Homin Eum, Joonsoo Kim, Hong-Chang Shin, Jeongil Seo
{"title":"Super Multi-view Autostereoscopic 3D Representation on Mobile Display","authors":"Homin Eum, Joonsoo Kim, Hong-Chang Shin, Jeongil Seo","doi":"10.1109/ICTC49870.2020.9289433","DOIUrl":"https://doi.org/10.1109/ICTC49870.2020.9289433","url":null,"abstract":"Autostereoscopic displays provide depth cues without glasses or HMD, but have limitations in its implementation. A very large number of viewpoint images must be synthesized and reproduced densely, and the limitation of the viewing zone and the low resolution at the viewpoint must be overcome. In particular, in order to relieve the vergence-accommodation conflict, the interval between viewpoints must be very close, and accordingly, the viewing zone is also narrowed. In this paper, a dense and large number of viewpoints were reproduced through a 10K-class mobile display and the viewing zone was expanded by using the pupil tracking module. In addition, the matching error between the display and the lens was corrected to improve the reproduced image quality.","PeriodicalId":282243,"journal":{"name":"2020 International Conference on Information and Communication Technology Convergence (ICTC)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115612182","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":"A Light-weight stereo matching network for an embedded vision system","authors":"Jo-In Kang, Seong-Won Lee","doi":"10.1109/ICTC49870.2020.9289158","DOIUrl":"https://doi.org/10.1109/ICTC49870.2020.9289158","url":null,"abstract":"In the embedded computer vision field, the stereo vision matching using two cameras can identify the distance of the surrounding environment at low prices. Recently, CNN based artificial intelligence algorithms have been showing good results with high accuracy. However, huge network size and slow computation prevent them used in embedded edge systems. In this paper, a CNN algorithm to use reduced parameters to find a accurate disparity map of stereoscopic images based on Siamese network is proposed. The proposed method performs network training through GPU-based parallel operation and produces better results than the existing one using fewer parameters.","PeriodicalId":282243,"journal":{"name":"2020 International Conference on Information and Communication Technology Convergence (ICTC)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117217185","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}
Shinho Lee, Jungwoon Lee, Wonrak Lee, Seohyun Lee, Suyoung Kim, Eui Tak Kim
{"title":"Design of Integrated Messenger Anti-virus System using Chatbot Service","authors":"Shinho Lee, Jungwoon Lee, Wonrak Lee, Seohyun Lee, Suyoung Kim, Eui Tak Kim","doi":"10.1109/ICTC49870.2020.9289514","DOIUrl":"https://doi.org/10.1109/ICTC49870.2020.9289514","url":null,"abstract":"Today, people use various types of messengers having each own function regardless of PC or Mobile, and the number of messenger users is more and more increasing. Like this, as the number of messenger users increased, malware attacks targeting messenger has been increasing. In this paper, we propose the Integrated Messenger Anti-virus System (IMAS) that utilizes chatbot service to predictively detect malware attacks targeting at a messenger. The IMAS integrates various messenger’s chatbot into a single form of Adapter so that it can support any messengers and contains multi anti-virus scanner in charge of detection of malware, so users can check detection results in real-time. Also, we implement a real environment based on the proposed design and present the result of detecting suspected malware by using various messenger chatbots.","PeriodicalId":282243,"journal":{"name":"2020 International Conference on Information and Communication Technology Convergence (ICTC)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117235017","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}
Eunjung Kwon, Won-Jae Shin, Hyunho Park, Sungwon Byon, Eui-Suk Jung, Yong-Tae Lee, Kyu-Chul Lee
{"title":"A Moving Pattern Classification Based on Multimodal Data for Public Safety Services","authors":"Eunjung Kwon, Won-Jae Shin, Hyunho Park, Sungwon Byon, Eui-Suk Jung, Yong-Tae Lee, Kyu-Chul Lee","doi":"10.1109/ICTC49870.2020.9289365","DOIUrl":"https://doi.org/10.1109/ICTC49870.2020.9289365","url":null,"abstract":"the location based services using logged data of having people's moving traces and activity patterns has been used in the real world today. While a number of models for predicting the next visiting position information by users or the class labels of moving objects has been rapidly adopted in service areas such as traffic management, public safety in order to maximize their requirements, There is the difficulty of developing feature compositions with low-dimensional and heterogeneous feature space. To address these issues, this paper proposes a movement classification model that can classify people’s movement paths according to their point of interests that is predicted by our proposed method.","PeriodicalId":282243,"journal":{"name":"2020 International Conference on Information and Communication Technology Convergence (ICTC)","volume":"251 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117284786","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":"Fast Initial Access Technique for Millimeter-Wave Systems Using Retrodirective Arrays","authors":"Yeong-Jun Kim, Hyun Jun Lee, Y. Cho","doi":"10.1109/ICTC49870.2020.9289396","DOIUrl":"https://doi.org/10.1109/ICTC49870.2020.9289396","url":null,"abstract":"The beam alignment procedure in mmWave systems requires a significant overhead because it increases proportional to the product of the number of transmitting beams and number of receiving beams. In this paper, we propose an initial access technique that can significantly reduce the beam training overhead in mmWave cellular systems, using retrodirective array (RDA). A preamble sequence is designed to identify the base station (BS), mobile station (MS) and beams simultaneously transmitted from the BS, using the Zadoff–Chu sequence. The ambiguity condition is derived so that we can identify the ID of BS, MS and beams for beam alignment. Simulation results show that the proposed technique can correctly detect the parameters for beam alignment in mmWave cellular systems.","PeriodicalId":282243,"journal":{"name":"2020 International Conference on Information and Communication Technology Convergence (ICTC)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127267306","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}
Jiyeon Kim, Ik-Hee Shin, Jong-Ryul Lee, Yong-Ju Lee
{"title":"Where to Cut and Paste: Data Regularization with Selective Features","authors":"Jiyeon Kim, Ik-Hee Shin, Jong-Ryul Lee, Yong-Ju Lee","doi":"10.1109/ICTC49870.2020.9289404","DOIUrl":"https://doi.org/10.1109/ICTC49870.2020.9289404","url":null,"abstract":"Deep convolutional neural networks are continually evolving through various effective training methods such as data augmentation. Among data augmentation methods, regional dropout or replacement strategies such as [3], [4], [5] have been proved effective in recognition and localization performance. However, such methods suffer from unintended content corruption like informative pixel loss. For example, cutting and pasting a random patch may consist of areas that are not important and even if a new cutout patch consists of informative pixels, it could be pasted at useful locations of input covering the interest of the object. Therefore, this operation can cause too much or meaningless regularization. Motivated by this, we propose a new data augmentation method strategy, called FocusMix, which exploits informative pixels based on proper sampling techniques. Through experiments, we analyzed and compared various data augmentation methods to provide improvements and effectiveness of FocusMix. Finally, we have shown that FocusMix results in improvements in performance compared to other data augmentation methods.","PeriodicalId":282243,"journal":{"name":"2020 International Conference on Information and Communication Technology Convergence (ICTC)","volume":"153 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127305536","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}
Kyounghyun Park, Min Jung Kim, Jungsook Kim, O. Kwon, Daesub Yoon, Hyunsuk Kim
{"title":"Requirements and Design of Mental Health System for Stress Management of Knowledge Workers","authors":"Kyounghyun Park, Min Jung Kim, Jungsook Kim, O. Kwon, Daesub Yoon, Hyunsuk Kim","doi":"10.1109/ICTC49870.2020.9289464","DOIUrl":"https://doi.org/10.1109/ICTC49870.2020.9289464","url":null,"abstract":"Knowledge workers are a group of people suffering from chronic stress. Stress at the workplace has been further increasing due to the recent deterioration of the domestic economic situation. For this reason, we need efforts and methods to relieve stress. In this paper, we describe how to efficiently manage the stress of knowledge workers at work and introduce the mental health management system, especially determining whether they are stressed or not and recommending stress-relief solutions optimized for individuals by collecting and analyzing physiological sensor data and other types of data such as environmental data and task data.","PeriodicalId":282243,"journal":{"name":"2020 International Conference on Information and Communication Technology Convergence (ICTC)","volume":"2882 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127449866","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":"Vehicle Synchronization Signal for NR-based C-V2X Systems","authors":"Yeong-Jun Kim, Jimin Lee, Y. Cho","doi":"10.1109/ICTC49870.2020.9289511","DOIUrl":"https://doi.org/10.1109/ICTC49870.2020.9289511","url":null,"abstract":"A vehicle synchronization signal design technique for millimeter-wave cellular vehicle-to-everything (C-V2X) communications is proposed. The proposed vehicle synchronization signal generated using a generalized reciprocal sequence of m-sequence is shown to have desirable properties for orthogonal frequency division multiplexing (OFDM)-based C-V2X, particularly for vehicle-to-vehicle (V2V) synchronization. It is shown that the detection probabilities of synchronization signals in C-V2X are not degraded when base stations and vehicles coexist, and the computational complexity can be significantly reduced with the proposed vehicle synchronization signal.","PeriodicalId":282243,"journal":{"name":"2020 International Conference on Information and Communication Technology Convergence (ICTC)","volume":"6 10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124806848","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":"Audio Watermarking System Robust to Offset Distortion in Acoustic Channel Transmission","authors":"Seungkwon Beack, Taejin Lee","doi":"10.1109/ICTC49870.2020.9289353","DOIUrl":"https://doi.org/10.1109/ICTC49870.2020.9289353","url":null,"abstract":"Audio watermarking is a technology for enriching multimedia services by hiding and delivering useful information in an audio signal. To extend its potential, audio watermarking has recently been applied to short-range communication between a speaker and microphone for easy accessibility to enriched data in a second portable device. Although many challengeable difficulties are expected to occur under such a scenario, the most important aspect is achieving robust synchronization by overcoming offset distortion in the time and frequency domains. In this paper, a polarized sequence-based audio watermarking system in the DFT domain is proposed. The main strength of this work is providing reliable synchronization that is robust to any distortion for time and frequency offset in an acoustic channel. Moreover, based on the results of an evaluation, performance aspects such as the synchronization under acoustic channel distortion, and preservation of the sound quality, were confirmed.","PeriodicalId":282243,"journal":{"name":"2020 International Conference on Information and Communication Technology Convergence (ICTC)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125827322","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":"Localization of Internet of Things Network via Deep Neural Network Based Matrix Completion","authors":"Sunwoo Kim, B. Shim","doi":"10.1109/ICTC49870.2020.9289280","DOIUrl":"https://doi.org/10.1109/ICTC49870.2020.9289280","url":null,"abstract":"In this paper, we propose a technique to acquire the sensor map of Internet of Things (IoT) network. Our approach consists of two main steps to reconstruct the Euclidean distance matrix. First, we recast Euclidean distance matrix completion problem into the alternating minimization problem. We next employ a cascade of multiple deep neural networks to recover the location map of sensors (and the original distance matrix) from the noisy observed matrix. From the numerical experiments, we demonstrate that the proposed method can achieve an accurate reconstruction performance of the distance matrix with much smaller measurement required by conventional approaches and also outperforms state-of-the-art matrix completion algorithms both in noisy and noiseless scenarios.","PeriodicalId":282243,"journal":{"name":"2020 International Conference on Information and Communication Technology Convergence (ICTC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126170657","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}