Korean Institute of Smart Media最新文献_第6页

Dynamic Computation Offloading Based on Q-Learning for UAV-Based Mobile Edge Computing 基于q -学习的无人机移动边缘计算动态卸载

Korean Institute of Smart Media Pub Date : 2023-04-30 DOI: 10.30693/smj.2023.12.3.68

Shreya Khisa, S. Moh

引用次数: 0

Research on depression and emergency detection model using smartphone sensors 基于智能手机传感器的抑郁与突发事件检测模型研究

Korean Institute of Smart Media Pub Date : 2023-04-30 DOI: 10.30693/smj.2023.12.3.9

Mingeun Son, Gang-rok Lee, J. Y. Park, Mingyeong Choi

引用次数: 0

A Study on Eye Tracking Techniques using Wearable Devices 基于可穿戴设备的眼动追踪技术研究

Korean Institute of Smart Media Pub Date : 2023-04-30 DOI: 10.30693/smj.2023.12.3.19

J. Jang, Jiuk Jung, Junghoon Park

{"title":"A Study on Eye Tracking Techniques using Wearable Devices","authors":"J. Jang, Jiuk Jung, Junghoon Park","doi":"10.30693/smj.2023.12.3.19","DOIUrl":"https://doi.org/10.30693/smj.2023.12.3.19","url":null,"abstract":"The eye tracking technology is widespread all around the society, and is demonstrating great performances in both preciseness and convenience. Hereby we can glimpse new possibility of an interface’s conduct without screen-touching. This technology can become a new way of conversation for those including but not limited to the patients suffering from Lou Gehrig’s disease, who are paralyzed each part by part of the body and finally cannot help but only moving eyes. Formerly in that case, the patients were given nothing to do but waiting for the death, even being unable to communicate with there families. A new interface that harnesses eyes as a new means of communication, although it conveys great difficulty, can be helpful for them. There surely are some eye tracking systems and equipment for their exclusive uses on the market. Notwithstanding, several obstacles including the complexity of operation and their high prices of over 12 million won($9,300) are hindering universal supply to people and coverage for the patients. Therefore, this paper suggests wearable-type eye tracking device that can support minorities and vulnerable people and be occupied inexpensively and study eye tracking method in order to maximize the possibility of future development across the world, finally proposing the way of designing and developing a brought-down costed eye tracking system based on high-efficient wearable device.","PeriodicalId":249252,"journal":{"name":"Korean Institute of Smart Media","volume":"144 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121122605","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

Size Estimation for Shrimp Using Deep Learning Method 基于深度学习方法的虾大小估计

Korean Institute of Smart Media Pub Date : 2023-04-30 DOI: 10.30693/smj.2023.12.3.112

Heng Zhou, Sunghoon Kim, Sang-Cheol Kim, Cheol-Won Kim, Seung-Won Kang

引用次数: 0

Eligibility Verification based on Immutable Personal Information without Revealing the Owner’s Identity 基于不泄露所有者身份的不可变个人信息的资格验证

Korean Institute of Smart Media Pub Date : 2023-04-30 DOI: 10.30693/smj.2023.12.3.38

Jun-Cheol Park

引用次数: 0

From Invisible to Irresistible: Intellectual Property and Digital Media & Entertainment Ventures in Korea 从无形到不可抗拒:韩国的知识产权和数字媒体与娱乐企业

Korean Institute of Smart Media Pub Date : 2023-04-30 DOI: 10.30693/smj.2023.12.3.93

Eunjung Hyun

引用次数: 0

Comparison of Korean Speech De-identification Performance of Speech De-identification Model and Broadcast Voice Modulation 语音去识别模型与广播语音调制的韩语语音去识别性能比较

Korean Institute of Smart Media Pub Date : 2023-03-30 DOI: 10.30693/smj.2023.12.2.56

Seung Min Kim, Dae Eol Park, Dae Seon Choi

{"title":"Comparison of Korean Speech De-identification Performance of Speech De-identification Model and Broadcast Voice Modulation","authors":"Seung Min Kim, Dae Eol Park, Dae Seon Choi","doi":"10.30693/smj.2023.12.2.56","DOIUrl":"https://doi.org/10.30693/smj.2023.12.2.56","url":null,"abstract":"In broadcasts such as news and coverage programs, voice is modulated to protect the identity of the informant. Adjusting the pitch is commonly used voice modulation method, which allows easy voice restoration to the original voice by adjusting the pitch. Therefore, since broadcast voice modulation methods cannot properly protect the identity of the speaker and are vulnerable to security, a new voice modulation method is needed to replace them. In this paper, using the Lightweight speech de-identification model as the evaluation target model, we compare speech de-identification performance with broadcast voice modulation method using pitch modulation. Among the six modulation methods in the Lightweight speech de-identification model, we experimented on the de-identification performance of Korean speech as a human test and EER(Equal Error Rate) test compared with broadcast voice modulation using three modulation methods: McAdams, Resampling, and Vocal Tract Length Normalization(VTLN). Experimental results show VTLN modulation methods performed higher de-identification performance in both human tests and EER tests. As a result, the modulation methods of the Lightweight model for Korean speech has sufficient de-identification performance and will be able to replace the security-weak broadcast voice modulation.","PeriodicalId":249252,"journal":{"name":"Korean Institute of Smart Media","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124041880","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

Face Recognition Network using gradCAM 基于gradCAM的人脸识别网络

Korean Institute of Smart Media Pub Date : 2023-03-30 DOI: 10.30693/smj.2023.12.2.9

Chan Hyung Baek, J. Kwon, H. Jung

引用次数: 0

Machine Learning-based Detection of HTTP DoS Attacks for Cloud Web Applications 基于机器学习的云Web应用HTTP DoS攻击检测

Korean Institute of Smart Media Pub Date : 2023-03-30 DOI: 10.30693/smj.2023.12.2.66

Jae-hun Cho, Jae Min Park, Tae Hyeop Kim, Seung Wook Lee, Jiyeon Kim

{"title":"Machine Learning-based Detection of HTTP DoS Attacks for Cloud Web Applications","authors":"Jae-hun Cho, Jae Min Park, Tae Hyeop Kim, Seung Wook Lee, Jiyeon Kim","doi":"10.30693/smj.2023.12.2.66","DOIUrl":"https://doi.org/10.30693/smj.2023.12.2.66","url":null,"abstract":"Recently, the number of cloud web applications is increasing owing to the accelerated migration of enterprises and public sector information systems to the cloud. Traditional network attacks on cloud web applications are characterized by Denial of Service (DoS) attacks, which consume network resources with a large number of packets. However, HTTP DoS attacks, which consume application resources, are also increasing recently; as such, developing security technologies to prevent them is necessary. In particular, since low-bandwidth HTTP DoS attacks do not consume network resources, they are difficult to identify using traditional security solutions that monitor network metrics. In this paper, we propose a new detection model for detecting HTTP DoS attacks on cloud web applications by collecting the application metrics of web servers and learning them using machine learning. We collected 18 types of application metrics from an Apache web server and used five machine learning and two deep learning models to train the collected data. Further, we confirmed the superiority of the application metrics-based machine learning model by collecting and training 6 additional network metrics and comparing their performance with the proposed models. Among HTTP DoS attacks, we injected the RUDY and HULK attacks, which are low- and high-bandwidth attacks, respectively. As a result of detecting these two attacks using the proposed model, we found out that the F1 scores of the application metrics-based machine learning model were about 0.3 and 0.1 higher than that of the network metrics-based model, respectively.","PeriodicalId":249252,"journal":{"name":"Korean Institute of Smart Media","volume":"315 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116536916","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

A Study on Zero Trust Technology Trends 零信任技术发展趋势研究

Korean Institute of Smart Media Pub Date : 2023-03-30 DOI: 10.30693/smj.2023.12.2.15

Miyeong Kim, Daegyeom Kim, Jong-Min Jang, Sang-jun Park, Souhwan Jung, Jungsoo Park

引用次数: 0