检索结果-内蒙古大学图书馆

4th International Conference on Informatics, Multimedia, Cyber and Information System, ICIMCIS 2022

作者： Tri Wahyuni, Cornelia Antoni, Darius Cholil, Widya Universitas Bina Darma Departement of Informatics Engineering Palembang Indonesia Universitas Indo Global Mandiri Faculty of Computer Science Palembang Indonesia Universitas Pembangunan Nasional Veteran Jakarta Faculty of Computer Science Jakarta Indonesia

ISBN: (纸本)9781665473279

The development of information technology is currently growing rapidly and has been implemented in many sectors including trade. Warung is one of the economic drivers of an area that sells basic needs, daily needs. The wa are relatively small and are located in residential areas, with extended working hours seven days a week and very limited availability of raw materials. This study aims to develop a warung information system that is integrated to all stakeholders. The method used to develop ewarung systems is the Prototype method, where this method describes customer needs in more detail. prototype is an unfinished program that provides an interface with a software flow simulation so that it looks like ready-made software. The prototype has three stages, namely Listen to Customer collects user needs, then Build/revice mock-ups, at this stage design and prototype systems are carried out, lastly Customer Test Drives/Mock-ups, Prototypes of the system are tested by users who will use the system until found specifications that match the wishes of the customer or user. In addition, to get maximum results, this study conducted observations used to find out information about business processes, culture and daily warung activities in the field. Interviews were conducted to obtain variations of authentic research results with the process of verifying and validating the data obtained and the last one being to do documentation, which is a record of every event that has occurred or can be said to be an event that has passed. The results of this study were in the form of an e-warung prototype design by obtaining results using alpha testing to respondents, namely running 15 processes and the results obtained were that the entire process was running accordingly. The next test, namely beta testing, was carried out on 5 respondents by asking 6 questions on the questionnaire that had been distributed, the results were that respondents who answered 'Yes' were 83.3% and respondents wh

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

An Improved Technique for Preliminary Diagnosis of COVID-19 via Cough Audio Analysis 4th

An Improved Technique for Preliminary Diagnosis of COVID-1...

引用

4th International Conference on Recent Trends in Image Processing and Pattern Recognition, RTIP2R 2021

作者： Pandhi, Tanya Kapoor, Teghdeep Gupta, Bharat Department of Computer Science and Engineering Jaypee Institute of Information Technology Uttar Pradesh Noida201309 India Faculty of Computer Science and Engineering Jaypee Institute of Information Technology Uttar Pradesh Noida201309 India

ISBN: (纸本)9783031070044

Humanity has suffered catastrophically due to the COVID-19 pandemic. One of the most reliable diagnoses of COVID-19 is RT-PCR (Reverse-Transcription Polymer Chain Reaction) testing. This method, however, has its limitations. It is time-consuming and requires scalability. This research work carries out a preliminary prognosis of COVID-19, which is scalable and less time-consuming. The research carried out a competitive analysis of four machine learning models namely, Multilayer Perceptron, Convolutional Neural Networks, Recurrent Neural Networks with Long Short-Term Memory, and VGG-19 with Support Vector Machines. Out of these models, Multilayer Perceptron outperformed with higher specificity of 94.5% and accuracy of 96.8%. The results show that Multilayer Perceptron was able to distinguish between positive and negative COVID-19 coughs by a robust feature embedding technique. © 2022, Springer Nature Switzerland AG.

关键词： Multilayer neural networks

来源：评论

学校读者我要写书评

暂无评论

GLC++: Source-Free Universal Domain Adaptation through Global-Local Clustering and Contrastive Affinity Learning

arXiv

引用

arXiv 2024年

作者： Qu, Sanqing Zou, Tianpei Röhrbein, Florian Lu, Cewu Chen, Guang Tao, Dacheng Jiang, Changjun The School of Automotive Engineering Department of Computer Science Tongji University China The Faculty of Computer Science Chemnitz University of Technology Germany The Department of Computer Science Shanghai Jiao Tong University China The School of Computer Science Faculty of Engineering The University of Sydney Australia The Department of Computer Science Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University China

Deep neural networks often exhibit sub-optimal performance under covariate and category shifts. Source-Free Domain Adaptation (SFDA) presents a promising solution to this dilemma, yet most SFDA approaches are restricted to closed-set scenarios. In this paper, we explore Source-Free Universal Domain Adaptation (SF-UniDA) aiming to accurately classify "known" data belonging to common categories and segregate them from target-private "unknown" data. We propose a novel Global and Local Clustering (GLC) technique, which comprises an adaptive one-vs-all global clustering algorithm to discern between target classes, complemented by a local k-NN clustering strategy to mitigate negative transfer. Despite the effectiveness, the inherent closed-set source architecture leads to uniform treatment of "unknown" data, impeding the identification of distinct "unknown" categories. To address this, we evolve GLC to GLC++, integrating a contrastive affinity learning strategy. We examine the superiority of GLC and GLC++ across multiple benchmarks and category shift scenarios. Remarkably, in the most challenging open-partial-set scenarios, GLC and GLC++ surpass GATE by 16.7% and 18.6% in H-score on VisDA, respectively. GLC++ enhances the novel category clustering accuracy of GLC by 4.3% in open-set scenarios on Office-Home. Furthermore, the introduced contrastive learning strategy not only enhances GLC but also significantly facilitates existing methodologies. Copyright © 2024, The Authors. All rights reserved.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Unlocking the Potential of DNA Microarray for Accurate Cancer Diagnosis with Deep Learning 7

Unlocking the Potential of DNA Microarray for Accurate Cance...

引用

7th International Conference on Advances in Biomedical engineering, ICABME 2023

作者： Chebli, Hassan Mashhadieh, Zeinab Ali, Mohamad Abou Madi, Mahmoud K. Kassem, Ibrahim Rida Lebanese International University Department of Biomedical Engineering Lebanon University of the Basque Country Department of Computer Science and Artificial Intelligence Spain Lebanese University Faculty of Science Biology Department Lebanon

ISBN: (纸本)9798350325850

Cancer is an abnormal cell growth and proliferation that is caused by mutations at the level of gene sequencing during DNA replication and thus altering normal gene activity. DNA microarray systems allow DNA/RNA hybridization analysis which by turn is involved in cancer diagnosis. However, microarray datasets encounter a real problem where there exists great number of irrelevant features so mainly the focus is on selecting the relevant features for better classification. In this paper, we aim to enhance the performance of detecting cancerous and non-cancerous microarray data. For that information gain is used for feature selection;a comparative analysis is carried using 1D convolutional neural network (CNN) and artificial neural network (ANN) each for classification. Performance parameters studied were accuracy rate, precision, recall, confusion matrix and training loss. Experimental results show that 1D CNN with information gain as feature selection produces accuracy rate 100% while ANN performed with lower accuracy of 88%. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Powered e-Wallet: Enhancing Security and Fraud Detection in Online Payments 1

Blockchain-Powered e-Wallet: Enhancing Security and Fraud De...

引用

1st International Conference on Cryptography and Information Security, VCRIS 2024

作者： Bui-Huu, Dong Le-Nhat, Tan Nguyen-An, Khuong Ho Chi Minh University of Banking Faculty of Management Information Systems Department of Computer Science Ho Chi Minh City Viet Nam Fulbright Vietnam University Undergraduate Faculty Ho Chi Minh city Viet Nam Faculty of Computer Science and Engineering Ho Chi Minh City Viet Nam Vietnam National University Ho Chi Minh City Ho Chi Minh City Viet Nam

ISBN: (纸本)9798331529949

Cashless payment has been emphasized in many countries, especially since the outbreak of the COVID-19 pandemic. Various payment methods have emerged, among which electronic wallets (e-wallets) have become a popular online payment method due to their convenience, flexibility, and time and cost savings for users. However, alongside the growth in the number and value of transactions, e-wallets face challenges from increasingly sophisticated and complex security threats, fraud, and forgery, originating both internally and externally, causing severe financial losses and diminishing customer trust. To ensure the safety of e-wallet, we propose an architecture developed based on the permissioned blockchain platform-Hyperledger Fabric, following a microservice model with high-performance APIs that can be easily integrated into e-wallet systems at an optimal cost without requiring complex infrastructure investments. Thanks to blockchain's immutable, transparent, and decentralized storage nature, this solution effectively monitors and supports real-time fraud detection and forgery prevention, ensuring the safety, security, and integrity of users' online payment transactions. Furthermore, this solution also provides users with immediate notifications via Email or SMS when an attack or fraud is detected on the e-wallet. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis using Machine Learning and Deep Learning Models

Sentiment Analysis using Machine Learning and Deep Learning ...

引用

2024 IEEE International Conference on Machine Learning and Applied Network Technologies, ICMLANT 2024

作者： Vu, Hoang-Dieu Pham, Quang-Tu Solanki, Vijender Kumar Hoang, Trong-Minh Tran, Duc-Tan Faculty of Electrical and Electronic Engineering Phenikaa University Hanoi Viet Nam Department of Computer Science and Enginnering Stanley College Of Engineering & Technology For Women TG Hyderabad India Posts and Telecommunications Institute of Technology Hanoi Viet Nam

ISBN: (纸本)9798350389180

This study investigates sentiment analysis methodologies using two distinct datasets: the IMDb Movie Reviews corpus and a novel Financial Sentiment dataset. Employing a comprehensive approach, the research integrates traditional Machine Learning algorithms and Deep Learning models to analyze and interpret sentiments. The preprocessing phase incorporates techniques such as punctuation removal, text lowercasing, and specialized considerations for financial symbols. Machine Learning models, including Logistic Regression and Random Forest, are applied to the IMDb dataset, with Naive Bayes demonstrating superior performance at 89% accuracy. The Deep Learning model achieves 82% accuracy on the testing set. In the Financial Sentiment dataset, Naive Bayes emerges as the optimal model, despite reduced overall performance due to dataset limitations and imbalance. This research contributes valuable insights into sentiment analysis methodologies, offering a nuanced understanding of model performance across diverse datasets and enhancing our comprehension of sentiment classification in various contexts. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Comparative Evaluation of Neural Network Models for Optimal Computational Offloading in Mobile Edge Computing

Comparative Evaluation of Neural Network Models for Optimal ...

引用

2024 International Conference on Future Telecommunications and Artificial Intelligence, IC-FTAI 2024

作者： Shahid, Zara Ali, Zaiwar Shahzadi, Nazia Abbas, Ziaul Haq Abbas, Ghulam Khan, Haris TelecoN Research Centre GIKI Swabi Topi Pakistan Faculty of Electrical Engineering GIKI Swabi Topi Pakistan Faculty of Computer Science GIKI Swabi Topi Pakistan

ISBN: (纸本)9798331534080

Mobile Edge Computing (MEC) has been promising in reducing latency for computational offloading to nearby edge servers and enhancing user experience. However, selecting the most suitable Machine Learning (ML) method for optimal task-offloading decisions remains a chal-lenge. This study proposes the most effective Neural Network Model (NNM) for making optimal offloading decisions. It has conducted a comparative analysis of several NNMs based on their performance metrics. The simulation results demonstrate that the Gated Recurrent Unit (GRU) delivers the best performance by achieving the accuracy of 95.71 %, including other parameter metrices. © 2024 IEEE.

关键词： Deep Learning (DL) Mobile Device (MD) Mobile Edge Computing (MEC) Mobile Edge Server (MES) Neural Network Models (NNM) optimal decision-making task offloading

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Powered Intrusion Detection for Network Security 12th

Machine Learning-Powered Intrusion Detection for Network Sec...

引用

12th International Conference on Recent Trends in Computing, ICRTC 2024

作者： Nandish, H.D. Rahul, R. Dasari, Hari Charan Kumaran, U. Umah, B. Nagarajan, Senthil Murugan Department of Electronics and Communication Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru India Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India Department of Mathematics Faculty of Science Technology and Medicine University of Luxembourg Esch-sur-AlzetteL-4365 Luxembourg

ISBN: (纸本)9789819788354

In today's digital age, network security is paramount. This paper introduces a robust web application designed to swiftly identify network attacks and real-time anomalies, enabling users to protect their networks effectively. By leveraging cutting-edge technologies and machine learning, our system provides insights into network accuracy, F1-score, and precision, allowing users to gauge their network's safety. Our intrusion detection system classifies attacks into four categories: Denial of Service (DoS), Probe, Remote-to-User (R2L), and User-to-Root (U2R). Positioned strategically within the network, it monitors data traffic from all connected devices and promptly responds to suspicious activity, ensuring network security. Users receive instant alerts to take immediate action. Key technologies include data preprocessing (LabelEncoder and MinMaxScaler), user-friendly web interface (MERN stack), and enhanced security with Google Earth 2.0 for authentication and MongoDB for secure data storage. The Python-based backend operates on the NSL-KDD dataset, facilitating effective intrusion detection evaluation. To enhance accuracy, our system employs four machine learning algorithms: K-Nearest Neighbors (KNN), Convolutional Neural Networks (CNN), Random Forest, and Long Short-Term Memory (LSTM), offering comprehensive protection against network threats. In summary, this paper presents a potent network intrusion detection system for real-time threat identification and security assessment. By combining advanced technologies and machine learning, it ensures accuracy and reliability, serving as a valuable tool for network administrators and security professionals in safeguarding digital networks from evolving threats. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Efficient pipelined flow classification for intelligent data processing in IoT

引用

Digital Communications and Networks 2022年第4期8卷 561-575页

作者： Seyed Navid Mousavi Fengping Chen Mahdi Abbasi Mohammad R.Khosravi Milad Rafiee Department of Computer Engineering Engineering FacultyBu-Ali Sina UniversityHamedanIran Shandong Provincial University Laboratory for Protected Horticulture Weifang University of Science and TechnologyShouguang262700China Telecommunications Group Department of Electrical and Electronic EngineeringShiraz University of TechnologyShirazIran

The packet classification is a fundamental process in provisioning security and quality of service for many intelligent network-embedded systems running in the Internet of Things(IoT).In recent years,researchers have tried to develop hardware-based solutions for the classification of Internet *** to higher throughput and shorter delays,these solutions are considered as a major key to improving the quality of *** of these efforts have attempted to implement a software algorithm on the FPGA to reduce the processing time and enhance the *** proposed architectures,however,cannot reach a compromise among power consumption,memory usage,and throughput *** view of this,the architecture proposed in this paper contains a pipelinebased micro-core that is used in network processors to classify *** this end,three architectures have been implemented using the proposed *** first architecture performs parallel classification based on header *** second one classifies packets in a serial *** last architecture is the pipeline-based classifier,which can increase performance by nine *** proposed architectures have been implemented on an FPGA *** results are indicative of a reduction in memory usage as well as an increase in speedup and *** architecture has a power consumption of is 1.294w,and its throughput with a frequency of 233 MHz exceeds 147 Gbps.

关键词： Efficiency Intelligent flow processing IoT Packet classification Pipeline

来源：评论

学校读者我要写书评

暂无评论

Inter-Vector Interference Self-Cancellation Scheme for Differential OSDM in Underwater Acoustic Communications 24

Inter-Vector Interference Self-Cancellation Scheme for Diffe...

引用

24th IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2023

作者： Wang, Yujie Zhang, Qunfei Ma, Shengqian Zhang, Lingling Han, Jing Leus, Geert Northwestern Polytechnical University School of Marine Science and Technology Xi'an710072 China Delft University of Technology Faculty of Electrical Engineering Mathematics and Computer Science Delft2826 CD Netherlands

ISBN: (纸本)9781665496261

Differential orthogonal signal-division multiplexing (OSDM) is attractive for underwater acoustic (UWA) communications because it can eliminate channel estimation, resulting in a substantial reduction of complexity at the receiver. However, when the channel is time-varying, it may suffer from serious inter-vector interference (IVI), which is similar to inter-carrier interference (ICI) in differential orthogonal frequency-division multiplexing (OFDM). To mitigate this degradation of system performance, this paper provides a novel two-hop differential OSDM system based on IVI self-cancellation. Although this method improves system reliability at the cost of losing data rate, it is easy to implement in UWA modems. Finally, numerical simulations demonstrate the effectiveness of the proposed two-hop differential OSDM system over time-varying UWA channels. © 2023 IEEE.

关键词： Underwater acoustic communication

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：