检索结果-内蒙古大学图书馆

Prediction of Gear Pitting Severity by Using Naive Bayes machine learning algorithm 1

4th International Conference on Advanced Materials and Modern Manufacturing, ICAMMM 2021

作者： Chandrasekaran, M. Sonawane, Pavankumar R. Sriramya, P. Tamilnadu Chennai India Department of Mechanical Engineering JSPM’s Rajarshi Shahu College of Engineering Tathawade Maharashtra Pune India Chennai India

ISBN: (数字)9789811902444

ISBN: (纸本)9789811902437

The application of the machine learning algorithm in the area of gearbox condition monitoring is miserable. If one has to take the condition monitoring field to the next level then new approaches by using the machine learning algorithm and conventional neural network should be formulated. In this research article, the Naive Bayes machine learning algorithm has been implemented to predict the severity of the gear pitting defect. The performance of the algorithm is evaluated based on the accuracy score and confusion matrix. This algorithm has proved that the severity of defect can be classified based on the gear noise level. The noise measurement was done by using a free-field microphone. The model prepared is showing good accuracy. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Condition monitoring Gear defects Gear pitting machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Fake News Detection Using machine learning algorithm 2

Fake News Detection Using Machine Learning Algorithm

引用

2nd IEEE International Conference on Communication, Security and Artificial Intelligence, ICCSAI 2023

作者： Narkhede, Apurva Patharkar, Devyani Chavan, Nekita Agrawal, Rahul Dhule, Chetan Iot Cyber Security G H Raisoni College of Engineering Department of Data Science Nagpur India

ISBN: (纸本)9798350369960

Fake news is a big concern since it spreads widely over social media and other media channels, creating significant social and national damage with devastating consequences. In order to address this issue, substantial research how to be recognized on fake news detection has been done. The purpose of this study is to analyze the existing research on fake news detection and select the best conventional machine learning frameworks to develop an algorithm for supervised machine learning. The algorithm will be able to classify false reports as true or fraudulent using textual analysis methods such as NLP. The proposed process involves data preprocessing and vectorization, where the NLP library will be used to perform tokenization and feature extraction of text data, utilizing tools such as Count Vectorizer and Tiff Vectorizer. Further, feature selection methods will be employed to evaluate and determine the most fitting features to achieve the highest precision based on confusion matrix results. The outcome of the decision tree classifier algorithm gives the accuracy of 90%. © 2023 IEEE.

关键词： data preprocessing Fake news feature extraction machine learning algorithm vectorization

来源：评论

学校读者我要写书评

暂无评论

AN INNOVATION DEVELOPMENT OF BANDWIDTH MANAGEMENT IN 4G WIRELESS LOCAL AREA NETWORK (4G-WLAN) USING SMART machine learning algorithm

AN INNOVATION DEVELOPMENT OF BANDWIDTH MANAGEMENT IN 4G WIRE...

引用

2023 IEEE International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering, RMKMATE 2023

作者： Gopinathan, B. Mukherjee, Papiya Naveen Kumar, N. Nandhini, R. Shanmugapriya, S. Lalitha, S.D. Department of Computer Science and Engineering Adhiyamaan College of Engineering Tamilnadu Hosur India Department of CSE Education Koneru Lakshmaiah Foundation Green Fields Andhra Pradesh Guntur India School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India Department of ECE Veltech Multitech Dr Rangarajan Dr Shakuntala Engineering College Tamil Nadu Chennai India Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Tamilnadu Virudhunagar India Department of CSE R.M.K. Engineering College RSM Nagar Tamilnadu Kavaraipettai India

ISBN: (纸本)9798350305708

Currently, the vast use of existing fourth generation networks is further increasing its users. A major problem with this process is the allocation of equal bandwidth to everyone on the network. This varies depending on the secondary users who are aging. But the time difference between them allows both of them to be switched to get the required bandwidth utilization. An advanced machine learning algorithm is proposed in this paper. It is designed to reduce the hassle for the primary user by calculating the login times of the primary user and the secondary user. Also the switching schedule data for the secondary user is given to improve and fix them so that they do not have immediate connection problems. And the most important thing in this system is time management for primary and secondary users. Two are even better designed to manage this effectively. © 2023 IEEE.

关键词： bandwidth utilization machine learning algorithm primary users secondary users

来源：评论

学校读者我要写书评

暂无评论

Application of machine learning algorithm in Financial Industry 3

Application of Machine Learning Algorithm in Financial Indus...

引用

3rd IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2023

作者： Chen, Jing Xi'An Mingde Institute of Technology Shaanxi Province Xi'an China

ISBN: (纸本)9798350317022

In the financial sector, data are collected from many sources, such as central banks, stock exchanges and other organizations. Then use various algorithms to process these data and predict the future results of the asset. These data can be used to predict the price trend of short-term and long-term securities or commodities. This is achieved by applying machine learning algorithms to analyze history and current market trends. The quantitative analysis method for financial data is a method that uses computers to analyze financial data, so as to predict the fluctuation direction of the securities market to obtain excess returns. machine learning has become an important means in quantitative analysis methods, and has shown better performance than traditional quantitative analysis methods. The quantitative analysis method based on machine learning is used to analyze and invest financial data, which has the advantages of objectivity, accuracy and other advantages that traditional investment methods do not have, so it is used by investors and financial institutions. © 2023 IEEE.

关键词： financial industry machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

machine learning algorithm based on optical sensors for simulating sports tourism environment

引用

Optical and Quantum Electronics 2024年第4期56卷 680-680页

作者： Tang, Huaming Quan, Na Guilin Tourism University Guilin 541006 China

Aiming at sports tourism environment simulation, this paper aims to explore the application of machine learning algorithm based on light sensor in this field. We propose a new method for sports tourism simulation, which is based on optical sensor data acquisition and processing. The aim of this research is to develop an accurate and efficient algorithm to simulate the optical properties of sports event venues in order to provide a more realistic sports tourism experience. The research method consists of two main steps: optical sensor data collection and machine learning algorithm modeling and training. First, a network of optical sensors was set up to collect light intensity and color information at different locations in the stadium. This data is then used to train a machine learning algorithm to predict and simulate the sports tourism environment under different optical scenarios. Through experiments and evaluations, the proposed algorithm performs well in terms of accuracy and efficiency, and can simulate the lighting characteristics of sports venues with high accuracy. This provides a strong technical support for sports tourism simulation, which can provide users with a more realistic experience. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Environmental simulation Light sensor machine learning algorithm Sports tourism

来源：评论

学校读者我要写书评

暂无评论

Mapping relationship analysis of welding assembly properties for thin-walled parts with finite element and machine learning algorithm

引用

Journal of Southeast University(English Edition) 2022年第2期38卷 126-136页

作者： Pan Minghui Liao Wenhe Xing Yan Tang Wencheng School of Mechanical Engineering Nanjing University of Science and Technology Nanjing 210094 China Digital Forming Technology and Equipment National-Local United Engineering Laboratory Nanjing University of Science and Technology Nanjing 210094 China School of Mechanical Engineering Southeast University Nanjing 211189 China

The finite element(FE)-based simulation of welding characteristics was carried out to explore the relationship among welding assembly properties for the parallel T-shaped thin-walled parts of an antenna *** effects of welding direction,clamping,fixture release time,fixed constraints,and welding sequences on these properties were analyzed,and the mapping relationship among welding characteristics was thoroughly *** machine learning algorithms,including the generalized regression neural network(GRNN),wavelet neural network(WNN),and fuzzy neural network(FNN),are used to predict the multiple welding properties of thin-walled parts to mirror their variation trend and verify the correctness of the mapping *** with those from GRNN and WNN,the maximum mean relative errors for the predicted values of deformation,temperature,and residual stress with FNN were less than 4.8%,1.4%,and 4.4%,*** results indicate that FNN generated the best predicted welding *** under various welding conditions also shows a mapping relationship among welding deformation,temperature,and residual stress over a period of *** finding further provides a paramount basis for the control of welding assembly errors of an antenna structure in the future.

关键词： parallel T-shaped thin-walled parts welding assembly property finite element analysis mapping relationship machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Application of machine learning algorithm for the estimation of time-dependent strength of basic oxygen furnace slag-treated soil

引用

DEVELOPMENTS IN THE BUILT ENVIRONMENT 2024年 17卷

作者： Kang, Gyeong-o Seo, Jaehyun Chang, Seongkyu Gwangju Univ Dept Civil Engn 277 Hyodeck Ro Gwangju 61743 South Korea Gwangju Univ Dept Comp Engn 277 Hyodeck Ro Gwangju 61743 South Korea

The main purpose of this study is to predict the time-dependent strength of BOF slag-treated dredged soil using four machine learning (ML) algorithms (random forests, multi-layer perceptron, support vector regression, knearest neighbors). These models were trained using a dataset developed from the published literature. The slag type, slag content, water content, and curing time were used as input values. Here, the curing time was divided into three stages according to the magnitude of strength development. Among the algorithms, the multi-layer perceptron (MLP) was selected as the optimal model, and its predicted strength was compared with that of BOF slag-treated soil calculated by the previous empirical equation. In addition, MLP accurately predicted the strength of BOF slag-treated soil compared with that of the empirical equation. Consequentially, ML algorithms had higher applicability for estimating of the time-dependent strength of BOF slag-treated soils.

关键词： BOF slag Dredged clay Time -dependent strength Prediction machine learning algorithm Empirical equation

来源：评论

学校读者我要写书评

暂无评论

Fiber grating loop ring-down strain sensors using overlap spectrum demodulation and machine learning algorithm

引用

OPTICAL FIBER TECHNOLOGY 2023年第1期76卷

作者： Chen, Dongying Zhang, Hao Xiao, Yiyi Zhang, Zilong Chen, Weijuan Huang, Shuyan Chen, Huaixi Fujian Jiangxia Univ Coll Elect Informat Sci Fuzhou 350108 Peoples R China Smart Home Informat Collect & Proc Internet Things Fuzhou 350108 Peoples R China Fuzhou Univ Coll Phys & Informat Engn Fuzhou 350007 Peoples R China Chinese Acad Sci Fujian Inst Res Struct Matter Fuzhou 350002 Peoples R China Fujian Jiangxia Univ Dept Elect Informat Sci Fuzhou 350007 Peoples R China

The fiber grating loop ring-down (FGLRD) can be used in strain sensors to reduce costs and enhance system sensitivity. Introducing the overlap spectrum demodulation technology in the FGLRD can improve the system's linearity and expand the measurement range. However, there is always strong amplified spontaneous emission (ASE) noise owing to erbium-doped fiber amplifiers (EDFAs) in the FGLRD structure. The noise increases the difficulty of detecting the output ring-down spectrum and reduces the detection accuracy. This study proposes a machine learning algorithm for data processing of chirped FGLRD strain sensors based on overlap spectrum demodulation. It uses a global average pooling one-dimensional convolutional neural network algorithm to construct a data recognition model. The experimental results show that the method can improve the recognition accuracy and reduce the recognition errors caused by ASE noise compared to the conventional ring-down spectral peak detection method. The model accuracy was 100 % for the training and test sets and 98 % for the validation set. The loss value was close to 0.06, and the recognition time was approximately 0.5 ms.

关键词： Fiber grating loop ring -down (FGLRD) Strain sensor Overlap spectrum machine learning algorithm One-dimensional convolutional neural network (1D-CNN)

来源：评论

学校读者我要写书评

暂无评论

MEMS fault-tolerant machine learning algorithm assisted attitude estimation for fixed-wing UAVs

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024年 129卷

作者： Pasha, Amjad Ali Sankaralingam, L. Rahman, Mustafa Mutiur Alam, Mohammad Irfan Juhany, Khalid Ahmad King Abdulaziz Univ Aerosp Engn Dept Jeddah 21589 Saudi Arabia Hindustan Inst Technol & Sci Sch Aeronaut Sci Chennai 603103 India Univ Waterloo Dept Mech & Mechatron Engn Waterloo ON N2L 3G1 Canada Konkuk Univ Konkuk Aerosp Design Airworthiness Res Inst KADA Seoul South Korea

The utilization of Micro-electromechanical Systems (MEMS) sensors is widespread for directly detecting attitude angles, such as Accelerometer, Gyro, and Magnetometer readings. However, these MEMS sensors are prone to flaws, leading to inaccurate estimates of attitude angles and, consequently, causing UAVs to lose control. Given that UAVs are operated remotely over long distances, ensuring accurate attitude estimates becomes crucial. This study aims to address this issue by employing machine learning algorithms (MLA). These algorithms were trained and evaluated to overcome the problem by predicting missing data from a malfunctioning MEMS sensor using the available data from other MEMS sensors. To calculate the attitude angles, the study utilizes the Extended Kalman Filter (EKF) technique. Furthermore, a novel fault-tolerant machine learning-aided estimation algorithm has been proposed specifically for estimating the attitude angles (phi, theta, psi) of fixed-wing UAVs. The significance of this research becomes even more prominent when considering the occurrence of MEMS sensor failure. In such cases, the machine learning algorithm plays a crucial role as it has been pre-trained specifically to handle these scenarios. The algorithm is equipped with the ability to effectively address and mitigate the challenges posed by MEMS sensor failures. By leveraging its pre-existing knowledge and learned patterns, the algorithm can accu-rately predict missing data caused by malfunctioning MEMS sensors. This capability proves invaluable in ensuring the reliable estimation of attitude angles, even in the face of sensor failures. Thus, the integration of machine learning into the estimation process enhances the resilience and robustness of the system, making it well-equipped to handle the uncertainties introduced by MEMS sensor failures.

关键词： Fault-tolerant machine learning algorithm Attitude angles estimation Kalman filter

来源：评论

学校读者我要写书评

暂无评论

Combustion of Raw Biogas/Hot Air in a Porous Radiant Burner and Performance Prediction Using a machine learning algorithm

引用

JOURNAL OF THERMAL SCIENCE AND ENGINEERING APPLICATIONS 2024年第6期16卷 064502-064502页

作者： Dash, Kishan Acharya, Saroj Kumar Samantaray, Sikata SOA Deemed Univ Dept Mech Engn ITER Bhubaneswar 751030 India

Combustion of raw biogas/hot air was performed in a porous radiant burner associated with a solar heater, and performance was predicted by a linear regression model using a machine learning algorithm. The test was conducted for the combustion of three different compositions of raw biogas mixtures having CO2 percentages of 25%, 30%, and 35% at the thermal load of 200-400 kW/m(2). The hot air was supplied at an average temperature of 50 degrees C from the solar heater air supply system for proper combustion in lean mixture conditions. The porous radiant burner associated with a solar heater has offered radiation efficiency of 15.34-47.93%, NOX of 1-3.1 ppm, and CO of 25-87 ppm for three different compositions of raw biogas mixtures at the thermal load of 200-400 kW/m(2) and equivalence ratio of 0.70-0.91. The increased radiation efficiency has indicated that the porous radiant burner can be an alternative for low-calorie fuel like raw biogas. Data analysis and processing have been performed using the machine learning algorithm, and the linear regression model has been developed using the python programming language. The error between predicted and experimentally calculated radiation efficiency is 1.67%.

关键词： porous radiant burner solar heater raw biogas combustion machine learning algorithm linear regression model

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：