2023 International Conference on Electronics, Information, and Communication (ICEIC)最新文献_第5页

Hardware Design of Intrusion Detection System for Automotive CAN Bus Using Random Forest 基于随机森林的汽车CAN总线入侵检测系统硬件设计

2023 International Conference on Electronics, Information, and Communication (ICEIC) Pub Date : 2023-02-05 DOI: 10.1109/ICEIC57457.2023.10049883

Daegi Lee, C. Han, Seongsoo Lee

引用次数: 0

EyeRis: Visual Image Recognition using Machine Learning for the Visually-Impaired eyeis:为视障人士使用机器学习进行视觉图像识别

2023 International Conference on Electronics, Information, and Communication (ICEIC) Pub Date : 2023-02-05 DOI: 10.1109/ICEIC57457.2023.10049927

Alliah May Eugenio, Marian Jowie Patulot, Lykha Jane Seguiro, Angelica Nicole Tuazon, Shekinah Lor B. Huyo-a, Mideth B. Abisado, G. Sampedro

{"title":"EyeRis: Visual Image Recognition using Machine Learning for the Visually-Impaired","authors":"Alliah May Eugenio, Marian Jowie Patulot, Lykha Jane Seguiro, Angelica Nicole Tuazon, Shekinah Lor B. Huyo-a, Mideth B. Abisado, G. Sampedro","doi":"10.1109/ICEIC57457.2023.10049927","DOIUrl":"https://doi.org/10.1109/ICEIC57457.2023.10049927","url":null,"abstract":"Visually impaired people struggle daily and have difficulty recognizing and distinguishing objects around them. Thus, they mainly depend on supervision from other people to assist them. Since smartphones have become a necessity in this modern world, the researchers formulated a solution to help the visually impaired through a machine learning-based mobile application for object recognition. Nowadays, software applications can provide accurate findings in picture classification and processing processes thanks to machine learning techniques and algorithms. In this study, the researchers use a convolutional neural network (CNN)-based system on TensorFlow Lite to create a mobile version of a visual information system employing a machine learning strategy and deep learning framework. The main objectives of the smartphone application, EyeRis, is to recognize and categorize items in real-time and to separate photographs from the user-selected scenarios. Results were analyzed and contrasted based on the app’s obtained recognition accuracy data. It demonstrated the utility of CNN as a model for image recognition algorithms.","PeriodicalId":373752,"journal":{"name":"2023 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122852432","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}

引用次数: 0

Image Stitching Method for Surround View Image without Seamline 无缝线的环绕视图图像拼接方法

2023 International Conference on Electronics, Information, and Communication (ICEIC) Pub Date : 2023-02-05 DOI: 10.1109/ICEIC57457.2023.10049955

Jin-Hyuk Choi, Heunseung Lim, Sang-Suk Yun, Minwoo Shin, J. Paik

{"title":"Image Stitching Method for Surround View Image without Seamline","authors":"Jin-Hyuk Choi, Heunseung Lim, Sang-Suk Yun, Minwoo Shin, J. Paik","doi":"10.1109/ICEIC57457.2023.10049955","DOIUrl":"https://doi.org/10.1109/ICEIC57457.2023.10049955","url":null,"abstract":"The surround view system delivers the surrounding environment to the driver in a top-down manner so that the driver can recognize blind spots. In this system, image stitching is combining camera images facing different directions into a single image. As an easy-to-access method, there is a method of warping through homography by extracting and matching the features of the images to be stitched. However, this method has a limitation in that stitching is not performed properly if the geometric distortion is severe. In order to solve this problem, a method of estimating a seam and stitching images is being studied in many existing methods, and a representative method is a method using a distance matrix using the difference of gradient components. However, this method has a problem of falling into the local minima and causing a loop phenomenon. To solve this problem, we propose a seamline estimation method using ℓ0-norm based gradient priors. The optimal seam can be found by obtaining the energy matrix through ℓ0-gradient priors and estimating the distance matrix through this. In this method, improved seam estimation is possible because the shortest distance is calculated as the point where the rate of change between the two images is minimized.","PeriodicalId":373752,"journal":{"name":"2023 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123923287","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}

引用次数: 0

Hardware-Based Isolation Technique to Guarantee Availability of Security Controls in a Gateway for Industrial Networks 基于硬件的隔离技术保证工业网络网关安全控制的可用性

2023 International Conference on Electronics, Information, and Communication (ICEIC) Pub Date : 2023-02-05 DOI: 10.1109/ICEIC57457.2023.10049871

Hojin Choi, Hyuk Kwon, Junghee Lee, Yonghee Lee, Kijoong Kim

引用次数: 0

Chiplet Heterogeneous-Integration AI Processor 芯片异构集成AI处理器

2023 International Conference on Electronics, Information, and Communication (ICEIC) Pub Date : 2023-02-05 DOI: 10.1109/ICEIC57457.2023.10049867

Youngsu Kwon, Jinho Han, Yongcheol Peter Cho, Juyeob Kim, Jaehoon Chung, Jaewoong Choi, Sujin Park, Igyeong Kim, Hyunjeong Kwon, Jinkyu Kim, Hyun-Mi Kim, Won Jeon, Youngdeuk Jeon, Minhyung Cho, Minseok Choi

{"title":"Chiplet Heterogeneous-Integration AI Processor","authors":"Youngsu Kwon, Jinho Han, Yongcheol Peter Cho, Juyeob Kim, Jaehoon Chung, Jaewoong Choi, Sujin Park, Igyeong Kim, Hyunjeong Kwon, Jinkyu Kim, Hyun-Mi Kim, Won Jeon, Youngdeuk Jeon, Minhyung Cho, Minseok Choi","doi":"10.1109/ICEIC57457.2023.10049867","DOIUrl":"https://doi.org/10.1109/ICEIC57457.2023.10049867","url":null,"abstract":"The scale of neural networks for Artificial Intelligence is ever increasing to achieve human-level intelligence. The era of data explosion computing is evolving with the advent of the huge AI network operating on huge amount of data including parameters, images, sentences, and etc. Designing AI processor which is the computational foundation of the data explosion computing is facing physical limitation of semiconductors as well as skyrocketing cost. The chiplet processor integrating multiple dies into a single chip is a viable solution to deal with AI processors for data explosion computing. The chiplet-based design compared to IP-based design provides much higher performance with lower cost. In this paper, we present design aspects of chiplet AI processor including the architecture design for incorporating NPU chiplets, HBM chiplets, and 2.5D interposers, signal integrity for high-speed interconnections on the interposer, PDN for chiplets, chiplet-bonding reliability, thermal stability, and chiplet link for inter-chiplet data transfer on heterogeneous integration architecture.","PeriodicalId":373752,"journal":{"name":"2023 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"138 11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128748965","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}

引用次数: 0

Please Be Nice: A Deep Learning Based Approach to Content Moderation of Internet Memes 请友善:基于深度学习的网络模因内容审核方法

2023 International Conference on Electronics, Information, and Communication (ICEIC) Pub Date : 2023-02-05 DOI: 10.1109/ICEIC57457.2023.10049865

Genevive Macrayo, Wilfredo Casiño, Jerecho Dalangin, Jervin Gabriel Gahoy, Aaron Christian Reyes, Christian Vitto, Mideth B. Abisado, Shekinah Lor B. Huyo-a, G. Sampedro

{"title":"Please Be Nice: A Deep Learning Based Approach to Content Moderation of Internet Memes","authors":"Genevive Macrayo, Wilfredo Casiño, Jerecho Dalangin, Jervin Gabriel Gahoy, Aaron Christian Reyes, Christian Vitto, Mideth B. Abisado, Shekinah Lor B. Huyo-a, G. Sampedro","doi":"10.1109/ICEIC57457.2023.10049865","DOIUrl":"https://doi.org/10.1109/ICEIC57457.2023.10049865","url":null,"abstract":"The internet has grown throughout time from a means for information distribution to a multipurpose tool that allows people to communicate, meet, and interact with one another. In socializing online, sending images with cultural and relatable context, otherwise known as memes, has become a common practice. Memes are sent everywhere, from forums and posts to even private messages. They are famous for converging thoughts, current events, or symbols creatively and colloquially. It combines text with a visual graphic and conveys many emotions, including hatred, which can harm other netizens. As a tool for communication, it can be used to convey humor or even as a tool for cyberbullying through hateful speech. Since memes are sent in image form, filtering out hateful speech in the form of memes can be difficult. To address this rising issue, researchers explore the use of deep learning approaches to detect hate speech on multimodal memes as a systematic approach for eliminating hate speech. The model performed well in this investigation, with an overall accuracy of 62.5%. When identifying pictures, it also has a high proportion of precision (71.37%). This brings the suggested model’s ability to detect hate speech in memes to a close.","PeriodicalId":373752,"journal":{"name":"2023 International Conference on Electronics, Information, and Communication (ICEIC)","volume":"276 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127379023","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}

引用次数: 0

Multi-Droplet Routing based on a Shape-Dependent Velocity Model on MEDA Biochips MEDA生物芯片上基于形状相关速度模型的多液滴路径

2023 International Conference on Electronics, Information, and Communication (ICEIC) Pub Date : 2023-02-05 DOI: 10.1109/ICEIC57457.2023.10049887

Chiharu Shiro, Hiroki Nishikawa, Xiangbo Kong, Hiroyuki Tomiyama, Shigeru Yamashita

引用次数: 0

Ambulance Dispatch Scheme based on Maximum Flow Minimum Cost models 基于最大流量最小成本模型的救护车调度方案

2023 International Conference on Electronics, Information, and Communication (ICEIC) Pub Date : 2023-02-05 DOI: 10.1109/ICEIC57457.2023.10049923

Junghoon Lee, Jihyun Park, Eunjeong Park

引用次数: 1

Direct Phase Control in Digital Phase-Locked Loop Mitigating Loop Delay Effect inside Digital Filter 数字锁相环的直接相位控制，减轻数字滤波器内的环路延迟效应

2023 International Conference on Electronics, Information, and Communication (ICEIC) Pub Date : 2023-02-05 DOI: 10.1109/ICEIC57457.2023.10049900

In-Woo Jang, Min-Seong Choo

引用次数: 0

Diagnose Label Errors for 3D Object Classification 诊断3D物体分类的标签错误

2023 International Conference on Electronics, Information, and Communication (ICEIC) Pub Date : 2023-02-05 DOI: 10.1109/ICEIC57457.2023.10049969

Jiayue Wang, Ren Wang, Tae Sung Kim, Jin-Sung Kim, Hyuk-Jae Lee

引用次数: 0