发布求助
文献互助 智能选刊 最新文献

2023 15th International Conference on Knowledge and Smart Technology (KST)最新文献

筛选
英文 中文
WAFL-GAN: Wireless Ad Hoc Federated Learning for Distributed Generative Adversarial Networks 分布式生成对抗网络的无线自组织联邦学习
2023 15th International Conference on Knowledge and Smart Technology (KST) Pub Date : 2023-02-21 DOI: 10.1109/KST57286.2023.10086811
Eisuke Tomiyama, H. Esaki, H. Ochiai
{"title":"WAFL-GAN: Wireless Ad Hoc Federated Learning for Distributed Generative Adversarial Networks","authors":"Eisuke Tomiyama, H. Esaki, H. Ochiai","doi":"10.1109/KST57286.2023.10086811","DOIUrl":"https://doi.org/10.1109/KST57286.2023.10086811","url":null,"abstract":"Diverse images are needed to train Generative Adversarial Network (GAN) with diverse image output, but privacy is a major issue. To protect privacy, federated learning has been proposed, but in conventional federated learning, the parameter server is a third party to the client. We propose WAFL-GAN, which does not require a third party, and which assumes that each node participating in the learning process is mobile and can communicate wirelessly with each other. Each node is trained only with the data it has locally, and when nodes opportunistically contact each other, they exchange and aggregate model parameters without exchanging raw data. This allows all nodes to eventually have a general model and produce a general output, even if each node has a dataset with a Non-IID distribution. We evaluated WAFL-GAN on the Non-IID MNIST dataset and quantitatively showed that the output diversity of WAFL-GAN can be as high as that of conventional federated learning.","PeriodicalId":351833,"journal":{"name":"2023 15th International Conference on Knowledge and Smart Technology (KST)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115305996","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
Framework for Fine-grained Recognition of Retail Products from a Single Exemplar 基于单一样本的零售产品细粒度识别框架
2023 15th International Conference on Knowledge and Smart Technology (KST) Pub Date : 2023-02-21 DOI: 10.1109/KST57286.2023.10086714
Ryosuke Sakai, Tomokazu Kaneko, Soma Shiraishi
{"title":"Framework for Fine-grained Recognition of Retail Products from a Single Exemplar","authors":"Ryosuke Sakai, Tomokazu Kaneko, Soma Shiraishi","doi":"10.1109/KST57286.2023.10086714","DOIUrl":"https://doi.org/10.1109/KST57286.2023.10086714","url":null,"abstract":"We propose a framework which allows one-shot fine-grained recognition of retail products in a real store from clean images used in e-commerce websites. We apply a metric learning approach to train the one-shot recognition model. To learn a suitable metric space for classification, we construct a data collection system which efficiently captures a large variety of products from various viewpoints under controllable lighting conditions. This dataset plays a role of an intermediate domain between the clean images and real stores. To expand applicable area of the intermediate domain, we use a domain generalization technique. In addition, we propose the pseudo class generation and metric learning method to enhance fine-grained recognition for retail products such as classification for products with multiple flavors. We demonstrate the effectiveness of each part of technique in our experiments for our target task, and show that our framework leads to high-accuracy recognition.","PeriodicalId":351833,"journal":{"name":"2023 15th International Conference on Knowledge and Smart Technology (KST)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127743288","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
zxCAPTCHA: New Security-Enhanced CAPTCHA zxCAPTCHA:新的安全增强的验证码
2023 15th International Conference on Knowledge and Smart Technology (KST) Pub Date : 2023-02-21 DOI: 10.1109/KST57286.2023.10086931
Nghia Dinh, Trung Nguyen, Vinh Truong Hoang
{"title":"zxCAPTCHA: New Security-Enhanced CAPTCHA","authors":"Nghia Dinh, Trung Nguyen, Vinh Truong Hoang","doi":"10.1109/KST57286.2023.10086931","DOIUrl":"https://doi.org/10.1109/KST57286.2023.10086931","url":null,"abstract":"Automated attacks using CNN (Convolutional Neural Network), ML (Machine Learning), and DNN (Deep Neural Network have been successful in bypassing traditional CAPTCHAs. However, Deep Learning techniques, adversarial examples and style neural transfer, have been shown to be particularly effective in protecting CAPTCHAs. In this study, the authors proposed zxCAPTCHA, a new CAPTCHA that combines cognitive-based, image-based, and text-based CAPTCHA characteristics with Deep Learning techniques to improve security. Extensive evaluations were conducted to assess the improvement of the CAPTCHA security. The experiment shows that zxCAPTCHA considerably enhances the security while maintaining comparable usability. We also demonstrate the effectiveness of combining cognitive techniques and Deep Learning to improve CAPTCHA security.","PeriodicalId":351833,"journal":{"name":"2023 15th International Conference on Knowledge and Smart Technology (KST)","volume":"655 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120876187","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
Chinese Finger Sign Language Recognition Method with ResNet Transfer Learning 基于ResNet迁移学习的中文手语识别方法
2023 15th International Conference on Knowledge and Smart Technology (KST) Pub Date : 2023-02-21 DOI: 10.1109/KST57286.2023.10086825
Varin Chouvatut, Benjamas Panyangam, Jiayu Huang
{"title":"Chinese Finger Sign Language Recognition Method with ResNet Transfer Learning","authors":"Varin Chouvatut, Benjamas Panyangam, Jiayu Huang","doi":"10.1109/KST57286.2023.10086825","DOIUrl":"https://doi.org/10.1109/KST57286.2023.10086825","url":null,"abstract":"Sign language is one of the most effective ways to help hearing-impaired people to communicate with other people. Although deep learning methods have been used in recognition, there are still problems with finger sign language recognition. The major issue is that the gradient approach usually fails, or the obtained recognition accuracy is not high when the depth is increasing. We thus propose a Chinese finger sign language recognition method based on ResNet and Adam optimizer together with additional image processing techniques to gain higher accuracy. We then compare our recognition results to other convolutional neural network models which are widely used deep learning techniques for recognition. Even though we have a small size of the dataset, our proposed deep learning method for finger sign recognition still gives a higher recognition rate. Also, our prototypical method provides the capability to be applied to other recognition tasks of different gestures or objects from image datasets.","PeriodicalId":351833,"journal":{"name":"2023 15th International Conference on Knowledge and Smart Technology (KST)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132143131","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
LightPEN: Optimizing the Vulnerability Exposures for Lightweight Penetration Test LightPEN:优化轻量级渗透测试的漏洞暴露
2023 15th International Conference on Knowledge and Smart Technology (KST) Pub Date : 2023-02-21 DOI: 10.1109/KST57286.2023.10086896
S. Fugkeaw, Lyhour Hak, Nutsuda Ploysopond, Witchaya Apichonkit, Sirapop Lahankaew
{"title":"LightPEN: Optimizing the Vulnerability Exposures for Lightweight Penetration Test","authors":"S. Fugkeaw, Lyhour Hak, Nutsuda Ploysopond, Witchaya Apichonkit, Sirapop Lahankaew","doi":"10.1109/KST57286.2023.10086896","DOIUrl":"https://doi.org/10.1109/KST57286.2023.10086896","url":null,"abstract":"Penetration Testing (PenTest) is crucial to an organization’s system security. It helps ensure the confidentiality, integrity, and availability of the system and reduces exposures to future risks. Specifically, the PenTest process is usually initiated after the vulnerability assessment (VA) scanning where its results are used to undertake the PenTest. Significantly, PenTest requires expert testers to test each vulnerability found in the VA stage thoroughly. Hence, the process is expert-dependent and time-consuming. To optimize the set of vulnerabilities to be tested in the PenTest process, we introduce the scheme called LightPEN to support the extraction of known vulnerabilities obtained from existing sources such as local code scanning, notice from vendors and developers, and previous VA reports. In addition, our system provides exploitable scripts for the PenTest process. Finally, we conducted the experiment to demonstrate the efficiency of our proposed system.","PeriodicalId":351833,"journal":{"name":"2023 15th International Conference on Knowledge and Smart Technology (KST)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115184140","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
Design and Development of Stress Monitoring System in Use Case: Twitter #Dek65 用例中压力监测系统的设计与开发:Twitter #Dek65
2023 15th International Conference on Knowledge and Smart Technology (KST) Pub Date : 2023-02-21 DOI: 10.1109/KST57286.2023.10086726
Nessara Sukumthammarat, Sasima Nimma, Pokpong Songmuang
{"title":"Design and Development of Stress Monitoring System in Use Case: Twitter #Dek65","authors":"Nessara Sukumthammarat, Sasima Nimma, Pokpong Songmuang","doi":"10.1109/KST57286.2023.10086726","DOIUrl":"https://doi.org/10.1109/KST57286.2023.10086726","url":null,"abstract":"Twitter is a social media platform where users can post, make a conversation, comments, and share experiences that express their emotions and sentiments. Our objective is to monitor and analyze the #Dek65 hashtag’s Twitter messages. We take 166,110 Twitter messages on the #Dek65 hashtag from August 2021 to July 2022 and bring them to analyze attitudes, thoughts, emotions, and stress during the preparation for university entrance exams and the Thai education system. We designed and developed a system by creating a model that can sentiment message, a model for cluster topics from the negative message then represent sentiment messages in a way that is simple to understand through visualization. We do this to make stakeholders can monitor and aware of the problems in the Thai education system.","PeriodicalId":351833,"journal":{"name":"2023 15th International Conference on Knowledge and Smart Technology (KST)","volume":"32 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131590555","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
Real-time Evaluation of Food Acceptance From Facial Expressions Based on Exponential Decay 基于指数衰减的面部表情食物接受度实时评估
2023 15th International Conference on Knowledge and Smart Technology (KST) Pub Date : 2023-02-21 DOI: 10.1109/KST57286.2023.10086796
Jian Han, Anilkumar Kothalil Gopalakrishnan
{"title":"Real-time Evaluation of Food Acceptance From Facial Expressions Based on Exponential Decay","authors":"Jian Han, Anilkumar Kothalil Gopalakrishnan","doi":"10.1109/KST57286.2023.10086796","DOIUrl":"https://doi.org/10.1109/KST57286.2023.10086796","url":null,"abstract":"This research paper proposes a novel method for estimating food acceptance from real-time food consumption video streaming under partially occluded facial expressions. The facial expressions are evaluated based on the Facial Expression Recognition (FER) system. Here, the occlusion is identified as a spoon, fork, or hand. And the Object Detection API from TensorFlow is used as an occlusion detection tool. The combination of the Exponential Decay and the Bayes’ theorem (called EB algorithm) is used to estimate the probabilities of food acceptance from the occluded facial expressions. The EB algorithm also calculates the facial reactions towards food tastes such as bitterness, sourness, sweetness, umami, and saltiness to predict the likelihood of food acceptance. The simulations and the customer comparison results indicate that the presented food acceptance system is one of the accurate ways to signify food acceptance in a real-time food environment.","PeriodicalId":351833,"journal":{"name":"2023 15th International Conference on Knowledge and Smart Technology (KST)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123263969","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
Time and performance comparison on suicide detection using various feature engineering and machine learning models 使用各种特征工程和机器学习模型进行自杀检测的时间和性能比较
2023 15th International Conference on Knowledge and Smart Technology (KST) Pub Date : 2023-02-21 DOI: 10.1109/KST57286.2023.10086874
Kittisak Thongsi, Nannaphas Booncherd, Pokpong Songmuang
{"title":"Time and performance comparison on suicide detection using various feature engineering and machine learning models","authors":"Kittisak Thongsi, Nannaphas Booncherd, Pokpong Songmuang","doi":"10.1109/KST57286.2023.10086874","DOIUrl":"https://doi.org/10.1109/KST57286.2023.10086874","url":null,"abstract":"Today more people use social media to express their opinion and their emotions. There are many types of text in social media including text that convey a tendency to be depressed or suicidal. We use sentiment analysis to detect suicidal texts, because if detected, it could save many lives and many families. In this research, we have an objective to explore a method that is both high performance and less time-using. We design experiments that have 30 combinations between five machine learning models with six feature engineering methods. All experiments use accuracy and total time for model generation as metrics. We use deep neural networks with glove embedding as a comparator because this combination performed well in this dataset on Kaggle competition. From the experimental results, we find that the suitable combination that generates fast and has good accuracy is Random Forest with TF-IDF with 0.897 and 145 seconds.","PeriodicalId":351833,"journal":{"name":"2023 15th International Conference on Knowledge and Smart Technology (KST)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125987028","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
Analysis of Defect Associated with Powder Bed Fusion with Deep Learning and Explainable AI 基于深度学习和可解释人工智能的粉末床熔合缺陷分析
2023 15th International Conference on Knowledge and Smart Technology (KST) Pub Date : 2023-02-21 DOI: 10.1109/KST57286.2023.10086905
Ayush Pratap, N. Sardana, Sapdo Utomo, A. John, P. Karthikeyan, Pao-Ann Hsiung
{"title":"Analysis of Defect Associated with Powder Bed Fusion with Deep Learning and Explainable AI","authors":"Ayush Pratap, N. Sardana, Sapdo Utomo, A. John, P. Karthikeyan, Pao-Ann Hsiung","doi":"10.1109/KST57286.2023.10086905","DOIUrl":"https://doi.org/10.1109/KST57286.2023.10086905","url":null,"abstract":"Research into the detection, classification, and prediction of internal defects using surface morphology data of parts created via powder bed fusion-type additive manufacturing has become a hot topic in the previous decade thanks to the development of deep learning. However, there is no other evidence to evaluate the model other than accuracy and metrics. In this paper, a novel data set is compiled from various literature and other sources to evaluate the black box model using explainable artificial intelligence (XAI). The data set contains three major powder bed fusion defects: gas porosity, lack of fusion, and balling. The anomaly was initially found using convolutional neural networks (CNN) and transfer learning. Based on test data, a model comparison was performed to determine the best accuracy and an F1 score. VGG16 has outperformed all other models in terms of accuracy, with an F1 score of 98.6 percent. Further, the model has been compared with the existing state-of-the-art model for classification in the domain of powder bed fusion defects. Finally, VGG16 was employed to interpret and explain the test data set. The LIME explanations revealed that the feature predicted by the model was present in conjunction with the fault. As a result, we are confident that the proposed model with XAI would considerably improve the fairness and trustworthiness of the output result in the powder bed fusion field. This can also aid in the automation of additive manufacturing in the realm of Industry 4.0.","PeriodicalId":351833,"journal":{"name":"2023 15th International Conference on Knowledge and Smart Technology (KST)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114415719","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: 1
Heart Rate Measurement on PC and Phone using Facial Videos 使用面部视频在PC和手机上测量心率
2023 15th International Conference on Knowledge and Smart Technology (KST) Pub Date : 2023-02-21 DOI: 10.1109/KST57286.2023.10086729
Tashfiq Rahman, Worarat Krathu, C. Arpnikanondt
{"title":"Heart Rate Measurement on PC and Phone using Facial Videos","authors":"Tashfiq Rahman, Worarat Krathu, C. Arpnikanondt","doi":"10.1109/KST57286.2023.10086729","DOIUrl":"https://doi.org/10.1109/KST57286.2023.10086729","url":null,"abstract":"Heart rate (HR) analysis has always piqued the curiosity of medical experts. Various apps have been designed using algorithms that assess the pulse using only one’s facial video. A recently developed technique called Eulerian Video Magnification (EVM) can detect temporal fluctuations in videos that are undetected by the naked human eye. It is feasible to visualize the flow of blood filling the face with this approach. Photoplethysmography (PPG) signals from the human face can be spotted by minute variations in skin tone that are connected to the blood vessels beneath the surface of the face. The output of the signals can then be used to determine the vitals of the person. In order to estimate the heartbeat of 40 participants at the initial, post-cardio, and after-resting stages, this study employed an implementation of the EVM computer vision algorithm, developed to remotely detect an individual’s HR in beats per minute from a static video of his or her face. The data from the desktop and smartphone were compared to the readings made simultaneously by an oximeter. The pulse oximeter, which likewise derives HR by PPG, and the PPG-derived HR utilizing EVM from the desktop and the smartphone both showed positive correlations.","PeriodicalId":351833,"journal":{"name":"2023 15th International Conference on Knowledge and Smart Technology (KST)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121221502","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
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：481959085
Book学术官方微信