检索结果-内蒙古大学图书馆

Utilization of genetic algorithm in tuning the hyper-parameters of hybrid NN-based side-slip angle estimators

Neural Computing and Applications 2024年第30期36卷 19055-19074页

作者： Essa, Mohamed G. Elias, Catherine M. Shehata, Omar M. Research Group Cairo Egypt Mechatronics Department Faculty of Engineering and Materials Science German University in Cairo Cairo Egypt Computer Science Department Faculty of Media Engineering and Technology German University in Cairo Cairo Egypt Mechatronics Department Faculty of Engineering Ain Shams University Cairo Cairo Egypt

This paper proposes a solution to enhance and compare different neural network (NN)-based side-slip angle estimators. The feed-forward neural networks (FFNNs), recurrent neural networks, long short-term memory units (LSTMs), and gated recurrent units are investigated. However, there is a lack in the selection criteria of the architectures’ hyper-parameters. Therefore, the genetic algorithm is integrated with the NN-based estimators to find the optimal hyper-parameters for the studied architectures. The tuned hyper-parameters in this work include the number of neurons, number of layers, activation function, optimizer type, and learning rate. The objective function of the optimization problem is minimizing the root-mean-square error (RMSE) on multiple testing data. The optimal models are further included in the design of a hybrid NN estimator with Kalman filter. In the hybrid estimators, the optimal NN estimators are used as virtual sensors to correct the prediction of the side-slip angle resulting from the mathematical lateral vehicle model. Eventually, the performance of the best selected model is evaluated in terms of different metrics;mean RMSE, mean error variance, mean training time, and mean estimation time. LSTMs are found to achieve the lowest mean RMSE while being tested on highly generalized data yielding the highest training and estimation time. However, FFNNs achieve the lowest RMSE while being tested on low generalized data and the lowest training and estimation time. Meanwhile, it is observed that the hybrid estimators achieved lower RMSE with great enhancement compared to the non-hybridized ones proving the effectiveness of the proposed approach and increasing the side-slip estimation generalization ability in unknown environments with high uncertainties, which are not covered by the training dataset for the NNs estimators. © The Author(s) 2024.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Multi-Site Aggregate Production Planning Using Particle Swarm Optimization

引用

Journal of engineering, Project, and Production Management 2022年第1期12卷 62-69页

作者： Wibawa, Aji Prasetya Mahmudy, Wayan F. Rizki, Agung Mustika Yuliastuti, Gusti Eka Tama, Ishardita Pambudi Electrical Engineering Department Universitas Negeri Malang Malang Indonesia Computer Science Faculty of Computer Science Brawijaya University Malang Indonesia Industrial Engineering Faculty of Engineering Brawijaya University Malang Indonesia

Aggregate planning is a crucial stage in the production process because it supports other processes. Careless production planning may cause production costs to spike sharply that hurts the company financially. This study explores the novel usage of particle swarm optimization (PSO) to discover a set of solutions among the objective of a multioptimization problem in aggregate production planning. The study uses a small home textile industry with complex production processes of school uniforms as a case study. The results show that the production cost difference between actual data and the proposed method is IDR330,670,000. Thus, PSO can solve the multi-site aggregate planning by reducing the company production cost. Copyright © Journal of engineering, Project, and Production Management (EPPM-Journal).

关键词： Aggregates

来源：评论

学校读者我要写书评

暂无评论

computer Vision and Deep Learning-enabled Weed Detection Model for Precision Agriculture

引用

computer Systems science & engineering 2023年第3期44卷 2759-2774页

作者： R.Punithavathi A.Delphin Carolina Rani K.R.Sughashinir Chinnarao Kurangit M.Nirmala Hasmath Farhana Thariq Ahmed S.P.Balamurugan Department of Information Technology M.Kumarasamy College of EngineeringKarur6391 I3India Department of Computer Science and Engineering K.Ramakrishnan College of TechnologyTiruchirapalli621112India Department of Electronics and Instrumentation Easwani Engineering CollegeTamil Nadu600089India Pondichery University Puducherry605014India Department of computer science and engineering The Oxford college of EngineeringBangalore560068India Department of Computer Science Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesSaveetha UniversityChennai602105India Department of Computer and Information Science Faculty of ScienceAnnamalai University Chidambaram608002India

Presently,precision agriculture processes like plant disease,crop yield prediction,species recognition,weed detection,and irrigation can be accom-plished by the use of computer vision(CV)*** plays a vital role in influencing crop *** wastage and pollution of farmland's natural atmosphere instigated by full coverage chemical herbicide spraying are *** the proper identification of weeds from crops helps to reduce the usage of herbicide and improve productivity,this study presents a novel computer vision and deep learning based weed detection and classification(CVDL-WDC)model for precision *** proposed CVDL-WDC technique intends to prop-erly discriminate the plants as well as *** proposed CVDL-WDC technique involves two processes namely multiscale Faster RCNN based object detection and optimal extreme learning machine(ELM)based weed *** parameters of the ELM model are optimally adjusted by the use of farmland fertility optimization(FFO)algorithm.A comprehensive simulation analysis of the CVDL-WDC technique against benchmark dataset reported the enhanced out-comes over its recent approaches interms of several measures.

关键词： Precision agriculture smart farming weed detection computer vision deep learning

来源：评论

学校读者我要写书评

暂无评论

In Search for Model-Driven eXplainable Artificial Intelligence 1

引用

10th IFIP International Workshop on Artificial Intelligence for Knowledge Management, AI4KMES 2023

作者： Ligęza, Antoni Sepiolo, Dominik Faculty of Electrical Engineering Automatics Computer Science and Biomedical Engineering Department of Applied Computer Science AGH University of Krakow al. Mickiewicza 30 Krakow30-059 Poland

ISBN: (数字)9783031610691

ISBN: (纸本)9783031610684

This paper reports on ongoing and innovative research in the area of eXplainable Artificial Intelligence (XAI). A classical XAI task is considered as finding an explanation of the model generated via Machine Learning by identifying the most influential variables for local decision-making. Such an approach suffers from severe limitations. The proposed approach moves the explanatory process to a new, knowledge-level dimension. It is oriented towards Model Discovery, i.e. the internal structure and functions of the components. The concept of Model-Driven XAI is put forward and explained with examples. An experiment on Function Discovery via Grammatical Evolution is reported in brief. © IFIP International Federation for Information Processing 2024.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Camera Calibration Algorithms for Football Applications 4

Comparative Analysis of Camera Calibration Algorithms for Fo...

引用

4th International Workshop on Information Technologies: Theoretical and Applied Problems, ITTAP 2024

作者： Sorokivskyi, Oleksandr Hotovych, Volodymyr Nazarevych, Oleg Shymchuk, Grygorii Department of Computer Science Faculty of Computer Information Systems and Software Engineering Ternopil Ivan Puluj National Technical University Ternopil Ukraine

In solving the problem of automated analysis of football match video recordings, special video cameras are currently used. This work presents a comparative characterization of known algorithms and methods for video camera calibration, including those utilizing machine learning and neural networks, with the aim of identifying their shortcomings and forming a theoretical foundation for developing modern, more effective methods and algorithms. Specifically, it examines both algorithms that require more input data but operate quickly [1, 2] and more accurate algorithms using machine learning [3, 4, 5, 6, 5]. It is demonstrated that their main drawback is either accuracy or speed. More accurate algorithms using machine learning often do not specify the algorithm's operational speed, which precludes their use in real-time applications. The examined works that emphasize speed frequently lack the accuracy necessary for practical use in real-life scenarios. Copyright © 2024 for this paper by its authors.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

EIMViT: A Model Integrating EEG Microstates and Deep Learning Methods for Depression Recognition 10

EIMViT: A Model Integrating EEG Microstates and Deep Learnin...

引用

10th IEEE Smart World Congress, SWC 2024

作者： Su, Yun Chang, Qi Zhou, Yueyang Zhu, Wenbing An, Kun Huang, Runhe Northwest Normal University College of Computer Science and Engineering Lanzhou China Hosei University Faculty of Computer and Information Sciences Tokyo Japan

ISBN: (纸本)9798331520861

EEG microstates, which are stable electrophysiological states, can reflect the activity levels and connectivity patterns of specific brain regions, and they are considered potential biomarkers for depression. EEG microstates can reveal brain mechanisms, but the classification accuracy of depression recognition studies based on EEG microstates is low. In contrast, deep learning models have high accuracy but fail to reveal brain mechanisms. Therefore, we propose a model combining deep learning methods with EEG microstates, named EEGbased integrating microstates and Vision Transformer Network (EIMViT). This model takes EEG data as input into threedimensional convolutional neural network (3DCNN) module and Vision Transformer (ViT) module to extract local and global spatial features of the EEG data. Subsequently, the extracted spatial features are fused with the microstate temporal parameters to identify depression. The experimental results demonstrate that the EIMViT model achieved a recognition accuracy of 9 6. 5 8 % on the MODMA dataset. Furthermore, statistical analysis of microstate temporal parameter results and ablative experiments confirmed strong correlations between microstate D and depression. The EEG source localization results indicated changes in the activation areas of each microstate in the depression group, potentially reflecting alterations in brain activity patterns among individuals with depression. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Extensive Numerical Analysis of PDF Parameters for Wind Energy in Brazil: A Study Across 27 Cities for 60 Years Wind Speed

引用

IEEE Access 2025年 13卷 84555-84568页

作者： Badawi, Ahmed Souza, Amaury Elzein, I.M. Ali, Hassan Zyoud, Alhareth College of Engineering Technology University of Doha for Science and Technology Qatar Federal University of Mato Grosso do Sul Brazil Birzeit University Faculty of Engineering Department of Electrical and Computer Engineering Birzeit Ramallah Palestine

This research conducts a comprehensive numerical assessment of wind energy potential across Brazil, leveraging six decades of wind speed data collected from 27 cities to analyze Probability Density Function (PDF) parameters and enhance wind resource mapping. The study employs the Weibull distribution, defined by its shape factor k and scale factor c, to represent variations in wind speed. A total of nine numerical practices and methods including the Maximum Likelihood Method (MLM), Method of Moments (MM), Empirical Method (EM), Standard Deviation Method (STDM), Modified Maximum Likelihood Method (MMLM), Second Modified Maximum Likelihood Method (SMMLM), Graphical Method (GM), Least Mean Square Method (LSM), and Energy Pattern Factor Method (EPF) were utilized to achieve optimal parameter estimation. Statistical analysis was performed using various metrics such as the Index of Agreement (IA), Root Mean Square Error (RMSE), Chi-square test (X2), Mean Absolute Percentage Error (MAPE), and Relative Root Mean Square Error (RRMSE). The findings indicated that MLM was the most precise method, followed by STDM, EM, MM, and EPF, while GM and LSM demonstrated lower effectiveness. The analysis determined a scale factor range of 2.17-2.36 m/s and a shape factor of 2.5-2.78, resulting in a bell-shaped Gaussian PDF. The Mean Wind Speed (MWS) was recorded at 2.06 m/s, which, despite being categorized as low, indicates the potential for effective deployment of small-scale wind turbines for energy production. This study offers significant insights for wind energy development in Brazil, presenting a methodological approach for optimizing the placement of wind turbines and minimizing electricity generation costs. © 2013 IEEE.

关键词： Weibull distribution

来源：评论

学校读者我要写书评

暂无评论

Intelligent System for Intrusion Detection Based on Machine Learning 6

Intelligent System for Intrusion Detection Based on Machine ...

引用

6th IEEE Novel Intelligent and Leading Emerging sciences Conference, NILES 2024

作者： Ragab, Mohamed Ibrahim Fouad, Khaled M. School of Information Technology and Computer Science Nile University Giza Egypt New Mansoura University and Nile University Faculty of Computer Science and Engineering Mansoura Egypt

ISBN: (纸本)9798350378511

In today's digital age, security challenges threaten user privacy as networks face increased vulnerability to malicious attacks due to large data volumes. Intrusion Detection Systems (IDS) play a crucial role in identifying cyber-attacks and protecting system resources and users. This study utilizes machine learning classifiers (MLC) to analyze the NSL-KDD dataset, optimizing by preprocessing to remove irrelevant features. System performance is assessed using four attribute subsets, comparing model accuracy across DoS, Probe, U2L, and R2L attack classes to determine the best algorithm for each class. Using Random Forest with 20 features successfully achieved an accuracy of up to 99 % in intrusion detection. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Exploring the Usage of Mobile Phones in the Assessment Process: A Case Study 47

Exploring the Usage of Mobile Phones in the Assessment Proce...

引用

47th ICT and Electronics Convention, MIPRO 2024

作者： Kovačević, Željko Bubnic, Bostjan Kosar, Tomaž Zagreb University Of Applied Sciences Department Of Computer Science And Information Technology Zagreb Croatia University Of Maribor Faculty Of Electrical Engineering And Computer Science Maribor Slovenia

ISBN: (纸本)9798350382495

Technology is changing how students learn in the 21st century significantly. Integrating mobile devices in teaching, learning, and assessment processes has emerged as an important strategy for improving teaching methodologies and students' learning. However, adopting mobile devices presents several challenges, including understanding the students' performance, impact on time, and efficiency in the assessment process. This study explores this area with an empirical study of using mobile devices and compares the results to those using traditional desktop computers. In the educational environment, we investigated students' effective use while interacting with mobile and desktop versions of the Second Introductory programming summative assessment. Multinational/multi-institutional research involved a comparative analysis between two student groups undertaking identical tasks on mobile phones and desktop computers. Our results suggest that the students' results are not affected significantly by using the mobile version of the assessment application. These results highlight the usability of mobile devices as a flexible and effective tool for various educational applications, strengthening their role in the modern learning environment. © 2024 IEEE.

关键词： Object oriented programming

来源：评论

学校读者我要写书评

暂无评论

A Study of Predicting Social Networking Sites(SNS) Media Disorder Survey Data Using a Machine Learning Approach

A Study of Predicting Social Networking Sites(SNS) Media Dis...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Munia, Jerin Akther Tahmiduzzaman, K.B.M. Saad, Izazul Haque Islam, Md Mynul Akash, Abdul Hady Zumma, Md. Thoufiq Daffodil International University Department of Computer Science and Engineering Dhaka Bangladesh University of Technology Sydney Faculty of Engineering and Information Technology Sydney Australia University of Asia Pacific Department of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798331509828

This study uses survey data and machine learning algorithms to forecast social media disorder in people. A total of 600 individuals answered questions on their social media usage patterns, internet habits, demographics, and signs of social media disorder. This dataset was used to train a number of machine learning models, such as Gaussian Naive Bayes (GaussianNB), Random Forest, K-Nearest Neighbors (KNN), Decision Tree, and Support Vector Machine (SVM). According to the findings, the GaussianNB model had the greatest accuracy of 97%, followed by SVM (94%), Random Forest (91%), Decision Tree (92%), and KNN (90%). These results demonstrate how well machine learning can identify those who may be at risk for social media disorder. In order to improve prediction performance, future research will concentrate on increasing feature size, diversifying datasets, and refining models. Furthermore, incorporating these models into user-friendly apps and intervention programs may offer useful resources for the early diagnosis and treatment of social media illness. © 2025 IEEE.

关键词： Adversarial machine learning

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：