for a single data sample. Noting that the on-line learning mode is not appropriate for the tasks with huge number of training data, this paper proposes a practical implementation of natural gradient for mini-batch learning mode, which is the most common setting in the real application with large data set. Computational experiments on benchmark datasets shows the efficiency of the proposed methods.
{"title":"Adaptive Natural Gradient Method for Learning Neural Networks with Large Data set in Mini-Batch Mode","authors":"Hyeyoung Park, Kwanyong Lee","doi":"10.1109/ICAIIC.2019.8669082","DOIUrl":"https://doi.org/10.1109/ICAIIC.2019.8669082","url":null,"abstract":"Natural gradient learning, which is one of gradient descent learning methods, is known to have ideal convergence properties in the learning of hierarchical machines such as layered neural networks. However, there are a few limitations that degrades its practical usability: necessity of true probability density function of input variables and heavy computational cost due to matrix inversion. Though its adaptive approximation have been developed, it is basically derived for online learning mode, in which a single update is done for a single data sample. Noting that the on-line learning mode is not appropriate for the tasks with huge number of training data, this paper proposes a practical implementation of natural gradient for mini-batch learning mode, which is the most common setting in the real application with large data set. Computational experiments on benchmark datasets shows the efficiency of the proposed methods.","PeriodicalId":273383,"journal":{"name":"2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121320131","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 : 2019-02-01DOI: 10.1109/ICAIIC.2019.8669071
Kyosuke Shibata, Hiroshi Yamamoto
In recent years, research and development of a people flow observation system is attracting attention in various fields (e.g., city area, shopping district) because the directional information of people flow is very useful for various objective (e.g., navigation, evacuation). However, existing studies of the observation system have mainly been utilizing cameras and image analysis techniques for specifying people flow, but the use of cameras is not preferable in actual fields because of the privacy issues.Therefore, in this study, we propose a new people crowd density observation system for people flow observation. In order to avoid privacy issues, the proposed system dmeasures only signal strength of radio waves of the cellular communication. Furthermore, the measurement results are analyzed by utilizing several machine learning techniques so as to estimate crowd density of many people who have a mobile phone or a smartphone.
{"title":"People Crowd Density Estimation System using Deep Learning for Radio Wave Sensing of Cellular Communication","authors":"Kyosuke Shibata, Hiroshi Yamamoto","doi":"10.1109/ICAIIC.2019.8669071","DOIUrl":"https://doi.org/10.1109/ICAIIC.2019.8669071","url":null,"abstract":"In recent years, research and development of a people flow observation system is attracting attention in various fields (e.g., city area, shopping district) because the directional information of people flow is very useful for various objective (e.g., navigation, evacuation). However, existing studies of the observation system have mainly been utilizing cameras and image analysis techniques for specifying people flow, but the use of cameras is not preferable in actual fields because of the privacy issues.Therefore, in this study, we propose a new people crowd density observation system for people flow observation. In order to avoid privacy issues, the proposed system dmeasures only signal strength of radio waves of the cellular communication. Furthermore, the measurement results are analyzed by utilizing several machine learning techniques so as to estimate crowd density of many people who have a mobile phone or a smartphone.","PeriodicalId":273383,"journal":{"name":"2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116670582","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 : 2019-02-01DOI: 10.1109/ICAIIC.2019.8669018
Changhun Hyun, Hyeyoung Park
Automatic report generation is a technology that automatically generates documents in the form of report by summarizing various materials according to a specific topic in time sequence or subject. Although the main content of the report is text, insertion of appropriate images can improve the completeness of the report. In this paper, we propose an image recommendation method for automatically selecting and inserting appropriate images corresponding to a specific part of a report. In our proposed method, reevaluation of the candidate images is performed based on the semantic similarity between query and the contents of the images. In order to transform semantic information of text query and image into one vector space, we extracted semantic information from image as a set of tags form using deep learning based object detection module. Also, we extracted tags from the given title of the image so that the proposed system can evaluate the candidate images even in the case that the given query includes specific keywords or proper nouns which were not learned by object detection and recognition module in advance. In this paper, we conducted experiments on eight queries related to recent events to verify the applicability of our proposed image recommendation system and evaluate the image selection accuracy.
{"title":"Image Recommendation for Automatic Report Generation using Semantic Similarity","authors":"Changhun Hyun, Hyeyoung Park","doi":"10.1109/ICAIIC.2019.8669018","DOIUrl":"https://doi.org/10.1109/ICAIIC.2019.8669018","url":null,"abstract":"Automatic report generation is a technology that automatically generates documents in the form of report by summarizing various materials according to a specific topic in time sequence or subject. Although the main content of the report is text, insertion of appropriate images can improve the completeness of the report. In this paper, we propose an image recommendation method for automatically selecting and inserting appropriate images corresponding to a specific part of a report. In our proposed method, reevaluation of the candidate images is performed based on the semantic similarity between query and the contents of the images. In order to transform semantic information of text query and image into one vector space, we extracted semantic information from image as a set of tags form using deep learning based object detection module. Also, we extracted tags from the given title of the image so that the proposed system can evaluate the candidate images even in the case that the given query includes specific keywords or proper nouns which were not learned by object detection and recognition module in advance. In this paper, we conducted experiments on eight queries related to recent events to verify the applicability of our proposed image recommendation system and evaluate the image selection accuracy.","PeriodicalId":273383,"journal":{"name":"2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132677326","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 : 2019-02-01DOI: 10.1109/ICAIIC.2019.8668985
M. Sato, Y. Fukuyama
This paper proposes operation planning of energy plants by swarm reinforcement learning in order to realize successful BEMS for small and mid-sized buildings. It usually takes many man-hours to develop an evolutionary computation based program and develop a model considering facility characteristics and so on for an energy management system, while engineering man-hours can be reduced and appropriate operational planning can be expected to be realized by a versatile program of swarm reinforcement learning without consideration of facility characteristics and so on. Moreover, the results of the proposed methods are compared with those of a basic Q learning based method and a basic particle swarm optimization (PSO) based method. It is verified that energy cost can be more reduced by one of the proposed methods (PSO-Q based method) than those by the original Q-learning based method. Since the rates to the whole cost are large in case of small and mid-sized buildings, the proposed swarm reinforcement learning based methods can contribute to successful BEMS for small and mid-sized buildings.
{"title":"Swarm Reinforcement Learning for Operational Planning of Energy Plants for Small and Mid-Sized Building Energy Management Systems","authors":"M. Sato, Y. Fukuyama","doi":"10.1109/ICAIIC.2019.8668985","DOIUrl":"https://doi.org/10.1109/ICAIIC.2019.8668985","url":null,"abstract":"This paper proposes operation planning of energy plants by swarm reinforcement learning in order to realize successful BEMS for small and mid-sized buildings. It usually takes many man-hours to develop an evolutionary computation based program and develop a model considering facility characteristics and so on for an energy management system, while engineering man-hours can be reduced and appropriate operational planning can be expected to be realized by a versatile program of swarm reinforcement learning without consideration of facility characteristics and so on. Moreover, the results of the proposed methods are compared with those of a basic Q learning based method and a basic particle swarm optimization (PSO) based method. It is verified that energy cost can be more reduced by one of the proposed methods (PSO-Q based method) than those by the original Q-learning based method. Since the rates to the whole cost are large in case of small and mid-sized buildings, the proposed swarm reinforcement learning based methods can contribute to successful BEMS for small and mid-sized buildings.","PeriodicalId":273383,"journal":{"name":"2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132280001","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 : 2019-02-01DOI: 10.1109/ICAIIC.2019.8669075
M. Shahjalal, Moh. Khalid Hasan, M. Z. Chowdhury, Y. Jang
Optical camera communication (OCC) refers to the wireless communications between optical sources and cameras (image sensor). Camera image sensors are used to receive data from light emitting diodes. This technology can be implemented in all cameras as well in smartphone as it has the capability of image processing. In this paper we provided some future OCC based indoor and outdoor applications and described their opportunities for 5G and beyond communication systems. Also, we addressed some future works in real-time OCC features.
{"title":"Future Optical Camera Communication Based Applications and Opportunities for 5G and Beyond","authors":"M. Shahjalal, Moh. Khalid Hasan, M. Z. Chowdhury, Y. Jang","doi":"10.1109/ICAIIC.2019.8669075","DOIUrl":"https://doi.org/10.1109/ICAIIC.2019.8669075","url":null,"abstract":"Optical camera communication (OCC) refers to the wireless communications between optical sources and cameras (image sensor). Camera image sensors are used to receive data from light emitting diodes. This technology can be implemented in all cameras as well in smartphone as it has the capability of image processing. In this paper we provided some future OCC based indoor and outdoor applications and described their opportunities for 5G and beyond communication systems. Also, we addressed some future works in real-time OCC features.","PeriodicalId":273383,"journal":{"name":"2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134557911","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 : 2019-02-01DOI: 10.1109/ICAIIC.2019.8668979
Ju-Bong Kim, Do-Hyung Kwon, Yong-Geun Hong, Hyun-kyo Lim, Min Suk Kim, Youn-Hee Han
A rotary inverted pendulum is an unstable and highly nonlinear device and is used as a common model for engineering applications in linear and nonlinear control. In this study, we created a cyber physical system (CPS) to demonstrate that a deep reinforcement learning agent using a rotary inverted pendulum can successfully control a remotely located physical device. The device we created is composed of a cyber environment and physical environment using the Message Queuing Telemetry Transport (MQTT) protocol with an Ethernet connection to connect the cyber environment and the physical environment. The reinforcement learning agent controls the physical device, which is located remotely from the controller and a classical proportional integral derivative (PID) controller is utilized to implement imitation and reinforcement learning and facilitate the learning process. In addition, the control and monitoring system is built on the open source EdgeX platform, so that learning tasks performed near the source of data generation and real-time data emitted from the physical device can be observed while reinforcement learning is performed. From our CPS experimental system, we verify that a deep reinforcement learning agent can control a remotely located real-world device successfully.
{"title":"Deep Q-Network Based Rotary Inverted Pendulum System and Its Monitoring on the EdgeX Platform","authors":"Ju-Bong Kim, Do-Hyung Kwon, Yong-Geun Hong, Hyun-kyo Lim, Min Suk Kim, Youn-Hee Han","doi":"10.1109/ICAIIC.2019.8668979","DOIUrl":"https://doi.org/10.1109/ICAIIC.2019.8668979","url":null,"abstract":"A rotary inverted pendulum is an unstable and highly nonlinear device and is used as a common model for engineering applications in linear and nonlinear control. In this study, we created a cyber physical system (CPS) to demonstrate that a deep reinforcement learning agent using a rotary inverted pendulum can successfully control a remotely located physical device. The device we created is composed of a cyber environment and physical environment using the Message Queuing Telemetry Transport (MQTT) protocol with an Ethernet connection to connect the cyber environment and the physical environment. The reinforcement learning agent controls the physical device, which is located remotely from the controller and a classical proportional integral derivative (PID) controller is utilized to implement imitation and reinforcement learning and facilitate the learning process. In addition, the control and monitoring system is built on the open source EdgeX platform, so that learning tasks performed near the source of data generation and real-time data emitted from the physical device can be observed while reinforcement learning is performed. From our CPS experimental system, we verify that a deep reinforcement learning agent can control a remotely located real-world device successfully.","PeriodicalId":273383,"journal":{"name":"2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129133025","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：