检索结果-内蒙古大学图书馆

1st international conference Ambient Intelligence in Health Care (ICAIHC)

作者： Durgadevi, Velusamy Arunagiri, Bharath Dhanapal, Vignesh Seeniraj, Yogesh Krishnan Thirugnanam, Shashangan M Kumarasamy Coll Engn Dept Comp Sci & Engn Karur 639113 India

ISBN: (纸本)9789811960703;9789811960680;9789811960673

COVID-19 infection is a transmissible virus causing acute respiratory syndrome spreading worldwide. The number of patients infected by this deadly virus increases steadily, causing a high mortality rate. Hence, it is crucial to diagnose and identify the COVID-19 infection for earlier treatment of the patients. This study has applied four algorithms, namely, Logistic Regression (LR), Nu-Support Vector machine (Nu-SVM), Multi-layer perceptron (MLP) and Naive Bayes (NB) to identify COVID-19 infection. The clinical laboratory findings of 600 individuals were taken from Hospital Isrelita Albert Einstein, Sao Paulo, Brazil, used in this study. We have selected significant features using Random forest-based recursive feature elimination for predicting the infection. Experiments are conducted with 90% training and 10% testing data. The performance result shows that the Nu-SVM algorithm obtained the prediction accuracy of 95% with 100% sensitivity and 94.23% specificity in predicting the infection. To our knowledge, the result achieved by Nu-SVM is the highest in the literature. Hence, the model can be used as a tool for the initial prediction of COVID-19 disease.

关键词： Clinical findings COVID-19 infection machine learning algorithm Nu-support vector machine

来源：评论

学校读者我要写书评

暂无评论

Design and Application of Public Risk Perception Early Warning System Based on machine learning algorithm 24

Design and Application of Public Risk Perception Early Warni...

引用

3rd International Conference on Cyber Security, Artificial Intelligence and Digital Economy (CSAIDE)

作者： Xu, Binghui Taizhou Vocat & Tech Coll Taizhou 318000 Zhejiang Peoples R China

ISBN: (纸本)9798400718212

As a negative event with group effect, public risk may be caused by a variety of reasons, but the final result is basically social or environmental turbulence, chaos, or even destruction. In order to avoid this phenomenon, it is necessary to design a public risk perception early warning system. In this paper, machine learning algorithms are used to give the perception and warning system the learning ability, so as to strengthen its perception and warning ability of risks. In addition, this paper also puts forward the perspective of using big data to analyze Internet text information, so as to strengthen the system's assessment ability of risks. Finally, the system based on the proposed method was compared with the conventional system in this paper. The average accuracy of the experimental group was 92.33%, while the average accuracy of the control group was 86.52%. The experimental results show that the proposed method can improve the performance of the risk perception early warning system, and also reflect the role of machine learning algorithms.

关键词： machine learning algorithm Public Risk Perception Early Warning System Big Data Analysis

来源：评论

学校读者我要写书评

暂无评论

The Research on College Students Physical Fitness Using machine learning algorithm 7

The Research on College Students Physical Fitness Using Mach...

引用

7th International Conference on Artificial Intelligence and Big Data (ICAIBD)

作者： Wang, Tingting Wang, Shengyu Yin, Guohao Wang, Yue Li, Bo Chengdu Neusoft Univ Dept Fundamental Educ Chengdu Peoples R China Chengdu Shude High Sch Chengdu Peoples R China Chengdu Neusoft Univ Dept Comp & Software Chengdu Peoples R China

ISBN: (纸本)9798350385113;9798350385106

Physical fitness is a critical component of college students' overall health and well-being. This study employs machine learning algorithms to identify key factors that influence fitness scores and to understand the relationship between students' physical attributes and their performance in fitness tests. The integration of multiple machine learning models not only enhances the predictive power of our analysis but also equips us with a robust framework to address the complexities inherent in physical fitness data. The study aspires to contribute to the development of personalized fitness programs that can significantly improve the health and fitness levels of college students.

关键词： MLP Physical Fitness Test machine learning algorithm Prediction Model

来源：评论

学校读者我要写书评

暂无评论

Reliability Analysis and Optimization of Computer Communication Network Based on machine learning algorithm

Reliability Analysis and Optimization of Computer Communicat...

引用

International Conference on Frontiers of Artificial Intelligence and machine learning (FAIML)

作者： Liu, Dai-xiong Wuhan Polytech Coll Comp Technol & Software Engn Wuhan 430074 Hubei Peoples R China

ISBN: (数字)9781665473644

ISBN: (纸本)9781665473644

machine learning is to find laws from observed data and use these laws to predict future data or unobservable data. Network measurement and routing optimization strategy are critical components in the routing optimization problem. Due to the continuous progress of information technology, computer information technology is widely used in various fields, so its security and reliability will be paid more and more attention. The unsupervised learning classification is carried out through the fast density clustering algorithm to classify the importance of nodes, which can be effectively applied to the important evaluation of communication network nodes and support the planning of the communication network. Given the progress of communication technology, optical fiber technology and computer internet technology, the network's functions have been strengthened daily, and the research on the reliability of computer communication networks has been promoted to develop in depth. Furthermore, optimization theory can realize the bandwidth allocation of a communication network. The important is that computer communication network reliability based on machine learning algorithm has great economic value, social value and social benefit.

关键词： machine learning algorithm Computer communication network Reliability Optimization

来源：评论

学校读者我要写书评

暂无评论

Investigation of data distribution effect in Random Forest machine learning algorithm for WLCSP Reliability Prediction 15

Investigation of data distribution effect in Random Forest M...

引用

15th International Microsystems, Packaging, Assembly and Circuits Technology Conference (IMPACT)

作者： Chen, B. W. Tsai, T. H. Chiang, K. N. Natl Tsing Hua Univ Dept Power Mech Engn Adv Microsyst Packaging & Nanomech Res Lab Hsinchu 300 Taiwan

ISBN: (纸本)9781728198514

In recent years, due to the consumer market become larger and larger, the electronic equipment improves every day, we pay more and more attention to the reliability of electronic packaging. Electronic packaging is a complex structure that protects IC devices and plays an important role in the semiconductor industry. Our research aims to evaluate the reliability of electronic packaging, and Thermal Cycling Testing (TCT) is one of the important tests to ensure packaging reliability. TCT is a good way to test electronic packaging reliability, but it takes a lot of time and cost to do this experiment. The time required to perform a TCT can be as long as several months or years. In order to effectively reduce the test time, we often use the Finite Element Method (FEM) instead of TCT. Although FEM takes less time than TCT, it still takes some time to use the FEM to get the simulation result. We build the model according to different parameters and fixed boundary conditions, and then apply the thermal cycle load on the model to obtain the prediction life value of the electronic package. Different researchers may lead to different results, even if they use the same model parameter. If we use a large amount of validated FEM data to build a database for machine learning(ML), then we can immediately evaluate the electronic package prediction life through machine learning methods. It not only saves the time to build the model and validation, but also avoid the simulation error. This research is to use the ML method to analyze the reliability of Wafer Level Chip Scale Packaging (WLCSP). ML can find potential rules of data sets through algorithms, establish mathematical models, and obtain prediction life of different WLCSP structures. For the same data set, different algorithms may get different results. So, choosing the suitable algorithm is the most important step in using machine learning algorithm. This research uses a Random Forest algorithm (RF) and Extremely Randomized Tre

关键词： Thermal Cycling Testing Wafer Level Chip Scale Packaging Finite Element Method machine learning algorithm Random Forest Extremely Randomized Trees

来源：评论

学校读者我要写书评

暂无评论

Electrical Fault Detection Using machine learning algorithm For Centrifugal Water Pumps 19

Electrical Fault Detection Using Machine Learning Algorithm ...

引用

19th IEEE International Conference on Environment and Electrical Engineering (EEEIC) / 3rd IEEE Industrial and Commercial Power Systems Europe Conference (I and CPS Europe)

作者： Chakravarthy, Ranganatha Bharadwaj, Sai Charan Umashankar, S. Padmanaban, Sanjeevikumar Dutta, Nabanita Holm-Nielsen, Jens Bo VIT Vellore SELECT Dept Energy & Power Elect Vellore Tamil Nadu India Prince Sultan Univ Coll Engn Renewable Energy Lab Riyadh Saudi Arabia Aalborg Univ Dept Energy Technol Esbjerg Denmark

ISBN: (纸本)9781728106526

The most essential part of any living being is water. Humans utilize water for various purposes such as cooking, bathing, washing, drinking, cultivating, cleaning, power generation and so on. Water pumps are employed to facilitate easy access near the requirement. Pumps can be classified into many groups according to the method of fluid displacement they inculcate to transport the fluid. Various faults are associated with the working of the water pumps due to the way it is handled, environmental conditions, supply imbalance, poor power quality or due to any other mechanical failures. Hence an effective process to determine the different various faults so as to mitigate the damage is required. This paper analyses the various faults in the centrifugal water pumps driven by induction motors used in agriculture fields and proposes a new algorithm to effectively and efficiently identify the fault and classify it according to its category using machine learning algorithms.

关键词： Centrifugal pumps faults machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Development of a machine learning algorithm for Efficient Localization of Damage in a Composite Structure Using Random Forest Technique

引用

Iranian Journal of Science and Technology - Transactions of Civil Engineering 2024年第6期48卷 4793-4809页

作者： Shinagam, Rama Krishna Maruvada, Tarun Janjeti, Sathish Talari, Rahul Mani Datta Shinagam, Raghu Vamsi Gayatri Vidya Parishad College of Engineering Visakhapatnam 530 048 India

Composite materials offer a unique combination of properties that make them highly versatile and advantageous in numerous applications, particularly in aircraft and automobile industries. However, despite their advantages, composite materials are susceptible to crack propagation under fatigue stress due to the absence of endurance limit. This susceptibility poses a significant safety risk in aircraft and automobile applications. Therefore, developing a quick, simple, and reliable technique for early detection of cracks is crucial for enhancing the safety of these vehicles. machine learning models trained on vibration data offer a promising approach for real-time health monitoring and damage detection in composite structures. This study develops an efficient solution using a Random Forest regression model to predict crack location based on the first three natural frequencies obtained through impact hammer testing on various cracked composite structures. A dynamic signal analyzer, impact hammer, and acceleration sensor are employed to acquire the data of the first three natural frequencies, which are then used to train the Random Forest regression algorithm. Min-max scaling is applied to normalize the input data, further enhancing the efficiency of the proposed scheme. The performance of the Random Forest regression model is evaluated using R-squared score, mean absolute error (MAE) and mean squared error (MSE). After applying the min-max scaler, the performance of the model is evaluated with the MAE, MSE, and R-squared score, which are 7.164, 137.309, and 0.972, respectively. The high R-squared score of the fitted Random Forest algorithm demonstrates its strong ability to accurately predict the crack location. The proposed method is further validated through experiments conducted on a cracked composite structure. The error between the measured and predicted values using the present scheme is found to be only 9.6%, thus validating the effectiveness of the proposed app

关键词： Composite structure Damage localization Data normalization High efficiency Impact hammer test machine learning algorithm Random forest regression model

来源：评论

学校读者我要写书评

暂无评论

Prediction of FBC Boiler Efficiency using machine learning algorithm 3

Prediction of FBC Boiler Efficiency using Machine Learning A...

引用

3rd IEEE International Power and Renewable Energy Conference (IPRECON)

作者： Pawar, Raunak Khandekar, M. A. Agashe, S. D. Makwana, Pratap COEP Technol Univ Dept Instrumentat & Control Engn Pune India Forbes Marshall Pune India

ISBN: (纸本)9781665491754

It is now clear that a fluidized bed combustion boiler is a feasible choice with many benefits over a traditional firing system. These boilers burn coal, washery waste, rice husk, bagasse, and other agricultural wastes as fuels. Calculations of boiler efficiency using the conventional method is time-consuming and very expensive. The work presented in this paper deals with establishing the statistical model for boiler efficiency using boiler parameters. Different machine learning algorithm like, Multilinear regression, support vector regression, K-nearest neighbors and decision tree regression have been used to build the boiler efficiency model. K-nearest neighbors algorithm shows the best model accuracy. So we can predict Fluidized bed combustion boiler efficiency using real time boiler parameters.

关键词： FBC Boiler machine learning algorithm K-nearest Neighbor Efficiency prediction

来源：评论

学校读者我要写书评

暂无评论

Smart Tourism Route Planning System Based on machine learning algorithm

Smart Tourism Route Planning System Based on Machine Learnin...

引用

International Conference on Computers and Artificial Intelligence Technologies (CAIT)

作者： Yu, Zhenzhen Wang, Shan Shandong Inst Commerce & Technol Jinan 250103 Shandong Peoples R China

ISBN: (纸本)9798350396171

With the development of economy and the improvement of life quality, people have a deeper pursuit. Therefore, tourism has developed into one of the pillar industries of China's economy. Tourism has gradually become an important part of people's life and entertainment, but people's tourism consumption behavior has undergone significant changes, and they have a higher standard for tourism quality, which is the background of the birth of the concept of smart tourism. This paper analyzes the current situation and existing problems of tourism market route planning, and constructs an intelligent tourism route planning system based on machine learning algorithm to meet the diversified needs of tourists and promote the high-quality development of tourism Through the analysis of the tourism situation of a province from 2016 to 2020, the response time of the system was tested after the intelligent tourism route planning system was put into use. It was found that the response time of the system would increase 0.0005 seconds for every 100000 additional passengers. The increase of people flow will lead to system interface congestion, but the time is very short and can be basically ignored. The research shows that the design of the system can still bring convenience to passengers.

关键词： machine learning algorithm smart tourism route planning system tourism industry

来源：评论

学校读者我要写书评

暂无评论

An Energy-Efficient Cmos Image Sensor With Embedded machine learning algorithm

An Energy-Efficient Cmos Image Sensor With Embedded Machine ...

引用

作者： Kyuseok Lee University of Michigan

学位级别：博士

In this thesis, an energy-efficient CMOS (Complementary MetalâOxide Semiconductor) image sensor for embedded machine-learning algorithms has been studied to provide low-power consumption, minimized hardware resources, and reduced data bandwidth in both digital and analog domains for power-limited applications. In power-limited applications, image sensors for embedded machine learning algorithms typically have these challenges to address: low-power operation from limited energy sources such as batteries or energy harvesting units, large hardware area due to complicated machine-learning algorithms, and high-data bandwidth due to video streaming images and large data movement for evaluating the machine-learning algorithms. This research focuses on developing the architectures, algorithm optimization, and associated electronic circuits for an energy-efficient CMOS image sensor with the embedded machine-learning algorithms. Three interdependent prototypes have been developed to solve major challenges: minimization of energy consumption and hardware resources while preserving a high degree of precision in machine-learning algorithm evaluation. Three prototypes have been fabricated and fully characterized to address these challenges. In the first chip, we implemented 2 bit spatial difference imaging, a customized look-up table (LUT) based gradient orientation assignment, and a cell-based supporting-vector-machine (SVM) to achieve both low-data bandwidth and higher area efficiency for a histogram-of-oriented-gradient (HOG)-based object detection. The proposed HOG-based object detection core operates with the 2D optic flow core to provide the vision-based navigation functionality for the nano-air-vehicle (NAV) application. The system operates at 244 pJ/pixel in 2D optic flow extraction mode and at 272.49 pJ/pixel in hybrid operation mode, respectively. The system achieved 75% reduction in memory size with proposed HOG feature extraction method and cell-based supporting-vec

关键词： CMOS image sensor machine learning algorithm Energy harvesting pixel Electrical Engineering Engineering

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：