检索结果-内蒙古大学图书馆

32nd International Conference on Organization and technology of Maintenance, OTO 2023

作者： Kljajić, Ružica Kraus, Zorislav Fekete, Krešimir Marić, Predrag Faculty of Electrical Engineering Computer Science and Information Technology Osijek University of Osijek Kneza Trpimira 2b Osijek31000 Croatia

ISBN: (纸本)9783031514937

Small industrial utilities, connected to the distribution grid, can cause various disturbances that need to be eliminated or mitigated. Due to the complexity of the system and the large number of motors, industrial consumers may have problems with the voltage deviations caused by the excessive amount of reactive energy which is a natural consequence of their operation and construction. Since industrial consumers have to pay for both active and reactive power delivered from the grid, the goal is to reduce those costs as well as to reduce feeder loadings. Delivered energy can be reduced by installing compensation devices or by connecting photovoltaic power plant, which would produce active and reactive energy at the point of consumption. This paper analyzes the power flows and voltage conditions of a small industrial facility in three scenarios: the basic scenario, the second scenario with built-in compensation devices and in the third scenario with integrated photovoltaic power plant. For all three scenarios, power flow analysis is performed and results are presented in the form of tables and graphically. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

A Progress Prediction Model Using Res-zLSTM for LOCA in Nuclear Power Plants

A Progress Prediction Model Using Res-zLSTM for LOCA in Nucl...

引用

2024 International Conference on Electrical Power Systems and Intelligent Control, EPSIC 2024

作者： Liu, Liang She, Jingke Shu, Lingyu Zhao, Yizhong College of Computer Science & Electronic Engineering Hunan University Changsha China Hunan 6906 Information Technology Co. Ltd Yueyang China

ISBN: (纸本)9798350366075

Predicting the changes in various operation conditions following a loss of coolant accident (LOCA) in a nuclear power plant is of great significance. To enhance the accuracy of prediction, this paper proposes a novel prediction model called Res-zLSTM. The Res-zLSTM model incorporates residual structure and attention mechanisms to effectively mitigate the gradient vanishing problem in traditional Long Short-Term Memory (LSTM) models. Additionally, it maintains a low network complexity while simultaneously strengthening its ability to learn from long-term sequence data. This allows for accurate predictions of key parameter trends in LOCA conditions. In validation experiments, the Res-zLSTM model was used to predict multiple important operational parameters under different LOCA conditions. The experimental results demonstrate that the Res-zLSTM model exhibits superior prediction accuracy, achieving a maximum improvement of 54% compared to the zLSTM model. While the prediction accuracy of the Res-zLSTM model may be influenced by the changing rate of operation data, its outstanding performance in predicting LOCA conditions provides a novel approach for predicting operation conditions in complex systems. ©2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Classification of Unbalanced Data Based on Bayesian Optimal Neural Network Model

Journal of Network Intelligence

引用

Journal of Network Intelligence 2024年第3期9卷 1427-1440页

作者： Ye, Li-Zhu Alkawaz, Mohammed Hazim Johar, Md Gapar Md School of Information Technology and Engineering Guangzhou College of Commerce Guangzhou511363 China School of Graduate Studies Management and Science University 40100 Shah Alam Selangor Malaysia Department of Computer Science College of Education for Pure Science University of Mosul Mosul41002 Iraq Software Engineering and Digital Innovation Center Management and Science University Shah Alam40100 Malaysia

Aiming at the unbalanced problem of big data classification, this paper proposes a classification method of unbalanced data on the ground of Bayesian optimal neural network model. The method firstly uses Optimized Graph Convolutional Network (OGCN) network to carry out message passing mechanism in data graph, designs neural network model with self-attention pooling and mean maximization pooling, and then uses Bayes optimization to update the posterior probability of optimization function by constantly updating the probability model and evaluating the objective function. Effectively solve the problem of speed and optimal solution of hyperparameter optimization in the neural network model. Secondly, the model is used for data set training to obtain the weight of the entire network. Secondly, the unbalanced data is mixed sampling to reduce the number of negative samples. Finally, the capability of the model was verified on the CiteSeer dataset. Experimental results showed that the accuracy rate, accuracy rate and recall rate of the proposed algorithm were 0.974, 0.982 and 0.973, respectively, which effectively improved the accuracy rate, accuracy rate and recall rate of unbalanced data classification compared with other algorithms. © 2024, Taiwan Ubiquitous information CO LTD. All rights reserved.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Motor Imagery Features Selection with Grey Wolf Optimization for Brain computer Interface

Motor Imagery Features Selection with Grey Wolf Optimization...

引用

2024 International Conference on Computational Intelligence and Computing Applications, ICCICA 2024

作者： Pawan Dhiman, Rohtash Saini, Jasbir Singh Saxena, Ankur Sharma, Vikas Meerut Institute Of Engineering Technology Department Of Computer Science And Engineering Uttar Pradesh Meerut India Deenbandhu Chhotu Ram University Of Science And Technology Department Of Electrical Engineering Haryana Murthal India Panipat Institute Of Engineering And Technology Panipat Institute Of Engineering And Technology Haryana Samalkha India Delhi Technological University Department Of Information Technology Delhi India

ISBN: (纸本)9798350306446

Feature selection is a significant process in brain-computer interfaces (BCIs) that has the potential to significantly enhance system performance, especially if a large number of features are present. Feature selection can help decrease noisy data, overtraining effects, storage needs, and computational complexity thereby enhancing classifier performance. The various feature selection strategies have been reported to attain these objectives. In this work, a hybrid feature selection technique is suggested. It uses a wavelet packet decomposition technique to extract features and grey wolf optimization (GWO) technique to obtain the best subset of features. It is then evaluated with support vector machine (SVM) classifier and obtains maximum classification accuracy of 82.88% for the approximate entropy feature. Experimental findings reveal that the suggested approach outperforms the contemporary MI-BCI systems even with relatively small training data sets. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Non-Markovian Memory-Based Model for Sequence Prediction 14

Non-Markovian Memory-Based Model for Sequence Prediction

引用

14th IEEE International Conference on Electronics information and Emergency Communication, ICEIEC 2024

作者： Khoshimov, Temur Yang, Guisong School of Optoelectronic Information and Computer Engineering University of Shanghai for Science and Technology No. 516 Jungong Road Yangpu District Shanghai200093 China

ISBN: (纸本)9798350361889

Recognizing the non-Markovian nature of natural language and visual information, we introduce a Non-Markovian Memory-Based Model (NMM) that adjusts dynamically to the training data sequence. This novel approach uses memory-augmented networks and non-Markovian learning to capture complex dependencies in sequential data such as text and images. Our model features a memory module for storing and retrieving past input information and a learning mechanism for long-term dependencies, dynamically updating with new embedding and positional memory vectors as new tokens appear. Our extensive experiments show that using memory vectors based on token position significantly improves learning effectiveness over traditional DNN models. The NMM's performance, demonstrated across various datasets, highlights its superior accuracy and adaptability in tasks such as token prediction and image recognition, marking a significant advancement in machine learning research. © 2024 IEEE.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Integrating Cloud-based Data Mining Algorithms for Smart City Infrastructure Management and Decision Support Systems 4

Integrating Cloud-based Data Mining Algorithms for Smart Cit...

引用

4th International Conference on Soft Computing for Security Applications, ICSCSA 2024

作者： Guru Vimal Kumar, M. Jude Moses Anto Devakanth, J. Selvapandian, D. Venkatesan, R. Revathi, J. Aruna, R. Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineering Chennai India Madanapalle Institute of Technology & Science Department of Computer Applications Chittoor India Academy of Higher Education Department of Computer Science and Engineering Coimbatore India Bannari Amman Institute of Technology Department of Information Technology Erode India Kongu Engineering College Department of Mathematics Erode India Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology School of Computing Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331515720

This study explores cloud-based data mining algorithm integration in elevating smart city infrastructure management and decision support systems. Specifically, the authors focus on optimizing traffic management through the analysis of real-Time traffic sensor data. Timestamped history records of vehicle count, traffic speed, density, weather condition, accidents, and traffic signals were utilized. Machine learning models such as Support Vector Machine, K-Nearest Neighbors, Decision Trees, and Random Forest were trained and tested. The analysis indicated SVM to be the most effective instrument, resulting in an accuracy of 98.98%. The model was also instrumental in reducing vehicle count by 16.7%, traffic density by 25%, and traffic speed was increased by 50%. KNN's overall accuracy experience was 94.5%, and the model was shown to be highly optimized for various forever traffic conditions. However, the overall impact on traffic speed and density was not as significant compared to the previously-discussed model. DT and RF demonstrated respective accuracies of 92.3% and 91.2%, offering varying levels of decision interpretation and ensemble learning opportunities. As a result, the study indicates that machine learning can play a critical role in improving urban traffic management via traffic congestion prediction and minimization, resulting in improved traffic flow, overall trip time reduction, and general urban mobility management. T. © 2024 IEEE.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

L1Norm Minimization in ISAR Imaging 23

L1Norm Minimization in ISAR Imaging

引用

23rd International Symposium on Electrical Apparatus and Technologies, SIELA 2024

作者： Lazarov, Andon Minchev, Dimitar Nikola Vaptzarov Naval Academy Information Technology Department Varna Bulgaria Burgas Free University Computer Science and Engineering Faculty Burgas Bulgaria

ISBN: (纸本)9798350382365

This work deals with an ISAR (Inverse Synthetic Aperture Radar) image enhancement algorithm using target's sparse image and image's l1 norm minimization. As calculation of l1 norm of two-dimensional (2D) image matrix is too complicated, target's image matrix is resized to one-dimensional (1D) one. According to ISAR theory, the ISAR signal matrix is a Fourier transform of the target's image matrix. Thus, the ISAR signal is obtained one dimensional one while modelling by Fourier transform of a certain target's image column matrix. In the image reconstruction algorithm, 12 norm constrained function and l12 objective function are defined. Simulation experimental results prove functionality of the developed algorithm. © 2024 IEEE.

关键词： Radar imaging

来源：评论

学校读者我要写书评

暂无评论

Image Encryption Using Chaotic Logistic and DNA Encoding 5

Image Encryption Using Chaotic Logistic and DNA Encoding

引用

5th International Conference on Data Intelligence and Cognitive Informatics, ICDICI 2024

作者： Kumar, G. Kiran Anila, M. Chandrika, C. Priyanka, M. Jayaram, D. Mohan, A. Chaitanya Bharathi Institute of Technology Department of Computer Science and Engineering Gandipet Telangana Hyderabad India Chaitanya Bharathi Institute of Technology Department of Information Technology Gandipet Telangana Hyderabad India

ISBN: (纸本)9798350389609

With a rapid development in technology and digital communication, there is a need of high speed with strong secured systems. In every sector, data is communicated in various formats, among them, images are one. It is crucial to protect the image data from unauthorized access from various sources like email spoofing and spamming, malicious software, unknown access through network, cloud, storage and other related activities. Therefore, securing our image from such unauthorized access is very important. Encryption is one method of achieving high security by shielding our data from unauthorized users. It is more difficult for attackers to decipher an image when Chaotic Logistic and DNA Encoding are used for image encryption. Using this encryption technique, each image that needs to be sent is split into parts, each of which is then encrypted and sent to the recipient. Consequently, an individual possessing only one or two portions of the image will be unable to utilize it. As a result, the goal of this strategy is to achieve high security and data confidentiality. In this research, Chaotic Logistic and DNA Encoding method is used to provide security for image data that outperformed when compared to other methods. © 2024 IEEE.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Sign to Speak: Real-time Recognition for Enhance Communication 3

Sign to Speak: Real-time Recognition for Enhance Communicati...

引用

3rd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2024

作者： Baghavathi Priya, S. Rao, P V R Subba Madeswaran, TamilSelvi Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Chennai India University of Technology and Applied Sciences Department of Information Technology Nizwa Oman

ISBN: (纸本)9798350375190

Recent developments in the area of research on sign language recognition have led to making use of deep learning techniques with the goal to assist the self-learning transition of sign language from one language to another. In order to detect and classify characters from photographs in multiple sign languages, a number of deep-learning models, have been deployed. SLR is a prominent area of study and technology that aims to mitigate speaking barriers for individuals who unable to talk and listen. This involves the development of tools capable of understanding and deciphering sign language movements, hence facilitating a wider range of interactions for those who are difficult of listening and speaking. This paper demonstrates a novel model called CNN Inception Net, which is a neural network based on convolution. The use of an Indian sign dataset enables the achievement of a notable performance rate of 98.9%, enabling precise recognition of actions in the language of signs. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Exploring the Development of Flexible Network Subsystems in Communications Software Design 15

Exploring the Development of Flexible Network Subsystems in ...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Mamatha, G.N. Pandeya, Megha Saraswat, Bhawna School of Engineering and Technology Department of Electronics and Communication Engineering Karnataka Bangalore India Maharishi University of Information Technology Maharishi School of Engineering & Technology Uttar Pradesh India Sanskriti University Department of Computer Science Engineering Uttar Pradesh Mathura India

ISBN: (纸本)9798350370249

The development of cutting-edge telecommunications systems more and more call for the implementation of community subsystems which might be bendy and can unexpectedly reply to modifications in user visitors. Such flexibility requires the layout of a structure able to scaling to distinctive gadget demands while nevertheless being capable of maintain excessive overall performance, reliability, and availability. This paper gives a systematic exploration of the strategies, gear, and ideas important in designing a bendy community subsystem for telecommunications software. We speak the necessities and challenges of developing network structures, and have a look at the feasibility of employing current trendy protocols which includes SIP, SDP, and RTP as a part of a usual structure. Furthermore, we speak the advantages and downsides of using software program-defined networking (SDN) as a part of a flexible community subsystem, along with issues for deploying it. Updates to present community control structures to assist dynamic reconfiguration are explored, in addition to an assessment of in-house and 1/3-celebration answers for integration into a bendy community subsystem. Sooner or later, key layout issues for deploying and managing a flexible community subsystem are discussed and summarized. © 2024 IEEE.

关键词： Downsides Implementation Necessities Networking Nevertheless Telecommunications

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：