检索结果-内蒙古大学图书馆

Enhancing Classification Algorithm Recommendation in Automated Machine Learning: A Meta-Learning Approach Using Multivariate Sparse Group Lasso

引用

Computer Modeling in engineering & Sciences 2025年第2期142卷 1611-1636页

作者： Irfan Khan Xianchao Zhang Ramesh Kumar Ayyasamy Saadat M.Alhashmi Azizur Rahim School of Software Dalian University of TechnologyDalian116620China Faculty of Information and Communication Technology Universiti Tunku Abdul RahmanKampar31900Malaysia College of Computing and Informatics University of SharjahSharjah27272United Arab Emirates Department of Computer Systems Engineering University of Engineering and Applied SciencesSwat19200Pakistan

The rapid growth of machine learning(ML)across fields has intensified the challenge of selecting the right algorithm for specific tasks,known as the Algorithm Selection Problem(ASP).Traditional trial-and-error methods have become impractical due to their resource *** Machine Learning(AutoML)systems automate this process,but often neglect the group structures and sparsity in meta-features,leading to inefficiencies in algorithm recommendations for classification *** paper proposes a meta-learning approach using Multivariate Sparse Group Lasso(MSGL)to address these *** method models both within-group and across-group sparsity among meta-features to manage high-dimensional data and reduce multicollinearity across eight meta-feature *** Fast Iterative Shrinkage-Thresholding Algorithm(FISTA)with adaptive restart efficiently solves the non-smooth optimization *** validation on 145 classification datasets with 17 classification algorithms shows that our meta-learning method outperforms four state-of-the-art approaches,achieving 77.18%classification accuracy,86.07%recommendation accuracy and 88.83%normalized discounted cumulative gain.

关键词： Meta-learning machine learning automated machine learning classification meta-features

来源：评论

学校读者我要写书评

暂无评论

Research on Garbled Circuits-Based Identity Authentication and Ciphertext Hidden Access Control in Vehicular Networks 24

Research on Garbled Circuits-Based Identity Authentication a...

引用

9th International Conference on Cloud computing and Internet of Things, CCIOT 2024

作者： Jiao, Zhilong Bai, Fenhua Zhang, Chi Zhang, Xiaohui Gong, Bei Faculty of Information Engineering and Automation Kunming University of Science and Technology China Kunming China Department of Computing Beijing University of Technology China Beijing China

ISBN: (纸本)9798400717161

Since most communications in vehicular networks rely on wireless transmissions, information broadcast by vehicles is highly susceptible to interception and eavesdropping by third parties, making it vulnerable to various attacks. This can result in communication messages being tampered with and the leakage of vehicle locations and identity privacy. From a security perspective, this paper introduces Yao's garbled circuit mechanism, combining random bytes with the solutions of linear equations as identity information assigned to vehicle nodes. By employing dual authentication, the proposed approach addresses issues such as privacy protection, anonymity, replay attacks, and collusion attacks in vehicular networks, thereby enhancing security. Moreover, considering the post-authentication access control scenario, this paper proposes a novel LSSS matrix transformation algorithm for ciphertext hidden access control strategy. It realizes a partially hidden policy, which makes matrix generation more efficient by supporting both AND and OR gates, thus improving the access control efficiency while ensuring security. Performance analysis indicates that in terms of identity authentication, the scheme reduces computational costs by an average of 96.25%, and in access control, the scheme reduces key generation time by an average of 80%. Copyright © 2024 held by the owner/author(s). Publication rights licensed to ACM.

关键词： Ciphertext

来源：评论

学校读者我要写书评

暂无评论

Aircraft parameter estimation using a stacked long short-term memory network and Levenberg-Marquardt method

引用

Chinese Journal of Aeronautics 2024年第2期37卷 123-136页

作者： Zhe HUI Yinan KONG Weigang YAO Gang CHEN School of Aerospace Science and Technology Xidian UniversityXi’an 710071China Computation Aerodynamics Institution China Aerodynamics Research and Development CenterMianyang 621000China Faculty of Computing Engineering and MediaDe Montfort UniversityLeicester LE19BHUnited Kingdom School of Aerospace Engineering Xi’an Jiaotong UniversityXi’an 710049China

To effectively estimate the unknown aerodynamic parameters from the aircraft’s flight data,this paper proposes a novel aerodynamic parameter estimation method incorporating a stacked Long Short-Term Memory(LSTM)network model and the Levenberg-Marquardt(LM)*** stacked LSTM network model was designed to realize the aircraft dynamics modeling by utilizing a frame of nonlinear functional mapping based entirely on the measured input-output data of the aircraft system without requiring explicit postulation of the *** LM method combines the already-trained LSTM network model to optimize the unknown aerodynamic *** proposed method is applied by using the real flight data,generated by ATTAS aircraft and a bio-inspired morphing Unmanned Aerial Vehicle(UAV).The investigation reveals that for the two different flight data,the designed stacked LSTM network structure can maintain the efficacy of the network prediction capability only by appropriately adjusting the dropout rates of its hidden layers without changing other network parameters(i.e.,the initial weights,initial biases,number of hidden cells,time-steps,learning rate,and number of training iterations).Besides,the proposed method’s effectiveness and potential are demonstrated by comparing the estimated results of the ATTAS aircraft or the bio-inspired morphing UAV with the corresponding reference values or wind-tunnel results.

关键词： Parameter estimation LSTM network model LM method Aerodynamic parameters Flight data Aircraft dynamics modeling Network prediction capability Network parameters

来源：评论

学校读者我要写书评

暂无评论

Svante Wold 1941 -2022

引用

Spectroscopy Europe 2022年第1期34卷 27-29页

作者： Davies, Antony N. Sustainable Environment Research Centre Faculty of Computing University of South Wales SERC Engineering and Science United Kingdom

Davies presents an obituary for Svante Wold who died on Jan 4, 2022. Wold wasn't the first statistically talented person in the Wold family, his father Herman Ole Andreas Wold was a famous statistician in his own right, born in Skien, Norway on Christmas Day 1908, Herman and his family emigrated to Sweden where they settled. Svante decided to work in the field of chemical data processing and provided us with the term "Chemometrics".

关键词：

来源：评论

学校读者我要写书评

暂无评论

USTW Vs. STW: A Comparative Analysis for Exam Question Classification based on Bloom’s Taxonomy

Mendel

引用

Mendel 2022年第2期28卷 25-40页

作者： Gani, Mohammed Osman Ayyasamy, Ramesh Kumar Fui, Tien Sangodiah, Anbuselvan Faculty of Information and Communication Technology Universiti Tunku Abdul Rahman Kampar Malaysia Department of Information Systems Faculty of Information and Communication Technology Universiti Tunku Abdul Rahman Kampar Malaysia School of Computing Faculty of Computing and Engineering Quest International University Perak Ipoh Malaysia

Bloom’s Taxonomy (BT) is widely used in educational institutions to produce high-quality exam papers to evaluate students’ knowledge at different cognitive levels. However, manual question labeling takes a long time, and not all evaluators are familiar with BT. The researchers worked to automate the exam question classification process based on BT as a solution. Enhancement in term weighting is one of the ways to increase classification accuracy while working with text data. However, all the past work on the term weighting in exam question classification focused on unsupervised term weighting (USTW) schemes. The supervised term weighting (STW) schemes showed effectiveness in text classification but were not addressed in past studies of exam question classification. As a result, this study focused on the effectiveness of STW in classifying exam questions using BT. Hence, this research performed a comparative analysis between the USTW schemes and STW for exam question classification. The STW schemes used in this study are TF-ICF, TF-IDF-ICF, and TF-IDF-ICSDF, whereas the USTW schemes used for comparison are TF-IDF, ETF-IDF, and TFPOS-IDF. This study used Support Vector Machines, Naïve Bayes, and Multilayer Perceptron to train the models. Accuracy and F1 score were used in this study to evaluate the classification results. The experiment results showed that overall, the STW scheme TF-ICF outperformed all the other schemes, followed by the USTW scheme ETF-IDF. Both the ETF-IDF and TFPOS-IDF outperformed standard TF-IDF. The outcome of this study indicates the future research direction where the combination of STW and USTW schemes may increase the accuracy of BT-based exam question classification. © 2022, Brno University of Technology. All rights reserved.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

Predicting Epileptic Seizures with Precision A Comprehensive Study of ML Algorithms 2

Predicting Epileptic Seizures with Precision A Comprehensive...

引用

2nd IEEE International Conference on Trends in Quantum computing and Emerging Business Technologies, TQCEBT 2024

作者： Ranjani, M. Ramya, G. Divya, G. Deepa, N. Lalitha, B. Srm Institute of Science and Technology Faculty of Engineering and Technology Department of Computing Technologies Chennai India Srm Institute of Science and Technology Faculty of Engineering and Technology Department of Networking and Communications Chennai India Kpr Institute of Engineering and Technology Department of Eee Coimbatore India

ISBN: (数字)9798350384277

ISBN: (纸本)9798350384277

Epilepsy, a complex neurological disorder, poses a significant challenge in the realm of healthcare. Encephalography (EEG) stands as a widely adopted clinical tool for recording the intricate electrical activity within the brain. This research delves into the application of machine learning techniques for the prediction of epileptic seizures using EEG signals obtained from the UCI Machine Learning Repository. Our study presents a comprehensive evaluation of various ML algorithms, including the SVM Classifier, RF Classifier, Gaussian Naive Bayes, K-Nearest Neighbors, and others. Significantly, the Support Vector Classifier and Random Forest Classifier achieved remarkable accuracies of 0.98, suggesting their potential for precise prediction. Meanwhile, Gaussian Naive Bayes and K-Nearest Neighbors demonstrated robust predictive capabilities, with accuracies of 0.96 and 0.93, respectively. This research contributes substantially to the field of epilepsy prediction, shedding light on the effectiveness of diverse machine-learning models for early seizure detection. These findings hold promise for enhancing patient care and improving their quality of life, marking the beginning of an exciting journey towards refined epilepsy management © 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

Yield Optimization for Exothermic Batch Process Using Particle Swarm Optimization 6

Yield Optimization for Exothermic Batch Process Using Partic...

引用

6th IEEE International Conference on Artificial Intelligence in engineering and Technology, IICAIET 2024

作者： Tan, Min Keng Bansing, Matthew Laurentius Xu, Huiyi Chuo, Helen Sin Ee Tham, Heng Jin Teo, Kenneth Tze Kin Universiti Malaysia Sabah Modelling Simulation & Computing Laboratory Faculty of Engineering Kota Kinabalu Malaysia School of Marine Science and Engineering Hainan Tropical Ocean University Hainan China

ISBN: (纸本)9798350389692

Modern advancements in optimizing processes have been explored by various researchers, particularly for exothermic batch processes, which are prolific in the chemical and pharmaceutical industries. This paper proposes using artificial intelligence, specifically particle swarm optimization (PSO), to enhance these exothermic batch processes. Given that most exothermic batch processes utilize generic model control (GMC), the PSO algorithm will primarily focus on optimizing the control of the GMC within the process. The precise control of the controllers will aim to maintain the reactor temperature during the processes, ensuring stability and efficiency. This approach leverages AI to improve process performance, highlighting the potential of PSO in industrial applications. The proposed algorithm is shown to be able to produce a result of an increase of 4.5% of production of the desired product, while decreasing by-product production of 97%. The time it takes for the production of the desired product is also improved by 11.8%. This shows an efficiency increase of the entire exothermic batch processes, The results show that an improvement of the efficiency of the process makes the proposed algorithm a great method to improve the controller of the processes. © 2024 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Lightweight Blockchain Prototype for Food Supply Chain Management 17

Lightweight Blockchain Prototype for Food Supply Chain Manag...

引用

17th International Conference on Security of Information and Networks, SIN 2024

作者： Rusakov, Alexey Moradpoor, Naghmeh Akbarzadeh, Aida School of Computing Engineering and the Built Environment Edinburgh Napier University Edinburgh United Kingdom Norwegian University of Science and Technology Faculty of Information Technology and Electrical Engineering Gjovik Norway

ISBN: (纸本)9798331509736

The modern food supply chain often involves multiple layers of participants spread across different countries and continents. This complex system offers significant benefits to businesses worldwide;however, it also presents several challenges. One major problem is the inability to trace the product flow back to its origin, a critical issue in many industries. Another issue is the lack of trust among supply chain participants. Blockchain technology can help address these and other challenges faced by the supply chain industry. However, it is surprising that, globally, there are still not many examples of the technology's adoption, with most projects remaining in the pilot stage. This paper explores the field of custom blockchain design tailored to specific applications, with a focus on supply chain operations in the food industry. It includes the development of a lightweight yet fully featured Python prototype for a decentralized blockchain system. In addition to common features like block validation and state updates, the prototype includes a newly designed type of transaction tailored specifically for supply chain operations. These transactions eliminate the need for smart contracts, making the system more lightweight compared to general-purpose blockchain platforms such as Ethereum and less prone to security vulnerabilities. The prototype is designed as a public blockchain network, with Proof of Work selected as the consensus algorithm. The novelty of this research work lies in advancing the concept of a custom blockchain solution for the food industry. The key elements of the prototype have been unit tested. The overall evaluation was completed using a Python script that simulates product flow through an example supply chain, allowing product provenance to be determined by tracing the product flow back to its origin. © 2024 IEEE.

关键词： Food industry

来源：评论

学校读者我要写书评

暂无评论

Development of Electrical Cabinet Prototypes Based on Technology of Laminated Conductors

Development of Electrical Cabinet Prototypes Based on Techno...

引用

2023 IEEE International Conference on Industrial Technology, ICIT 2023

作者： Stegic, Josipa Odak, Marija Erceg, Igor Sumina, Damir Topcagic, Elvedin University of Zagreb Faculty of Electrical Engineering and Computing Zagreb Croatia Duplico Ltd. Sveta Nedelja Croatia

ISBN: (纸本)9798350336504

The traditional technology used in the production of electrical cabinets is generally outdated and complex. Therefore, there is a need for a new production technology that minimises both production time and physical labour. As part of this research, a brand new, patented laminated conductor technology was used to connect electrical cabinet components. The assembly process is based on the alternating layering of conductive and insulating layers. By using laminated conductors with a rectangular cross-section, the main advantage of the implemented technology is the possibility to connect the components in a fully automated production process. Other advantages include reduced size as well as simpler installation and use. The basis of this technology is the web application used to upload circuit diagrams and configure the electrical cabinet. Before prototyping the electrical cabinet, a digital twin is created based on the previously collected plans. For research purposes, two prototypes were built, one with a AC power supply and the other with a DC power supply. The electromagnetic compatibility (EMC) test results are given in this study for both prototypes. © 2023 IEEE.

关键词： Electromagnetic compatibility

来源：评论

学校读者我要写书评

暂无评论

Language Modelling Approaches to Adaptive Machine Translation

arXiv

引用

arXiv 2024年

作者： Moslem, Yasmin School of Computing Faculty of Engineering and Computing Dublin City University Ireland

Consistency is a key requirement of high-quality translation. It is especially important to adhere to pre-approved terminology and adapt to corrected translations in domain-specific projects. Machine translation (MT) has achieved significant progress in the area of domain adaptation. However, in-domain data scarcity is common in translation settings, due to the lack of specialised datasets and terminology, or inconsistency and inaccuracy of available in-domain translations. In such scenarios where there is insufficient in-domain data to fine-tune MT models, producing translations that are consistent with the relevant context is challenging. While real-time adaptation can make use of smaller amounts of in-domain data to improve the translation on the fly, it remains challenging due to supported context limitations and efficiency constraints. Large language models (LLMs) have recently shown interesting capabilities of in-context learning, where they learn to replicate certain input-output text generation patterns, without further fine-tuning. Such capabilities have opened new horizons for domain-specific data augmentation and real-time adaptive MT. This work attempts to address two main relevant questions: 1) in scenarios involving human interaction and continuous feedback, can we employ language models to improve the quality of adaptive MT at inference time? and 2) in the absence of sufficient in-domain data, can we use pre-trained large-scale language models to improve the process of MT domain adaptation? © 2024, CC BY.

关键词： Machine translation

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：