检索结果-内蒙古大学图书馆

Explainable machine learning models for estimating daily dissolved oxygen concentration of the Tualatin River

Engineering applications of Computational Fluid Mechanics 2024年第1期18卷

作者： Li, Shuguang Qasem, Sultan Noman Band, Shahab S. Ameri, Rasoul Pai, Hao-Ting Mehdizadeh, Saeid School of Computer Science and Technology Shandong Technology and Business University Yantai China Computer Science Department College of Computer and Information Sciences Imam Mohammad Ibn Saud Islamic University (IMSIU) Riyadh Saudi Arabia Computer Science Department Faculty of Applied Science Taiz University Taiz Yemen Future Technology Research Center National Yunlin University of Science and Technology Douliu Taiwan Department of Information Management International Graduate School of Artificial Intelligence National Yunlin University of Science and Technology Douliu Taiwan Department of Information Management National Yunlin University of Science and Technology Douliu Taiwan Bachelor Program of Big Data Applications in Business National Pingtung University Pingtung Taiwan Water Engineering Department Urmia University Urmia Iran

Monitoring the quality of river water is of fundamental importance and needs to be taken into consideration when it comes to the research into the hydrological field. In this context, the concentration of the dissolved oxygen (DO) is one of the most significant indicators of the quality of river water. The current study aimed to estimate the minimum, maximum, and mean DO concentrations (DO min, DO max, DO mean) at a gauging station located on Tualatin River, United States. To that end, four machine learning models, such as support vector regression (SVR), multi-layer perceptron (MLP), random forest (RF), and gradient boosting (GB) were established. Root mean square error (RMSE), mean absolute error (MAE), coefficient of correlation (R), and Nash-Sutcliffe efficiency (NSE) metrics were employed to better assess the accuracies of these models. The modeling results demonstrated that the SVR and MLP surpassed the RF and GB models. Despite this, the SVR was concluded to be the best-performing method when used to estimate the DO min, DO max, and DO mean. The best error statistics in the testing phase were related to the SVR model with full (four) inputs to estimate DO mean concentration (RMSE = 0.663 mg/l, MAE = 0.508 mg/l, R = 0.945, NSE = 0.875). Finally, the explainability of the superior models (i.e. SVR models) was conducted using SHapley Additive exPlanations (SHAP) for the first time to estimate DO concentration. In fact, evaluating the explainability of machine learning models can provide useful information about the impact of each of the input estimators used in the procedure of models development. It was concluded that the specific conductance (SC) and followed by water temperature (WT) could provide the most contributions for estimating the DO min, DO max, and DO mean concentrations. © 2024 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

关键词： dissolved oxygen concentration estimation Explainable machine learning SHapley additive explanations

来源：评论

学校读者我要写书评

暂无评论

Analysis and Optimization of Neural Networks for Image and Speech Recognition

Analysis and Optimization of Neural Networks for Image and S...

引用

Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： Komala C R R. Purushothaman Pavan Kumar Ande P M Dinesh Anitha Rani K S Yamuna P Department of Information Science and Engineering HKBK College of Engineering Bengaluru Karnataka India Faculty of Engineering and Technology Sri Ramachandra Institute of Higher Education and Research Chennai Tamil Nadu India Department of Computer Science and Engineering KoneruLakshmaiah Education Foundation Guntur Andhra Pradesh India Department of Electronics and Communication Engineering Sona College of Technology Salem Tamil Nadu India School of Computer Science and Applications REVA University Bengaluru Karnataka India Department of Computer Applications Acharya Institute of Graduate Studies Soladevanahalli Karnataka India

The strategy of transforming vocal discourse signals into text using records is known as programmed discourse acknowledgment (ASR). In the ongoing time of the PC unrest, the ASR has a huge impact in further developing the client experience while communicating with the PCs in a characteristic manner. Conventional instruments like a console and mouse can't be utilized, and the client might do a limitless number of undertakings like controlling of contraptions and correspondence with client care. This study presents an air terminal enquiry framework in view of ASR. The program was made solely for the Telugu language. In view of the most generally posed inquiries about air terminals, a data set was created. Convolutional Brain Organization (CNN) has been utilized for preparing and testing the information base in view of its extraordinary exhibition. Convolution brain organizations (CNNs) have as of late been demonstrated to perform better on the telephone discovery test than regular completely associated profound brain networks when utilized in a half and half profound brain organization/stowed away Markov model (DNN/Gee) design.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Optimizing Parameters and Feature Selection in SVM Based on Improved Cockroach Swarm Optimization 16th

An Optimizing Parameters and Feature Selection in SVM Based ...

引用

16th International Conference on Intelligent information Hiding and Multimedia Signal Processing, IIH-MSP 2020 in conjunction with the 13th International Conference on Frontiers of information technology, applications and Tools, FITAT 2020

作者： Nguyen, Trong-The Yu, Jie Nguyen, Thi-Thanh-Tan Lai, Quoc-Anh Ngo, Truong-Giang Dao, Thi-Kien Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China College of Mechanical and Automotive Engineering Fujian University of Technology Fuzhou China Information Technology Faculty Electric Power University Hanoi Viet Nam Department of Pattern Recognition & Image Processing Institute of Information Technology Vietnam Academy of Science and Technology Hanoi Viet Nam Faculty of Computer Science and Engineering Thuyloi University 175 Tay Son Dong Da Hanoi Viet Nam

ISBN: (纸本)9789813367562

This study improves a classifier of the support vector machine (SVM) by optimizing its parameters by adjusting cockroach swarm optimization (CSO). Classification system design includes data inputs, pre-process, and classification. The relief technique selects the feature subset, and the kernel parameters used as input for the system. The feature selection and classification of data sets were figured out by the combination of ICSO and SVM with its optimized parameters synchronous. Simulation results of the proposed scheme are compared with other systems, e.g., GA-SVM, PSO-SVM, and CSO-SVM, which show that the proposed project can achieve better classification accuracy than the different algorithms. It is promising that the proposed scheme can be applied to high-dimensional data classification, such as image classification, signal classification. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Model for the Analytical Performance of Data Lake in Stock Market Analysis with Databricks Delta Lake

A Model for the Analytical Performance of Data Lake in Stock...

引用

Self Sustainable Artificial Intelligence Systems (ICSSAS), International Conference on

作者： S. Kamalakkannan A. Yasmin Arunkumar. R P. Kavitha Department of Information Technology School of Computing Sciences Vels Institute of Science Technology & Advanced Studies Pallavaram Chennai India Department of Computer Science JBAS College for women Chennai India Faculty of Computing Engineering and Science University of South Wales Treforest/Newport Campus United Kingdom Department of Computer Applications School of Computing Sciences Vels Institute of Science Technology & Advanced Studies Pallavaram Chennai India

Stock market investments are highly rewarding but also high in risk. Modern investors use variety of tools to take informed investment decisions. In the current era of digital world, financial service industry has generated huge volume and immense verities of data with extreme speed. Due to the rapid growth in data collection and the heterogeneous nature and complexity of the data, there is a need for Big Data analytical solution that would be able to deal with the stock market data. Large volumes of unstructured, heterogeneous raw data can be stored in a massively scalable manner using data lakes, which are the ideal solution to the big data storage conundrum. The ability of a data lake to preserve data in its original format while processing it at runtime using a schema on-read technique is its key feature. The challenge faced in the data lake is performing analytics which is a significant tool to calculate and analyze the stock market. The proposed architecture of Azure Databricks DeltaLake (ADDL) with Azure DataLake Storage Generation 2 (ADLSG2) is used for analytical processes like Fibonacci retracement for better stock analysis, which aid in forecasting the market price for better investment. As a result, the research focus is to produce a storage having read as well as write capabilities by taking into consideration the Extract-Load-Transform (ELT) operation on the datasource. In this experimental databricks implementation, runtime is performed using open source of Apache Spark API and a highly improved execution engine, which results in a significant performance improvement when comparing to the standard source of Apache Spark available on the ADLS platform. Additionally, the Fibonacci retracement level calculation is achieved with the analytics and forecasting of test close price with various ML and DL techniques such as KNN, LSTM are compared with original price of the test data for better prediction of forecast close price.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Experimental Evaluation of Cross-Platform Recognition of Identical and Unknown Users over Social Networking Environment

Experimental Evaluation of Cross-Platform Recognition of Ide...

引用

Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： Kancharla Nagababu S. Ananthi Neeraj Sunheriya Venkata Siva Prasad Ch J. Jayanthi Hamed Fawareh Department of Computer Applications Aditya University Department of CSE St. Joseph's College of Engineering Chennai Department of Mechanical Engineering Yeshwantrao Chavan College of Engineering Nagpur India Department of ECE Jeppiaar Engineering College Chennai-119 Department of CSE Sona College of Technology Salem Software Engineering Dept Faculty of Information Technology Zarqa University Zarqa Jordan University of Business and Technology Jeddah Saudi Arabia

ISBN: (数字)9798331543624

ISBN: (纸本)9798331543631

The capacity to individually identify and categorize people across sites and apps is vital for trustworthiness, fraud prevention, and personalized experiences in online social networking. In this study, strategies for platform identification among similar and unknown social networking users are evaluated. We study strategies that employ user attributes, behavior history, and inter-network connections to match profiles on multiple platforms and uncover new, previously connected people. This cross-validation on the proposed method uses Social Linkage Identification Strategy (SLIS) and Friend Relationship Evaluator. According to quantitative experiment results, our approach improves search people across multiple social networks more than FRE. The extensive social connection web in many online social networks is used to enhance user identification and verification via the Friend Relationship Evaluator (FRE) system. Our process uses advanced machine learning and data fusion to handle a wide variety of natural ventilation phenomena from different sensors and platform formats. We evaluate attribute-based matching, graph approaches, and behavior analytics for accuracy, scalability, and computing cost. This study advances user identification systems across digital platforms and helps service providers and end-users establish more sophisticated online identity management strategies.

关键词： Couplings Accuracy Social networking (online) Scalability Sensor phenomena and characterization Sensor fusion Ventilation User experience Protection Standards

来源：评论

学校读者我要写书评

暂无评论

Multi-Tier Kernel for Disease Prediction using Texture Analysis with MR Images

Multi-Tier Kernel for Disease Prediction using Texture Analy...

引用

2022 International Conference on Edge Computing and applications, ICECAA 2022

作者： Mohan, M. Anuradhapatil Mohana, S. Subhashini, P. Kushwaha, Sumit Pandian, S. Manikandaprabu Department of Computer Science and Engineering SRM University Delhi-NCR Haryana Sonepat131029 India Department of Electronics and Communication Engineering Faculty of Engineering and Technology Exclusive for Women Sharnbasva University Karnataka585105 India Department of Computer Science and Engineering Saranathan College of Engineering Tamil Nadu Panjappur620012 India Department of Information Technology Vel Tech Multi Tech Dr.Rangarajan Dr.Sakunthala Engineering College Tamil Nadu Chennai600062 India Department of Computer Applications University Institute of Computing Chandigarh University Punjab Gharuan140413 India Department of Mechanical Engineering Sona College of Technology Tamil Nadu Salem636005 India

ISBN: (数字)9781665482325

ISBN: (纸本)9781665482325

Denoising magnetic resonance images are traditionally done individually, introducing undesired artefacts like blurring. To solve this issue, this paper offers a unique adaptive interpolation architecture that simultaneously allows for image data augmentation, noise removal, and detail augmentation. The multi-tier kernel (MTK) algorithm adjusts the extrapolation weights based on mathematical features in magnetic resonance (MR) data. The MTK weight matrix is then adaptively sharpened, and a Rician bias corrective is used to reduce Rician noise and improve small details. After processing, the noise eliminates the bias produced by the asymmetric sources. The adaptive MTK, in this way, extends the zero ordering estimating methodology to higher regression power facilitating edge maintenance and detail restoration. Investigation outcomes using genuine and MR images (with/without noise) evidenced that the algorithm delivered good restoration outcomes than conventional deep-learning-based approaches but with fewer requirements and calculation burden. © 2022 IEEE.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Experimental Analysis of an Efficient Dental Carries Prediction System Based on Improved Convolutional Neural Network (iCNN) Principle

Experimental Analysis of an Efficient Dental Carries Predict...

引用

Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： Ranjith S Vanitha Lakshmi M Sujatha V Suresh Govindasamy Pallavi Giri Khaled Al-Qawasmi Department of ECE Jeppiaar Engineering College Chennai Department of ECE. SOE Presidency University Bengaluru Department of Master of Computer Applications S.A. Engineering College Chennai Department of Electrical and Electronics Engineering Sona College of Technology Salem Department of Civil engineering Laxminarayan Innovation Technological University Nagpur India Department of Cyber Security Faculty of Information Technology Zarqa University Zarqa Jordan University of Business and Technology Jeddah Saudi Arabia

ISBN: (数字)9798331543624

ISBN: (纸本)9798331543631

Dental caries is a kind of infectious illness that weakens the structure of teeth, leading to cavities. Because of the discomfort and expense of treatment, studies on dental caries have focused on early diagnosis, as it is one of the most common oral health problems. Due to the high costs and lengthy research times associated with oral healthcare, artificial intelligence has recently been employed to create models that can forecast the likelihood of dental caries. The agony and expensive price of therapy have prompted this investigation toward early detection. Models that may forecast the possibility of dental caries have recently been developed using artificial intelligence. This is in response to the high expenditures and significant time commitments connected with medical research in oral healthcare. In this study, a new method for efficiently identifying dental caries is presented using an Improved Convolutional Neural Network (iCNN). To test how well the suggested scheme works, it is cross-validated with the standard method called Support Vector Machine (SVM). This paper's suggested method, iCNN, demonstrates that dental practitioners may greatly benefit from deep learning to aid in the early diagnosis and treatment of dental caries.

关键词： Support vector machines Deep learning Neural networks Teeth Predictive models Dentistry Convolutional neural networks Artificial intelligence Standards Diseases

来源：评论

学校读者我要写书评

暂无评论

Human-computer Interaction and Computational Intelligence: Machine Learning Approaches

Human-Computer Interaction and Computational Intelligence: M...

引用

Sustainable Computing and Integrated Communication in Changing Landscape of AI (ICSCAI), International Conference on

作者： Er. Shashank Shekhar Tiwari Tanusha Mittal Mohammed I. Habelalmateen Madhu P Nimmalaharathi Saloni Bansal Rohit Kaushik Department of Information Technology REC Ambedkar Nagar U.P Dr. Abdul Kalam Technical University Lucknow Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun Department of computers Techniques engineering College of technical engineering The Islamic university Najaf Iraq Department of Information Science and Engineering Malnad College of Engineering Hassan Karnataka Department of EIE (School of Engineering) Sree Vidyanikethan Engineering College AP Department of Computer Engineering and Applications GLA University Mathura Faculty of Management SRM Institute of Science and Technology NCR Campus

ISBN: (数字)9798350355338

ISBN: (纸本)9798350355345

Machine learning is a field that was established some years ago with the lofty goal of building computational methods to implement various aspects of teaching, Machine Learning (ML) has changed materials science fields that have been able to generate large sufficient datasets to use appropriate statistical methods, yet databases for many important types of materials remain intact. Machine learning is an emerging technology that has attracted the attention of academics and business leaders, and it is expected to develop in the near term. Wireless nodes are anticipated to have ubiquitous connectivity due to machine learning methods. IML (Interactive Machine Learning) strives to augment subjective experience and intellect by closely combining these abilities with machine computing speed and power. This paper provides a full study and characterization of Interactive Machine Learning from the standpoint of interaction design. We present and explain a functional and structural model of a generalized IML system, as well as solution concepts for developing successful IML interactions.

关键词： Wireless communication Human computer interaction Materials science and technology computer aided instruction Statistical analysis Databases Computational modeling Machine learning Computational intelligence Business

来源：评论

学校读者我要写书评

暂无评论

A Solution to Sensor Node Localization Using Glow-Worm Swarm Optimization Hybridizing Positioning Model 16th

A Solution to Sensor Node Localization Using Glow-Worm Swarm...

引用

作者： Nguyen, Trong-The Yu, Jie Nguyen, Thi-Thanh-Tan Dao, Thi-Kien Ngo, Truong-Giang Fujian Provincial Key Lab of Big-Data-Mining and Applications Fujian University of Technology Fujian350118 China College of Mechanical and Automotive Engineering Fujian University of Technology Fuzhou350118 China Information Technology Faculty Electric Power University Hanoi Viet Nam Faculty of Computer Science and Engineering Thuyloi-University 175 Tay Son Dong-Da Hanoi Viet Nam University of Management and Technology Haiphong180000 Viet Nam

ISBN: (纸本)9789813367562

The sensor node localization is related to the NP-hard problem due to the complicated determination of the actual coordinate of the sensor node. The metaheuristic algorithms considered as computational intelligence approach is one of the most affected ways to assist in obtaining an optimal solution to the given NP-hard problem. This study presents a new localization solution in wireless sensor networks (WSN) by using glowworms swarm optimization (GSO) combined localizing model. The objective function is calculated mathematically based on three dimension (3D) of the localizing model and Pareto distances. The glowworms groups are created by dividing from the GSO population for their updating positions to enhance swarms for improving localization accuracy. The simulation compared results of the computational algorithm suggest that the proposed task using GSO produces better performance in terms of mean localization error computational cost and the number of localized nodes than the competitors. The proposed scheme also reduced the line of sight problem for sensor nodes with efficient use of network resources. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

A Power Balance Control Strategy of Wireless Sensor Network with Collaborating Heuristic 16th

A Power Balance Control Strategy of Wireless Sensor Network ...

引用

作者： Yu, Jie Dao, Thi-Kien Ngo, Truong-Giang Nguyen, Trong-The College of Mechanical and Automotive Engineering Fujian University of Technology Fuzhou350118 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China Faculty of Computer Science and Engineering Thuyloi University 175 Tay Son Dong Da Hanoi Viet Nam Department of Information Technology Haiphong University of Management and Technology Haiphong18000 Viet Nam

ISBN: (纸本)9789813367562

In order to effort a strong enough signal, nodes in wireless sensor networks (WSN) have to increase their transmission power that continues to maintain the transmission power. However, a vicious circle is iterated that causes a decline in the overall network performance, low utility, and network life cycle shorten. This paper presents a solution to the power balance control strategy for WSN with collaborating heuristic. A distance between the weight factors and obtained nodes interference value is used to establish a useful interference model for enhancing the signal-to-interference-noise ratio (SINR). The utility function of the nodes residual energy and transmission rate is modeled by apply heuristic strategy. The optimal transmission power is obtained after several iterations of the heuristic algorithm. Simulation results show that the proposed approach can prolong the network life cycle and achieve higher network utility. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021.

关键词： Heuristic algorithms

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：