Korean Institute of Smart Media最新文献_第8页

A Study about Learning Graph Representation on Farmhouse Apple Quality Images with Graph Transformer 用图转换器学习农家乐苹果品质图像的图表示研究

Korean Institute of Smart Media Pub Date : 2023-02-28 DOI: 10.30693/smj.2023.12.1.9

Ji-Hoon Bae, Jinyoung Kim, Ju-Hwan Lee, Gwanghyun Yu, Gyeong-Ju Kwon

{"title":"A Study about Learning Graph Representation on Farmhouse Apple Quality Images with Graph Transformer","authors":"Ji-Hoon Bae, Jinyoung Kim, Ju-Hwan Lee, Gwanghyun Yu, Gyeong-Ju Kwon","doi":"10.30693/smj.2023.12.1.9","DOIUrl":"https://doi.org/10.30693/smj.2023.12.1.9","url":null,"abstract":"Recently, a convolutional neural network (CNN) based system is being developed to overcome the limitations of human resources in the apple quality classification of farmhouse. However, since convolutional neural networks receive only images of the same size, preprocessing such as sampling may be required, and in the case of oversampling, information loss of the original image such as image quality degradation and blurring occurs. In this paper, in order to minimize the above problem, to generate a image patch based graph of an original image and propose a random walk-based positional encoding method to apply the graph transformer model. The above method continuously learns the position embedding information of patches which don`t have a positional information based on the random walk algorithm, and finds the optimal graph structure by aggregating useful node information through the self-attention technique of graph transformer model. Therefore, it is robust and shows good performance even in a new graph structure of random node order and an arbitrary graph structure according to the location of an object in an image. As a result, when experimented with 5 apple quality datasets, the learning accuracy was higher than other GNN models by a minimum of 1.3% to a maximum of 4.7%, and the number of parameters was 3.59M, which was about 15% less than the 23.52M of the ResNet18 model. Therefore, it shows fast reasoning speed according to the reduction of the amount of computation and proves the effect.","PeriodicalId":249252,"journal":{"name":"Korean Institute of Smart Media","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126637477","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

An Effective Smart Greenhouse Data Preprocessing System for Autonomous Machine Learning 一种有效的智能温室自主机器学习数据预处理系统

Korean Institute of Smart Media Pub Date : 2023-02-28 DOI: 10.30693/smj.2023.12.1.47

Jongtae Lim, Jae-soo Yoo, Christopher RETITI DIOP EMANE, Y. Kim, Jeong-Hyun Beak

引用次数: 0

An Investigation of the Framework for User Experience in Museum Mobile Applications 博物馆移动应用的用户体验框架研究

Korean Institute of Smart Media Pub Date : 2023-02-28 DOI: 10.30693/smj.2023.12.1.62

zheng Lin, Jonghwan Seo

引用次数: 0

Terrestrial UHD activation strategy to strengthen global competitiveness 加强全球竞争力的地面超高清激活策略

Korean Institute of Smart Media Pub Date : 2023-02-28 DOI: 10.30693/smj.2023.12.1.92

W. J. Hyun

引用次数: 0

Korean Text to Gloss: Self-Supervised Learning approach 韩语文本到注释:自我监督学习方法

Korean Institute of Smart Media Pub Date : 2023-02-28 DOI: 10.30693/smj.2023.12.1.32

Thanh-Vu Dang, Jinyoung Kim, Gwanghyun Yu, Ji Yong Kim, Young Hwan Park, Chilwoo Lee

{"title":"Korean Text to Gloss: Self-Supervised Learning approach","authors":"Thanh-Vu Dang, Jinyoung Kim, Gwanghyun Yu, Ji Yong Kim, Young Hwan Park, Chilwoo Lee","doi":"10.30693/smj.2023.12.1.32","DOIUrl":"https://doi.org/10.30693/smj.2023.12.1.32","url":null,"abstract":"Natural Language Processing (NLP) has grown tremendously in recent years. Typically, bilingual, and multilingual translation models have been deployed widely in machine translation and gained vast attention from the research community. On the contrary, few studies have focused on translating between spoken and sign languages, especially non-English languages. Prior works on Sign Language Translation (SLT) have shown that a mid-level sign gloss representation enhances translation performance. Therefore, this study presents a new large-scale Korean sign language dataset, the Museum-Commentary Korean Sign Gloss (MCKSG) dataset, including 3828 pairs of Korean sentences and their corresponding sign glosses used in Museum-Commentary contexts. In addition, we propose a translation framework based on self-supervised learning, where the pretext task is a text-to-text from a Korean sentence to its back-translation versions, then the pre-trained network will be fine-tuned on the MCKSG dataset. Using self-supervised learning help to overcome the drawback of a shortage of sign language data. Through experimental results, our proposed model outperforms a baseline BERT model by 6.22%.","PeriodicalId":249252,"journal":{"name":"Korean Institute of Smart Media","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129439575","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

Few-shot learning using the median prototype of the support set 使用支持集的中值原型进行少射学习

Korean Institute of Smart Media Pub Date : 2023-02-28 DOI: 10.30693/smj.2023.12.1.24

Eu-Tteum Baek

引用次数: 0

Automatic Generation Tool for Open Platform-compatible Intelligent IoT Components 开放平台兼容智能物联网组件自动生成工具

Korean Institute of Smart Media Pub Date : 2022-12-31 DOI: 10.30693/smj.2022.11.11.32

Seoyeon Kim, Joonhyouk Jang, Jinmang Jung, Bongjae Kim, Young-Sun Yun

引用次数: 0

Personalized Speech Classification Scheme for the Smart Speaker Accessibility Improvement of the Speech-Impaired people 提高语障人士智能扬声器可及性的个性化语音分类方案

Korean Institute of Smart Media Pub Date : 2022-12-31 DOI: 10.30693/smj.2022.11.11.17

SeungKwon Lee, Gwang il Jeon, U. Choe

{"title":"Personalized Speech Classification Scheme for the Smart Speaker Accessibility Improvement of the Speech-Impaired people","authors":"SeungKwon Lee, Gwang il Jeon, U. Choe","doi":"10.30693/smj.2022.11.11.17","DOIUrl":"https://doi.org/10.30693/smj.2022.11.11.17","url":null,"abstract":"With the spread of smart speakers based on voice recognition technology and deep learning technology, not only non-disabled people, but also the blind or physically handicapped can easily control home appliances such as lights and TVs through voice by linking home network services. This has greatly improved the quality of life. However, in the case of speech-impaired people, it is impossible to use the useful services of the smart speaker because they have inaccurate pronunciation due to articulation or speech disorders. In this paper, we propose a personalized voice classification technique for the speech-impaired to use for some of the functions provided by the smart speaker. The goal of this paper is to increase the recognition rate and accuracy of sentences spoken by speech-impaired people even with a small amount of data and a short learning time so that the service provided by the smart speaker can be actually used. In this paper, data augmentation and one cycle learning rate optimization technique were applied while fine-tuning ResNet18 model. Through an experiment, after recording 10 times for each 30 smart speaker commands, and learning within 3 minutes, the speech classification recognition rate was about 95.2%.","PeriodicalId":249252,"journal":{"name":"Korean Institute of Smart Media","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131423899","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

Road Image Recognition Technology based on Deep Learning Using TIDL NPU in SoC Enviroment SoC环境下基于深度学习的TIDL NPU道路图像识别技术

Korean Institute of Smart Media Pub Date : 2022-12-31 DOI: 10.30693/smj.2022.11.11.25

Yunseon Shin, Injung Kim, Juhyun Seo, Minyoung Lee

引用次数: 0

A study on the Construction of a Big Data-based Urban Information and Public Transportation Accessibility Analysis Platforms: Focused on Gwangju Metropolitan City 基于大数据的城市信息与公共交通可达性分析平台构建研究——以光州为例

Korean Institute of Smart Media Pub Date : 2022-12-31 DOI: 10.30693/smj.2022.11.11.49

Sangkeun Lee, Daeill Kim, SeungChang Yu, Jun Lee

{"title":"A study on the Construction of a Big Data-based Urban Information and Public Transportation Accessibility Analysis Platforms: Focused on Gwangju Metropolitan City","authors":"Sangkeun Lee, Daeill Kim, SeungChang Yu, Jun Lee","doi":"10.30693/smj.2022.11.11.49","DOIUrl":"https://doi.org/10.30693/smj.2022.11.11.49","url":null,"abstract":"Recently, with the development of Smart City Solutions such as Big data, AI, IoT, Autonomous driving, and Digital twins around the world, the proliferation of various smart devices and social media, and the record of the deeds that people have left everywhere, the construction of Smart Cities using the “Big Data” environment in which so much information and data is produced that it is impossible to gauge the scale is actively underway. The Purpose of this study is to construct an objective and systematic analysis Model based on Big Data to improve the transportation convenience of citizens and formulate efficient policies in Urban Information and Public Transportation accessibility in sustainable Smart Cities following the 4th Industrial Revolution. It is also to derive the methodology of developing a Big Data-Based public transport accessibility and policy management Platform using a sustainable Urban Public DB and a Private DB. To this end, Detailed Living Areas made a division and the accessibility of basic living amenities of Gwangju Metropolitan City, and the Public Transportation system based on Big Data were analyzed. As a result, it was Proposed to construct a Big Data-based Urban Information and Public Transportation accessibility Platform, such as 1) Using Big Data for public transportation network evaluation, 2) Supporting Transportation means/service decision-making based on Big Data, 3) Providing urban traffic network monitoring services, and 4) Analyzing parking demand sources and providing improvement measures.","PeriodicalId":249252,"journal":{"name":"Korean Institute of Smart Media","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124761264","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