检索结果-内蒙古大学图书馆

2023 International Conference on Power Energy, Environment and Intelligent Control, PEEIC 2023

作者： Narmadha, T. Shree, Ritu Alam, Intekhab Computer Science Engineering Department Bangalore India Vivekananda Global University Department of Computer Science & Application Jaipur India Maharishi University of Information Technology Engineering Department Uttar Pradesh India

ISBN: (纸本)9798350357769

This research presents the mechanical implementation and management of freely available modules for the construction of smart conversions systems. Converts that are scattered or unsophisticated are not clever converts. To transmit the maximum power, they have stabilizers that have comparable impedance online. In current energy environments, intelligent adaptations provide fascinating solutions;in fact, their uses have become more and more varied. The suggested method was developed and tested in a laboratory environment using both real photovoltaic units and a solar cell simulator. Innovative conversions are shown in research, and enhanced intelligent capabilities allow for on-the-fly configuration adjustments, real-time diagnostics, and the management of the system's programs. Furthermore, the project's capabilities allows for a wide range of combinations and groups of various energy sources, generators, and modulation techniques. To the best of our knowledge, this project remains the sole platform for smart conversions that is available for free and is currently being utilized by research, industry, and government. © 2023 IEEE.

关键词： Cloud-Connected Smart Converters DC/AC Transformer Electrical Architectural Experimental Results FPGA technology Maximum Power Point Tracking MPPT Techniques Power Shield Design and Efficiency Analysis Renewable Energy Techniques Smart Conversion Devices Wi-Fi Networking Module

来源：评论

学校读者我要写书评

暂无评论

Applying Transfer Learning to Medical Image Classification Tasks 5th

Applying Transfer Learning to Medical Image Classification T...

引用

5th International Conference on Data Science, Machine Learning and applications, ICDSMLA 2023

作者： Gupta, Manali Haripriya, V. Singh, Akhilendra Pratap Yadav, Surendra Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India Karnataka Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Department of Computer Science & Application Vivekananda Global University Jaipur India

ISBN: (纸本)9789819780426

Transfer studying is a machine learning approach that permits a model to leverage know-how from a previous challenge to boost studying in the following tasks. It's been used increasingly in medical photo classification obligations, allowing area-particular knowledge to be leveraged from current fashions. This method can enhance the overall performance of clinical photograph-type structures and reduce the amount of labeled information required to analyze a brand-new venture. In this paper, we assess the present-day kingdom of switches, getting to know the scientific photo category and the results for clinical picture evaluation. We discuss present switch studying techniques and their influences on the accuracy of medical photo category responsibilities and the challenges related to constructing generalizable fashions. Eventually, we take a look at existing datasets and implementations available for the clinical photo category and factor into promising destiny studies guidelines. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Shop Scheduling Using Space-Cooperation Multi-Objective Optimization

IEEE Transactions on Sustainable Computing

引用

IEEE Transactions on Sustainable Computing 2025年第3期10卷 601-615页

作者： Ding, Jiepin Xia, Jun Yang, Yaning Zhou, Junlong Chen, Mingsong Li, Keqin East China Normal University MoE Engineering Research Center of Software/Hardware Co-Design Technology and Application Shanghai200062 China Ningxia Normal University School of Physics and Electronic Information Engineering Guyuan756500 China Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China State University of New York Department of Computer Science New PaltzNY12561 United States

Since Industry 5.0 emphasizes that manufacturing enterprises should raise awareness of social contribution to achieve sustainable development, more and more meta-heuristic algorithms are investigated to save energy in manufacturing systems. Although non-dominated sorting-based meta-heuristics have been recognized as promising multi-objective optimization methods for solving the energy-efficient flexible job shop scheduling problem (EFJSP), it is hard to guarantee the quality of the Pareto front (e.g., total energy consumption, makespan) due to the lack of population diversity. This is mainly because an improper individual comparison inevitably reduces population diversity, thus limiting exploration and exploitation abilities during population updates. To achieve efficient population evolution, this paper introduces a novel space-cooperation multi-objective optimization (SCMO) method that can effectively solve EFJSP to obtain scheduling schemes with better trade-offs. By cooperatively evaluating the similarity among individuals in both the decision space and objective space, we propose a space-cooperation population update method based on a three-vector representation that can accurately eliminate repetitive individuals to derive higher-quality Pareto solutions. To further improve search efficiency, we propose a difference-driven local search, which selectively changes the positions of operations with higher differences to search for neighbors effectively. Based on the Taguchi method, we conduct experiments to obtain a suitable parameter combination of SCMO. Comprehensive experimental results show that, compared to state-of-the-art methods, our SCMO method achieves the highest HV and NR and the lowest IGD, with an average of 0.990, 0.952, and 0.001, respectively. Meanwhile, compared to traditional local search approaches, our difference-driven local search obtains twice the HV on instance Mk12 and reduces the solving time from 1521 s to 475 s. © 2016 IEEE.

关键词： Job shop scheduling

来源：评论

学校读者我要写书评

暂无评论

Identifying Neuronal Damage and Plasticity by Analyzing Changes in Diffusion Tensor Imaging 5th

Identifying Neuronal Damage and Plasticity by Analyzing Chan...

引用

5th International Conference on Data Science, Machine Learning and applications, ICDSMLA 2023

作者： Chandra, Subhash Rengarajan, A. Sahoo, Girija Shankar Sharma, Sunil Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India Karnataka Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Department of Computer Science & Application Vivekananda Global University Jaipur India

ISBN: (纸本)9789819780426

This paper presents a unique method, which investigates the neuronal damage and plasticity, the use of changes in diffusion tensor imaging (DTI). Thru combining the information from DTI, collectively with cognitive and demographic records, this method identifies and assesses the adjustments inside the brain's white count number integrity. The findings suggest that the proposed approach is capable of signify the structural modifications in the white be counted, whilst additionally offering significant data about the diploma of neuronal harm and plasticity. This research consequently gives a significant device for in addition investigation into the diagnosis of certain neurological illnesses, especially in stroke and traumatic brain injury, wherein identifying modifications within the mind is critical for proper direction of remedy. In addition, the challenges related to the DTI statistics analysis is discussed, collectively with capability applications and future extensions. This paper presents a complete survey of ways Diffusion Tensor Imaging (DTI) may be applied to become aware of neural harm and plasticity. It explains how DTI can discover microstructural modifications in frightened tissue, making it a promising device for Neuro-imaging research. The paper compares the maximum popular indices used in analysis and model fitting the use of DTI to measure modifications, including fractional anisotropy and imply diffusivity. Subsequently, the paper examines destiny guidelines and potential packages of DTI within the clinical setting. In the end, the paper shows that DTI gives a valuable supply of perception into the neural machine, allowing researchers to discover, quantify, and better apprehend structural modifications to neurons. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Diffusion tensor imaging

来源：评论

学校读者我要写书评

暂无评论

Joint Graph Convolutional Network and Convolutional Neural Network for Recommendation 3

Joint Graph Convolutional Network and Convolutional Neural N...

引用

3rd International Conference on Frontiers of Electronics, information and Computation Technologies, ICFEICT 2023

作者： Wang, Hui Ding, Di Li, Zhiwen Li, Shengchang Zeng, Shuai Huaxin Consulting Design Research Institute Group Customer Department Hangzhou China China Ordnance Industry Computer Application Technology Institute Internet and Information Technology Department Beijing China

ISBN: (纸本)9798350302356

The recommendation algorithms based on graph convolutional network can extract the association relationship between users and items by interaction data, but most of these algorithms ignore the general preferences in the review data of users and items. The recommendation algorithms based on convolutional neural network with review can learn user behaviors and item properties. In order to combine the advantages of two kinds of algorithm and make use of both review text data and user-item interaction data fully, we proposed a new model called Joint Graph Convolutional Network and Convolutional Neural Network for Recommendation (JGCR) in this paper. This model used the graph convolutional network to extract association relations, and used convolutional neural network to extract the general preferences from review text, and carried out feature fusion to improve the recommendation effect. This paper conducted comparative experiments on four datasets of amazon dataset to verify the effectiveness of the proposed model. The evaluation metric is mean square error. Experiments results demonstrate that JGCR significantly outperforms all baseline recommendation algorithms. The feature from jointing graph convolutional network and convolutional neural network can improve the recommendation effect. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Social Recommendation Algorithm Based on Fusion Graph Convolutional Neural Network and Gated Recurrent Unit Network 4

Social Recommendation Algorithm Based on Fusion Graph Convol...

引用

4th International Conference on computer, Big Data and Artificial Intelligence, ICCBD+AI 2023

作者： Ding, Di Wang, Hui Li, Zhiwen Huaxin Consulting Design & Research Institute Group Customer Department Hangzhou China China Ordnance Industry Computer Application Technology Institute Internet and Information Technology Department Beijing China

ISBN: (纸本)9798350373233

This paper proposes a fusion model named FGCN-GRU (Fusion Graph Convolutional Neural network and Gated Recurrent Unit network) to predict users' ratings on items. Firstly, FGCN-GRU constructs a new graph convolutional neural network by regarding users' ratings on items as relative ratings and introduces the GRU network by considering the fact that the user's interest in items will change over time. Then the improved graph convolutional neural network, GRU network and users' social network are used to model users, items, and social relations respectively. The experimental results on the datasets of Ciao and Epinions show that the recommendation performance of the proposed model is better. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Examining the Advantages of Dynamic Communications Software Design in Networks 5th

Examining the Advantages of Dynamic Communications Software ...

引用

5th International Conference on Data Science, Machine Learning and applications, ICDSMLA 2023

作者： Raghavendra, R. Das, Neeraj Inzimam Kurmi, Raviraj Singh Karnataka Bangalore India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Department of Computer Science and Application Vivekananda Global University Jaipur India Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India

ISBN: (纸本)9789819780426

This paper examines the blessings of dynamic communications software program design in networks. By leveraging advances in generation, dynamic communications provide an ever-evolving method of connecting, communicating, and sharing facts inside networks without relying on static, often outdated, hardware. The principle blessings related to this community layout are scalability, flexibility, and excellent reliability. As networks extend, dynamic communications software can auto-regulate accordingly to ensure the overall capability of the general gadget. Moreover, users can count on operational performance upgrades and extended capability to address protection and privacy worries. Moreover, using dynamic software allows for more green aid usage, which facilitates lessening expenses related to the control and operation of the network. Moreover, dynamic communications have also helped reduce downtime and sell extra resilience in the face of surprising changes or unanticipated threats. Standard, this paper provides an in-depth knowledge of the advantages of dynamic communications software layout in networks. Dynamic Communications software program design and its various benefits in networking have been gaining substantial attention in recent years. Dynamic Communications software program layout additionally allows protocols to be modified on an as-needed foundation. That is useful for networks that might be constantly changing and want to adapt, which will take care of the converting environment. New protocols may be introduced or eliminated as wished, and the gadget will adjust to make the most efficient performance. In addition, using Dynamic Communications software design allows for a more straightforward integration of different systems. It is useful for networks that require a couple of systems to work together in order for them to function well. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Delay-Beat Differential Phase Demodulation for Laser Phase Noise Immunity in Phase-Sensitive OTDR

Delay-Beat Differential Phase Demodulation for Laser Phase N...

引用

2023 Asia Communications and Photonics Conference/2023 International Photonics and Optoelectronics Meetings, ACP/POEM 2023

作者： Qian, Heng Li, Chuan Li, Chengli Kunming University of Science and Technology Yunnan Key Laboratory of Computer Technologies Application Faculty of Information Engineering and Automation Kunming China School of Physics and Electronic Information Yunnan Normal University Yunnan Key Laboratory of Opo-electronic Information Technology Kunming China

ISBN: (纸本)9798350312614

A phase demodulation method immune to laser phase noise based on time-delay beat-frequency coherent Φ-OTDR is proposed. In this method, the two Rayleigh backscattered light beams with time delay are beat with local light beams respectively, and the phase difference of the two beat signals is used instead of the traditional distance-difference phase to obtain the local disturbance information. In this way, the impact of laser phase noise introduce by the distance-difference phase is avoid, and the constraint of laser linewidth on phase demodulation performance is weakened. In the experiment, a demodulation accuracy of -63.5dB rad2/Hz is achieved under the condition of a laser with a linewidth of 100kHz, which is improve by 11dB compared to traditional phase demodulation method. © 2023 IEEE.

关键词： distributed optical fiber sensing laser phase noise phase demodulation phase-sensitive optical time-domain reflectometry

来源：评论

学校读者我要写书评

暂无评论

An alert-situation text data augmentation method based on MLM

引用

High technology Letters 2024年第4期30卷 389-396页

作者： DING Weijie MAO Tingyun CHEN Lili ZHOU Mingwei YUAN Ying HU Wentao Department of Computer and Information Security Zhejiang Police CollegeHangzhou 310053P.R.China Key Laboratory of Public Security Information Application Based on Big-Data Architecture Ministry of Public SecurityHangzhou 310053P.R.China Zhejiang Dahua Technology Co. LtdHangzhou 310053P.R.China

The performance of deep learning models is heavily reliant on the quality and quantity of train-ing *** training data will lead to ***,in the task of alert-situation text classification,it is usually difficult to obtain a large amount of training *** paper proposes a text data augmentation method based on masked language model(MLM),aiming to enhance the generalization capability of deep learning models by expanding the training *** method em-ploys a Mask strategy to randomly conceal words in the text,effectively leveraging contextual infor-mation to predict and replace masked words based on MLM,thereby generating new training *** Mask strategies of character level,word level and N-gram are designed,and the performance of each Mask strategy under different Mask ratios is analyzed and *** experimental results show that the performance of the word-level Mask strategy is better than the traditional data augmen-tation method.

关键词： deep learning text data augmentation masked language model(MLM) alert-sit-uation text classification

来源：评论

学校读者我要写书评

暂无评论

Leveraging Machine Learning to Optimize Real-Time Data Analysis Performance 5th

Leveraging Machine Learning to Optimize Real-Time Data Analy...

引用

5th International Conference on Data Science, Machine Learning and applications, ICDSMLA 2023

作者： Singh, Vaishali Kaushik, Harshita Verma, Archana Raghavendra, R. Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Department of Computer Science and Application Vivekananda Global University Jaipur India Noida Institute of Engineering and Technology Uttar Pradesh Greater Noida India Karnataka Bangalore India

ISBN: (纸本)9789819780426

Leveraging system mastering (ML) algorithms has become an increasingly exciting technique for optimizing actual-time facts analysis performance. In the ever-growing age of massive facts, ML permits us to effectively make the experience of this information extra quickly and correctly. Traditionally, real-time statistics analysis requires complex guide evaluation or is constrained by the insufficient skills of conventional rule-based total strategies. ML can automate this method and identify patterns in the records that may not be apparent at once, even optimizing performance significantly. In addition, ML algorithms, including supervised and unsupervised methods, can be applied to label facts because it comes in, making it simpler to identify styles inside the statistics before a manual evaluation. This technique is called predictive analytics, and it dramatically reduces the time spent manually exploring the statistics. Usually, leveraging system learning to optimize the performance of actual-time records evaluation can improve the process of creating a sense of these facts. Through that specialization in predictive analytics and utilizing supervised and unsupervised techniques, we will quickly and appropriately analyze the statistics and make powerful selections. It can be pretty helpful in a selection of industries and conditions. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Predictive analytics

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：