检索结果-内蒙古大学图书馆

Improving Association Rules Accuracy in Noisy Domains Using Instance Reduction Techniques

Computers, Materials & Continua 2022年第8期72卷 3719-3749页

作者： Mousa Al-Akhras Zainab Darwish Samer Atawneh Mohamed Habib College of Computing and Informatics Saudi Electronic UniversityRiyadh11673Saudi Arabia King Abdullah II School for Information Technology The University of JordanAmman11942Jordan Faculty of Engineering Port Said UniversityPort Said42523Egypt

Association rules’learning is a machine learning method used in finding underlying associations in large *** intentionally or unintentionally present,noise in training instances causes overfitting while building the classifier and negatively impacts classification *** paper uses instance reduction techniques for the datasets before mining the association rules and building the *** reduction techniques were originally developed to reduce memory requirements in instance-based *** paper utilizes them to remove noise from the dataset before training the association rules *** experiments were conducted to assess the accuracy of association rules with different instance reduction techniques,namely:DecrementalReduction Optimization Procedure(DROP)3,DROP5,ALL K-Nearest Neighbors(ALLKNN),Edited Nearest Neighbor(ENN),and Repeated Edited Nearest Neighbor(RENN)in different noise *** show that instance reduction techniques substantially improved the average classification accuracy on three different noise levels:0%,5%,and 10%.The RENN algorithm achieved the highest levels of accuracy with a significant improvement on seven out of eight used datasets from the University of California Irvine(UCI)machine learning *** improvements were more apparent in the 5%and the 10%noise *** RENN was applied,the average classification accuracy for the eight datasets in the zero-noise test enhanced from 70.47%to 76.65%compared to the original *** average accuracy was improved from 66.08%to 77.47%for the 5%-noise case and from 59.89%to 77.59%in the 10%-noise *** confidence was also reported in building the association rules when RENN was *** above results indicate that RENN is a good solution in removing noise and avoiding overfitting during the construction of the association rules classifier,especially in noisy domains.

关键词： Association rules classification instance reduction techniques classification overfitting noise data cleansing

来源：评论

学校读者我要写书评

暂无评论

Classification Based on Texture Analysis for Synthetic Hazy Image from Mount Kelud Haze Image Density 8

Classification Based on Texture Analysis for Synthetic Hazy ...

引用

8th International Conference on Electrical, Electronics and Information Engineering, ICEEIE 2023

作者： Nugroho, Fresy Basid, Puspa Miladin Safitri A. Arif, Yunifa Miftachul Diah, Norizan Mat Bahtiar, Firma Sahrul Nurhayati, Hani Kurniawan, Fachrul Priandani, Nurizal Dwi Dermawan, Dodik Arwin Universitas Islam Negeri Maulana Malik Ibrahim Informatics Engineering Faculty of Science and Technology Malang Indonesia School of Computing Sciences College of Computing Informatics and Media Universiti Teknologi Mara Shah Alam Malaysia Library and Information Science Universitas Islam Negeri Maulana Malik Ibrahim Faculty of Science and Technology Malang Indonesia Manajemen Informatika Program Vokasi Universitas Negeri Surabaya Surabaya Indonesia

ISBN: (纸本)9798350340501

This paper classifies the simulations of homogeneous synthetic images, heterogeneous synthetic hazy images, and original hazy images taken from CCTV (Close Circuit Television) of Mt. Kelud crater using the GLCM (Gray Level Co-Occurrence Matrix) method. The average feature values obtained using the GLCM (Gray Level Co-Occurrence Matrix) method are used to compare the similarity of gray feature values of the three and then classify thin, medium, and thick images. The results for classifying thin haze, medium haze, and thick haze on the homogeneous synthetic hazy image test data obtained an accuracy value of 50%, a precision value of 46%, and a sensitivity value of 65%. As for the classification of thin, medium, and thick fog on heterogeneous synthetic hazy images, test data obtained an accuracy value of 42%, a precision value of 32%, and a sensitivity value of 48%. © 2023 IEEE.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based Data Sharing Framework for Malaysia Government Aid Management System

Blockchain-based Data Sharing Framework for Malaysia Governm...

引用

2023 International Conference on Digital Applications, Transformation and Economy, ICDATE 2023

作者： Azmi, Azman Yahya, Farashazillah Moung, Ervin Gubin Sallehudin, Hasimi Utomo, Rio Guntur Azman, Nur Afrina Universiti Malaysia Sabah Advanced Machine Intelligence Research Lab Faculty of Computing and Informatics Sabah Kota Kinabalu Malaysia Universiti Malaysia Sabah Data Technologies and Application Research Lab Faculty of Computing and Informatics Sabah Kota Kinabalu Malaysia Universiti Kebangsaan Malaysia Centre for Software Technology and Management Faculty of Information Science and Technology Malaysia Telkom University School of Computing Bandung Indonesia Foundation Study and Language Institute University of Reading Malaysia Johor Iskandar Puteri Malaysia

ISBN: (纸本)9798350310689

The Covid-19 pandemic has impacted the world economy, and Malaysia is no exception. Due to the closure of businesses, the rate of unemployment has been recorded at an all-time high. The Malaysian Government through its agencies is assisting citizens through an online platform for incentives and an aid-giving platform. The current architecture of data sharing is using centralized, organization-oriented authentication and is not immutable for audit capability. In addition, the blockchain network is still a proof of concept in the digital government ecosystem. This paper studies the current aid data-sharing ecosystem and analyzes the potential of having a state government consortium blockchain framework that will be used in the Government Network Infrastructure for decentralized, transparent data sharing with audit capability. Several works involving Blockchain adoption based on domain, Blockchain consortium architecture and Government applications using blockchain are being presented. The need for a framework in implementing decentralized data sharing using consortium blockchain architecture for multi-agencies data sharing focusing on Malaysia Government Aid Management is discussed in this paper to provide the opportunity for the research domain. The findings in this paper will be used for future work on the requirement of a proposed government multi-layer consortium blockchain framework for data sharing in the Malaysian Government specifically for the Johore State Government ecosystem. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Explainable Transformer-based Intrusion Detection in Internet of Medical Things (IoMT) Networks

Explainable Transformer-based Intrusion Detection in Interne...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Rajesh Kalakoti Sven Nõmm Hayretdin Bahsi School of Information Technology TalTech Tallinn Estonia School of Informatics Computing and Cyber Systems Northern Arizona University United States

ISBN: (数字)9798350374889

ISBN: (纸本)9798350374896

Internet of Medical Things (IoMT) systems have brought transformative benefits to patient monitoring and remote diagnosis in healthcare. However, these systems are prone to various cyber attacks that have a high impact on security and privacy. Detecting such attacks is crucial for implementing timely and effective countermeasures. Machine learning methods have been applied for intrusion detection tasks in various networks, but explaining the reasons for detection decisions remains an obstacle for security analysts. In this paper, we demonstrate that Transformer architecture, the core of the recent revolutionary large language models, constitutes a promising solution for intrusion detection in IoMT networks. We utilized a comprehensive dataset, CICIoMT2024, recently released specifically for these networks. We created a binary classification model for discriminating attacks from benign traffic and a multi-class model for the identification of specific attack types. We applied Explainable AI (XAi) methods such as LIME and SHAP to generate posthoc explanations for the model decisions. We evaluated and compared the quality of explanations based on three metrics: faithfulness, sensitivity, and complexity. Our findings demonstrate that the applied XAI methods enhance transparency in the predictions of Transformer-based intrusion detection models for IoMT networks, proving that both transparency and high performance can be achieved simultaneously.

关键词： Privacy Sensitivity Explainable AI Intrusion detection Internet of Medical Things Telecommunication traffic Transformer cores Predictive models Transformers Security

来源：评论

学校读者我要写书评

暂无评论

Sensors, Signals, and Imaging informatics: Best contributions from 2023

引用

Yearbook of Medical informatics 2025年第1期33卷 277-279页

作者： Rittner, Leticia Baumgartner, Christian Deserno, Thomas M. Medical Imaging Computing Lab (MICLab) School of Electrical and Computer Engineering University of Campinas Brazil Institute of Health Care Engineering with European Testing Center of Medical Devices Graz University of Technology Austria Peter L. Reichertz Institute for Medical Informatics of TU Braunschweig and Hannover Medical School Braunschweig Germany

OBJECTIVES: To identify and highlight research papers that represent the advances and trends in the field of sensors, signals, and imaging informatics in 2023. METHOD: We performed a bibliographic search on Scopus and PubMed databases using Medical Sub-ject Heading (MeSH) terms combined with keywords. Our aim was to build specific queries for sen-sors, signals, and imaging informatics. We disregarded journals that returned less than three papers on the query and then evaluated titles and abstracts of the papers using a 3-point Likert scale, ranging from 1 (do not include) to 3 (should be included). Only the papers with a total score of 8 or more were re-evaluated again, this time considering the full text, and the top 14 papers with the highest scores were then reviewed by external reviewers and editors of the International Medical informatics Association (IMIA) Yearbook. RESULTS: Among the 643 returned papers published in 2023 in the various areas of sensors, signals, and imaging informatics (SSII), we selected 58 papers with at least 8 Likert points (in total). After a comprehensive evaluation, we identified 14 papers as the best contributions and sent them to eight external reviewers. The full review process resulted in a selection of the four best papers, which were then approved by consensus by the IMIA Yearbook Editorial Board. Although the imaging informatics sub-search returned all of these four papers, one is about sensorless freehand 3D ultrasound recon-struction (representing sensors), and another deals with video-based pulse rate estimation (representing signals). CONCLUSIONS: Sensors, signals, and imaging informatics is a dynamic field of intensive research. The four best papers in 2023 represent advanced approaches focusing on DL-based image processing, analysis, and indicate a shift in the research field from sensor technology development to biosignal and image analysis. The Author(s). This is an open access article published by Thieme under the terms

关键词： Biomedical informatics Deep learning Imaging informatics International Medical informatics Association Yearbook Machine learning Personalized medicine Sensor informatics Signal in-formatics

来源：评论

学校读者我要写书评

暂无评论

Tangles in IOTA to make crypto currency transactions free and secure

引用

International Journal of Cloud computing 2022年第1期11卷 1-13页

作者： Anakath, A.S. Kannadasan, R. Prabakaran, N. Basha, M.S. Saleem Department of MCA EGS Pillai Engineering College Nagapattinam 611002 India School Computer Science and Engineering Vellore Institute of Technology Vellore632014 India Department of Computing and Informatics Mazoon College Muscat133 Oman

Blockchain introduction has made a revolutionary change in the crypto currency around the world but it has not delivered on its promises of free and faster transaction confirmation. Serguei Popov's proposal of using tangles, a directed acyclic graph, which essentially is considered to be the successor of blockchains and offers the required features like machine to machine micro payment and fee-less transaction. It requires the user to approve the previous two transactions in the web to participate in the network. This essentially eliminates the miners and the mining part form the currency exchange and provides the user or participants to do their transactions fee-less. Since the participant verifies the previous two transactions it also contributes to the security of the tangle. In this paper, features of internet of things application (IOTA) and all the improvements in it using tangles are discussed along with how it contributed to the security and how it enables the participants to have fee-less transactions is also discussed. Copyright © 2022 Inderscience Enterprises Ltd.

关键词： Distributed ledger

来源：评论

学校读者我要写书评

暂无评论

Beamspace Channel Estimation Via PARAFAC Decomposition for RIS Assisted Millimeter-Wave Multiuser MISO Communications

引用

IEEE Transactions on Vehicular technology 2024年第5期74卷 7594-7609页

作者： Guo, Xinying Xie, Zongyuan Zhang, Jiankang Chen, Sheng Zhu, Chunhua Key Laboratory of Grain Information Processing and Control Henan University of Technology Ministry of Education China Henan University of Technology College of Information Science and Engineering Zhengzhou450001 China Bournemouth University Department of Computing & Informatics BH12 5BB United Kingdom University of Southampton School of Electronics and Computer Science SouthamptonSO17 1BJ United Kingdom

The reconfigurable intelligent surface (RIS) with massive low-cost passive reflecting elements integrated on a planar surface has the ability to favourably reconfigure the wireless propagation environment, thereby significantly improving the performance of wireless communication networks. In this work, we consider uplink (UL) channel estimation for the RIS assisted millimeter-wave multiuser multiple-input single-output beamspace system where the base station (BS) is equipped with lens antenna array. This channel state information (CSI) estimation task is extremely challenging for two reasons. First, the BS only has limited number of radio frequency chains but the size of beamspace channel is very large. Second, the number of passive components in the RIS is abundance but they lack signal processing capabilities. By exploiting the parallel factor (PARAFAC) decomposition of the received signals, we derive an iterative estimation algorithm, called unitary approximate message passing (UAMP), to accurately estimate the channels between the BS and the RIS as well as the channels between the RIS and the users. To guide the selection of the system parameters, we provide the uniqueness conditions for our PARAFAC decomposition based channel estimation. To theoretically verify the efficiency of our UAMP algorithm, the Cramér-Rao bound (CRB) of the estimation is also derived. Besides, we investigate the achievable downlink (DL) sum rate for the channel estimation obtained by the proposed algorithm by using the maximum power beam selection, the optimized phase shift matrix and the zero forcing precoding. Extensive simulation results demonstrate the excellent mean squared error (MSE) performance of our UAMP estimation algorithm. In particular, for sufficiently high UL signal-to-noise ratio, the MSE of our channel estimation reaches the CRB. Simulation results also show that the DL sum rate achieved by the estimated CSI is very close to that obtained by the perfect CSI. Theoretica

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Predicting Mushroom Edibility with Effective Classification and Efficient Feature Selection Techniques 3

Predicting Mushroom Edibility with Effective Classification ...

引用

3rd International Conference on Robotics, Electrical and Signal Processing Techniques, ICREST 2023

作者： Morshed, Md. Samin Bin Ashraf, Faisal Islam, Muhammad Usama Shafi, Md. Shafiur Raihan Islamic University of Technology Department of Computer Science and Engineering Bangladesh Brac University Department of Cse Bangladesh School of Computing and Informatics Ul Lafayette United States Southeast University Department of Cse Bangladesh

ISBN: (纸本)9798350346435

Machine learning in agriculture has added a new dimension to research field through providing actionable insights for better crop yield. In our work, we have explored various types of mushrooms and utilized efficient feature selection techniques coupled with effective machine learning based classification methods to classify the edibility of mushrooms automatically. Through experimentation with nine distinct machine learning methods and twenty selected features, the result shows that our best model (k-NN) performed significantly better with an accuracy of 99% and F-1 score of 99% in comparison to other machine learning methods. Our research work provided us with valuable actionable insights to devise further scopes in research in the field of mushroom edibility predicting through machine learning. © 2023 IEEE.

关键词： Agriculture

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing STEM Education: BeSAR Augmented Reality Application Sparks Passion for Science in Rural Primary schools 4th

Revolutionizing STEM Education: BeSAR Augmented Reality Appl...

引用

4th International Conference on Advances in Computational Science and Engineering, ICACSE 2023

作者： Tanalol, Siti Hasnah Baharum, Aslina Tahir, Asni Saudi, Azali A. Wahab, Shaliza Hayati Saad, Nordin F. Michael, Jurry Center of Preparatory for Science and Technology UMS Sabah Kota Kinabalu Malaysia School of Engineering and Technology Sunway University Selangor Bandar Sunway Malaysia Faculty of Computing and Informatics UMS Sabah Kota Kinabalu Malaysia Faculty of Humanities Arts and Heritage UMS Sabah Kota Kinabalu Malaysia

ISBN: (纸本)9789819729760

In 2020, it was found that only 20% of the 2 million high school students majored in STEM (Science, technology, Engineering and Mathematics), compared to the national target of 40% of students. This requirement is important for the country to guarantee the sustainability of its development and progress. STEM education provides students with the critical skills needed to succeed in a rapidly changing and increasingly technology-dependent world. With this motivation, the idea was born to help increase the motivation and interest of primary school students in learning science and STEM by using augmented reality (AR) technology. This project has produced an Integrated Science Learning Module and a mobile AR Application, BeSAR: Learning Science through AR, to support STEM teaching and learning outside the classroom. The selected Science Learning Modules are topics based on the elements found in the SK Eco-Science Park Kundasang, namely Aquaponics, Biocompost, Water Cycle and Food Web. Using the developed BeSAR application allows students to experience a more interactive and interesting learning experience. The BeSAR mobile application was developed using the prototyping methodology. Using the Kansei assessment method, after the students used the BeSAR application, the findings showed that the students could accept the use of AR technology in learning and feel that STEM subjects, especially Science, are something fun. The Kansei evaluation method is used to analyze the emotions or feelings of users towards the interface design of mobile applications. This study implies that the use of AR in Science learning can be used as one of the ways to increase interest in science among rural students. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Soil microbes-mediated enzymes promoted the secondary succession in post-mining plantations on the Loess Plateau,China

引用

Soil Ecology Letters 2023年第1期5卷 79-93页

作者： Qi Zhang Jing Ma Alejandro Gonzalez-Ollauri Yongjun Yang Fu Chen School of Public Policy and Management China University of Mining and TechnologyXuzhou 221116China Engineering Research Center of Ministry of Education for Mine Ecological Restoration Xuzhou 221116China School of Computing Engineering and Built EnvironmentGlasgow Caledonian UniversityGlasgowG40BA ScotlandUK School of Environment Science and Spatial Informatics China University of Mining and TechnologyXuzhou 221116China

The diversity of vegetation configuration is the key to ecological restoration in open-pit coal mine ***,the recovery outcomes of different areas with the same vegetation assemblage pattern are completely different after long-term ***,understanding the causes of differential vegetation recovery and the mechanism of plant succession is of great significance to the ecological restoration of *** Pinus tabulaeformis plantations with similar initial site conditions and restoration measures but with different secondary succession processes were selected from the open-pit coal mine dump that has been restored for 30 *** physicochemical properties,enzyme activities,vegetation and microbial features were investigated,while the structural equation models were established to explore the interactions between plants,soil and *** results showed that original vegetation configuration and soil nutrient conditions were altered due to secondary *** the advancement of the secondary succession process,the coverage of plants increased from 34.8%to 95.5%(P<0.05),soil organic matter increased from 9.30 g kg^(-1)to 21.13 g kg^(-1)(P<0.05),and total nitrogen increased from 0.38 g kg^(-1)to 1.01 g kg^(-1)(P<0.05).The activities of soil urease and p-glucosidase were increased by 1.7-fold and 53.26%,***,the secondary succession also changed the soil microbial community structure and *** relative abundance of Nitrospira genus which dominates the nitrification increased *** results showed that urease andβ-glucosidase promoted the increase of vegetation diversity and biomass by promoting the accumulation of soil organic matter and nitrate nitrogen,which promoted the ecological restoration of mine dumps.

关键词： Soil microbes Secondary succession Pinus tabulaeformis Soil enzyme Ecological restoration

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：