检索结果-内蒙古大学图书馆

Reverse-Nearest-Neighbor-Based Clustering by Fast Search and Find of Density Peaks

Chinese Journal of Electronics 2023年第6期32卷 1341-1354页

作者： ZHANG Chunhao XIE Bin ZHANG Yiran College of Computer and Cyber Security Hebei Normal University Hebei Provincial Engineering Research Center for Supply Chain Big Data Analytics and Data Security Hebei Normal University Hebei Provincial Key Laboratory of Network and Information Security Hebei Normal University

Clustering by fast search and find of density peaks(CFSFDP) has the advantages of a novel idea, easy implementation, and efficient clustering. It has been widely recognized in various fields since it was proposed in Science in 2014. The CFSFDP algorithm also has certain limitations, such as non-unified sample density metrics defined by cutoff distance, the domino effect for the assignment of remaining samples triggered by unstable assignment strategy, and the phenomenon of picking wrong density peaks as cluster centers. We propose reverse-nearest-neighbor-based clustering by fast search and find of density peaks(RNN-CFSFDP) to avoid these shortcomings. We redesign and unify the sample density metric by introducing reverse nearest neighbor. The newly defined local density metric and the K-nearest neighbors of each sample are combined to make the assignment process more robust and alleviate the domino effect. A cluster fusion algorithm is proposed, which further alleviates the domino effect and effectively avoids the phenomenon of picking wrong density peaks as cluster centers. Experimental results on publicly available synthetic data sets and real-world data sets show that in most cases, the proposed algorithm is superior to or at least equivalent to the comparative methods in clustering performance. The proposed algorithm works better on manifold data sets and uneven density data sets.

关键词： Measurement Manifolds Shape Clustering algorithms Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Double auction mechanisms for peer-to-peer energy trading: A comparative analysis 7

Double auction mechanisms for peer-to-peer energy trading: A...

引用

7th IEEE International Energy Conference, ENERGYCON 2022

作者： Malik, Sweta Thakur, Subhasis Duffy, Maeve Breslin, John G. Insight Centre for Data Analytics Galway Ireland School of Engineering Galway Ireland

ISBN: (纸本)9781665479820

Peer-to-Peer (P2P) energy trading, one of the new paradigms driven by decentralization, decarbonization, and digitalization of the smart grid, has become a widespread technique in recent years. Additionally, the rise of the double auction for P2P energy trading suggests better trading algorithms with unprecedented economic and technical benefits. This work evaluates various discrete double auction mechanisms, i.e., Average, VCG, Trade reduction, and McAfee's for multiple microgrids. By doing this, the trading algorithm provides players more flexibility to decide from the types of double auctions available. We further study properties such as individual rationality, balanced budget, truthfulness, and economic efficiency associated with energy trading. For practical applicability, we simulate the functionality of the trading algorithms using IEEE LV feeder data. In the end, this work demonstrates a variation in energy trading and social welfare due to the time of usage tariff and change in bidding range. © 2022 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Strategic Blended Learning for Addressing Multiclass Imbalance in Classification

Strategic Blended Learning for Addressing Multiclass Imbalan...

引用

2025 IEEE International Conference on Computational, Communication and Information Technology, ICCCIT 2025

作者： Sridhar, S. Anusuya, S. SRM Institute of Science and Technology Department of CSE Emerging Technologies TN Chennai India Saveetha School of Engineering Department of Data Analytics SIMATS TN Chennai India

ISBN: (纸本)9798331512965

Numerous practical applications involve multiclass classification challenges, where the spread of data across the classes is frequently uneven. Due to this inherent data imbalance, supervised learning models often exhibit a bias toward classifying instances into the category with the highest number of data points, posing a significant problem that requires attention. In the realm of classification of data with multiple classes and imbalanced distributions, researchers in machine learning persistently endeavor to mitigate the classifier's inclination towards dominant class with more sample size. Existing studies aim to alleviate this inclination by alternatively adjusting the data for balance prior to the classifier's learning process or adjusting the classifier's training process to focus more on rare class having least number of samples, or employing hybrid strategies. Existing learning approaches encounter challenges in delineating clear boundaries between samples of classes resulting from an imbalanced class distribution and issues with class overlapping. Consequently, the recognition rate for minority classes is hindered. A novel Strategic Blended Learning (SBL) approach is introduced, employing dual decision trees. The first decision tree is utilized to generate an induced dataset through a grouping approach, while the second decision tree is employed to train and make decisions guided by the induced dataset. A noteworthy aspect of this algorithmic approach is its ability to identify rare data points without affecting the inherent distribution of data. To evaluate the proposed algorithm, various multiclass imbalanced datasets from UCI were employed for classification. The findings revealed that the Strategic Blended Learning method excels in detecting both rare and dominant category samples. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Effect of Atomic Vacancy Defect in h - BN Monolayer on Electronic Properties: A DFT Study 13

Effect of Atomic Vacancy Defect in h - BN Monolayer on Elect...

引用

13th International Physics Seminar 2024, IPS 2024

作者： Nenohai, A.J.W.T. Santana, F.M. Arifin, R. Asih, R. Darminto Department of Physics Faculty of Science and Data Analytics Sepuluh Nopember Institute of Technology Surabaya60111 Indonesia Department of Mechanical Engineering Faculty of Engineering Muhammadiyah University of Ponorogo Ponorogo63471 Indonesia

h-BN is a 2D material which also has considerable development potential in several fields. 2D materials such as h-BN are basically insulating materials but have unique properties and it would be good if they could be developed, especially to meet future energy needs or in the development of electronic devices. Therefore, the properties of h-BN are certainly needed to support this, one of which is the magnetic properties of h-BN. In this research, we modified the h-BN structure by providing defects in the form of vacancy defects by removing atoms in the h-BN layer. We modeled a monolayer h-BN with a supercell size of 4 x 4 x 1, and our calculations were carried out with Quantum ESPRESSO, which is based on density functional theory. The results we obtained showed the emergence of magnetic moment values in h-BN due to defects in the form of atomic vacancies. Furthermore, this research successfully illustrates how vacancy defects in h-BN can modify the band structure, leading to changes in electron behavior around the Fermi energy level. © Published under licence by IOP Publishing Ltd.

关键词： Monolayers

来源：评论

学校读者我要写书评

暂无评论

Mobile Keystroke Biometrics Using Transformers 17

Mobile Keystroke Biometrics Using Transformers

引用

17th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2023

作者： Stragapede, Giuseppe Delgado-Santos, Paula Tolosana, Ruben Vera-Rodriguez, Ruben Guest, Richard Morales, Aythami Universidad Autonoma de Madrid Biometrics and Data Pattern Analytics Lab Spain School of Engineering University of Kent United Kingdom

ISBN: (纸本)9798350345445

Among user authentication methods, behavioural biometrics has proven to be effective against identity theft as well as user-friendly and unobtrusive. One of the most popular traits in the literature is keystroke dynamics due to the large deployment of computers and mobile devices in our society. This paper focuses on improving keystroke biometric systems on the free-text scenario. This scenario is characterised as very challenging due to the uncontrolled text conditions, the influence of the user's emotional and physical state, and the in-use application. To overcome these drawbacks, methods based on deep learning such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) have been proposed in the literature, outperforming traditional machine learning methods. However, these architectures still have aspects that need to be reviewed and improved. To the best of our knowl-edge, this is the first study that proposes keystroke biometric systems based on Transformers. The proposed Transformer architecture has achieved Equal Error Rate (EER) values of 3.84% in the popular Aalto mobile keystroke database using only 5 enrolment sessions, outperforming by a large margin other state-of-the-art approaches in the literature. © 2023 IEEE.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Guest editorial: data and business analytics

引用

Journal of Systems and Information Technology 2022年第2期24卷 73-74页

作者： Hu, Zhongyi Bao, Yukun Jiang, Wu School of Information Management Wuhan University Wuhan China Center for Big Data Analytics Jiangxi University of Engineering Xinyu China

来源：评论

学校读者我要写书评

暂无评论

Prediction of circularity of the holes in electrical discharge machining of inconel alloy using machine learning technique

引用

Interactions 2024年第1期245卷 1-10页

作者： Sujatha, M. Kavitha, B.C. Vimalarani, G. David, D. Beulah Muthukumar, K. Ram, S. Department of Electrical and Electronics Engineering Easwari Engineering College Chennai India Department of Electronics and Communication Engineering Hindustan Institute of Technology and Science Chennai India Department of Data Analytics Institute of Information Technology Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Thandalam Tamilnadu Chennai India Department of Electrical and Electronics Engineering Sri Krishna College of Engineering and Technology Coimbatore India

Accuracy and finishing of the component is playing an essential role in metal forming process. The quality of the product is depending on accuracy of the shape and size. The measurement of holes is a challenging task in electric discharge machining (EDM) of materials. Sometimes, the diameter of the holes are different and its seems to be conical shape. The circularity of the hole is not maintained due to over current, low voltage and improper electrode materials. In this article, the circularity of the holes and its dimensions are analyzed by coordinate measuring machine (CMM). The experimental results are compared with predicted results with the aid of machine learning technique through regularized random forest (RRF) model. Inconel 718 alloy is used as a work material for this experimental investigation. The material characterization and its performance against the EDM process are studied. Prediction of circularity of the holes by machining of inconel alloy is perfectly done by machine learning technique. It’s used to enhance the accuracy of the hole and performance of the process. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Metal forming

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Techniques for Autism Spectrum Disorder: Current trends and future directions 4

Machine Learning Techniques for Autism Spectrum Disorder: Cu...

引用

4th International Conference on Innovative Trends in Information Technology, ICITIIT 2023

作者： Khan, Kainat Katarya, Rahul Delhi Technological University Big Data Analytics and Web Intelligence Laboratory Department of Computer Science and Engineering New Delhi India

ISBN: (纸本)9781665494144

ASD or autism spectrum disorder is a critical neuro-developmental disorder that hinders an individual's capability of social communication and interaction. This disorder has acquired considerable attention and importance due to its ubiquity among individuals covering all the countries worldwide. Individuals with ASD struggles in daily life activities. Detection of autism with the help of medical tests is a tedious and very costly task. However, detection and care of ASD still remains unfamiliar due to inadequate awareness, knowledge among the society, limited number of diagnostic devices and limited verbal therapy services for ASD patients. This paper investigates and displays reviews of various machine learning approaches on extracting useful data associated with distinctive characteristics of ASD such as brain functioning, hyperactivitperactivity, language disability, etc. Current researches reveal that analysis of biological traits by employing machine learning techniques have helped in the progress of early detection of ASD. ABIDE dataset is very much explored for the research in ASD. Additionally, numerous studies for the advancement of tools are still in progression. The presented research work can remarkably aid future studies on machine learning for ASD. © 2023 IEEE.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

A Semantic Mention Graph Augmented Model for Document-Level Event Argument Extraction 30

A Semantic Mention Graph Augmented Model for Document-Level ...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Zhang, Jian Yang, Changlin Zhu, Haiping Lin, Qika Xu, Fangzhi Liu, Jun School of Computer Science and Technology Xi'an Jiaotong University China National Engineering Lab for Big Data Analytics Xi'an China National University of Singapore Singapore

ISBN: (纸本)9782493814104

Document-level Event Argument Extraction (DEAE) aims to identify arguments and their specific roles from an unstructured document. The advanced approaches on DEAE utilize prompt-based methods to guide pre-trained language models (PLMs) in extracting arguments from input documents. They mainly concentrate on establishing relations between triggers and entity mentions within documents, leaving two unresolved problems: a) independent modeling of entity mentions;b) document-prompt isolation. To this end, we propose a semantic mention Graph Augmented Model (GAM) to address these two problems in this paper. Firstly, GAM constructs a semantic mention graph that captures relations within and between documents and prompts, encompassing co-existence, co-reference and co-type relations. Furthermore, we introduce an ensembled graph transformer module to address mentions and their three semantic relations effectively. Later, the graph-augmented encoder-decoder module incorporates the relation-specific graph into the input embedding of PLMs and optimizes the encoder section with topology information, enhancing the relations comprehensively. Extensive experiments on the RAMS and WikiEvents datasets demonstrate the effectiveness of our approach, surpassing baseline methods and achieving a new state-of-the-art performance. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Electronic Properties of Monolayer Graphene with Doping of Nitrogen Atom: A Density Functional Theory Study 13

Electronic Properties of Monolayer Graphene with Doping of N...

引用

13th International Physics Seminar 2024, IPS 2024

As a material that has been widely researched, graphene is certainly interesting because it has many unique features. In its development, graphene is very promising as an optoelectronic material. However, in theory, graphene has obstacles in its development because its band gap position is zero. With various modifications in opening the band gap so that it does not have a value of zero. In the current research, structural modifications were carried out on graphene layers by doping with a number of Nitrogen atoms. The modeling was carried out using graphene with a supercell size of 4 x 4 x 1. Our calculations are based on Density Functional Theory using the PBE - GGA function for potential exchange correlation. The result is the Fermi level shifting and emergence of magnetic moment through doping with Nitrogen atoms. The results obtained certainly open up opportunities for the development of graphene. © Published under licence by IOP Publishing Ltd.

关键词： Atoms

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：