Chanran Kim, Jaehoon Lee, Kanghoon Lee, Jong-Il Park
{"title":"There is only you: Actively diminishing people in a scene","authors":"Chanran Kim, Jaehoon Lee, Kanghoon Lee, Jong-Il Park","doi":"10.23919/ELINFOCOM.2018.8330604","DOIUrl":"https://doi.org/10.23919/ELINFOCOM.2018.8330604","url":null,"abstract":"There are various objects in a scene, and some of them are unwanted. In particular, background photographs and portraits contain photographs of unwanted people. It is also problematic to include unwanted objects in terms of portrait rights, trademark exposure, and copyright protection. It is important to diminish these unwanted objects more naturally than to simply erase or mosaic them. We propose a method to actively detect a person and naturally fill that region. The proposed methods perform diminishing people by combining an object detection method based on deep learning and an exemplar-based image inpainting method. To measure the performance accurately, the object to be removed is synthesized with the image. In addition, we constructed the proposed method partially or in whole by deep learning and compared the results.","PeriodicalId":413646,"journal":{"name":"2018 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"226 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122979434","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}
Yoojeong Seo, Baeksan On, Beomhui Jang, S. Im, Iksu Seo
{"title":"Underwater cylinder recognition using machine learning with DFT-based feature vectors","authors":"Yoojeong Seo, Baeksan On, Beomhui Jang, S. Im, Iksu Seo","doi":"10.23919/ELINFOCOM.2018.8330543","DOIUrl":"https://doi.org/10.23919/ELINFOCOM.2018.8330543","url":null,"abstract":"In detecting an object bottoming at the seabed, the target recognition is an important problem. Previous studies were based on energy detection. In this case, a false detection usually occurs when the clutter energy is larger. In this paper, we try to improve the performance of target recognition using the logistic regression model under a shallow water environment. The goal of this study is to develop a logistic regression model for recognition of a target by training the model using the DFT values of the signal received by the active sonar. The performance of the proposed method is verified through simulation experiments in terms of the target to clutter ratio.","PeriodicalId":413646,"journal":{"name":"2018 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122127580","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":"Power estimation of cryptographic modules using virtual SoC platform","authors":"Sungjae Yoon, Kihyuk Park, Wonjong Kim, H. Cho","doi":"10.23919/ELINFOCOM.2018.8330655","DOIUrl":"https://doi.org/10.23919/ELINFOCOM.2018.8330655","url":null,"abstract":"The power consumption in cryptographic modules depends on hardware and software. The virtual SoC platform is a good candidate for co-designing them together and to estimate performance and power consumption. We proposed the method to estimate power consumption of the cryptographic modules using virtual SoC platform. The power consumption of cryptographic modules depends on the status of each cryptographic module. To minimize the increase in simulation time, we only consider the changes of state registers. The experimental results show that the power estimation of cryptographic modules can be estimated with reasonable error bounding using the proposed method.","PeriodicalId":413646,"journal":{"name":"2018 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126262679","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 power-efficient search line driver for 3T-2R non-volatile ternary content addressable memory with power gating and replica cell","authors":"I. Jung, K. Kwon","doi":"10.23919/ELINFOCOM.2018.8330702","DOIUrl":"https://doi.org/10.23919/ELINFOCOM.2018.8330702","url":null,"abstract":"This paper presents a power efficient search line driver circuit for reducing DC current of 3T-2R non-volatile ternary CAM (nvTCAM) using power gating and replica cell. Although the low resistive non-volatile memory has a short write time, a significant DC current through the resistive cell during the search period limits adoption to nvTCAM application. This DC current can be controlled by power gating circuit and the replica cell that senses the proper triggering point for power gating. This method is proved to save the DC current by 90% at maximum, 24% in average when simulated in 64-bit row array using 180nm CMOS technology.","PeriodicalId":413646,"journal":{"name":"2018 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129683563","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 mobile cloudlet clustering for fog computing","authors":"Yuanjie Li, Nguyen Tung Anh, Azhar Saeed Nooh, Kuwon Ra, Minho Jo","doi":"10.23919/ELINFOCOM.2018.8330676","DOIUrl":"https://doi.org/10.23919/ELINFOCOM.2018.8330676","url":null,"abstract":"Although mobile devices have obtained more and more capabilities such as CPU power, memory, and battery, they still cannot satisfy the requirement of high resource consuming applications. Fog Computing is one of the solutions for offloading the task of a mobile. However the capability of fog server is still limited due to the high deployment cost. In this paper, we propose a dynamic mobile cloudlet cluster policy (DMCCP) to use cloudlets as a supplement for the fog server for offloading. The main idea is that by monitoring each mobile device resource amount, the DMCCP system clusters the optimal cloudlet to meet the requests of different tasks from the local mobile device. In simulation results, we demonstrated that our proposed policy can cluster the approximated optimal cloudlets for different resource demands of a task in a real-time processing time compared to the optimal method.","PeriodicalId":413646,"journal":{"name":"2018 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"800 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116146489","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":"Outage probability of simultaneous wireless information and power transfer in heterogeneous information/energy ad hoc networks","authors":"Jaehyun Park","doi":"10.23919/ELINFOCOM.2018.8330575","DOIUrl":"https://doi.org/10.23919/ELINFOCOM.2018.8330575","url":null,"abstract":"In this paper, we analyze the outage probability (OP) of simultaneous wireless information and power transfer (SWIPT) in heterogeneous ad hoc networks, where an energy ad hoc network and an information ad hoc network coexist and share a common spectrum resource. The receiving nodes with a single antenna are power-limited and therefore, each node either decodes the incoming information data (information decoding, ID) from information access point (IAP) or harvests the RF energy (energy harvesting, EH) from energy access point (EAP) (and possibly, IAP). When EAP and IAP with multiple antennas transmit energy/information signals with different power levels, we analyze the OP in the information/energy perspectives, which gives us a useful insight into the design of heterogeneous SWIPT-based ad hoc networks.","PeriodicalId":413646,"journal":{"name":"2018 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"369 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120878465","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 multiple-mode biquadratic circuit employing only plus type DVCCs","authors":"T. Tsukutani, N. Yabuki","doi":"10.23919/ELINFOCOM.2018.8330705","DOIUrl":"https://doi.org/10.23919/ELINFOCOM.2018.8330705","url":null,"abstract":"This paper introduces a multiple-mode biquadratic circuit employing only plus type differential voltage current conveyors (DVCCs) and grounded passive components. The biquadratic circuit can perform multiple-mode operation selecting the input and output terminals. And the circuit enables low-pass (LP), band-pass (BP), high-pass (HP), band-stop (BS) and all-pass (AP) transfer functions by suitably choosing the input terminals. The circuit parameters ω0 and Q can be tuned orthogonally through adjusting the passive components. The biquadratic circuit enjoys very low sensitivities with respect to the circuit components. The achievement example is given together with simulation results by PSPICE.","PeriodicalId":413646,"journal":{"name":"2018 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127007297","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":"Automatic estimation of distortion coefficient for correcting radial distortion","authors":"Woon Cho, Minjung Lee, Hyungtae Kim, J. Paik","doi":"10.23919/ELINFOCOM.2018.8330606","DOIUrl":"https://doi.org/10.23919/ELINFOCOM.2018.8330606","url":null,"abstract":"This study proposes the facial landmark points based distortion coefficients estimation to overcome the radial distortion. Existing methods estimate the distortion rate using the predefined information, such as design model of lens, pattern information, and prior learning. The extracted scene information based on the proposed method successively correct the distortion in distortion image without predefined information and significantly improves the predefined step of distortion correction method.","PeriodicalId":413646,"journal":{"name":"2018 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132743888","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 buffered clock tree synthesis in multi corner multi mode scenario","authors":"Deokkeun Oh, Juho Kim","doi":"10.23919/ELINFOCOM.2018.8330583","DOIUrl":"https://doi.org/10.23919/ELINFOCOM.2018.8330583","url":null,"abstract":"As CMOS technology continuously scales down, robust clock tree synthesis (CTS) has become increasingly critical in high-performance synchronous chip design. Recently, the process variation during manufacturing affects the performance of the circuit design. In this paper, we proposed fast buffered clock tree synthesis (FBCTS) in multi-corner multi-mode (MCMM) scenario. The ISPD '09 benchmark is used to verify the proposed method. The experiment results show our method reduce about 59% of computation time compared to existing method.","PeriodicalId":413646,"journal":{"name":"2018 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132043109","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":"CMOS transmitter and receiver for spin-torque nano-oscillator based wireless communication","authors":"Hee Sung Lee, Seung Hun Kim, T. Jang, C. Park","doi":"10.23919/ELINFOCOM.2018.8330556","DOIUrl":"https://doi.org/10.23919/ELINFOCOM.2018.8330556","url":null,"abstract":"In this study, wireless transmitter and receiver including high gain amplifiers have been implemented in CMOS circuits for the first time for spin-torque nano-oscillator based wireless communication. The system block diagram is defined, and the power budget is calculated for 1-meter OOK wireless communication. The transmitter consists of STNO, LNA and SPDT switch, the receiver consists of LNA, demodulator and Schmitt trigger, and all are implemented in 0.18 um CMOS. Simulated gain of the LNA in transmitter and receiver are 38.5 dB and 31.0 dB, respectively. The fabricated chip sizes of transmitter and receiver are 2.34 and 4.42 mm2. The transmitter and receiver operate with 18 mW and 21.2 mW power dissipation, respectively. An STNO-based wireless communication will be demonstrated using CMOS circuits in the presentation.","PeriodicalId":413646,"journal":{"name":"2018 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134488116","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}