2022 26th International Computer Science and Engineering Conference (ICSEC)最新文献_第6页

Is Deep Diffusion Probabilistic Model Applicable for Fingerprint-based Indoor Localization? 深度扩散概率模型是否适用于基于指纹的室内定位?

2022 26th International Computer Science and Engineering Conference (ICSEC) Pub Date : 2022-12-21 DOI: 10.1109/ICSEC56337.2022.10049366

Dwi Joko Suroso, P. Sooraksa, P. Cherntanomwong

{"title":"Is Deep Diffusion Probabilistic Model Applicable for Fingerprint-based Indoor Localization?","authors":"Dwi Joko Suroso, P. Sooraksa, P. Cherntanomwong","doi":"10.1109/ICSEC56337.2022.10049366","DOIUrl":"https://doi.org/10.1109/ICSEC56337.2022.10049366","url":null,"abstract":"The latest deep learning (DL) phenomenon is the Denoising Diffusion Model (DDM). DDM is in a class of latent variable models of the deep generative model (DGM) along with the big name of Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs). Moreover, in a recent finding, DDM beats GANs in image synthesis. This paper presents the prospective applicability discussion of DDM for indoor localization research as previous models, e.g., GANs and VAEs, which are successfully implemented. Here, we focus more on how DDM can synthesize localization parameters with the help of fingerprinting technique's database enhancement. The fingerprint technique needs a preconstructed database which has the main drawbacks of its cost, time inefficient, and high complexity. We found valuable works of literature on this specific topic for GANs and VAEs. However, there are few DDM applications for discrete data types, and as the authors' concern, there is no attempt to apply them to indoor localization yet. DDM implementation is to generate continuous data domains, e.g., image, text, and audio data. A radio map or fingerprint database is essentially needed for fingerprint-based indoor localization. Learning this database pattern helps increase the system's performance. Obtaining a high-density and quality database is expensive and challenging to implement. Then, it raises a question, is DDM applicable for synthesizing this database and alleviating this problem?","PeriodicalId":430850,"journal":{"name":"2022 26th International Computer Science and Engineering Conference (ICSEC)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130237957","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

Empirical Study of U-Net Based Models for 2D Face Recovery from Face-Mask Occlusions 基于U-Net的二维人脸遮挡恢复模型的实证研究

2022 26th International Computer Science and Engineering Conference (ICSEC) Pub Date : 2022-12-21 DOI: 10.1109/ICSEC56337.2022.10049324

Yuan Ling Leong, Joi San Tan, Seng Poh Lim, Iman Yi Liao, Seng Chee Lim

{"title":"Empirical Study of U-Net Based Models for 2D Face Recovery from Face-Mask Occlusions","authors":"Yuan Ling Leong, Joi San Tan, Seng Poh Lim, Iman Yi Liao, Seng Chee Lim","doi":"10.1109/ICSEC56337.2022.10049324","DOIUrl":"https://doi.org/10.1109/ICSEC56337.2022.10049324","url":null,"abstract":"Human face related digital technologies have been widely applied in various fields including face recognition based biometrics, facial landmarks based face deformation for gaming, facial reconstruction for those who are disfigured from an accident in the medical field and others. Such technologies typically rely on the information of a full, uncovered face and their performance would suffer varying degrees of deterioration according to the level of facial occlusion exhibited. 2D face recovery from occluded faces has therefore become an important research area as it is both crucial and desirable to attain full facial information before it is used in downstream tasks. In this paper, we address the problem of 2D face recovery from facial-mask occlusions, a pertinent issue that is widely observed in situations such as the Covid-19 pandemic. In recent trends, most researches are carried out through deep learning techniques to recover masked faces. The whole process consists of two tasks which are image segmentation and image inpainting. As U-Net is a typical deep learning model for image segmentation, but it also helpful in image inpainting and image colorization, so it has been frequently used in solving face recovery problems. To further explore the capability of U-Net and its variants for face recovery from masked faces, we propose to conduct a comparative study on several U-Net based models on a synthetic dataset that was generated based on public face datasets and mask generator. Results showed that Resnet U-Net and VGG16 U-Net had performed better in face recovery among the six different U-Net based models.","PeriodicalId":430850,"journal":{"name":"2022 26th International Computer Science and Engineering Conference (ICSEC)","volume":"516 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116221284","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 Hybrid Book Recommendation System for University Library 面向高校图书馆的混合图书推荐系统

2022 26th International Computer Science and Engineering Conference (ICSEC) Pub Date : 2022-12-21 DOI: 10.1109/ICSEC56337.2022.10049318

Pitiwat Arunruviwat, V. Muangsin

{"title":"A Hybrid Book Recommendation System for University Library","authors":"Pitiwat Arunruviwat, V. Muangsin","doi":"10.1109/ICSEC56337.2022.10049318","DOIUrl":"https://doi.org/10.1109/ICSEC56337.2022.10049318","url":null,"abstract":"Nowadays, Recommendation systems become an important role in daily life such as recommended goods, recommended musics, recommended books, or recommended movies. Furthermore, a university library initiated a book recommendation system for improving the efficiency of book searching. This paper presents a methodology for book recommendation in a university library using a hybrid recommendation technique by weighting a combination of 2 similarity scores from two recommendations system. Normally a hybrid recommendation system is built on a combination of content-based filtering and collaborative filtering, whereas this paper use technique for applied books from the Course Syllabus and combines it with a standard hybrid recommendation system. To solve the cold start problem and improve the accuracy of the book recommendation system in the university library. For the evaluation, RSME has been used to collaborate with K-Fold Cross Validation and Train Test Split technique. Eventually, the result of the evaluated book recommendation system shown RSME is 1.2061 for 5-Fold Cross Validation and 1.2247 for Train & Test Split","PeriodicalId":430850,"journal":{"name":"2022 26th International Computer Science and Engineering Conference (ICSEC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130158942","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

ClinicYA: An Application for Pill Identification Using Deep Learning and K-means Clustering ClinicYA:基于深度学习和K-means聚类的药丸识别应用

2022 26th International Computer Science and Engineering Conference (ICSEC) Pub Date : 2022-12-21 DOI: 10.1109/ICSEC56337.2022.10049345

Supawadee Srikamdee, U. Suksawatchon, J. Suksawatchon, Worawit Werapan

引用次数: 0

Analysis of Matching between Student and Curricula via TOPSIS Algorithm for Admission Decision Support 基于TOPSIS算法的录取决策支持学生与课程匹配分析

2022 26th International Computer Science and Engineering Conference (ICSEC) Pub Date : 2022-12-21 DOI: 10.1109/ICSEC56337.2022.10049314

Pooripat Thongdeelert, Pientham Khongwiwat, Dussadee Somjaiwang, W. Yukunthorn

引用次数: 0

Job-Candidate Classifying and Ranking System-Based Machine Learning Method 基于系统的求职者分类与排名机器学习方法

2022 26th International Computer Science and Engineering Conference (ICSEC) Pub Date : 2022-12-21 DOI: 10.1109/ICSEC56337.2022.10049350

Thapanee Boonchob, Nuengwong Tuaycharoen, Santisook Limpeeticharoenchot, Narongthat Thanyawet

{"title":"Job-Candidate Classifying and Ranking System-Based Machine Learning Method","authors":"Thapanee Boonchob, Nuengwong Tuaycharoen, Santisook Limpeeticharoenchot, Narongthat Thanyawet","doi":"10.1109/ICSEC56337.2022.10049350","DOIUrl":"https://doi.org/10.1109/ICSEC56337.2022.10049350","url":null,"abstract":"Finding suitable candidates for an open job position could be a repetitive and time-consuming task, especially from a large pool of candidates. Besides, this task could truly make fair screening and shortlisting tedious. Losing the opportunity to hire top talent candidates due to the slow screening process or the wrong selection by human error is unacceptable. This paper presented a method for human resources to categorize and select the top candidates for the job opening they applied for. The proposed system is directed to alter a machine learning algorithm to classify the candidate into i) shortlist or ii) not-suitable group. The productive preprocessing data approaches of many works were applied. The Decision Tree, Support Vector Machine, K Nearest Neighbor, and CatBoost were compared to find the most suitable classification model. Then, the system ranked the candidates in a shortlist group in descending order. The proposed system operates with an accuracy of 87%, a weighted F1 score of 88%, and a recall of 75% from the Support Vector Machine classifier. This enables the business to identify suitable candidates for a certain position and make more informed decisions about whom to invite for an interview.","PeriodicalId":430850,"journal":{"name":"2022 26th International Computer Science and Engineering Conference (ICSEC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127602163","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

A Framework for Bang Saen Safe Food Avenue Management System 邦盛安全食品大道管理系统架构

2022 26th International Computer Science and Engineering Conference (ICSEC) Pub Date : 2022-12-21 DOI: 10.1109/ICSEC56337.2022.10049320

Wantana Sisomboon, Nuttaporn Phakdee, Apisit Saengsai, Yupaporn Sameenoi, Watcharapong Yookwan

{"title":"A Framework for Bang Saen Safe Food Avenue Management System","authors":"Wantana Sisomboon, Nuttaporn Phakdee, Apisit Saengsai, Yupaporn Sameenoi, Watcharapong Yookwan","doi":"10.1109/ICSEC56337.2022.10049320","DOIUrl":"https://doi.org/10.1109/ICSEC56337.2022.10049320","url":null,"abstract":"The coronavirus (COVID-19) epidemic has had a significant impact on people’s lives and businesses. After the epidemic situation, Saensuk Sub-district, Chonburi is one area that has a need to change its tourism management. Saen Suk Municipality launched a campaign to promote Bang Saen as a \"Safe Food Avenue\". The pilot project began with production of an application to support a special test for formalin (FA) in sea foods which shows the result to food shops and tourists online. The FA test kit was produced and approved with accurate test results verified by a team of specialists from Burapha university. The application was developed using a responsive website technique. Specialists used the system to upload images of FA test results. Then a machine learning in image processing technique was used to analyze the test results. The Server sends the result through a RESTFUL API in JSON format to the application so that users can see the results online. The experiment using Circular Hough Transform (CHT) algorithm to detect circular shape in two-dimensional space by voting in Hough parameter with 400 data records for training. Based on the FA test result dataset, training accuracy are 100%. The SafeFoodAvenue mobile application using responsive technology FA test result’s dataset accuracy is 100%.","PeriodicalId":430850,"journal":{"name":"2022 26th International Computer Science and Engineering Conference (ICSEC)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131696801","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 Implementation of DNS Operator and Network Guideline for Migrating Virtual Machine to KubeVirt DNS操作符的实现及虚拟机向KubeVirt迁移的网络指南

2022 26th International Computer Science and Engineering Conference (ICSEC) Pub Date : 2022-12-21 DOI: 10.1109/ICSEC56337.2022.10049369

Supakorn Trakulmaiphol, K. Piromsopa

{"title":"An Implementation of DNS Operator and Network Guideline for Migrating Virtual Machine to KubeVirt","authors":"Supakorn Trakulmaiphol, K. Piromsopa","doi":"10.1109/ICSEC56337.2022.10049369","DOIUrl":"https://doi.org/10.1109/ICSEC56337.2022.10049369","url":null,"abstract":"We created a customize DNS operator to address the shortcoming of CoreDNS in Kubernetes. While Kubernetes is gaining popularity in orchestrating containers, many organizations with Virtual Machine (VM) based legacy applications still struggle to containerize. Rehost strategy seems to be a faster method. On Kubernetes, KubeVirt can be used to manage rehosted VM. However, there is a huge difference between the long-term use of the VMs and containers. For example, container IP addresses change over time is problematic for VMs that need a static IP. In addition, some VM-based applications may require multiple network interfaces or a specific domain name for service discovery. These issues prevent some VMs from functioning properly after the migration to KubeVirt. We developed an operator framework to solve network problems that arise in the application layer such as DNS queries. In addition, we provide a guideline on how to use open-source projects like the Multus Container Network Interface, NMState to enable the migration of VMs with applications related to network function properly. Our operator and guideline allow most VMs to function properly with few modifications (to none) after migrating to KubeVirt. This facilitated the adoption of Kubernetes in more organizations.","PeriodicalId":430850,"journal":{"name":"2022 26th International Computer Science and Engineering Conference (ICSEC)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124850175","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

Thai Privacy Notice Analysis Based On Named-Entity Recognition Technique 基于命名实体识别技术的泰语隐私声明分析

2022 26th International Computer Science and Engineering Conference (ICSEC) Pub Date : 2022-12-21 DOI: 10.1109/ICSEC56337.2022.10049321

Chanoksuda Wongvises, A. Khurat, Thanapon Noraset

{"title":"Thai Privacy Notice Analysis Based On Named-Entity Recognition Technique","authors":"Chanoksuda Wongvises, A. Khurat, Thanapon Noraset","doi":"10.1109/ICSEC56337.2022.10049321","DOIUrl":"https://doi.org/10.1109/ICSEC56337.2022.10049321","url":null,"abstract":"With the spread of global technology and the rising value of personal data, privacy has become a major problem. Many countries have enacted privacy laws to protect their citizens' privacy. Thailand has a similar law known as the Personal Data Protection Act (PDPA). According to the PDPA, the data controllers must provide data subjects with information about handling of personal data which is generally referred to as privacy notices. A privacy notice is typically a comprehensive document that uses formal language. As a result, many customers find it difficult to comprehend essential information in a short time. One of Natural Language Processing (NLP) methods, Named-Entity Recognition (NER), is a technique that can be used to capture the main contents of a document. The feasibility of NLP techniques for extracting significant privacy practices regarding the PDPA requirements for Thai privacy notices, however, has not yet been explored. Therefore, this study explores this feasibility and proposes a dataset of Thai privacy notices and a privacy annotation scheme based on PDPA requirements. The effectiveness of NLP approaches in extracting Thai privacy practice information is also evaluated in this study. The privacy notices comprehension has been formulated into the problem of Thai privacy information extraction, Thai privacy NER. The results show that the pre-trained transformer model outperforms the traditional method, and the increasing training dataset can affect higher performance value.","PeriodicalId":430850,"journal":{"name":"2022 26th International Computer Science and Engineering Conference (ICSEC)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131418761","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

Mae Mai Muay Thai Layered Classification Using CNN and LSTM Models 基于CNN和LSTM模型的泰拳分层分类

2022 26th International Computer Science and Engineering Conference (ICSEC) Pub Date : 2022-12-21 DOI: 10.1109/ICSEC56337.2022.10049339

Shujaat Ali Zaidi, Varin Chouvatut

{"title":"Mae Mai Muay Thai Layered Classification Using CNN and LSTM Models","authors":"Shujaat Ali Zaidi, Varin Chouvatut","doi":"10.1109/ICSEC56337.2022.10049339","DOIUrl":"https://doi.org/10.1109/ICSEC56337.2022.10049339","url":null,"abstract":"In competitive physical sports such as boxing, analytics on a boxer's efficiency, particularly the number and kind of punches delivered, offer information and feedback commonly utilized for performance and coaching enhancement. In this paper, we look at the challenge of recognizing Mae Mai Muay Thai (MMM-Thai) actions in still imagery. By activity recognition, we mean a collection of problems that encompasses both action categorization and action recognition. Bag-of-words picture representations do a great job of classifying actions, while deformable component models do a great job of recognizing objects. Action recognition representations often employ shape cues and omit color information. This research proposes a comprehensive framework for automated MMM-Thai style classification. MMM-Thai recognition is tackled using Convolutional Neural Network (CNN) and Long Short-term Memory (LSTM) classifiers. This framework was employed to analyze MMM-Thai boxing picture sequences. Experiments were carried out using the MMM-Thai dataset with four professional boxers. The findings provide evidence that the strategy that was presented was successful. The combination of CNN and LSTM classifiers achieved an accuracy of 99%, indicating that they are appropriate for analyzing boxers' techniques during competition. Finally, we will evaluate the model's overall effectiveness using a confusion matrix. To evaluate the performance of our model, we also utilize the ROC Receiver Operating Characteristics (ROC) curve and Area Under the Curve (AUC). Accuracy, precision, recall, and the F1-score performance indicators were also used in the analysis.","PeriodicalId":430850,"journal":{"name":"2022 26th International Computer Science and Engineering Conference (ICSEC)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131905397","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