检索结果-内蒙古大学图书馆

Dynamics analysis and cryptographic implementation of a fractional-order memristive cellular neural network model

Chinese Physics B 2024年第4期33卷 418-433页

作者：周新卫蒋东华 Jean De Dieu Nkapkop Musheer Ahmad Jules Tagne Fossi Nestor Tsafack 吴建华 Department of Information Engineering Gongqing CollegeNanchang UniversityJiujiang 332020China School of Computer Science and Engineering Sun Yat-Sen UniversityGuangzhou 511400China Department of Electrical Engineering and Industrial Computing University Institute of TechnologyDoualaCameroon Department of Computer Engineering Jamia Millia IslamiaNew Delhi 110025India Department of Physics Faculty of ScienceUniversity of YaoundeCameroon Electrical Engineering Department and Industrial Computing of ISTAMA University of DoualaDoualaCameroon

Due to the fact that a memristor with memory properties is an ideal electronic component for implementation of the artificial neural synaptic function,a brand-new tristable locally active memristor model is first proposed in this ***,a novel four-dimensional fractional-order memristive cellular neural network(FO-MCNN)model with hidden attractors is constructed to enhance the engineering feasibility of the original CNN model and its ***,its hardware circuit implementation and complicated dynamic properties are investigated on multi-simulation ***,it is used toward secure communication application *** it as the pseudo-random number generator(PRNG),a new privacy image security scheme is designed based on the adaptive sampling rate compressive sensing(ASR-CS)***,the simulation analysis and comparative experiments manifest that the proposed data encryption scheme possesses strong immunity against various security attack models and satisfactory compression performance.

关键词： cellular neural network memristor hardware circuit compressive sensing privacy data protection

来源：评论

学校读者我要写书评

暂无评论

EDU-GAN:Edge Enhancement Generative Adversarial Networks with Dual-Domain Discriminators for Inscription Images Denoising

引用

computers, Materials & Continua 2024年第7期80卷 1633-1653页

作者： Yunjing Liu Erhu Zhang Jingjing Wang Guangfeng Lin Jinghong Duan School of Mechanical and Precision Instrument Engineering Xi’an University of TechnologyXi’an710048China Department of Information Science Xi’an University of TechnologyXi’an710054China School of Faculty of Painting Packaging Engineering and Digital MediaXi’an University of TechnologyXi’an710048China School of Computer Science and Engineering Xi’an University of TechnologyXi’an710048China

Recovering high-quality inscription images from unknown and complex inscription noisy images is a challenging research *** fromnatural images,character images pay more attention to stroke ***,existingmodelsmainly consider pixel-level informationwhile ignoring structural information of the character,such as its edge and glyph,resulting in reconstructed images with mottled local structure and character *** solve these problems,we propose a novel generative adversarial network(GAN)framework based on an edge-guided generator and a discriminator constructed by a dual-domain U-Net framework,i.e.,*** existing frameworks,the generator introduces the edge extractionmodule,guiding it into the denoising process through the attention mechanism,which maintains the edge detail of the restored inscription ***,a dual-domain U-Net-based discriminator is proposed to learn the global and local discrepancy between the denoised and the label images in both image and morphological domains,which is helpful to blind denoising *** proposed dual-domain discriminator and generator for adversarial training can reduce local artifacts and keep the denoised character structure *** to the lack of a real-inscription image,we built the real-inscription dataset to provide an effective benchmark for studying inscription image *** experimental results show the superiority of our method both in the synthetic and real-inscription datasets.

关键词： Dual-domain discriminators inscription images denoising edge-guided generator

来源：评论

学校读者我要写书评

暂无评论

Object detection of linear structures on Mars based on YOLO network 5

Object detection of linear structures on Mars based on YOLO ...

引用

5th International Conference on Algorithms, Computing and Artificial Intelligence, ACAI 2022

作者： Xu, Jingkun Liang, Jiarui Yan, Pengcheng Tian, Xiaolin School of Computer Science and Engineering/Faculty of Innovation Engineering Macau University of Science and Technology China

ISBN: (纸本)9781450398343

The geographic feature of terrestrial planets is a critical and important reference that could help researchers have a further understanding of planetary history and its evo-lution. Traditionally, the detection of specific landforms and their geographic parameter extraction basically relies on manual marking, these types of approach may consume a lot of labor and time costs. On the other side, with the development of convolutional neural networks (CNNs),it is able to handle more complicated tasks such as object detection and semantic segmentation with high efficiency and accuracy. In order to solve this problem, this paper presents an introduction about using neural network to do object detection of the linear structures on Mars, like dorsum, fossa and so on. Based on the DEM data of Mars, this paper makes a linear structure data set. The neural network be used is YOLO-v5. In the test of 300 iterations, the algorithm can get the best detection results when it iterates 200 times, the accuracy of the object detection can reach 81% when mAP = 0.5. The results show that the method proposed in this paper can effectively judge whether there is a linear structure in the graph and mark it, which can be used to assist scientists to reduce the time cost required for detection. © 2022 ACM.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Even Search in a Promising Region for Constrained Multi-Objective Optimization

引用

IEEE/CAA Journal of Automatica Sinica 2024年第2期11卷 474-486页

作者： Fei Ming Wenyin Gong Yaochu Jin School of Computer Science China University of GeosciencesWuhan 430074China IEEE Faculty of Technology Bielefeld UniversityNorth Rhine-Westphalia 33619Germany School of Engineering Westlake UniversityHangzhou 310030China

In recent years, a large number of approaches to constrained multi-objective optimization problems(CMOPs) have been proposed, focusing on developing tweaked strategies and techniques for handling constraints. However, an overly finetuned strategy or technique might overfit some problem types,resulting in a lack of versatility. In this article, we propose a generic search strategy that performs an even search in a promising region. The promising region, determined by obtained feasible non-dominated solutions, possesses two general ***, the constrained Pareto front(CPF) is included in the promising region. Second, as the number of feasible solutions increases or the convergence performance(i.e., approximation to the CPF) of these solutions improves, the promising region shrinks. Then we develop a new strategy named even search,which utilizes the non-dominated solutions to accelerate convergence and escape from local optima, and the feasible solutions under a constraint relaxation condition to exploit and detect feasible regions. Finally, a diversity measure is adopted to make sure that the individuals in the population evenly cover the valuable areas in the promising region. Experimental results on 45 instances from four benchmark test suites and 14 real-world CMOPs have demonstrated that searching evenly in the promising region can achieve competitive performance and excellent versatility compared to 11 most state-of-the-art methods tailored for CMOPs.

关键词： Constrained multi-objective optimization even search evolutionary algorithms promising region real-world problems

来源：评论

学校读者我要写书评

暂无评论

Bank credit risk prediction using machine learning model

引用

Neural Computing and Applications 2025年第16期37卷 10333-10350页

作者： Gasmi, Ines Neji, Sana Mansouri, Nesrine Soui, Makram University of Manouba Manouba Tunisia School of Innovation and Technology University of Michigan-Flint FlintMI United States School of Engineering and Computer Science Oakland University Rochester HillsMI United States

Credit risk is one of the most prevalent risks in the banking sector. For credit risk management, digital transformation brings greater clarity to the risk profiles. Typically, datasets include various features, and many of them may be irrelevant. Removing relevant features and keeping irrelevant ones in the dataset may be harmful and lead to ruining the decision-making process. In this paper, we investigate the interesting decision variables that can be used to create a credit risk prediction model. This model will help the bank staff evaluate the loan applications of customers and classify the loan applicants as "defaulter" and "non-defaulter" customers. In addition, the loan applicants can decide on the loan acceptance status online without physical visits to the bank. In this work, we build a machine learning model by using a multilayer perceptron (MLP) algorithm based on the Australian and Taiwan banking dataset. Besides, we deploy the SMOTE technique to balance the data and overcome the suboptimal results. For statistical calculations, we use the R computing environment. The results show that demographic, financial, economic, and ‘behavioral indicators have significant effects on credit risk and the efficiency of the proposed model, with an average accuracy of 89.543% for the Australian dataset and 88.345% for the Taiwan dataset. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Banking Credit risk Machine learning model Neural network

来源：评论

学校读者我要写书评

暂无评论

Chain of Thought Prompting in Vision-Language Model for Vision Reasoning Tasks 37th

Chain of Thought Prompting in Vision-Language Model for V...

引用

37th Australasian Joint Conference on Artificial Intelligence, AJCAI 2024

作者： Ou, Jianjiu Zhou, Jianlong Dong, Yifei Chen, Fang School of Computer Science Institute Faculty of Engineering and IT University of Technology Sydney Ultimo Australia

ISBN: (纸本)9789819603503

The large language model has demonstrated its ability to reason and interpret in text-to-text applications. Current Chain of Thought (CoT) research focuses on either explaining reasoning steps or improving prediction results. This paper proposes a transformer-based language model to generate explanations as the Chain of Thoughts, then fuse visual (image) modality. The proposed model allows a multimodal reasoning chain based on text and image information. In particular, we adopt an attention layer with a gated fusion mechanism to form a joint representation for image and text input. The experiment results show that using CoT as part of the input can increase answer prediction by 19% in our study. Therefore, in our modelling process, CoT prompting is not only a part of the output to generate reasoning explanations but is also used as the input of the decoder to predict answers. The proposed method outperforms GPT-3.5 (two-shot) by 14% and GPT-4 (CoT) by 4.71% with a much smaller parameter size pre-trained language model. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

ViT-SENet-Tom: machine learning-based novel hybrid squeeze–excitation network and vision transformer framework for tomato fruits classification

引用

Neural Computing and Applications 2025年第9期37卷 6583-6600页

作者： Swapno, S M Masfequier Rahman Nobel, S. M. Nuruzzaman Islam, Md Babul Bhattacharya, Pronaya Mattar, Ebrahim A. Department of CSE Bangladesh University of Business and Technology Dhaka1216 Bangladesh Department of Computer Modeling Electronic and System Engineering UNICAL Rende Italy Department of Computer Science and Engineering Amity School of Engineering and Technology and Research and Innovation Cell Amity University West Bengal Kolkata India Robotics - Cybernetic College of Engineering University of Bahrain Manama Bahrain

Tomatoes are essential fruits in numerous nations for their vast demand. It is very important to maintain the freshness of tomatoes. One of the primary challenges in the recent culinary landscape is accurately identifying healthy tomatoes while effectively eliminating damaged or rejected ones. Existing approaches employ various strategies for categorizing tomato fruit, but they often suffer from inaccuracies, slow detection, and suboptimal performance. Thus, motivated by this gap, in this paper, we propose a novel machine learning (ML) framework, ViT-SENet-Tom, which is a hybrid vision transformer (ViT) model with squeeze and excitation (SENet) block network for fast, accurate, and efficient tomato fruit classification. The framework works on three tomato classes, respectively, the ripe, unripe, and reject. In developing the proposed model, we utilized advanced and newly designed layers and functions. This integration created a more complex and sophisticated neural network, significantly enhancing efficiency and contributing to the model’s novelty. Our chosen dataset was small initially, but we implemented augmentation techniques to increase its size. This approach made our system more reliable, efficient, and effective. The hybrid ViT-SENet framework employs encoders and self-attention networks with squeeze and excitation channel functions to allow precise, robust, fast, and efficient tomato classification. In simulation, the framework achieves a training accuracy of 99.87% and validation accuracy of 93.87%, indicating the precise classification of tomatoes. Besides, this work tests accuracy using fivefold cross-validation. The highest accuracy seen at fold-5 is 99.90%. These testing results demonstrate the efficacy of the proposed framework in real-deployment scenarios. The implementation has the potential to provide enhanced and more sustainable food security and safety in future. © The Author(s) 2025.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Assisted Channel Estimation for Adaptive Parameter Selection in mMIMO-SEFDM

引用

IEEE Internet of Things Journal 2025年第13期12卷 24174-24184页

作者： Ahmad, Muneeb Sarwar, Muhammad Sajid Shin, Soo Young Convergence Innovation Talents Training Group for Smart Manufacturing Innovation Gumi39177 Korea Republic of University of British Columbia Okanagan campus Faculty of Applied Science School of Engineering Canada Kumoh National Institute of Technology Department of IT Convergence Engineering Gumi39177 Korea Republic of

This paper introduces a massive multiple-input-multiple-output (mMIMO) system that utilizes spectrally efficient frequency division multiplexing (SEFDM) and incorporates a deep neural network (DNN) for enhanced SEFDM channel estimation. Unlike existing studies on DNN-based channel estimation, this research employs estimated channel feedback to dynamically adjust SEFDM signal characteristics at the transmitter, thereby improving the system’s adaptability. This adaptive mechanism optimizes the SEFDM compression value and modulation order based on real-time channel conditions, significantly enhancing the symbol error rate (SER). Detailed simulations demonstrate that higher modulation techniques experience substantial performance degradation with increased sub-carrier compression in SEFDM. The proposed DNN-based channel estimation and adaptive parameter selection outperform traditional linear schemes, utilizing a more stable SEFDM system to achieve significant spectral efficiency (SE) compared to conventional orthogonal frequency division multiplexing (OFDM). © 2014 IEEE.

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Maximum Power Point Tracking Control of Offshore Wind-Photovoltaic Hybrid Power Generation System with Crane-Assisted

引用

computer Modeling in engineering & sciences 2025年第4期143卷 289-334页

作者： Xiangyang Cao Yaojie Zheng Hanbin Xiao Min Xiao School of Transportation and Logistics Engineering Wuhan University of TechnologyWuhan430063China Sanya Science and Education Innovation Park Wuhan University of TechnologySanya572024China School of Computer Science and Artificial Intelligence Wuhan University of TechnologyWuhan430063China

This study investigates the Maximum Power Point Tracking(MPPT)control method of offshore windphotovoltaic hybrid power generation system with offshore crane-assisted.A new algorithm of Global Fast Integral Sliding Mode Control(GFISMC)is proposed based on the tip speed ratio method and sliding mode *** algorithm uses fast integral sliding mode surface and fuzzy fast switching control items to ensure that the offshore wind power generation system can track the maximum power point quickly and with low *** offshore wind power generation system model is presented to verify the algorithm *** offshore off-grid wind-solar hybrid power generation systemis built in MATLAB/*** with other MPPT algorithms,this study has specific quantitative improvements in terms of convergence speed,tracking accuracy or computational ***,the improved algorithm is further analyzed and carried out by using Yuankuan Energy’s ModelingTech semi-physical simulation *** results verify the feasibility and effectiveness of the improved algorithm in the offshore wind-solar hybrid power generation system.

关键词： Offshore wind power generation efficiency maximum power point tracking(MPPT) integral sliding mode control grey wolf optimization algorithm offshore photovoltaic cells

来源：评论

学校读者我要写书评

暂无评论

CMCF-Net: An End-to-End Context Multiscale Cross-Fusion Network for Robust Copy-Move Forgery Detection

引用

IEEE Transactions on Multimedia 2024年 26卷 6090-6101页

作者： Xiong, Lizhi Xu, Jianhua Yang, Ching-Nung Zhang, Xinpeng Nanjing University of Information Science and Technology School of Computer Science Nanjing210044 China Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment Technology Engineering Research Center of Digital Forensics Ministry of Education Nanjing210044 China Nanjing University of Information Science and Technology Software Engineering Nanjing210044 China National Dong Hwa University Department of Computer Science and Information Engineering Hualien974301 Taiwan Fudan University School of Computer Science Shanghai200433 China

Image copy-move forgery detection (CMFD) has become a challenging problem due to increasingly powerful editing software that makes forged images increasingly realistic. Existing algorithms that directly connect multiple scales of features in the encoder part may not effectively aggregate contextual information, resulting in poor performance. In this paper, an end-to-end context multiscale cross-fusion network (CMCF-Net) is proposed to detect image copy-move forgery. The proposed network consists of a multiscale feature extraction fusion (MSF) module and a multi-information fusion decoding (MFD) module. Multiscale information is efficiently extracted and fused in the MSF module utilizing stacked-scale feature fusion, which improves the network's forgery localization ability on objects of different scales. The MFD module employs contextual information combination and weighted fusion of multiscale information to guide the network in obtaining relevant clues from correlated information at multiple different scales. Experimental results and analysis have demonstrated that the proposed CMCF-Net achieves the best localization results with higher robustness. © 1999-2012 IEEE.

关键词： Feature extraction

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：