检索结果-内蒙古大学图书馆

NOVEL MULTI-CLASS svm algorithm FOR MULTIPLE OBJECT RECOGNITION

INTERNATIONAL JOURNAL ON SMART SENSING AND INTELLIGENT SYSTEMS 2015年第2期8卷 1203-1224页

作者： Wang, Yongqing Zhang, Yanzhou Zhengzhou Inst Aeronaut Ind Management Dept Comp Sci & Applicat Zhengzhou 450015 Peoples R China Henan Aviat Econ Res Ctr Aviat Econ Dev & Aeronaut Mat Technol Collaborat Zhengzhou Peoples R China Henan Polytech Basic Course Dept Zhengzhou 450046 Peoples R China

Object recognition is a fundamental task in applications of computer vision, which aims at detecting and locating the interested objects out of the backgrounds in images or videos, and can be originally formulated as a binary classification problem that can be effectively handled by binary svm. Although the binary technique can be naturally extended to solve the multiple object recognition, which are known as one-vs.-one and one-vs.-all techniques, but the scalability of traditional methods tend to be poor, and limits the wide applications. Inspired by the idea presented by Multi-class Core Vector Machine, we propose a novel Multi-class svm algorithm, which achieves excellent performance on dealing with multiple object recognition. The simulation results on synthetic numerical data and recognition results on real-world pictures demonstrate the validity of the proposed algorithm.

关键词： Object recognition computer vision multi-class svm algorithm classification problem

来源：评论

学校读者我要写书评

暂无评论

Research on the analysis method of power system relay protection action characteristics based on fault recording data

引用

JOURNAL OF RADIATION RESEARCH AND APPLIED SCIENCES 2024年第3期17卷

作者： Guo, Wen Hou, Xiaohu China Yangtze Power Co Ltd Xiluodu Hydropower Plant Zhaotong 657300 Yunnan Peoples R China

The action characteristics of power system relay protection devices can well analyze whether the relevant actions are correct. An analysis method of relay protection action characteristics in power system based on fault recording data is designed. After analyzing the relay device structure and protection action characteristics and requirements, the power system relay protection action record data recorded by the fault recorder;The second order RC low-pass filter is used to preprocess the recorded data;The filtered data is input into the analysis model of relay protection action characteristics based on svm algorithm. The svm algorithm classifies whether the relay protection action characteristics recorded by the filtered fault recording data meet the expectations, and completes the analysis of power system relay protection action characteristics. The experimental results show that this method can effectively analyze the operation characteristics of power system relay protection, and can accurately check whether the relay protection device can operate correctly.

关键词： Fault recording data Power system Relay protection Action characteristic analysis svm algorithm Low pass filter

来源：评论

学校读者我要写书评

暂无评论

Evaporation residue cross sections of superheavy nuclei based on optimized nuclear data

引用

Chinese Physics C 2023年第12期47卷 124-130页

作者：李佳星张鸿飞 School of Physics Xi’an Jiaotong UniversityXi’an 710049China School of Nuclear Science and Technology Lanzhou UniversityLanzhou 730000China

This study proposes an optimized method for estimating atomic nucleus masses by combining the finiterangedroplet model (FRDM) with the support vector machine algorithm. The optimization process significantly improvesthe accuracy of the FRDM by reducing the root mean square error from 0.606 to 0.253 MeV. The optimizedmass data obtained from this method are then used to calculate the evaporation residue cross-sections (ERCSs) forfusion-evaporation reactions, employing the di-nuclear system model. The experimental results for the 48Ca+238U reactionare relatively well reproduced using these optimized mass data. Additionally, the study investigates the impactof mass uncertainties on fusion and survival probabilities. By considering the mass uncertainties, the ERCSs fornew elements 119 and 120 are predicted based on the obtained optimized mass data.

关键词： superheavy nuclei svm algorithm DNS model evaporation residue cross-sections

来源：评论

学校读者我要写书评

暂无评论

Multi-dimensional Data Optimal Classification algorithm for Quality Evaluation of Distance Teaching in Universities

引用

MOBILE NETWORKS & APPLICATIONS 2023年第3期28卷 889-899页

作者： Chen, Feng Gadekallu, Thippa Reddy Xizang Minzu Univ Coll Informat Engn Xianyang 712082 Peoples R China Zhongda Grp Jiaxing 314312 Peoples R China Lebanese Amer Univ Dept Elect & Comp Engn Byblos Lebanon Vellore Inst Technol Sch Informat Technol & Engn Vellore 632014 India Jiaxing Univ Coll Informat Sci & Engn Jiaxing 314001 Peoples R China Lovely Profess Univ Div Res & Dev Phagwara India

In order to effectively extract the multi-dimensional data of teaching quality evaluation and accurately evaluate the quality of network distance teaching quality in universities, an optimal classification algorithm for network distance teaching quality evaluation is proposed. From the perspectives of teaching attitude, teaching skill, teaching skill, teaching content, teaching method and means, the quality evaluation indices of network distance teaching is designed. Combined with the evaluation indices, the multi-dimensional data mining method based on OLAP technology is used to mine the required multi-dimensional data of teaching quality evaluation in the distance teaching data warehouse of universities, the required multi-dimensional data is input into svm algorithm to solve the optimal classification hyperplane of multi-dimensional data and implement the optimal classification of multi-dimensional data. The quality of distance teaching is evaluated by improving the salp group algorithm and setting the penalty factor and kernel function of svm algorithm. The experimental results show that the classification accuracy of this method for multidimensional data is over 90%, and the evaluation accuracy is as high as 99%, it can extract multi-dimensional teaching quality evaluation from the network distance teaching data, which has good classification effect and can improve the accuracy of network distance teaching quality evaluation.

关键词： OLAP Technology svm algorithm University Network Distance Teaching Quality Evaluation and Evaluation Index

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis of Aviation Secondary Power Supply Based on svm 14

Fault Diagnosis of Aviation Secondary Power Supply Based on ...

引用

14th IEEE Global Reliability and Prognostics and Health Management Conference, PHM-Hangzhou 2023

作者： Che, Shuangxi Zhang, Yanxi Chen, Runzhe Ma, Yaoxuan Li, Xing Wang, Li College of Automation Engineering Nanjing University of Aeronautics and Astronautics Nanjing China Beijing Electro-Mechanical Engineering Institute Beijing China

ISBN: (纸本)9798350301359

Timely and effective fault diagnosis for aviation secondary power supplies to minimize the failure rate and ensure the power supply of the load is critical. In this paper, in order to realize the fault diagnosis of aviation secondary power supply main topology phase shifted full bridge (PSFB) converter, the working principle, fault mechanism, mode, modelling method are studied. Based on the fault data analysis and feature extraction, the fault diagnosis is carried out by using support vector machine (svm) algorithm, the results of which show that the methodology proposed in this paper has a high accuracy rate. © 2023 IEEE.

关键词： Falut diagnosis PSFB converter svm algorithm

来源：评论

学校读者我要写书评

暂无评论

Optimization of Injection Production Matching Strategy in Reservoir Development Process Using Support Vector Machine algorithm 24

Optimization of Injection Production Matching Strategy in Re...

引用

International Conference on Machine Intelligence and Digital Applications (MIDA)

作者： Jiang, Chunhua Daqing Oilfield Ltd Co Inst Geol Oil Prod Plant 6 Daqing 163000 Heilongjiang Peoples R China

ISBN: (纸本)9798400718144

This article explores how to use Support Vector Machine (svm) algorithm to optimize the injection production matching strategy in the process of reservoir development. By establishing an svm-based prediction model, this article aims to improve the injection and production efficiency of oil fields and address the limitations of traditional methods in processing nonlinear and complex data. The article first reviews the main challenges in current reservoir management and existing injection production matching methods, followed by a detailed introduction to the principle of svm algorithm and its application in reservoir management. Through comparative experiments and case analysis, the effectiveness of the svm model in improving oilfield recovery and economic benefits is verified. After adopting the svm strategy, the injection production efficiency improves by about 15% and the oil-water ratio improves by 20%. The svm model also tends to perform stably in oil fields of different geological types. During the one-year experimental period, the svm algorithm maintains a performance improvement of about 5% in each month. The experimental data results show the effectiveness and reliability of svm algorithm in oilfield injection production matching optimization, demonstrating the potential of svm algorithm in improving oilfield development efficiency and economic benefits.

关键词： Reservoir management Injection production matching strategy svm algorithm Linear regression method

来源：评论

学校读者我要写书评

暂无评论

Research on Ocean Adaptation Zone Classification Prediction Model Based on Gravity Anomaly data 2

Research on Ocean Adaptation Zone Classification Prediction ...

引用

2nd IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2024

作者： He, Chenkai He, Hongyi Chen, Yiru Dalian Polytechnic University School of Food Science and Technology Liaoning Dalian China Dalian Polytechnic University School of Biological Engineering Liaoning Dalian China

ISBN: (纸本)9798350317558

This paper aims to propel the development of the marine economy by proposing a crucial underwater navigation adaptation zone classification prediction technique. Firstly, through meticulous processing of gravity anomaly benchmark data, the maritime area is delineated, and adaptability is calibrated to ensure the navigation precision of underwater vehicles. Using the K-means classification model, the data is refined and categorized into zones of medium-high accuracy, low accuracy, medium accuracy, and high accuracy. Subsequently, specific feature attribute indicators are selected, and an effective regional adaptation zone classification prediction model system, denoted as F, is established to ensure navigation accuracy within regions with different gravity anomaly feature distributions. Finally, transferability predictions are performed on new gravity anomaly data to explore the model's applicability to novel data, validating the robustness and generalization capability of the model and fostering further advancements in underwater navigation technology. This research holds significant importance for driving the marine economy forward. © 2024 IEEE.

关键词： Data-driven interpolation processing K-means clustering algorithm Python svm algorithm

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Machine Learning Techniques for Breast Cancer Prediction 2

A Comparative Analysis of Machine Learning Techniques for Br...

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Dutta, Umesh Kaushik, Simran Iyer, Srinidhi Singh, Ina Manav Rachna International Institute of Research and Studies Department of Electronics and Communication Engineering Haryana Faridabad India Manav Rachna International Institute of Research and Studies Manav Rachna Innovation & Incubation Centre Haryana Faridabad India

ISBN: (纸本)9798350327533

One of the major diseases found in women worldwide is Breast Cancer. More than 2.2M cases have been reported with about a 30% mortality rate in accordance with WHO. The rapid advancement of technology has led to breakthroughs in different fields such as medicine, automotive, etc. Despite advancements in screening technologies, achieving high sensitivity and specificity for early detection remains a challenge. Machine Learning is one of the front runners and is currently playing a vital role in solving real-world problems, particularly in the healthcare domain. Using different Machine Learning algorithms prediction of Breast Cancer has been tallied in this work. Various algorithms such as svm (Support Vector Machine), KNN (K-Nearest Neighbours), DT (Decision Tree), and RF (Random Forest) have vast application areas. In this study, these algorithms have been tested and evaluated on the basis of precision, recall, and accuracy which are the key performance metrics for the evaluation of the model. The dataset for breast Cancer has been pulled from Kaggle, which is the most prominently used dataset by researchers. The simulation results revealed that Random Forest outperformed the others with the precision of 94.5%, recall of 94%, and accuracy of 95%, clearly showing its potential to be used for early prediction of Breast Cancer. © 2024 IEEE.

关键词： Breast Cancer Prediction DT algorithm KNN algorithm Modelling using ML RF algorithm svm algorithm

来源：评论

学校读者我要写书评

暂无评论

Intelligent Personalized Nutrition Guidance System Using IoT and Machine Learning algorithm 2

Intelligent Personalized Nutrition Guidance System Using IoT...

引用

2nd International Conference on Smart Technologies for Smart Nation, SmartTechCon 2023

作者： Santhuja, P. Choudri, Subramani Roy Balaji, S. Reddy, Elangovan Guruva Muthulekshmi, M. Department of Computer Science Engineering CMR Technical Campus Telangana Hyderabad India Department of Computer Science and Engineering Vardhaman College of Engineering Telangana Hyderabad India Department of Information Technology Sri Shanmugha College of Engineering and Technology Tamil Nadu Salem India Department of Artificial Intelligence and Data Science Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamil Nadu Chennai India

ISBN: (纸本)9798350305418

Nowadays, dietary issues are increasing around the world. Numerous problems, such as weight gain, obesity, diabetes, etc., can arise from an unbalanced diet. By integrating image processing, the system can assess food images in new ways to provide personalized solutions for better eating habits. The system uses machine learning, IoT, and image processing techniques to evaluate food image data and extract useful information. IoT devices like smartphones or specialized cameras take images of food and send to the cloud for analysis. The Support Vector Machine (svm) is a machine learning technique that is integrated with Internet of Things (IoT) technology in this study to propose a novel method for creating a system that uses personalized nutritional suggestions. The svm algorithm is then used to analyze and analyze this data to find patterns, correlations, and individual dietary requirements. A cloud database is used to process and store all the data related to food consumption. The system analyzes food images and determines the nutrition and caloric content of the food using image processing and segmentation. The system takes up new abilities using an extensive collection of dietary records that have been labeled and include details about the sorts of foods, portion sizes, and nutritional value. The system can predict and identify users' nutritional needs, deficits, and personalized dietary objectives by using this trained svm model to their nutritional data. © 2023 IEEE.

关键词： Dietetics IoT Machine Learning Nutrition Guidance svm algorithm

来源：评论

学校读者我要写书评

暂无评论

Real-Time Video Management System for Robotic Waste Sorting and Recycling Using IoT and Machine Learning 2

Real-Time Video Management System for Robotic Waste Sorting ...

引用

2nd International Conference on Smart Technologies for Smart Nation, SmartTechCon 2023

作者： Raman, Ramakrishnan Meenakshi, R. Latha, R. Rawandale, Chandrashekhar J. Jayaprakash, S. Srinivasan, C. Maharashtra Pune India Department of Computer Science and Engineering Chennai Institute of Technology Tamil Nadu Chennai India Department of Computer Science and Engineering K.Ramakrishnan College of Engineering Tamil Nadu Trichy India Symbiosis Law School Uttar Pradesh Noida India Maharashtra Pune India School of Electrical and Electronics Engineering Sathyabama Institute of Science and Technology Tamil Nadu Chennai India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamil Nadu Chennai India

ISBN: (纸本)9798350305418

The system automated robotic for waste sorting and recycling by identifying and categorizing various forms of waste. Traditional sorting of waste takes time and is prone to human mistakes. This solution uses IoT and machine learning to overcome these restrictions and improve waste management efficiency. The system begins with waste-collecting area sensors and cameras. The sensors record waste item weight, size, and color, while the cameras record images. The Raspberry Pi, a small image-processing single-board computer, processes sensor and camera data. Raspberry Pi transfers processed data to the cloud for analysis and decision-making. The Support vector machine (svm) method classifies waste in the cloud using machine learning. A dataset of waste categories trains the svm algorithm to discriminate recyclable from non-recyclable materials. The system controls robotic arms or conveyor belts to segregate waste after classification. The robotic arms effectively classify garbage into containers. Real-time video management ensures fast, precise waste sorting, enhancing recycling efficiency. The system can gather data from many garbage-collecting regions concurrently. The cloud architecture enables real-time data processing and analysis. svm-based machine learning techniques improve waste categorization accuracy, improving trash sorting. Waste sorting and recycling using the real-time video management system is novel. IoT, machine learning, and cloud computing facilitate robotic waste segregation. The method might improve waste management and environmental conservation. Optimizing waste management operations, reducing manual labor, and promoting sustainable methods. © 2023 IEEE.

关键词： Cloud Internet of Things Recycling Sensors svm algorithm Waste Sorting

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：