Changgyun Jin, Chanwoo Shin, Hanul Kim, Seong-Eun Kim
{"title":"Multitask Autoencoder-Based Two-Phase Framework Using Multilevel Feature Fusion for EEG Emotion Recognition","authors":"Changgyun Jin, Chanwoo Shin, Hanul Kim, Seong-Eun Kim","doi":"10.1109/ICEIC61013.2024.10457197","DOIUrl":"https://doi.org/10.1109/ICEIC61013.2024.10457197","url":null,"abstract":"Emotion recognition has emerged as a active research area, gaining relevance from advancements in deep learning. This study focuses on using electroencephalogram (EEG) data for emotion recognition and addresses the challenge of subject-dependent variability in EEG-based emotion recognition by proposing a novel architecture that employs multilevel feature fusion and a multitask autoencoder-based two-phase framework. The first phase generates classspecific data, while the second phase uses these for model training. The proposed model was validated using the SEED dataset and demonstrated state-of-the art perforamnce with an accuracy of 99.4 % in a subject-independent setting.","PeriodicalId":518726,"journal":{"name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"308 5","pages":"1-3"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530040","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}
Yuna Sim, S. Sin, Jina Ma, Kyunam Kim, Huaping Liu, Sangmi Moon, Intae Hwang
{"title":"Optimization Algorithm for Physical Layer Security in Multiple Flying RISs-Based Systems","authors":"Yuna Sim, S. Sin, Jina Ma, Kyunam Kim, Huaping Liu, Sangmi Moon, Intae Hwang","doi":"10.1109/ICEIC61013.2024.10457158","DOIUrl":"https://doi.org/10.1109/ICEIC61013.2024.10457158","url":null,"abstract":"Recently, as data demand has increased due to the rapidly increasing demand for wireless devices and the influence of data traffic, various technologies are being developed to support it. Among them, in the case of millimeter wave (mmWave) frequencies with rich spectra and high data transmission rates, there is a problem of large path loss. As a result, there is a growing interest in unmanned aerial vehicle (UAV) and reconfigurable intelligent surfaces (RIS) that can be reconstructed advantageously to communicate wireless communication environments. Therefore, this paper introduces the penalty-based successive convex approximation (SCA) and minorization-maximization (MM) algorithms to optimize transmission beamforming vectors and RIS beamforming vectors in a large system consisting of multiple users, eavesdroppers, and a number of Flying RISs combining UAV and RIS.","PeriodicalId":518726,"journal":{"name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"366 1","pages":"1-3"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530457","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":"Longest Prefix Matching Using Longest-First Search in a Leaf-Pushing Trie","authors":"Jinsol Lee, Hyesook Lim","doi":"10.1109/ICEIC61013.2024.10457170","DOIUrl":"https://doi.org/10.1109/ICEIC61013.2024.10457170","url":null,"abstract":"This paper introduces a new algorithm for IP address lookup, a pivotal task for routers to determine the appropriate output link for each incoming packet. With the advent of classless inter-domain routing (CIDR) scheme, the IP address lookup problem encounters the challenge of efficiently finding the longest matching prefix (LMP) at wire-speed. While off-chip ternary content addressable memories (TCAMs) are commonly employed for this purpose, they have drawbacks, particularly in power consumption and large cost. To address this, our research explores algorithmic alternatives, focusing specifically on utilizing a Bloom filter (BF) stored in an on-chip memory and a hash table stored in an off-chip memory. We propose to perform the longest-first search for the Bloom filter storing every prefix in a leaf-pushing trie. Since prefixes are exclusively located at the leaves of a trie following the leaf-pushing procedure, querying the BF from the longest level of the trie is highly effective. The on-chip BF serves the role of avoiding unnecessary off-chip hash table accesses by producing negative results for non-existing nodes. We have constructed the proposed algorithm using C++ code and tested against real-world routing data from backbone routers. Our results demonstrate that, given a Bloom filter of sufficient size, the proposed algorithm requires only one off-chip hash table access on average for each IP address lookup.","PeriodicalId":518726,"journal":{"name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"362 6","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530479","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":"Artificial Neural Network-Based Compact Model for Circuit Simulation of a 4- Transistor Active Pixel Sensor Including Conversion Gain Prediction","authors":"Yohan Kim, Soyoung Kim","doi":"10.1109/ICEIC61013.2024.10457179","DOIUrl":"https://doi.org/10.1109/ICEIC61013.2024.10457179","url":null,"abstract":"This paper presents an accurate compact model to simulate a 4-transistor active pixel sensor (APS) circuit to investigate the impacts of transistor output resistances and sensing node capacitances. The compact model includes an artificial neural network-based model for the asymmetric APS transistors and an accurate capacitance model at sensing node using 3D-parasitic extraction and compositional analysis. All models are implemented in Verilog-A, and the transient characteristics for reset, integration, and readout operations of CIS are successfully reproduced in the circuit simulation. The simulation results show how the sensing node fluctuation, conversion gain, output swing, and settling time are correlated to the light intensities, parasitic capacitances of layout, and output resistances of APS transistors. This SPICE-compatible compact model provides new insights into APS circuit design and layout optimization for the state-of-the-art CMOS image sensor technologies.","PeriodicalId":518726,"journal":{"name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"13 3-4","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530186","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":"6G Repeaters for Non-Terrestrial Network","authors":"Hoondong Noh, Hyungsik Ju, Junhwan Lee","doi":"10.1109/ICEIC61013.2024.10457257","DOIUrl":"https://doi.org/10.1109/ICEIC61013.2024.10457257","url":null,"abstract":"This paper investigates required features for repeaters to enable robust and stable 6G non-terrestrial networks with various types of transceivers from hand-held user equipment to satellite. In this paper, we show that the 5G repeater cannot fully cover the 6G non-terrestrial network operation scenarios due to its stationary nature, optimized for the legacy terrestrial networks. By introducing new repeater features as suggested in this paper, it is expected that the 6G repeater will provide seamless connectivity as backhauls and fronthauls for NTN in near future.","PeriodicalId":518726,"journal":{"name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"317 2","pages":"1-3"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530217","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}
Chanyeong Park, Seongjun Lee, Hankyul Choi, Donghyun Kim, Yunyoung Jeong, Joonki Paik
{"title":"Enhancing Defense Surveillance: Few-Shot Object Detection with Synthetically Generated Military Data","authors":"Chanyeong Park, Seongjun Lee, Hankyul Choi, Donghyun Kim, Yunyoung Jeong, Joonki Paik","doi":"10.1109/ICEIC61013.2024.10457124","DOIUrl":"https://doi.org/10.1109/ICEIC61013.2024.10457124","url":null,"abstract":"Acquiring military-related data to train object detection algorithms for defense surveillance can be highly challenging due to security restrictions. To overcome this challenge, we utilize a few-shot object detection approach that can identify objects using a limited number of examples, deviating from the standard object detection methods that typically require large datasets for training. To compensate for the limited availability of military data, we employ generative models to create synthetic military datasets. This artificially generated data is then used as a support set to train the few-shot object detection network. We assess our method using a self-created dataset that includes four categories: soldiers, tanks, helicopters, and fighter planes.","PeriodicalId":518726,"journal":{"name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"142 5","pages":"1-2"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530093","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 Review on Integrated RC Frequency References for IoT Applications","authors":"Woojun Choi","doi":"10.1109/ICEIC61013.2024.10457145","DOIUrl":"https://doi.org/10.1109/ICEIC61013.2024.10457145","url":null,"abstract":"This article presents a technical overview of on-chip RC frequency references, which achieve high energy efficiency and high frequency stability required for internet-of-things applications. Among such references, the frequency locked-loop (FLL) based references have achieved state-of-the-art performances. In the FLL, a large loop gain forces the loop to be locked to the time delay of the RC filter. As a result, the FLL output frequency is dominantly determined by the RC time constant without suffering from artifacts of analog front-end circuits. Furthermore, to compensate high temperature sensitivity of the on-chip resistor, digital FLL architectures based on digital temperature compensation are promising recently by extremely improving temperature inaccuracy. Various structures of RC frequency references are compared, and their performances are summarized.","PeriodicalId":518726,"journal":{"name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"382 3","pages":"1-3"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530442","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":"Image Generation of Ultra-Thin Polymer Films Using Diffusion Models from Tensile Testing for Mechanical Failure Prediction","authors":"S. Suh, Haebom Lee, Tae Yeob Kang","doi":"10.1109/ICEIC61013.2024.10457216","DOIUrl":"https://doi.org/10.1109/ICEIC61013.2024.10457216","url":null,"abstract":"The mechanical reliability of ultra-thin polymer films, crucial in microelectronic applications, poses significant challenges. Polymethyl methacrylate (PMMA) is widely utilized in this context, yet conventional methods assessing mechanical reliability are limited in scope, often failing to predict failure accurately. Furthermore, these methods neglect the complex nanoscale physics of polymer films, which may lead to the formation of wrinkles during plastic deformation. In this paper, we present a novel approach that combines diffusion models with measured tensile properties to generate sequential PMMA images, enabling the prediction of mechanical failure in ultra-thin films. The proposed diffusion model not only accurately generates PMMA images from tensile testing but also simulates wrinkle formation, providing a more comprehensive and accurate assessment of PMMA thin film integrity. This research offers a promising avenue for enhancing the mechanical reliability of microelectronic devices.","PeriodicalId":518726,"journal":{"name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"122 3-4","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530375","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":"Design of a Low-Jitter Digitally Controlled Oscillator With Supply Noise Compensation","authors":"Min-Ji Kim, Won-Young Lee","doi":"10.1109/ICEIC61013.2024.10457171","DOIUrl":"https://doi.org/10.1109/ICEIC61013.2024.10457171","url":null,"abstract":"This paper proposes a clock buffer with compensator technology to achieve low-jitter design in the digitally controlled oscillator (DCO). The compensator consists of a PMOS transistor and a MOS capacitor. The compensator that provides the opposite sensitivity to the delay cell is connected to the node between each delay cell. The compensated DCO has a reduced jitter of approximately 12.7-ps (peak-to-peak) based on the 3-GHz output frequency under ±0.1% VDD noise.","PeriodicalId":518726,"journal":{"name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"6 3","pages":"1-3"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530191","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":"Construction of Multi-View Capturing System for Laparotomy","authors":"Ryotaro Takatsuki, Chun Xie, Koichiro Kumano, Daichi Kitazuch, Shinji Hashimoto, Tatsuya Oda, Itaru Kitahara","doi":"10.1109/ICEIC61013.2024.10457148","DOIUrl":"https://doi.org/10.1109/ICEIC61013.2024.10457148","url":null,"abstract":"While surgical videos are crucial for training young surgeons, traditional video capturing methods often suffer from significant occlusions caused by the movements of surgeons' heads and hands. Hence the surgical field, which is important for the transmission of procedural skills, is often invisible in the videos. To solve this problem, this paper proposes a multi-view capturing system formed by a ring-shape camera array. The occlusion can be avoided by shifting the viewpoints between cameras views. We also inducted bullet-time video technology to realize smooth and intuitive camera switching. Clinical experiments in the operating room are conducted to verify the effectiveness of the capturing method against the occlusion problem.","PeriodicalId":518726,"journal":{"name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"319 2","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530215","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}