检索结果-内蒙古大学图书馆

Inversion of Chlorophyll-a Concentration in Donghu Lake Based on machine learning algorithm

WATER 2021年第9期13卷 1179-1179页

作者： Tang, Xiaodong Huang, Mutao Huazhong Univ Sci & Technol Sch Civil & Hydraul Engn Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Sch Elect & Elect Engn Wuhan 430074 Peoples R China

machine learning algorithm, as an important method for numerical modeling, has been widely used for chlorophyll-a concentration inversion modeling. In this work, a variety of models were built by applying five kinds of datasets and adopting back propagation neural network (BPNN), extreme learning machine (ELM), support vector machine (SVM). The results revealed that modeling with multi-factor datasets has the possibility to improve the accuracy of inversion model, and seven band combinations are better than seven single bands when modeling, Besides, SVM is more suitable than BPNN and ELM for chlorophyll-a concentration inversion modeling of Donghu Lake. The SVM model based on seven three-band combination dataset (SVM3) is the best inversion one among all multi-factor models that the mean relative error (MRE), mean absolute error (MAE), root mean square error (RMSE) of the SVM model based on single-factor dataset (SF-SVM) are 30.82%, 9.44 mu g/L and 12.66 mu g/L, respectively. SF-SVM performs best in single-factor models, MRE, MAE, RMSE of SF-SVM are 28.63%, 13.69 mu g/L and 16.49 mu g/L, respectively. In addition, the simulation effect of SVM3 is better than that of SF-SVM. On the whole, an effective model for retrieving chlorophyll-a concentration has been built based on machine learning algorithm, and our work provides a reliable basis and promotion for exploring accurate and applicable chlorophyll-a inversion model.

关键词： chlorophyll-a inversion machine learning algorithm Donghu Lake

来源：评论

学校读者我要写书评

暂无评论

Evaluating the integrated performance and effectiveness of RUSLE through machine learning algorithm on soil erosion susceptibility in tropical plateau basin, India

引用

JOURNAL OF SEDIMENTARY ENVIRONMENTS 2024年第3期9卷 665-693页

作者： Kundu, Moumita Ghosh, Arnab Abu Zafor, Md Maiti, Ramkrishna Vidyasagar Univ Dept Geog Midnapore West Bengal India Integrated Inst Adv Res & Informat IIARI Res Incubat Ctr Kolkata West Bengal India Bangladesh Army Int Univ Sci & Technol Dept Civil Engn Cumilla Bangladesh

Soil erosion is a huge problem in any plateau region as the population increases with rapid urbanization, which, in turn, increases the amount of sedimentation in the river through the increasing amount of soil erosion in the plateau region. If different methods identify these soil erosion zones, it is possible to take various measures to prevent soil erosion. This article discusses the nature, extent, and rate of soil erosion and its spatial pattern along the Rupnarayan basin with the help of RUSLE (Revised Universal Soil Loss Equation) and a machine learning algorithm. This area is highly affected by monsoonal rainfall and changes in land use patterns over time. By discussing the performance of RUSLE through machine learning models i.e. Frequency Ratio (FR), Artificial neural network (ANN), support vector machine (SVM), Extreme Gradient Boosting (XGB) and ensemble model using some permutation combination of aforesaid model with various GIS (Geographical Information System) and spatial basis parameters, it is seen that the undulating upper portion of the region is the highest soil erosion susceptible zone. Except for any other GIS platform, these models are developed through Google Earth Engine and interpreted by SHapley Additive Explanation (SHAP), based on game theory. This study developed a new interpretable model in the field of soil erosion that is helpful for global and local representation. Erosional locations obtained from field studies are focused on achieving this goal. This study used 389 soil erosion points as a dependent factor against 14 soil-affecting independent factors. The best-performing model is determined from the AUC (Area Under the Curve) curve and kappa indices and interpreted globally and locally by the SHAP method to evaluate the effectiveness of each factor in soil erosion for the entire study area and the specific region. The result shows that the AUC values of FR, SVM, ANN, XGB and ensemble XGB-FR-SVM are 0.842, 0.831, and 0.828. 0.920

关键词： Soil erosion RUSLE machine learning algorithm Ensemble model GEE (google earth engine) SHAP (shapley additive explanation)

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

Research on machine learning algorithm-Based Approach for Detecting Abnormal Data from Environmental Sensors in Different Dimensions 23

Research on Machine Learning Algorithm-Based Approach for De...

引用

Proceedings of the 2023 International Joint Conference on Robotics and Artificial Intelligence

作者： Wenqiang Yue Li-an Chen Haiyan Huang School of Electrical Engineering and Automation Xiamen University of Technology China School of Electrical Engineering and Automation Xiamen Key Laboratory of Frontier Electric Power Equipment and Intelligent Control Xiamen University of Technology China Xiamen Minghan Electric Co. Ltd. China

ISBN: (纸本)9798400707704

With the development of environmental sensor technology, more and more environmental sensors are widely used in various fields, such as environmental monitoring, smart home, smart city and so on. However, due to the complexity and diversity of environmental sensor data, there are a high number of anomalous data in sensor data, which can lead to misjudgment and false positives, compromising data reliability and accuracy. Therefore, the detection method of abnormal data in different dimensions of environmental sensors based on machine learning algorithms were studied in this paper. Firstly, the environmental sensor data of IBRL (Intel Berkeley Research Lab) data set was preprocessed, including data cleaning, data normalization and feature extraction. Then, the simulation experiment was completed using the data set, and the data of different dimensions was detected using machine learning algorithms such as OneClass Support Vector machine algorithm, Local Outlier Factor algorithm, and Isolation Forest algorithm. Finally, through experimental comparison and analysis of the application effects of the above three algorithms in anomaly detection of environmental data in different dimensions, the Isolation Forest algorithm with the best comprehensive detection effect was finally selected for practical engineering projects. In practical engineering projects, maintenance costs can be effectively reduced, project safety and reliability can be improved, and the purpose of improving project efficiency can ultimately be achieved by the proposed method.

关键词： Abnormal data detection Environmental sensor machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Football Player Injury Full-Cycle Management and Monitoring System Based on Blockchain and machine learning algorithm

引用

INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS 2023年第1期16卷 41-41页

作者： Pu, Chunwang Zhou, Jun Sun, Jian Zhang, Jianpeng Yuxi Normal Univ Sch Phys Educ Yuxi 653100 Peoples R China Coll Art & Sci Kunming Sch Phys Educ Kunming 650201 Peoples R China Yunnan Agr Univ Sch Phys Educ Kunming 650201 Peoples R China

Football injuries are the most common factor affecting a football player's performance, and the last thing a football player wants. To understand the causes of football players' injuries and how to recover sports injuries most efficiently, the football players' injuries were managed and monitored throughout the whole cycle. However, the traditional football player injury cycle management and monitoring system are not only insecure in data storage, but more importantly, it lacks intelligent analysis of the collected data. With the continuous development of blockchain and machine learning technologies, blockchain technology is used to collect, store, clean, mine and visualize the full-cycle data of football players' injuries, and machine learning is used to provide intelligent solutions for football players' injury recovery. This paper compared the football player's injury full-cycle management and monitoring system based on blockchain and machine learning algorithm with the traditional football player's injury management and monitoring system. The experimental results showed that the average self-processing capacity of the football player injury MMS based on blockchain and ML algorithm was 70%, while the average self-processing capacity of the traditional football player injury management and monitoring system was 50%. Therefore, the application of blockchain and machine learning algorithm in the football player's injury full-cycle management and monitoring system can effectively improve the system's self-processing ability.

关键词： Full-cycle management and supervision system Football player injury machine learning algorithm Blockchain technology Support vector machine

来源：评论

学校读者我要写书评

暂无评论

Multi Strategy machineenglish Translation System based on machine learning algorithm 5

Multi Strategy Machineenglish Translation System based on Ma...

引用

5th International Conference on machine learning and machine Intelligence, MLMI 2022

作者： Jiang, Shuang Jilin Animation Institute Jilin Province Changchun China

ISBN: (纸本)9781450397551

The advent of the big data era has brought unprecedented data to machine translation, which is particularly important for data-driven models and algorithms. The degree of public quotation of source text is becoming more and more difficult to understand, but the overall translation performance is improving. On this basis, the multi Strategy machineenglish translation (MSMT) system based on MLA is designed in this paper. Firstly, the MSMT system and machineenglish translation process are analyzed, and the Interactive MSMT system is discussed. Then the neural network translation model of machine learning is proposed. In order to improve the performance of the MSMT system based on MLA proposed in this paper, The results show that in the case of full-text retrieval, the time of English translation is greatly increased, and these time are basically spent in finding and matching these sentences. The sentences that cannot be translated due to the failure of feature index can be translated by the Multi Strategy machine English translation system based on MLA proposed in this paper, which verifies the rationality of the translation system proposed in this paper. © 2022 ACM.

关键词： English Translation machine learning algorithm Multi Strategy machine Translation System Design

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

Application of random-forest machine learning algorithm for mineral predictive mapping of Fe-Mn crusts in the World Ocean

引用

ORE GEOLOGY REVIEWS 2023年 162卷

作者： Josso, Pierre Hall, Alex Williams, Christopher Le Bas, Tim Lusty, Paul Murton, Bramley British Geol Survey Environm Sci Ctr Nottingham NG12 5GG England Natl Oceanog Ctr Waterfront CampusEuropean Way Southampton SO14 3ZH England

Mineral prospectivity mapping constitutes an efficient tool for delineating areas of highest interest to guide future exploration. Multiple knowledge-driven approaches have been applied for the creation of prospectivity maps for deep-sea ferromanganese (Fe-Mn) crusts over the last decades. The results of a data-driven approach making use of an extensive data collection exercise on occurrences of Fe-Mn crusts in the World Ocean and recent increase in global marine datasets are presented. A Random Forest machine learning algorithm is applied, and results compared with previously established expert-driven maps. Optimal predictive conditions for the algorithm are observed for (i) a forest size superior to a hundred trees, (ii) a training dataset larger than 10%, and (iii) a number of predictors to be used as nodes superior to two. The confusion matrix and out-of-bag errors on the remaining unused data highlight excellent predictive capabilities of the trained model with a prediction accuracy for Fe-Mn crusts of 87.2% and 98.2% for non-crusts locations, with a Kohen's K index of 0.84, validating its application for prediction at the World scale. The slope of the seafloor, sediment thickness, sediment type, biological productivity, and abyssal mountain constitute the five strongest explanatory variables in predicting the occurrence of Fe-Mn crusts. Most 'hand-drawn' knowledge-driven prospective areas are also considered prospective by the random forest algorithm with notable exceptions along the coast of the American continent. However, poor correlation is observed with knowledge-driven GIS-based criterion mapping as the Random Forest considers un-prospective most target areas from the GIS approach. Overall, the Random Forest prediction performs better in predicting a high chance of Fe-Mn crust occurrence in ISA licensed area than the GIS approach, which constitutes an external validation of the predictive quality of the random forest model.

关键词： Ferromanganese crust Deep-sea mineral Prospectivity analysis Mineral resources machine learning algorithm Random forest

来源：评论

学校读者我要写书评

暂无评论

Potential application of generative artificial intelligence and machine learning algorithm in oil and gas sector: Benefits and future prospects

引用

TECHNOLOGY IN SOCIETY 2024年 79卷

作者： Ochieng, Edward G. Ominde, Diana Zuofa, Tarila British Univ Dubai BUiD Fac Business & Law Project Management Dubai U Arab Emirates Strathmore Univ Strathmore Business Sch Off Ole Sangale Rd Nairobi Kenya Univ Wisconsin Parkside Coll Business Econ & Comp Somers WI USA

With the rapid advancement of technology and societies, the global energy sector now acknowledges that by integrating contemporary digital technologies into their operations and capabilities, can improve their competitive advantage and innovation performance and processes. Moreover, energy operators are also facing a significant undertaking: how to best use and secure large amounts of data that promote sustainable productivity performance and minimise potential threats in the oil and gas value chain and project operations. In view of the foregoing, various facets like Generative Artificial Intelligence (GAI) and machine learning algorithms (MLA) are increasingly gaining popularity within oil and gas sector operations. Thus, we explored how GAI and ML algorithms can enhance oil and gas value chain productivity performance. The Principal Component Analysis (PCA) was employed to identify significant GAI and MLA variables influencing performance in the oil and gas value chain, while Structural Equation Modelling (SEM) was used to test regression equations related to their application. The study found that risk portfolios and profiles can be appraised throughout the value chain by effectively utilising GAI and ML algorithms in upstream, midstream and downstream undertakings. While these findings are noteworthy and have significant implications for current practice, the paper advocates that an array of digital technologies beyond GAI and ML can still be examined during future studies to demonstrate a holistic perspective on how digital transformation can be achieved across the energy sector value and project operations.

关键词： Generative artificial intelligence machine learning algorithm Value chain operations Oil and gas Productivity performance Risk management

来源：评论

学校读者我要写书评

暂无评论

Obtaining the molar heat capacities and entropies of HCl and HBr by combining density functional theory and machine learning algorithm

引用

INTERNATIONAL JOURNAL OF QUANTUM CHEMISTRY 2023年第18期123卷 e27175-e27175页

作者： Yang, Zhangzhang He, Guiling Wei, Qinqin Fu, Jia Fan, Qunchao Xie, Feng Zhang, Yi Ma, Jie Xihua Univ Sch Sci Key Lab High Performance Sci Computat Chengdu Peoples R China Tsinghua Univ Inst Nucl & New Energy Technol Collaborat Innovat Ctr Adv Nucl Energy Technol Minist EducKey Lab Adv Reactor Engn & Safety Beijing Peoples R China Natl Univ Def Technol Coll Adv Interdisciplinary Studies Changsha Peoples R China Shanxi Univ Coll Phys & Elect Engn Laser Spect Lab State Key Lab Quantum Opt & Quantum Opt Devices Taiyuan Peoples R China Xihua Univ Sch Sci Key Lab High Performance Sci Computat Chengdu 610039 Peoples R China

An integrated approach combing density functional theory (DFT) and machine learning algorithm (MLA) is proposed here to obtain the molar heat capacities and entropies of diatomic macroscopic gasses with high quality. The DFT approach takes care of the main physical effects, while machine learning takes care of the intricate details it leaves out. After machine learning algorithm correction, a complete set of accurate prediction of vibrational energy spectrum is obtained, which is better than the results of DFT methods in accuracy. And then it is used to replace the vibrational part in the ro-vibrational energy calculated by DFT to obtain the rectified ro-vibrational energy. Furthermore, through the quantum ensemble theory, the thermodynamic properties of the macroscopic gas are calculated by the predicted ro-vibrational energy spectrum, and are modified again by the machine learning algorithm. The study of the HCl$$ HCl $$ and HBr$$ HBr $$ system show that, compared with CCSD(T)/cc-pV5Z and the improved variational algebraical method, the macroscopic thermodynamic properties calculated by this work in the temperature range of 300-6000 K are the closest to the experimental values. The relative error is less than 1% at each temperature.

关键词： density functional theory diatomic macroscopic gasses machine learning algorithm macroscopic thermodynamic properties

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：