Recently, the demand for unmanned stores has increased year by year, and how to calculate the number of people entering and leaving the unmanned stores is increasingly important. In this paper, a sensor floor based on a push button switch array is proposed. The sensor floor periodically transmits floor information to a cloud database for analysis as well as transmits the analysis result to the manager's smart device. In this way, managers can get the results of instant flow control in unmanned stores. If this sensor floor is built into the entire store, more information (such as hotspot analysis) will be available, which will protect personal privacy more than existing camera image analysis.
{"title":"The Flow Control in Unmanned Stores with Sensing Floor","authors":"Hsin-Yu Huang, Yong-Yi Fanjiang, Chi-Huang Hung, Wen‐Chin Tsen","doi":"10.1109/GCCE46687.2019.9015364","DOIUrl":"https://doi.org/10.1109/GCCE46687.2019.9015364","url":null,"abstract":"Recently, the demand for unmanned stores has increased year by year, and how to calculate the number of people entering and leaving the unmanned stores is increasingly important. In this paper, a sensor floor based on a push button switch array is proposed. The sensor floor periodically transmits floor information to a cloud database for analysis as well as transmits the analysis result to the manager's smart device. In this way, managers can get the results of instant flow control in unmanned stores. If this sensor floor is built into the entire store, more information (such as hotspot analysis) will be available, which will protect personal privacy more than existing camera image analysis.","PeriodicalId":303502,"journal":{"name":"2019 IEEE 8th Global Conference on Consumer Electronics (GCCE)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115376529","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 : 2019-10-01DOI: 10.1109/GCCE46687.2019.9015241
Jun'ichi Murakami, Ikuhisa Mitsugami
This paper proposes a VR system that efficiently collects data of gaze behaviors and head motions required for modeling of the eye-head coordination. It consists of a 6-DoF type VR goggle, controllers, and eye trackers attachable to the goggle. This system makes it possible to collect data containing many natural gaze behaviors by imposing the spot-the-difference trials in various VR scenes on a user. Besides, we construct the eye-head coordination model by applying the existing modeling method to the collected data and evaluated the performance of the model.
{"title":"VR-based Eye and Head Motion Collection for Modeling Their Coordination","authors":"Jun'ichi Murakami, Ikuhisa Mitsugami","doi":"10.1109/GCCE46687.2019.9015241","DOIUrl":"https://doi.org/10.1109/GCCE46687.2019.9015241","url":null,"abstract":"This paper proposes a VR system that efficiently collects data of gaze behaviors and head motions required for modeling of the eye-head coordination. It consists of a 6-DoF type VR goggle, controllers, and eye trackers attachable to the goggle. This system makes it possible to collect data containing many natural gaze behaviors by imposing the spot-the-difference trials in various VR scenes on a user. Besides, we construct the eye-head coordination model by applying the existing modeling method to the collected data and evaluated the performance of the model.","PeriodicalId":303502,"journal":{"name":"2019 IEEE 8th Global Conference on Consumer Electronics (GCCE)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115565226","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 : 2019-10-01DOI: 10.1109/GCCE46687.2019.9015338
Hiroshi Takeda, Soh Yoshida, M. Muneyasu
High-quality tags play an important role in many applications such as multimedia information retrieval. This paper proposes a social tag relevance learning method using a data-driven approach to improving tag-based video retrieval performance. The tag relevance means how a tag is relevant to multimedia content. To learn the tag relevance, we apply a well-known tag neighbor voting algorithm, which accumulates votes from visual neighbors. However, an imbalance in the number of tags among the datasets causes a loss in the accuracy of tag voting. Therefore, in the proposed method, we examine a formula for calculating the tag relevance score considering the tag occurrence frequency imbalance. We conduct experiments on the YouTube-8M dataset, and the results show that our approach is effective and efficient.
{"title":"Tag-based Video Retrieval with Social Tag Relevance Learning","authors":"Hiroshi Takeda, Soh Yoshida, M. Muneyasu","doi":"10.1109/GCCE46687.2019.9015338","DOIUrl":"https://doi.org/10.1109/GCCE46687.2019.9015338","url":null,"abstract":"High-quality tags play an important role in many applications such as multimedia information retrieval. This paper proposes a social tag relevance learning method using a data-driven approach to improving tag-based video retrieval performance. The tag relevance means how a tag is relevant to multimedia content. To learn the tag relevance, we apply a well-known tag neighbor voting algorithm, which accumulates votes from visual neighbors. However, an imbalance in the number of tags among the datasets causes a loss in the accuracy of tag voting. Therefore, in the proposed method, we examine a formula for calculating the tag relevance score considering the tag occurrence frequency imbalance. We conduct experiments on the YouTube-8M dataset, and the results show that our approach is effective and efficient.","PeriodicalId":303502,"journal":{"name":"2019 IEEE 8th Global Conference on Consumer Electronics (GCCE)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114510501","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 : 2019-10-01DOI: 10.1109/GCCE46687.2019.9015426
Yue Hu, Haotong Cao, Shengchen Wu, Feng Tian, Longxiang Yang
In virtualization environment, the resource allocation issue is called as virtual network embedding(VNE). In the literature, prior VNE algorithms adopt ‘one fits all’ manner to serve all different VN services, requested by users. However, different VN services usually have different resource and QoS demands in the virtualization environment. Hence, it is essential to research the service oriented VNE algorithm in order to achieve the efficient resource allocation. On this basis, we study the service oriented resource allocation problem. In addition, preliminary results are illustrated in this paper.
{"title":"A Study on Service Oriented Resource Allocation in Virtualization Environment","authors":"Yue Hu, Haotong Cao, Shengchen Wu, Feng Tian, Longxiang Yang","doi":"10.1109/GCCE46687.2019.9015426","DOIUrl":"https://doi.org/10.1109/GCCE46687.2019.9015426","url":null,"abstract":"In virtualization environment, the resource allocation issue is called as virtual network embedding(VNE). In the literature, prior VNE algorithms adopt ‘one fits all’ manner to serve all different VN services, requested by users. However, different VN services usually have different resource and QoS demands in the virtualization environment. Hence, it is essential to research the service oriented VNE algorithm in order to achieve the efficient resource allocation. On this basis, we study the service oriented resource allocation problem. In addition, preliminary results are illustrated in this paper.","PeriodicalId":303502,"journal":{"name":"2019 IEEE 8th Global Conference on Consumer Electronics (GCCE)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116739415","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 : 2019-10-01DOI: 10.1109/GCCE46687.2019.9015592
Toshinori Sato, Tomoaki Ukezono
This paper proposes a technique that increases the lifetime of consumer electronics devices. As semiconductor technology improves in miniaturizing transistors, aging effect due to Bias Temperature Instability (BTI) has serious impact on their lifetime. BTI increases the threshold voltage of transistors and thus the delay of an electronics device also increases, resulting in failures due to timing violations. To compensate for aging-induced timing violations, this paper exploits configurable approximate computing. Assuming that target circuits have an exact and an approximate modes, they are configured to the approximate mode if an aging sensor predicts the violations. The estimation on an example circuit shows its lifetime is increased to over ten years without any additional power consumption.
{"title":"Tolerating Aging-Induced Timing Violations Via Configurable Approximations","authors":"Toshinori Sato, Tomoaki Ukezono","doi":"10.1109/GCCE46687.2019.9015592","DOIUrl":"https://doi.org/10.1109/GCCE46687.2019.9015592","url":null,"abstract":"This paper proposes a technique that increases the lifetime of consumer electronics devices. As semiconductor technology improves in miniaturizing transistors, aging effect due to Bias Temperature Instability (BTI) has serious impact on their lifetime. BTI increases the threshold voltage of transistors and thus the delay of an electronics device also increases, resulting in failures due to timing violations. To compensate for aging-induced timing violations, this paper exploits configurable approximate computing. Assuming that target circuits have an exact and an approximate modes, they are configured to the approximate mode if an aging sensor predicts the violations. The estimation on an example circuit shows its lifetime is increased to over ten years without any additional power consumption.","PeriodicalId":303502,"journal":{"name":"2019 IEEE 8th Global Conference on Consumer Electronics (GCCE)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116281597","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 : 2019-10-01DOI: 10.1109/GCCE46687.2019.9015602
Osamu Watanabe, D. Taubman
The High Throughput JPEG 2000 (HTJ2K) is the new part of JPEG 2000 family of standards and it is currently at FDIS status within ISO/IEC JTC 1/SC 29/WG 1 (JPEG). In this paper, an implementation with MATLAB is introduced. The MATLAB implementation is not only a good prototype of an actual product but an option for easy understanding of the new block-coding algorithm adopted in the HTJ2K standard. The experimental results demonstrate the encoding/decoding speed of the HTJ2K is significantly faster than that of the conventional JPEG 2000 Part 1.
{"title":"A Matlab Implementation of the Emerging HTJ2K Standard","authors":"Osamu Watanabe, D. Taubman","doi":"10.1109/GCCE46687.2019.9015602","DOIUrl":"https://doi.org/10.1109/GCCE46687.2019.9015602","url":null,"abstract":"The High Throughput JPEG 2000 (HTJ2K) is the new part of JPEG 2000 family of standards and it is currently at FDIS status within ISO/IEC JTC 1/SC 29/WG 1 (JPEG). In this paper, an implementation with MATLAB is introduced. The MATLAB implementation is not only a good prototype of an actual product but an option for easy understanding of the new block-coding algorithm adopted in the HTJ2K standard. The experimental results demonstrate the encoding/decoding speed of the HTJ2K is significantly faster than that of the conventional JPEG 2000 Part 1.","PeriodicalId":303502,"journal":{"name":"2019 IEEE 8th Global Conference on Consumer Electronics (GCCE)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115302395","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 : 2019-10-01DOI: 10.1109/GCCE46687.2019.9015395
Fengyu Li, Yasuhiro Akiyama, Xianglong Wan, Yoji Yamada, S. Okamoto
Currently, it becomes more important to anticipate the intention of the user who touches the product. However, in case of the soft material, the internal deformation and stress distribution, which is the information of the way of touch, are hard to be estimated nor observed using current interactive shear force sensors except for limited situations. In this study, we developed a sensor system, which is embedded in the soft material and measures shear deformation and stress distribution inside of soft material. The validity of this sensor system, which consists of the array of piezoelectric sensors of Polyvinylidene fluoride (PVDF), was tested by measuring the stress distribution of an artificial human skin.
{"title":"Shear Stress Sensor for Soft Material with Built-In Piezoelectric Polymer Films","authors":"Fengyu Li, Yasuhiro Akiyama, Xianglong Wan, Yoji Yamada, S. Okamoto","doi":"10.1109/GCCE46687.2019.9015395","DOIUrl":"https://doi.org/10.1109/GCCE46687.2019.9015395","url":null,"abstract":"Currently, it becomes more important to anticipate the intention of the user who touches the product. However, in case of the soft material, the internal deformation and stress distribution, which is the information of the way of touch, are hard to be estimated nor observed using current interactive shear force sensors except for limited situations. In this study, we developed a sensor system, which is embedded in the soft material and measures shear deformation and stress distribution inside of soft material. The validity of this sensor system, which consists of the array of piezoelectric sensors of Polyvinylidene fluoride (PVDF), was tested by measuring the stress distribution of an artificial human skin.","PeriodicalId":303502,"journal":{"name":"2019 IEEE 8th Global Conference on Consumer Electronics (GCCE)","volume":"209 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122794092","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 : 2019-10-01DOI: 10.1109/GCCE46687.2019.9015332
Tomonori Tanaka, M. Ohta
Orthogonal precoding (OP) is a preceding scheme for the out-of-band emission (OOBE) reduction of orthogonal frequency division multiplexing (OFDM) signals. It can shape a spectrum with deep notches at desired frequencies, while OOBE outside the frequencies are not reduced sufficiently. To improve the conventional OP, this paper proposes a hybrid method for OOBE reduction. Numerical experiments show that the proposed method can sufficiently reduce the OOBE.
{"title":"Hybrid Method for Out-of-Band Emission Reduction of OFDM Signal","authors":"Tomonori Tanaka, M. Ohta","doi":"10.1109/GCCE46687.2019.9015332","DOIUrl":"https://doi.org/10.1109/GCCE46687.2019.9015332","url":null,"abstract":"Orthogonal precoding (OP) is a preceding scheme for the out-of-band emission (OOBE) reduction of orthogonal frequency division multiplexing (OFDM) signals. It can shape a spectrum with deep notches at desired frequencies, while OOBE outside the frequencies are not reduced sufficiently. To improve the conventional OP, this paper proposes a hybrid method for OOBE reduction. Numerical experiments show that the proposed method can sufficiently reduce the OOBE.","PeriodicalId":303502,"journal":{"name":"2019 IEEE 8th Global Conference on Consumer Electronics (GCCE)","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122853593","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}
This paper introduces a pavement distress detection framework based on a devised deep convolutional neural network for improving the automatic driving safety on intelligent vehicles. In contrast to the conventional detection methods by utilizing multiple sensors, the proposed framework directly profiles the features of road conditions from the incoming road images as the perspective maps. Experiment results demonstrate that the proposed framework achieves superior representation of pavement distress with higher accuracy than that made by the baseline convolutional neural network.
{"title":"Towards Perspective-Free Pavement Distress Detection via Deep Learning","authors":"Jia-Li Yin, Tzu-Hsuan Peng, Jo-Lan Kuan, Bo-Hao Chen","doi":"10.1109/GCCE46687.2019.9015591","DOIUrl":"https://doi.org/10.1109/GCCE46687.2019.9015591","url":null,"abstract":"This paper introduces a pavement distress detection framework based on a devised deep convolutional neural network for improving the automatic driving safety on intelligent vehicles. In contrast to the conventional detection methods by utilizing multiple sensors, the proposed framework directly profiles the features of road conditions from the incoming road images as the perspective maps. Experiment results demonstrate that the proposed framework achieves superior representation of pavement distress with higher accuracy than that made by the baseline convolutional neural network.","PeriodicalId":303502,"journal":{"name":"2019 IEEE 8th Global Conference on Consumer Electronics (GCCE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124185950","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 : 2019-10-01DOI: 10.1109/GCCE46687.2019.9015220
Naoki Kobayashi, Hiroki Kiyozumi, Taichi Ezaki, Keitaro Ohba, M. Ishikawa
For monitoring vital data in telecare systems, performing noncontact plethysmography measurement is important. We herein propose a precise plethysmography measurement method using multispectral video and investigate optimized process conditions for that measurement. Using independent component analysis of combination signals of RGB videos and 900-nm nIR video yields a better reproduction of plethysmography than other combinations. Concerning region-of-interest selection, using a region of high nIR signal area is favorable for plethysmography estimation. With these optimizing conditions, we attempt obtaining more precise measurements of vital data using multispectral video.
{"title":"Optimized Process Conditions for Plethysmography Measurement using Multispectral Video","authors":"Naoki Kobayashi, Hiroki Kiyozumi, Taichi Ezaki, Keitaro Ohba, M. Ishikawa","doi":"10.1109/GCCE46687.2019.9015220","DOIUrl":"https://doi.org/10.1109/GCCE46687.2019.9015220","url":null,"abstract":"For monitoring vital data in telecare systems, performing noncontact plethysmography measurement is important. We herein propose a precise plethysmography measurement method using multispectral video and investigate optimized process conditions for that measurement. Using independent component analysis of combination signals of RGB videos and 900-nm nIR video yields a better reproduction of plethysmography than other combinations. Concerning region-of-interest selection, using a region of high nIR signal area is favorable for plethysmography estimation. With these optimizing conditions, we attempt obtaining more precise measurements of vital data using multispectral video.","PeriodicalId":303502,"journal":{"name":"2019 IEEE 8th Global Conference on Consumer Electronics (GCCE)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126441624","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：