检索结果-内蒙古大学图书馆

2nd International Conference on technology Innovation and Its Applications, ICTIIA 2024

作者： Sylvia, Visca Lydia, Maya Silvi Nasution, Benny Benyamin Universitas Sumatera Utara Faculty of Computer Science and Information Technology Medan Indonesia Politeknik Negeri Medan Department of Computer Engineering and Informatics Medan Indonesia

ISBN: (纸本)9798350351613

The purpose of this study is to improve the performance of Support Vector Machine (SVM) algorithm in sentiment analysis of trainee reviews through parameter optimization using Grid Search. Trainee reviews were taken from the Vocational and Productivity Training Center (BBPVP) Medan, which is the context of this study. The method used includes collection and preprocessing of review data, followed by the application of SVM for sentiment analysis. Grid Search is used to optimize the cost and kernel parameters of SVM. The results show that after optimization, the resulting SVM model shows significant performance improvement compared to the model before optimization. Accuracy increased from 68.75% to 71.96%, with improvements in other metrics such as precision, recall, and F1 score. These findings suggest that Grid Search is an effective method to optimize SVM parameters in sentiment analysis, providing a more accurate evaluation of the effectiveness of training programs at BBPVP Medan. This research makes an important contribution by applying hyperparameter optimization to SVM and suggests the application of this method for similar analysis in the future. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Distribution of ultra wideband (UWB) receive timestamps in dense indoor environment based on the Saleh-Valenzuela channel model 14

Distribution of ultra wideband (UWB) receive timestamps in d...

引用

14th International Conference on Communications, COMM 2022

作者： Hollosi, Gergely Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics Dept. of Telecommunications and Media Informatics BudapestH-1111 Hungary

ISBN: (纸本)9781665494854

In ultra wideband (UWB) based localization and ranging systems, the main error source of ranging is the multi path effect on the timestamping process. However, in the literature it is widely assumed that the receive timestamp has some Gaussian distribution. The paper uses simulations featuring the recommended channel model of the IEEE 802.15.4a standard to investigate the distribution of the receive timestamps in dense office indoor environments. It is shown here that the distribution of receive timestamps is dissimilar to the Gaussian distribution, and the paper proposes a distribution applicable for probability inference methods. © 2022 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

A Cocoa Ripeness Detection and Classification Model Based on Improved YOLOv5s 10

A Cocoa Ripeness Detection and Classification Model Based on...

引用

10th International Conference on Advanced informatics: Concept, Theory and Application, ICAICTA 2023

作者： Ayubi, Aula Faiz, Muhammad Situmorang, George B. Ramadhani, Kurniawan Nur Utama, Nugraha P. School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia Telkom University of School of Computing Bandung Indonesia

ISBN: (纸本)9798350329919

The present study introduces a novel approach to identifying the maturity of cacao fruits, utilizing YOLOv5s in tandem with the Convolutional Block Attention Module (CBAM). The efficacy of this method was evaluated on two distinct datasets, namely the Cocoa Maturity Dataset TCS 01 and the dataset from PT. Cargill Indonesia. The integration of CBAM into the network is aimed at enhancing the feature representation of the model, leading to an improvement in detection accuracy. The method under consideration demonstrated efficacy in attaining elevated levels of precision while concurrently maintaining a condensed model magnitude, thereby conferring benefits for real-world applications. The results indicate that the suggested approach holds promise for enhancing the cacao industry by increasing the level of cocoa cultivation productivity. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Combining TL and KD for Object Detection Model Compression 13

Combining TL and KD for Object Detection Model Compression

引用

Joint 13th International Conference on Soft Computing and Intelligent Systems and 25th International Symposium on Advanced Intelligent Systems, SCIS and ISIS 2024

作者： Peng, Yuhan Lyu, Yan Zhao, Qiangfu The University of Aizu Computer Science and Engineering Aizuwakamatsu965-8580 Japan Muroran Institute of Technology Sciences and Informatics Muroran050a-8585 Japan

ISBN: (纸本)9798350373332

In modern society, object detection tasks have become extremely important due to their numerous applications in fields such as autonomous driving, surveillance, and healthcare. Real-time detection is particularly crucial for many applications. However, with the advancements in deep learning-based object detection methods, high performance often comes with high computational resource requirements, posing challenges for real-time monitoring, especially on resource-constrained devices. To address this issue, we study model compression using both transfer learning (TL) and knowledge distillation (KD). Specifically, we use the YOLOv5n model as a test case to show the basic idea for improving the performance of a small student model using a larger dataset for TL and a larger model for KD. As for KD, we further investigate feature-based and output-based KD. Experimental results show that the small student model can be improved significantly using TL and KD, with the mean Average Precision (mAP0.5) being increased by 13.28% compared to the baseline model. These results demonstrate the effectiveness of TL and KD in achieving high detection performance while reducing computational demands, making them suitable for various real-world applications. © 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

The Optimization of Planning and Operation Control: Case Study in East Kalimantan, Indonesia 6

The Optimization of Planning and Operation Control: Case Stu...

引用

6th International Conference on Power engineering and Renewable Energy, ICPERE 2024

作者： Annurrahman, Yoga Fitrah Rahman, Fathin Saifur Hariyanto, Nanang Yasa, I Made Harta Bandung Institute of Technology School of Electrical Engineering and Informatics Bandung Indonesia PT PLN Indonesia Power Unit Bisnis Pembangkitan Bali Bali Indonesia

ISBN: (纸本)9798331504694

The reliability of the electrical system is one of the most important aspects in ensuring the distribution of electrical power supply, especially in remote and isolated areas. With the increase in customer loads each year, the stability of the power system is quite fluctuating, therefore PLN in this case as the main supplier of electrical power must guarantee the quality of power and the stability of the electrical power system. Therefore, a thorough planning is needed to meet the needs of electrical power, especially in West Kutai Regency, East Kalimantan. This experiment focuses on optimizing the planning and operation control in Melak Isolated Electrical Power System in West Kutai Regency, East Kalimantan. Therefore, the system is more reliable and stable, can meet the needs of the electrical energy supply in the area. Some of the steps taken in this experiment include conducting mathematical modeling of the generating system;determining the objective function;collecting planning data and generator operation dispatch;formulating parameters into objective functions;starting optimization of planning and operation;testing with planning and operation simulations;and analysis of optimization result data. © 2024 IEEE.

关键词： Power distribution planning

来源：评论

学校读者我要写书评

暂无评论

The Optimization of n-Gram Feature Extraction Based on Term Occurrence for Cyberbullying Classification

引用

Data Science Journal 2024年第1期23卷

作者： Setiawan, Yudi Maulidevi, Nur Ulfa Surendro, Kridanto School of Electrical Engineering and Informatics Institute of Technology Bandung Bandung Indonesia

Cyberbullied communications should be bundled since online harassment is growing and has serious implications. High cyberbullying requires strong text classification algorithms to safeguard persons and communities. The n-Gram models language by collecting ‘n’ components, usually words or characters, from a text and detecting how words relate and if major items or sentences are cyberbullying document types. The research improves term value generation and text classification accuracy by extracting features using TF-IDF and n-Gram. The optimum TF-IDF feature extraction pattern demonstrated the usefulness of n-Gram in cyberbullying document classification. This field demands good categorization and feature extraction. Because cyberbullying takes numerous forms and venues, broad classification is essential. To test unigram, bigram, and trigram approaches across text lengths and frequencies, this study uses several parameter values. The research also shows the limitations and gaps in earlier methods and underscores the necessity for various n-Gram parameter values to overcome cyberbullying text complexity. Short-sentence articles, fluctuating data frequencies, and dynamic online interactions necessitate complex solutions. Ideal n-Gram patterns increase cyberbullying text categorization and give context to the field. This research acknowledges cyberbullying’s prevalence and effects, the necessity for effective categorization methods, and current techniques’ limitations, opening the way for more comprehensive and adaptive online harassment combating strategies. © 2024 The Author(s).

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Digital Twin Model for Smart Maintenance of Data Center Facilities : Study Literature Review 10

Digital Twin Model for Smart Maintenance of Data Center Faci...

引用

10th International Conference on ICT for Smart Society, ICISS 2023

作者： Ramdani, Dani Supangkat, Suhono Harso Hidayat, Fadhil Purwoadi, Michael Andreas School of Electrical and Informatics Engineering Bandung Institute of Technology Bandung Indonesia National Research and Innovation Agency Jakarta Indonesia

ISBN: (纸本)9798350339543

Digital twin is a technology that supports the implementation of digital transformation. The digital twin was developed to support decision making in various sectors. The digital twin concept is almost 20 years old and continues to evolve for use cases for the technology in new industries. Maintenance is one of the important points of the product life cycle as the origin of the digital twin. The data center facility is one of the supporters of digital transformation which must be able to guarantee the availability of its services. The availability of data center services is affected by the chosen maintenance strategy. This paper will discuss data centers and maintenance strategies as well as definitions, characteristics to examples of implementing digital twins, especially in the case of implementing intelligent maintenance. It is hoped that with the description of this paper, more specific research opportunities related to optimizing the application of digital twins for maintenance specifically used in data center facilities are expected. © 2023 IEEE.

关键词： Maintenance

来源：评论

学校读者我要写书评

暂无评论

High performance of Dengue shock syndrome detection using extreme gradient boosting with ANOVA feature selection

Journal of Biotech Research

引用

Journal of Biotech Research 2024年 16卷 22-31页

作者： Muflikhah, Lailil Iskandar, Agustin Yudistira, Novanto Nadlori, Isbat Uzzin Dewanto, Bambang Nur Faculty of Computer Science Brawijaya University Malang India Faculty of Medicine Brawijaya University Malang India Department of Informatics Engineering and Computer Politeknik Elektronika Negeri Surabaya India Faculty of Technology Information Merdeka University Malang India

Dengue shock syndrome (DSS) is an infectious disease that affects millions of people every year all over the world. Early detection of DSS is essential for providing effective therapy and promoting patient recovery. In this work, we proposed a method to enhance DSS detection by combining the Extreme Gradient Boosting (XGBoost) algorithm with variance (ANOVA) feature selection analysis. We used a clinical dataset that contained important information gleaned from people with dengue virus infection. The dataset used for the research was collected from patients at Syaiful Anwar Hospital and consisted of 501 instances. Of these, 401 cases were related to DSS, while the other instances were unrelated to this specific medical condition. An analysis of variance (ANOVA) evaluated the most significant factors that distinguished persons with DSS from those with other dengue diseases. After that, the XGBoost model gave the characteristics of the selected features. For evaluation, we split the data into 80% and 20% for training and testing, respectively. The experimental result showed that the created model had a high degree of performance evaluation in detecting DSS. The highest performance achieved an accuracy of 0.839, precision of 0.875, recall of 0.92, and f1-score of 0.897. Most importantly, the model could detect DSS early on, enabling more proactive therapy and faster responses for individuals at risk of developing the condition. © (2024), (Bio Tech System). All Rights Reserved.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

New Cloud Computing Authentication Based on Secure Hash Algorithm (SHA-3) and Lightweight Sosemanuk Algorithm 2nd

New Cloud Computing Authentication Based on Secure Hash Algo...

引用

2nd International Conference on Cyber Intelligence and Information Retrieval, CIIR 2023

作者： Niaf, Jolan Rokan Kadhim, Aqeel Kamil Mohammed, Qutaiba Humadi Hoomod, Haider K. Salman, Muna Muhsen Iraqi Commission for Computers & Informatics Informatics Institute for Postgraduate Studies Baghdad Iraq Computer Techniques Engineering Department Imam Al-Kadhim College Baghdad Iraq College of Nursing University of Baghdad Baghdad Iraq College of Education Al-Mustansiriyah University Baghdad Iraq Ministry of Science and Technology Department of Information Technology Baghdad Iraq

ISBN: (纸本)9789819776023

The term "cloud computing" refers to a vast network of linked, virtually hosted, and easily updatable computer resources. That are capable of consisting of a number of different apps and offering a number of different services to customers, and that have the potential to do so. Customers are required to pay for the cost of using the Services in accordance with the company's "pay-for-use only" policy. However, there are certain firms, such as Google Inc, that provide customers with particular free storage space even though the services provided by the company are limited, specifically with regard to the public cloud. A third-party service provider frequently owns and maintains the infrastructure required to run cloud computing services. But because more and more data and files pertaining to individuals and businesses are being stored in the cloud, worries have started to grow about how safe it actually is. Among these are the protection of software for virtualization and distributed computing, the safety of application software, the administration of identities, and the authentication and restriction of access. Nevertheless, efficient user authentication is the most essential need of cloud computing, as it limits unauthorized usage of a cloud server. Cloud computing has become increasingly popular in recent years. In this research, we present a new authentication method between users and online computing systems that is based on the suggested secure hash algorithm (SHA-3) and makes use of the lightweight Sosemanuk method. We created this technique. That system is going to be known as the SoSha3 system. The design that has been proposed for the system deals with data in three different sizes: 128, 256, and 512 bits. In order to make these authentication systems suitable for cloud computing at high rates, some modifications were made to them. The three-dimensional chaotic system, also known as the Lorenz system, will be combined with the authentication architecture tha

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

Modeling Hybrid Feature-Based Phishing Websites Detection Using Machine Learning Techniques

引用

Annals of Data Science 2024年第1期11卷 217-242页

作者： Das Guptta, Sumitra Shahriar, Khandaker Tayef Alqahtani, Hamed Alsalman, Dheyaaldin Sarker, Iqbal H. Department of Computer Science and Engineering Chittagong University of Engineering & ampTechnology Chittagong4349 Bangladesh Unit of Cybersecurity Department of Computer Science Center of Artificial Intelligence King Khalid University Abha Saudi Arabia School of Engineering Computing and Informatics Dar Al-Hekma University Jeddah Saudi Arabia

In this paper, we mainly present a machine learning based approach to detect real-time phishing websites by taking into account URL and hyperlink based hybrid features to achieve high accuracy without relying on any third-party systems. In phishing, the attackers typically try to deceive internet users by masking a webpage as an official genuine webpage to steal sensitive information such as usernames, passwords, social security numbers, credit card information, etc. Anti-phishing solutions like blacklist or whitelist, heuristic, and visual similarity based methods cannot detect zero-hour phishing attacks or brand-new websites. Moreover, earlier approaches are complex and unsuitable for real-time environments due to the dependency on third-party sources, such as a search engine. Hence, detecting recently developed phishing websites in a real-time environment is a great challenge in the domain of cybersecurity. To overcome these problems, this paper proposes a hybrid feature based anti-phishing strategy that extracts features from URL and hyperlink information of client-side only. We also develop a new dataset for the purpose of conducting experiments using popular machine learning classification techniques. Our experimental result shows that the proposed phishing detection approach is more effective having higher detection accuracy of 99.17% with the XG Boost technique than traditional approaches. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022.

关键词： Search engines

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：