2021 13th International Conference on Knowledge and Systems Engineering (KSE)最新文献_第4页

Vietnamese Fake News Detection Based on Hybrid Transfer Learning Model and TF-IDF 基于混合迁移学习模型和TF-IDF的越南假新闻检测

2021 13th International Conference on Knowledge and Systems Engineering (KSE) Pub Date : 2021-11-10 DOI: 10.1109/KSE53942.2021.9648676

Ngoc-Dong Pham, Thi-Hanh Le, Thanh-Dat Do, Thanh-Toan Vuong, Thi-Hong Vuong, Quang-Thuy Ha

引用次数: 2

SST-GCN: Structure aware Spatial-Temporal GCN for 3D Hand Pose Estimation SST-GCN:三维手部姿态估计的结构感知时空GCN

2021 13th International Conference on Knowledge and Systems Engineering (KSE) Pub Date : 2021-11-10 DOI: 10.1109/KSE53942.2021.9648765

Viet-Thanh Le, Thanh-Hai Tran, Van-Nam Hoang, Van-Hung Le, Thi-Lan Le, Hai Vu

{"title":"SST-GCN: Structure aware Spatial-Temporal GCN for 3D Hand Pose Estimation","authors":"Viet-Thanh Le, Thanh-Hai Tran, Van-Nam Hoang, Van-Hung Le, Thi-Lan Le, Hai Vu","doi":"10.1109/KSE53942.2021.9648765","DOIUrl":"https://doi.org/10.1109/KSE53942.2021.9648765","url":null,"abstract":"Human hand gesture is an efficient way of communication for Human-computer interaction (HCI) applications. To this end, one of the main requirements is an automatic hand pose estimation. Existing methods usually explore spatial relationships among hand joints in a single image to estimate the 3D hand pose. By doing so, the temporal constraints among hand poses are under-investigated. In this paper, we propose SST-GCN (Structure aware Spatial-Temporal Graphic Convolutional Network) that incorporates both spatial dependencies and temporal consistencies to improve 3D hand pose estimation results. Our method bases on an existing spatial-temporal GCN for 3D pose estimation. In addition, we introduce a new loss function that takes geometric constraints of hand structure into account. Our proposed method takes a 2D hand pose as an input to estimates the 3D hand pose. Finally, we evaluate our method on the First-Person Hand Action Benchmark (FPHAB) dataset. The experimental results show that the proposed method gives promising results in comparison with the original ST-GCN network.","PeriodicalId":130986,"journal":{"name":"2021 13th International Conference on Knowledge and Systems Engineering (KSE)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116466264","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: 2

A Summary of the ALQAC 2021 Competition ALQAC 2021竞赛总结

2021 13th International Conference on Knowledge and Systems Engineering (KSE) Pub Date : 2021-11-10 DOI: 10.1109/kse53942.2021.9648724

Nguyen Ha Thanh, Minh Q. Bui, Chau Nguyen, Tung Le, Phuong Minh Nguyen, Binh Dang, Vuong Thi Hai Yen, Teeradaj Racharak, Nguyen Le Minh, Duc-Vu Tran, Phan Viet Anh, Nguyen Truong Son, Huy-Tien Nguyen, Bhumindr Butr-indr, P. Vateekul, P. Boonkwan

引用次数: 11

fastTIGER: A rapid method for estimating evolutionary rates of sites from large datasets fastTIGER:一种从大型数据集估计位点进化速率的快速方法

2021 13th International Conference on Knowledge and Systems Engineering (KSE) Pub Date : 2021-11-10 DOI: 10.1109/KSE53942.2021.9648748

Thu Kim Le, L. Vinh

{"title":"fastTIGER: A rapid method for estimating evolutionary rates of sites from large datasets","authors":"Thu Kim Le, L. Vinh","doi":"10.1109/KSE53942.2021.9648748","DOIUrl":"https://doi.org/10.1109/KSE53942.2021.9648748","url":null,"abstract":"The evolutionary processes vary among sites of an alignment, called rate heterogeneity, that must be properly handled when analyzing the evolutionary relationships among species based on their genomic data. To this end, methods have been proposed to estimate the relative evolutionary rates between sites. Tree Independent Generation of Evolutionary Rates (TIGER) is a popular method to estimate the evolutionary rates among sites. However, the TIGER method is computationally expensive to calculate the evolutionary rates for large datasets, especially for whole genome datasets. In this paper, we present a simplified, fast, and accurate method, called fastTIGER, to estimate evolutionary rates for large datasets. Experiments on several large real datasets show that the evolutionary rates from the fastTIGER method have a reasonable correlation with ones estimated from the TIGER method while the fastTIGER method is several orders of magnitudes faster than the TIGER method. Moreover, the site rates estimated by fastTIGER method are as good as the ones estimated from the TIGER method in partitioning alignments to build maximum likelihood trees. The fastTIGER method enhances us to study the evolutionary relationships among species using their genomic data.","PeriodicalId":130986,"journal":{"name":"2021 13th International Conference on Knowledge and Systems Engineering (KSE)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115628464","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 Hybrid Multi-answer Summarization Model for the Biomedical Question-Answering System 生物医学问答系统的混合多答案汇总模型

2021 13th International Conference on Knowledge and Systems Engineering (KSE) Pub Date : 2021-11-10 DOI: 10.1109/KSE53942.2021.9648640

Quoc-An Nguyen, Quoc-Hung Duong, Minh-Quang Nguyen, Huy-Son Nguyen, Hoang-Quynh Le, Duy-Cat Can, Tam Doan Thanh, Mai-Vu Tran

{"title":"A Hybrid Multi-answer Summarization Model for the Biomedical Question-Answering System","authors":"Quoc-An Nguyen, Quoc-Hung Duong, Minh-Quang Nguyen, Huy-Son Nguyen, Hoang-Quynh Le, Duy-Cat Can, Tam Doan Thanh, Mai-Vu Tran","doi":"10.1109/KSE53942.2021.9648640","DOIUrl":"https://doi.org/10.1109/KSE53942.2021.9648640","url":null,"abstract":"In natural language processing problems, text summarization is a difficult problem and always attracts attention from the research community, especially working on biomedical text data which lacks supporting tools and techniques. In this scientific research report, we propose a multi-document summarization model for the responses in the biomedical question and answer system. Our model includes components which is a combination of many advanced techniques as well as some improved methods proposed by authors. We present research methods applied to two main approaches: an extractive summarization architecture based on multi scores and state-of-the-art techniques, presenting our novel prosper-thy-neighbor strategies to improve performance; EAHS model (Extractive-Abstractive hybrid model) based on a denoising auto-encoder for pre-training sequence-to-sequence models (BART). In which we propose a question-driven filtering phase to optimize the selection of the most useful information. Our propose model has achieved positive results with the best ROUGE-1/ROUGE-L scores being the runner-up by ROUGE-2 $F1$ score by extractive summarization results (over 24 participated teams in MEDIQA2021).","PeriodicalId":130986,"journal":{"name":"2021 13th International Conference on Knowledge and Systems Engineering (KSE)","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127377489","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: 2

Apply Bert-based models and Domain knowledge for Automated Legal Question Answering tasks at ALQAC 2021 应用基于bert的模型和领域知识在ALQAC 2021自动法律问答任务

2021 13th International Conference on Knowledge and Systems Engineering (KSE) Pub Date : 2021-11-10 DOI: 10.1109/KSE53942.2021.9648727

Truong-Thinh Tieu, Chieu-Nguyen Chau, Nguyen-Minh-Hoang Bui, Truong-Son Nguyen, Le-Minh Nguyen

引用次数: 6

Deep Representation Learning for Vietnamese Speaker Recognition 深度表征学习在越南语说话人识别中的应用

2021 13th International Conference on Knowledge and Systems Engineering (KSE) Pub Date : 2021-11-10 DOI: 10.1109/KSE53942.2021.9648808

Cao Truong Tran, Dinh Tan Nguyen, Ho Tan Hoang

引用次数: 0

KSE 2021 Conference Committee KSE 2021会议委员会

2021 13th International Conference on Knowledge and Systems Engineering (KSE) Pub Date : 2021-11-10 DOI: 10.1109/kse53942.2021.9648822

引用次数: 0

Leveraging CPLEX to Solve the Vehicle Routing Problem with Time Windows 利用CPLEX求解带时间窗的车辆路径问题

2021 13th International Conference on Knowledge and Systems Engineering (KSE) Pub Date : 2021-11-10 DOI: 10.1109/KSE53942.2021.9648591

Van Manh Tran, T. Vu

{"title":"Leveraging CPLEX to Solve the Vehicle Routing Problem with Time Windows","authors":"Van Manh Tran, T. Vu","doi":"10.1109/KSE53942.2021.9648591","DOIUrl":"https://doi.org/10.1109/KSE53942.2021.9648591","url":null,"abstract":"In recent years, the problem of urban traffic has become increasingly urgent when the number of vehicles has increased rapidly while the transport infrastructure has not kept up with the increasing needs of passengers and drivers. Ridesharing or vehicle sharing are the optimal solutions to save travel time and cost and enhance convenience for passengers and vehicle drivers. The vehicle routing problem with time window (VRPTW), an expansion of Vehicle Routing Problem (VRP), has been examined in recent literature to find the most effective solutions to address the arrangement of customers with known requests while minimizing the cost on a given set of routes. This paper presents a model to address the vehicle routing problem with time windows (VRPTW) applying Mixed-Integer Programming (MIP) to optimize transportation costs and vehicles' numbers. The mathematical model of MIP was conducted in Java using the Branch and Cut algorithm and dynamic search algorithm in the IBM CPLEX library (cplex.jar). The model has been tested with two well-known cases of Solomon's benchmarking problem. The testing results demonstrate that both the cost and the number of vehicles are optimized reasonably with this model. Furthermore, sensitivity analysis for passenger nodes conducted on this model results indicates that the computation time and the number of vehicles increased when the number of customer nodes increased. This paper has widened several directions for future research to develop optimal solutions to vehicle sharing.","PeriodicalId":130986,"journal":{"name":"2021 13th International Conference on Knowledge and Systems Engineering (KSE)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123038923","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

Content based Lecture Video Retrieval using Textual Queries: to be Smart University 基于内容的基于文本查询的讲座视频检索:打造智慧大学

2021 13th International Conference on Knowledge and Systems Engineering (KSE) Pub Date : 2021-11-10 DOI: 10.1109/KSE53942.2021.9648820

Cu Vinh Loc, Nguyen Thanh Nhan, V. Truong, Tran Hoang Viet, Le Hoang Thao, Nguyen Hoang Viet

{"title":"Content based Lecture Video Retrieval using Textual Queries: to be Smart University","authors":"Cu Vinh Loc, Nguyen Thanh Nhan, V. Truong, Tran Hoang Viet, Le Hoang Thao, Nguyen Hoang Viet","doi":"10.1109/KSE53942.2021.9648820","DOIUrl":"https://doi.org/10.1109/KSE53942.2021.9648820","url":null,"abstract":"The amount of lecture videos is rapidly growing due to the popularity of massive online open courses in academic institutions. Thus, the efficient method for lecture video retrieval in various languages is needed. In this paper, we propose an approach for automated lecture video indexing and retrieval. First, the lecture video is segmented into keyframes in a manner that the duplication of these frames is minimal. The textual information embedded in each keyframe is then extracted. We consider this issue as a matter of text detection and recognition. The text detection is solved by our segmentation network in which we propose a binarization approach for optimizing text locations in an image. For text recognition, we take advantage of VietOCR to recognize both English and Vietnamese text. Lastly, we integrate a vector-based semantic search in ElasticSearch to enhance the ability of lecture video search. The experimental results show that our approach gives high performance in detecting and recognizing the text content in both English and Vietnamese as well as enhancing the speed and accuracy of lecture video retrieval.","PeriodicalId":130986,"journal":{"name":"2021 13th International Conference on Knowledge and Systems Engineering (KSE)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116776653","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