检索结果-内蒙古大学图书馆

6th international conference on Intelligent Computing and Control Systems, ICICCS 2022

作者： Avinash, M. Nithya, M. Aravind, S. Sri Sairam Engineering College Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9781665410359

In recent years, the impact and usage of machine learning have increased multi-fold. To get the best outcome, it is imperative to choose the right algorithm. Hence, Algorithm Selection is one of the most important stages in the machine learning Lifecycle. Selecting the optimal algorithm out of many possible algorithms for a given problem statement is always a tedious and time-consuming process. This project assists the researchers and machine learning enthusiasts in selecting the appropriate algorithm by providing a comparative selection among the different machine learning algorithms available for a pre-processed dataset. Besides the best Algorithm Selection, this project also aims to provide the best hyper-parameters for the opted algorithm using a novel technique. The Algorithm Selection functionality is furnished by comparing the various accuracy metrics like Accuracy, Recall, Precision, F1 Score, R2 Score, Mean Squared Error, etc. The objective of this project is to compare numerous algorithms and suggest the best algorithm. Thus, the user can instead concentrate on data Collection and data Pre-processing to achieve success in building the best model. © 2022 IEEE.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Use machine learning Technologies in E-learning

Use Machine Learning Technologies in E-learning

引用

IEEE international IOT, Electronics and Mechatronics conference (IEMTRONICS)

作者： Akter, Taslina Sadman, Yeaser Bala, Shatabdee Independent Univ Dept EEE Dhaka Bangladesh Gono Bishwabidyalay Dept CSE Dhaka Bangladesh

ISBN: (纸本)9781665486842

In this article, we generated some data as a result of new technologies, the internet, and linked items. Putting these facts into context and structuring them so that they may be perceived, understood, and reflected is critical. Humans had traditionally studied data. As the availability of data grows larger, humans are progressively turning to computerized technologies that can replicate them. machine learning refers to technologies that can resolve issues by learning from both data and data modifications. Artificial intelligence (AI) has a significant influence on e-learning studies, and machine learning-based methodologies may be used to improve Technology Enhanced learning Environments (TELEs). This publication provides an outline of relevant study outcomes in this domain. Initially, we'll go over some basic machine learning ideas. Then, we'll go through the significant latest research in the domain of e-learning that uses machine learning.

关键词： E-learning Technology Enhanced learning Environments machine learning Artificial Intelligence

来源：评论

学校读者我要写书评

暂无评论

machine learning for Enhanced Exercise Performance and Planning 11th

Machine Learning for Enhanced Exercise Performance and Plann...

引用

11th international conference on Future data and Security engineering, FDSE 2024

作者： Thien, Nguyen Phuoc Dang, Chau N. B. Trinh, Truc T. T. Nhut, Nguyen Minh Thuan, Nguyen Dinh University of Information Technology Ho Chi Minh City Viet Nam Vietnam National University Ho Chi Minh City Viet Nam

ISBN: (纸本)9789819604364

This study proposes a machine learning-based approach to improve exercise evaluation and schedule planning. Key point detection via MoveNet assesses user movements, compares them to standard exercises, and analyzes body metrics. In the absence of body data, BodyPix estimates BMI through body part segmentation. The application, built on React Expo Go, provides real-time feedback to help users correct their form during workouts. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Prediction and data Analysis of Price Based on PSO with Extreme learning machine Algorithm and Particle Swarm Optimization 2

Prediction and Data Analysis of Price Based on PSO with Extr...

引用

2nd international Signal Processing, Communications and engineering Management conference, ISPCEM 2022

作者： Chen, Huanyun Zhao, Weiming Private Hualian College Guangzhou China

ISBN: (纸本)9781665492713

The changes in the trading market are affected by many factors, and traditional forecasting methods are more and more difficult to meet people's needs. In order to improve the accuracy of prediction, this paper proposes an extreme learning machine algorithm based on particle swarm optimization for prediction and analysis. First, the fluctuation data of previous years are collected, and the closing price of the stock is determined as an experiment and simulated to establish a learning sample, and then the learning sample is input. Based on the online extreme learning machine model optimized by particle swarm optimization, the prediction model is established. The results show that the optimized extreme learning machine algorithm, compared with models such as ELM, PSO-BP and DE-ELM, has better surface prediction accuracy and fitting effect, and can more accurately describe the change trend, which is more efficient than other methods. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Distribution-dependent McDiarmid-type Inequalities for Functions of Unbounded Interaction 40

Distribution-dependent McDiarmid-type Inequalities for Funct...

引用

40th international conference on machine learning

作者： Li, Shaojie Liu, Yong Renmin Univ China Gaoling Sch Artificial Intelligence Beijing Peoples R China Beijing Key Lab Big Data Management & Anal Method Beijing Peoples R China

The concentration of measure inequalities serves an essential role in statistics and machine learning. This paper gives unbounded analogues of the McDiarmid-type exponential inequalities for three popular classes of distributions, namely sub-Gaussian, sub-exponential and heavy-tailed distributions. The inequalities in the sub-Gaussian and sub-exponential cases are distribution-dependent compared with the recent results, and the inequalities in the heavy-tailed case are not available in the previous works. The usefulness of the inequalities is illustrated through applications to the sample mean, U-statistics and V-statistics.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Improved BLS based transformer fault diagnosis considering imbalanced samples

引用

ENERGY REPORTS 2022年 8卷 1446-1453页

作者： Xu, Chao Li, Xiaolan Wang, Zhenhao Zhao, Beijia Xie, Jie State Grid ShenYang Elect Power Supply Co Shenyang 110000 Peoples R China Shenyang Aibeike Sci & Technol Co Ltd Shenyang 110000 Peoples R China

At present, the traditional machine learning diagnosis method has some problems, such as the imbalance of various fault types and the great difference of recognition effect between different fault types. In order to solve the problem of low accuracy of traditional machine learning diagnosis methods, a multilevel fault diagnosis model of transformer based on hierarchical classification, generalized learning and ensemble learning is established. According to the imbalanced degree of each category sample, the method established the corresponding classifier, and carried on the diagnosis step by step. At the first level, the broad learning system was selected to extract three generalized feature labels-normal, discharge and overheat, which were fused with the original parameter input to guide the nine more detailed state types. In the second-level classifier, EasyEnsemble learning method is used to generate multiple data-balanced training subsets through under-sampling, fully balancing the fault information of most classes and a few classes, and then synthesized the final classifier through parallel training sub-classifiers, avoiding the problem of missing data information due to under-sampling. Experimental results show that, compared with the traditional diagnosis methods, the proposed method improved the generalization characteristics of a few types of faults, improved the overall accuracy rate, and had a more accurate and balanced fault diagnosis effect of power transformer. (C) 2022 Published by Elsevier Ltd.

关键词： Imbalanced samples Hierarchical classification Broad learning system Ensemble learning

来源：评论

学校读者我要写书评

暂无评论

Supply Chain Security: Pre-training Model for Python Source Code Vulnerability Detection 3

Supply Chain Security: Pre-training Model for Python Source ...

引用

3rd international Joint conference on Information and Communication engineering (JCICE)

作者： Le, Yiwang Li, Hui Wang, Bin Luo, Zhixiong Yang, Ao Ma, Ziheng Peking Univ Shenzhen Grad Sch Shenzhen Peoples R China Qinghai Co LTD China Mobile Commun Grp Xining Qinghai Peoples R China

ISBN: (纸本)9798350388732;9798350388725

In this paper, we propose an innovative deep learning-based model designed to detect potential security vulnerabilities in source code. The model is pretrained on the open-source PyPI code repository and a specially curated malicious code dataset, allowing it to deeply learn the syntactic structure and semantic information of the code, thus building a deep knowledge representation. We further refine this knowledge representation through fine-tuning to form a classifier focused on malicious code detection. Evaluation results on an open-source malicious code dataset indicate that our model's performance not only surpasses traditional machine learning methods, recurrent neural networks (RNNs), and convolutional neural networks (CNNs), but also outperforms popular open-source security tools and significantly exceeds advanced detection models designed for other programming languages. Despite our model's smaller scale, limited by the amount of data and model parameters, it demonstrates exceptional performance on the test dataset, far exceeding traditional machine learning techniques. This achievement highlights the strong potential of our model in the analysis of source code security and provides new directions and possibilities for future research in this field.

关键词： vulnerability detection software vulnerabilites pre-training deep learning

来源：评论

学校读者我要写书评

暂无评论

Ultra-Precision Diamond Turning Error Compensation via Iterative learning from On-machine Measured data

引用

international JOURNAL OF PRECISION engineering AND MANUFACTURING 2023年第12期24卷 2181-2195页

作者： Chen, ZaoZao Huang, WeiWei Zhu, ZhiWei Zhang, XinQuan Zhu, LiMin Jiang, XiangQian Shanghai Jiao Tong Univ Sch Mech Engn State Key Lab Mech Syst & Vibrat Shanghai 200240 Peoples R China Nanjing Univ Sci & Technol Sch Mech Engn Nanjing 210094 Peoples R China Univ Huddersfield Sch Comp & Engn Future Metrol Hub Engn & Phys Sci Res Council EPSRC Huddersfield HD1 3DH England

In ultra-precision diamond turning, the reduction of machining form errors can generally be achieved through on-machine measurement and compensation. However, the efficiency of conventional compensation methods is often insufficient, particularly when high form accuracy is required or when intricate surface topography and microstructures need to be machined. Consequently, this research proposes a novel machining error compensation method based on iterative learning from on-machine measured data to enhance the machining accuracy and compensation efficiency. The on-machine measurement system and cutting path generation algorithm are introduced first. Then, the compensation method via iterative learning is presented theoretically, demonstrating a higher convergence order compared to the conventional method. Finally, machining experiments involving the cutting of cosine surfaces are conducted, followed by measurements of the processed workpieces. The experimental results indicate that after four rounds of compensation using the conventional method, the peak-to-valley (PV) value of the form error is reduced to 0.1134 mu m. In contrast, employing the proposed method, a similar value of 0.1156 mu m is achieved after only two rounds of compensation. This highlights the significant reduction in compensation time facilitated by the proposed method. Furthermore, the measurement results verify that the proposed compensation method maintains excellent surface quality.

关键词： On-machine measurement Ultra-precision machining Compensation strategy Iterative learning

来源：评论

学校读者我要写书评

暂无评论

CVE Severity Prediction from Vulnerability Description - A Deep learning Approach 2

CVE Severity Prediction from Vulnerability Description - A D...

引用

2nd international conference on machine learning and data engineering, icmlde 2023

作者： Manjunatha, A. Kota, Kethan Babu, Anoop S. Sree Vivek, S. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India ICU Medical Cybersecurity Device R&D Chennai600006 India

The Common Vulnerabilities and Exposures (CVE) system is a widely used standard for identifying and tracking known vulnerabilities in software systems. The severity of these vulnerabilities must be determined in order to prioritize mitigation efforts. However, assigning severity to a vulnerability is a challenging task that requires careful analysis of its characteristics and potential impact. Considering the vast number of vulnerabilities identified every year, it is vital to automate the severity assignment, thereby reducing manual effort. This paper proposes a novel approach for predicting the severity of vulnerabilities based on their CVE description using GPT-2, a state-of-the-art language model. The CVSS severity values distribution imbalance is addressed using oversampling and contextual data augmentation techniques. This approach leverages the large-scale language modeling capabilities of GPT-2 to automatically extract relevant features from CVE descriptions and predict the severity level of the vulnerability. The model is evaluated on a test data set of 7,765 CVEs and achieves a high accuracy of 84.2% and an F1 score of 0.82 in predicting the severity of the vulnerabilities on the test data. A comparative analysis of this approach was done against state-of-the-art methods, demonstrating the superior performance of the proposed approach. Based on the results, the proposed approach could be considered a valuable tool for quickly and accurately identifying high-severity vulnerabilities, facilitating more efficient and effective vulnerability management practices. Furthermore, this approach could be extended to other natural language processing tasks related to vulnerability analysis and management. © 2024 Elsevier B.V.. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

machine learning-Based Adaptive Optics for Free-Space Optical Communication: a Training data Generation Study

Machine Learning-Based Adaptive Optics for Free-Space Optica...

引用

2022 international conference on Space Optics, ICSO 2022

作者： Nery, Vinícius F. Nakasuka, Shinichi Department of Aeronautics and Astronautics The University of Tokyo Tokyo Japan

ISBN: (纸本)9781510668034

Recently, free-space optical (FSO) communication systems have gained attention as they pose as a possible solution to cope with the ever-increasing requirements for data transmission. FSO systems have a number of attractive attributes, such as high bandwidth, license-free spectrum, long operational range, security, spatial re-usability, and immunity to electromagnetic interference. On the other hand, optical links suffer from strict pointing and tracking requirements due to narrow beam divergence and channel losses that greatly hinder their reliability. Particularly in the near-Earth satellite optical communications scenario, the atmosphere represents a major challenge to overcome for the establishment of successful and enduring satellite optical links. In that sense, adaptive optics (AO) solutions have been considered for turbulence compensation but given communication requirements solutions are either expensive or sub-optimal. This paper proposes a machine learning-based AO system general framework for atmospheric turbulence compensation. The theoretical foundation for training data generation based on Monte-Carlo phase screens, Zernike polynomials, and optical propagation is presented and validated through simulations. Furthermore, evaluation criteria for the neural network and overall system performance are also discussed. © 2023 SPIE. All rights reserved.

关键词： machine learning

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：