发布求助
文献互助 智能选刊 最新文献

2022 9th NAFOSTED Conference on Information and Computer Science (NICS)最新文献

筛选
英文 中文
Adversarial Attacks in Some Recognition Models for Vietnamese Speech Classification 越南语语音分类识别模型中的对抗性攻击
2022 9th NAFOSTED Conference on Information and Computer Science (NICS) Pub Date : 2022-10-31 DOI: 10.1109/NICS56915.2022.10013376
Nguyen Huu Hong Huy, Tien-Thinh Nguyen, Hong-Tai Tran, Tan-Duc Nguyen, Khuong Nguyen-An
{"title":"Adversarial Attacks in Some Recognition Models for Vietnamese Speech Classification","authors":"Nguyen Huu Hong Huy, Tien-Thinh Nguyen, Hong-Tai Tran, Tan-Duc Nguyen, Khuong Nguyen-An","doi":"10.1109/NICS56915.2022.10013376","DOIUrl":"https://doi.org/10.1109/NICS56915.2022.10013376","url":null,"abstract":"The last decade witnessed the tremendous development of Artificial Intelligence (AI). More and more real-life problems are involved with AI. Nonetheless, Machine Learning/Deep Learning models depend strongly on the data we feed in training/validation time. Training with noisy data was proved to cause harmful problems. This paper addresses adversarial attacks against recognition models for Vietnamese speech classification. The attacks are processes of creating audio samples that carry the original content; however, they distract the models with noises, which are hard to detect. Notably, we make attacks for different models that can be applied widely in practice to Vietnamese. This research is an essential first step in building measures to prevent such attacks in the future.","PeriodicalId":381028,"journal":{"name":"2022 9th NAFOSTED Conference on Information and Computer Science (NICS)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133009825","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 IoT Solution for Multiple Sensors Control and Management 多传感器控制和管理的物联网解决方案
2022 9th NAFOSTED Conference on Information and Computer Science (NICS) Pub Date : 2022-10-31 DOI: 10.1109/NICS56915.2022.10013474
Bao Bach-Gia, Lam Luu-Trinh, Minh Nguyen-Dinh, Trung Pham-Dinh, C. Pham-Quoc
{"title":"An IoT Solution for Multiple Sensors Control and Management","authors":"Bao Bach-Gia, Lam Luu-Trinh, Minh Nguyen-Dinh, Trung Pham-Dinh, C. Pham-Quoc","doi":"10.1109/NICS56915.2022.10013474","DOIUrl":"https://doi.org/10.1109/NICS56915.2022.10013474","url":null,"abstract":"The era of the fourth industrial revolution and the Covid-19 pandemic gives rise to the incredible growth of the IoT (Internet of Things) field. The trend of an immense amount of devices connected to specific networks brings up various problems, but most noticeable, control and management issues. In this paper, we propose a structural and efficient solution to solve this problem in a large-scale IoT system - along with two implementations of the proposed solution. The paper's main contribution is to present an overview of the architecture for an IoT system inspired by numerous IoT-based implementations. The design is expected to be dynamic, transparent, and easily deployed for newcomers. Furthermore, with the different implementations in health care and agriculture mentioned later, we want to demonstrate the flexibility and adaptability of the design to various fields.","PeriodicalId":381028,"journal":{"name":"2022 9th NAFOSTED Conference on Information and Computer Science (NICS)","volume":"270 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133354795","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 Model of Discovering Customer Insights in Tourism Sector Approach to Vietnamese Reviews Analytics 越南评论分析中旅游部门发现顾客见解的模型
2022 9th NAFOSTED Conference on Information and Computer Science (NICS) Pub Date : 2022-10-31 DOI: 10.1109/NICS56915.2022.10013410
T. Le, Van-Ho Nguyen, T. Ho
{"title":"A Model of Discovering Customer Insights in Tourism Sector Approach to Vietnamese Reviews Analytics","authors":"T. Le, Van-Ho Nguyen, T. Ho","doi":"10.1109/NICS56915.2022.10013410","DOIUrl":"https://doi.org/10.1109/NICS56915.2022.10013410","url":null,"abstract":"Today, customer-centric business models are more focused. In addition, businesses increasingly own more data about customers and user behavior, especially from social networking platforms. However, the effective exploitation and use of this amount of data is still very limited. Based on those objective motivations, this research proposes a model as a foundation for analyzing and understanding customers to help businesses transform and transform this data into forms of knowledge to support the business, make intelligent business decisions. A data set of 90,513 reviews in Vietnamese from Agoda e-commerce websites in the tourism sector is collected and experimented. In experimental phase, raw corpus was cleaned by text preprocessing, then, the research will use the Net Promoter Score (NPS) to separate the data into three data sets according to three groups of Detractors, Passives and Promoters. From that, Latent Dirichlet Allocation (LDA) was built to extract the hidden topics in the input dataset. The experimental results show that the extracted topics and their features from corpus of customer reviews are reliable. The novelty in this research is to identify the topics that customers are interested in and complaining about.","PeriodicalId":381028,"journal":{"name":"2022 9th NAFOSTED Conference on Information and Computer Science (NICS)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115939707","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 Model for Floating Garbage Detection and Quantification Using Fixed Camera 一种基于固定摄像机的漂浮垃圾检测与量化模型
2022 9th NAFOSTED Conference on Information and Computer Science (NICS) Pub Date : 2022-10-31 DOI: 10.1109/NICS56915.2022.10013461
Trinh Duc Minh, Nguyen Thi Xuan Hoa, T. Le
{"title":"A Model for Floating Garbage Detection and Quantification Using Fixed Camera","authors":"Trinh Duc Minh, Nguyen Thi Xuan Hoa, T. Le","doi":"10.1109/NICS56915.2022.10013461","DOIUrl":"https://doi.org/10.1109/NICS56915.2022.10013461","url":null,"abstract":"A large amount of plastic waste generated from production and living activities is polluting and threatening aquatic habitats. Large amounts of this plastic waste found in the oceans originate from land. It finds its way to the vast ocean through rivers and other waterways. In this study, we present a model, which is an algorithm consisting of 5 main steps to detect and quantify floating waste based on images obtained from a fixed camera. In which the image obtained from the camera will be calibrated to the bird's-eye view, then the floating waste will be detected and quantified using the pre-trained Mask R-CNN model. Experimental results show that our model has the potential to be applied in automated tasks of monitoring and quantifying floating waste along the riverbank from images obtained by fixed cameras on autonomous surface vehicles.","PeriodicalId":381028,"journal":{"name":"2022 9th NAFOSTED Conference on Information and Computer Science (NICS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129602506","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
FLC: A New Secure and Efficient SPN-Based Scheme for Block Ciphers FLC:一种安全高效的基于spn的分组密码方案
2022 9th NAFOSTED Conference on Information and Computer Science (NICS) Pub Date : 2022-10-31 DOI: 10.1109/NICS56915.2022.10013379
Cuong Nguyen, Nam Tran, L. Nguyen
{"title":"FLC: A New Secure and Efficient SPN-Based Scheme for Block Ciphers","authors":"Cuong Nguyen, Nam Tran, L. Nguyen","doi":"10.1109/NICS56915.2022.10013379","DOIUrl":"https://doi.org/10.1109/NICS56915.2022.10013379","url":null,"abstract":"The FLC scheme was proposed and analyzed the theoretic security in [1]. In this paper, We add the practically secure proofs of a structure based on FLC against the linear and differential cryptanalysis. Then, we propose the MDS matrices to implement this structure with two 128-bit/256-bit block sizes. Finally, we evaluate the above experimental results and compare them with several implementations of the well-known block ciphers. These results show that FLC is indeed a prospective scheme for post-quantum cryptography.","PeriodicalId":381028,"journal":{"name":"2022 9th NAFOSTED Conference on Information and Computer Science (NICS)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126226211","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
Viscous Resistance Acting on a Symmetrical Hull with Different Turbulent Viscous Model 不同湍流粘性模型下对称船体的粘性阻力
2022 9th NAFOSTED Conference on Information and Computer Science (NICS) Pub Date : 2022-10-31 DOI: 10.1109/NICS56915.2022.10013465
Ngo Van He, N. Van Hien
{"title":"Viscous Resistance Acting on a Symmetrical Hull with Different Turbulent Viscous Model","authors":"Ngo Van He, N. Van Hien","doi":"10.1109/NICS56915.2022.10013465","DOIUrl":"https://doi.org/10.1109/NICS56915.2022.10013465","url":null,"abstract":"This topic talks about effects of the turbulent viscous models on viscous resistances acting on a symmetrical hull in water by using a commercial Computational Fluid Dynamic (CFD). An original symmetrical model is made from under water hull part of a ship or a hull part of an Autonomous Underwater Vehicles (AUV). By using CFD, the hydrodynamic performances and viscous resistances acting on the model is investigated in the different computed cases. The eight turbulent viscous models as well as k-ε standard, k-ε realizable, k-ε RNG, k-ω standard, k-ω SST, Reynolds stress seven equations, transition fourth equation and Transition k-kl-ω three equations are used in the simulation. By analyzing obtained results, effect of the turbulent viscous models on hydrodynamic performances of the symmetrical model is investigated. The CFD results of pressure distribution, velocity distribution in boundary layer around hull is useful to understand the reasons effects on viscous resistance of the symmetrical model.","PeriodicalId":381028,"journal":{"name":"2022 9th NAFOSTED Conference on Information and Computer Science (NICS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122762343","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
Improving Automatic Speech Recognition for Low-Resource Language by Data Augmentation 基于数据增强的低资源语言语音自动识别方法
2022 9th NAFOSTED Conference on Information and Computer Science (NICS) Pub Date : 2022-10-31 DOI: 10.1109/NICS56915.2022.10013370
Huynh Thi Nguyen Nghia, Nguyen Tran Hoan Duy, Nguyen Gia Huy, Nguyen Mau Minh Due, Le Dinh Luan, Do Duc Hao, Nguyen Duc Dung, Pham Minh Hoang, V. T. Hung
{"title":"Improving Automatic Speech Recognition for Low-Resource Language by Data Augmentation","authors":"Huynh Thi Nguyen Nghia, Nguyen Tran Hoan Duy, Nguyen Gia Huy, Nguyen Mau Minh Due, Le Dinh Luan, Do Duc Hao, Nguyen Duc Dung, Pham Minh Hoang, V. T. Hung","doi":"10.1109/NICS56915.2022.10013370","DOIUrl":"https://doi.org/10.1109/NICS56915.2022.10013370","url":null,"abstract":"Automatic speech recognition (ASR) is one of the emergency tasks in human-computer interaction. There are many studies work in the field of building network architecture to deal with this task. While data augmentation was deeply discovered in computer vision, it is a big lag behind in the field of speech. Large data collection is not trivial, and in some cases it is impossible. The problem with data size is even more serious in some low-resource languages, such as Vietnamese. This study focuses on the data augmentation approach to deal with the small-size datasets to help the deep learning network better coverage in the ASR task. The experiment results on various configures of the VIVOS dataset, and two variations of the Conformer network architecture show that our proposed method gets promising improvement.","PeriodicalId":381028,"journal":{"name":"2022 9th NAFOSTED Conference on Information and Computer Science (NICS)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124136922","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
Performance Enhancement of Satellite-to-Ground FSO System using Deep Learning-Based Detection 基于深度学习检测的星对地FSO系统性能增强
2022 9th NAFOSTED Conference on Information and Computer Science (NICS) Pub Date : 2022-10-31 DOI: 10.1109/NICS56915.2022.10013450
Nguyen Thi Hang Duy, M. Vu, H. Pham, N. Dang
{"title":"Performance Enhancement of Satellite-to-Ground FSO System using Deep Learning-Based Detection","authors":"Nguyen Thi Hang Duy, M. Vu, H. Pham, N. Dang","doi":"10.1109/NICS56915.2022.10013450","DOIUrl":"https://doi.org/10.1109/NICS56915.2022.10013450","url":null,"abstract":"This paper proposes to use deep learning to improve the performance of satellite-to-ground free-space optical (FSO) communication system under the negative impact of many physical impairments such as atmospheric turbulence, atmospheric attenuation, and free-space path loss. We first implement a simulation of the satellite-to-ground FSO system over Gamma-Gamma turbulence channel using a conventional detection to obtain the binary data at the receiver. This data is subsequently utilized for training the deep learning (DL)-based detection model via a convolutional neural network (CNN) model. Simulation results show that bit-error rate (BER) of the satellite-to-ground FSO communication system is significantly lower than that of the traditional systems. Moreover, we demonstrate that the proposed DL detection model is especially effective in term of the performance gain.","PeriodicalId":381028,"journal":{"name":"2022 9th NAFOSTED Conference on Information and Computer Science (NICS)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126429062","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
PROCTORING ONLINE EXAM USING IOT TECHNOLOGY 使用物联网技术监考在线考试
2022 9th NAFOSTED Conference on Information and Computer Science (NICS) Pub Date : 2022-10-31 DOI: 10.1109/NICS56915.2022.10013409
X. Nguyen, Viet Man Le-Pham, T. Than, Minh-Son Nguyen
{"title":"PROCTORING ONLINE EXAM USING IOT TECHNOLOGY","authors":"X. Nguyen, Viet Man Le-Pham, T. Than, Minh-Son Nguyen","doi":"10.1109/NICS56915.2022.10013409","DOIUrl":"https://doi.org/10.1109/NICS56915.2022.10013409","url":null,"abstract":"Organizing exams is an important part of teaching activities that measure learners' learning outcomes. Normally, there are 2 forms of exam organization today: face-to-face and online exams. Proctoring of candidates aims to minimize fraud and to make statistical reports on the unusual behavior of candidates during the exam as the main challenges of online examination [1]. In this paper, we propose a model of Proctoring of Online Test (POT) built on the foundation of an embedded system integrating artificial intelligence algorithms to solve the problem of authentication and predict the cheating behavior of candidates in the exam. The highlight of the system is the ability to automatically and continuously monitor in real time during the online exam. Experimental results show that the POT system is capable of detecting fraud at over 85%. Therefore, the POT solution provides training institutions with a method to assess the learning quality of learners with low operating costs and rapid deployment.","PeriodicalId":381028,"journal":{"name":"2022 9th NAFOSTED Conference on Information and Computer Science (NICS)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133240433","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
GCA-Net: Geometrical Constraints-based Advanced Network for Polyp Segmentation GCA-Net:基于几何约束的高级多边形分割网络
2022 9th NAFOSTED Conference on Information and Computer Science (NICS) Pub Date : 2022-10-31 DOI: 10.1109/NICS56915.2022.10013367
Q. Nguyen, Thi-Thao Tran, Van-Truong Pham
{"title":"GCA-Net: Geometrical Constraints-based Advanced Network for Polyp Segmentation","authors":"Q. Nguyen, Thi-Thao Tran, Van-Truong Pham","doi":"10.1109/NICS56915.2022.10013367","DOIUrl":"https://doi.org/10.1109/NICS56915.2022.10013367","url":null,"abstract":"Colonoscopy is a common procedure for detecting and screening colorectal polyps, however, it poses a number of challenges because of the properties of images and the features of polyps inside, which can vary in shape, color, condition, and clear non-distinction with the surrounding context. Deep learning-based approaches have recently emerged, which considerably boost polyp segmentation procedures and gradually convert and replace out-of-date methods. Nevertheless, determining an effective measure remains a significant difficulty, which motivates us to propose GCA-Net for polyp segmentation. We first employ EfficientNetV2 as the backbone to extract improved salient features, then pass them via two modules, SE-PASPP and SE-RFB, to capture more contexture before feeding them into a dual-asymmetrical partial decoder to build a final resolution map. Finally, we develop a novel loss function based on the region-based strength of Dice loss and the geometrical constraints-based advantages of Active Contour with Elastica (ACE) loss. The suggested method's preeminence is demonstrated by comparing results to over state-of-the-art approaches in both learning and generalization assessment.","PeriodicalId":381028,"journal":{"name":"2022 9th NAFOSTED Conference on Information and Computer Science (NICS)","volume":"37 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131776982","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：604180095
Book学术官方微信