Thathupara Subramanyan Kavya, Tao Peng, Young-Min Jang, Erdenetuya Tsogtbaatar, Sang-Bock Cho
{"title":"Face Tracking Using Unscented Kalman Filter","authors":"Thathupara Subramanyan Kavya, Tao Peng, Young-Min Jang, Erdenetuya Tsogtbaatar, Sang-Bock Cho","doi":"10.1109/ICEIC49074.2020.9102214","DOIUrl":"https://doi.org/10.1109/ICEIC49074.2020.9102214","url":null,"abstract":"In this paper, we present an efficient vision-based face detection and tracking system. For face detection, we have improved the Viola-Jones algorithm by increasing the number of sample images for training. This improved cascade classifier is performing better than the standard algorithm. In this proposed method, we used the practical implementation of a face tracking system based on a nonlinear filter such as Unscented Kalman Filter (UKF). The experimental results indicate that real-time nonlinear tracking problem can be resolved by using this nonlinear Unscented Kalman Filter. This method is efficient in detecting moving faces and tracks them from a video without any apriori information about the captured scene.","PeriodicalId":271345,"journal":{"name":"2020 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133950187","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}
{"title":"Comparison and Evaluation of Various Lateral Controller for Autonomous Vehicle","authors":"Y. Lee, Byungyong You","doi":"10.1109/ICEIC49074.2020.9051294","DOIUrl":"https://doi.org/10.1109/ICEIC49074.2020.9051294","url":null,"abstract":"This paper is a study on the lateral control of autonomous vehicles. The main purpose is to compare the controller's performance in different environments. We design three controllers (PID, Stanley, Sliding Mode Control) and compare them in seven environments. We show which controllers perform well in each environment. Based on the results of the comparison, we can design an efficient controller for various environments.","PeriodicalId":271345,"journal":{"name":"2020 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132336616","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}
Seyoung Ahn, Teasung Kim, Yongseok Kwon, Sunghyun Cho
{"title":"Packet Aggregation Scheme to Mitigate the Network Congestion in Blockchain Networks","authors":"Seyoung Ahn, Teasung Kim, Yongseok Kwon, Sunghyun Cho","doi":"10.1109/ICEIC49074.2020.9051158","DOIUrl":"https://doi.org/10.1109/ICEIC49074.2020.9051158","url":null,"abstract":"This paper proposes a packet aggregation scheme for reducing a network overload and mitigating bottle-neck in byzantine fault tolerance (BFT) based blockchain network. In a plain blockchain network, the traffic may explosively increase due to the broadcasting packets generated by consensus procedure. The proposed scheme is composed of C-mode and X-mode. The modes can be implemented by customizing the routing policy in software-defined networking (SDN). C-mode concatenates packets into the single packet. X-mode exploits exclusive-or (XOR) operation to combine two packets into one packet. We compare the performance of the proposed scheme with a plain network in terms of traffic volume and processing time to complete the practical BFT. For the performance evaluation, we implement the virtual SDN simulator which shows that the proposed scheme reduces the PBFT processing time by 23% and thus can mitigate network congestion.","PeriodicalId":271345,"journal":{"name":"2020 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115715459","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}
Thi Le Trinh Vuong, Daigeun Lee, J. T. Kwak, Kyungeun Kim
{"title":"Multi-task Deep Learning for Colon Cancer Grading","authors":"Thi Le Trinh Vuong, Daigeun Lee, J. T. Kwak, Kyungeun Kim","doi":"10.1109/ICEIC49074.2020.9051305","DOIUrl":"https://doi.org/10.1109/ICEIC49074.2020.9051305","url":null,"abstract":"Automated cancer grading is an important subject of study in digital pathology. In this paper, we introduce a multi-task learning approach to analyze digitized pathology images. The approach performs both classification and regression tasks in combination with a deep convolutional neural network to predict the tumor grade. Employing tissue microarrays (TMAs) and whole slide images (WSI), the proposed method achieved an accuracy of 85.91% in classifying colon tissues into four distinctive pathology classes, including benign and well differentiated, moderately differentiated, and poorly differentiated tumors.","PeriodicalId":271345,"journal":{"name":"2020 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"288 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115892069","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}
Jorge David Iranzo Bartolomé, Luis Cavazos Quero, Jundong Cho, Sunggi Jo
{"title":"Exploring Thermal Interaction for Visual Art Color Appreciation for the Visually Impaired People","authors":"Jorge David Iranzo Bartolomé, Luis Cavazos Quero, Jundong Cho, Sunggi Jo","doi":"10.1109/ICEIC49074.2020.9051245","DOIUrl":"https://doi.org/10.1109/ICEIC49074.2020.9051245","url":null,"abstract":"Visually impaired people can take much advantage of multimodal systems in which visual information is communicated by several modes whose combined strengths make up for the lack of vision. Among possible interaction modes, thermal interaction applied to assistive devices for the blind is a field which lacks research in spite of its potential. In this paper, a novel temperature-color cross-modal algorithm is designed and applied to the context of tactile artwork exploration by the visually impaired people. Initial interviews and tests were performed after developing a relief model of an artwork and a heating device. The goal is to assess the potential for the cross-modal algorithm and of thermal interaction for blind people in tactile art appreciation.","PeriodicalId":271345,"journal":{"name":"2020 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124350457","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}
{"title":"Color image classification on neuromorphic system using reinforcement learning","authors":"Junhee Park, Sumin Jo, Jungwon Lee, Wookyung Sun","doi":"10.1109/ICEIC49074.2020.9051310","DOIUrl":"https://doi.org/10.1109/ICEIC49074.2020.9051310","url":null,"abstract":"Neuromorphic hardware system has been studied based on binary monochromatic numerical data. In this study, the input to neuromorphic hardware systems uses binary color images rather than monochrome. Color image classification is implemented using reinforcement learning. In addition, the smaller degree of freedom of synaptic weights is experimented to implement a binary neuromorphic hardware system. More complicated color image classification can be developed with this study.","PeriodicalId":271345,"journal":{"name":"2020 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115088152","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}
{"title":"Multi-Stage Unknown Input Filtering of Linear Systems","authors":"C. Hsieh","doi":"10.1109/ICEIC49074.2020.9051095","DOIUrl":"https://doi.org/10.1109/ICEIC49074.2020.9051095","url":null,"abstract":"In the paper, a practical unknown input filtering problem, whether or not the unknown input model is given, is explored. Through the existing various two-stage Kalman filters, a unified two-stage Kalman filter based on the previously proposed optimal two-stage Kalman filter is developed to implement different unknown input estimators. Moreover, a multiple unknown input model-based system transformation is proposed to transform the original system into an augmented state system. Then, a cost-effective multi-stage Kalman filter is developed to implement the augmented state filter within a parameterized unknown input model-based filtering approach, which is suitable for parallel computing. An illustrative example is given to show the effectiveness of the proposed results.","PeriodicalId":271345,"journal":{"name":"2020 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123674680","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}
{"title":"An Energy-Aware Robust MAC Protocol for Prolonging Network Lifetime in Cognitive Radio Sensor Networks","authors":"Subash Luitel, S. Moh","doi":"10.1109/ICEIC49074.2020.9051013","DOIUrl":"https://doi.org/10.1109/ICEIC49074.2020.9051013","url":null,"abstract":"A cognitive radio sensor network (CRSN) is a wireless sensor network (WSN) with cognitive radio capabilities that ensures efficient spectrum management. In general, CRSNs facilitate the combined use of unused licensed frequency spectrum and unlicensed frequency spectrum. Prolonging network lifetime is very important in the design of a medium access control (MAC) protocol in CRSNs because additional energy for spectrum sensing and dynamic spectrum access is required, in comparison to conventional WSNs. In this paper, an energy-aware robust MAC (ER-MAC) protocol for prolonging network lifetime in CRSNs is proposed, in which the network lifetime is increased by reducing collisions and adjusting sensing interval. Furthermore, the number of retransmissions is reduced by utilizing more reliable channels. Simulation results show that the proposed ER-MAC outperforms the conventional protocol in terms of network lifetime.","PeriodicalId":271345,"journal":{"name":"2020 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131060189","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}
{"title":"Dynamic Allocation of Replication and Erasure Codes for Enhancing Storage Efficiency in OpenStack Swift","authors":"Cheong-Jin Ahn, M. Pirahandeh, Deok‐Hwan Kim","doi":"10.1109/ICEIC49074.2020.9051133","DOIUrl":"https://doi.org/10.1109/ICEIC49074.2020.9051133","url":null,"abstract":"The object storage system introduced data redundancy techniques such as replication and erasure codes to build a reliable system. However, replication method has storage efficiency problem with large and less frequently accessed data types, and erase coding method has performance problem with small and frequently accessed data types. In this paper, we propose a dynamic allocation of replication and erasure coding approach (DARE) to improve storage efficiency and performance using access frequency and object size factors. Experimental results show that the proposed DARE can improve storage efficiency by 21 percent compared to the traditional resilient system","PeriodicalId":271345,"journal":{"name":"2020 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125521203","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}
C. Bae, Seung-Sik Shin, Jiteck Jung, Minsu Park, Kibaek Kwon, Jinhyun Kim, T. Jung, Joongho Choi
{"title":"An 11-bit Ring Amplifier Pipeline ADC with Settling-Time Improvement Scheme","authors":"C. Bae, Seung-Sik Shin, Jiteck Jung, Minsu Park, Kibaek Kwon, Jinhyun Kim, T. Jung, Joongho Choi","doi":"10.1109/ICEIC49074.2020.9051188","DOIUrl":"https://doi.org/10.1109/ICEIC49074.2020.9051188","url":null,"abstract":"In this paper, an 11-bit ring amplifier (RAMP) pipeline ADC with settling-time improvement scheme is proposed. A RAMP-based ADC is adopted to achieve the reduced current consumption and hardware area. Novel technique utilizing the highpass filter is incorporated to improve the settling time of the amplifier. Each stage consists of a 1.5-bit multiplying digital-to-analog (MDAC) and flash ADC (FADC) since the unity-gain frequency of RAMP is affected by the load of MDAC. The conventional sample and hold amplifier (SHA) is used instead of RAMP in order to relieve the nonlinear distortion at the first stage. The pipelined ADC is designed in a 65nm CMOS process. For a single supply voltage of 1.2V, total current consumption is 15.5mA. At the sampling rate of 100MS/sec, SNDR and ENOB are 66.83dB and 10.81bits, respectively.","PeriodicalId":271345,"journal":{"name":"2020 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126759147","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}