检索结果-内蒙古大学图书馆

19th Orissa Information Technology Society International Conference on Information Technology, OCIT 2021

作者： Nayak, Manas Ranjan Parida, Ajaya Kumar Pattnayak, Parthasarathi Khan, Asif Uddin School of Computer Engineering KIIT Deemed To Be University Bhubaneswar India School of Computer Application KIIT Deemed To Be University Bhubaneswar India Silicon Institute of Technology Department of Computer Science Engineering Bhubaneswar India

ISBN: (纸本)9781665416641

The outcomes from Perceptual watermarking attain full benefits of Human Visual System (HVS). Saliency and Phase Congruency (PC) use these benefits by categorizing various perceptual regions of an image. Saliency gives the low perceptual region of an image where Phase Congruency identifies the corner points of an image. Hiding information at this low perceptual region of an image gives better imperceptibility. In this proposed method, bit depth images are generated from Saliency and Phase Congruency which are used to create hiding capacity map for inserting watermark data. Low perceptually visible pixels of Hiding Capacity Map are used for better hiding locations. Watermark information are inserted into the cover image by the help of a LSB matching technique where insertion and extraction are carried out using pair of pixels. The experimental result ensures better Imperceptibility and Robustness with superior data hiding Capacity. © 2021 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Analysis and Evaluation of Bio-Inspired Algorithmic Framework, Potential application in Cloud/Multi-Cloud Environment

Analysis and Evaluation of Bio-Inspired Algorithmic Framewor...

引用

Cybernetics, Cognition and Machine Learning applications (ICCCMLA), IEEE International Conference on

作者： Ramanpreet Kaur Divya Anand Upinder Kaur Sahil Verma School of Computer Applications Lovely Professional University Phagwara India Department of Computer Application Baba Farid College Bathinda India School of Computer Science and Engineering Lovely Professional University Phagwara India Department of Computer Science Akal University Talwandi Sabo Bathinda India Department of Computer Science and Engineering CGC Mohali India

Cloud computing allows web-based services to use a variety of reasonably priced services or resources, removing the requirements of centralized knowledge access. There are many provocations available in cloud computing and multi-cloud, so bio-inspired algorithms frequently used to handle particular problems such as load imbalance, resource equipping, and performance optimization. Bio-inspired algorithms have a proclivity for spontaneously resolving a wide range of challenges by giving optimum solutions. The ability has an impact on how bio-inspired algorithms are used to tackle the crucial issues in cloud computing. This study presents a comprehensive review of bio-inspired methods for resolving and optimizing solutions in multi-cloud. ACO, GA, PSO, FPA, BA and COSMIC bio inspired techniques are considered based on cost, scalability, fault tolerance, security, energy consumption, and throughput. ACO is secure and having capability of fault tolerance, PSO is fast but less secure and costly than others. Thus, FPA has a better capability than others for various parameters. FPA is better in security, cost, fault tolerance and energy consumption

关键词：

来源：评论

学校读者我要写书评

暂无评论

Estimation of the Generalization Ability of Deep Learning Model Based on Complexity

Estimation of the Generalization Ability of Deep Learning Mo...

引用

International Conference on Big Data and Information Analytics (BigDIA)

作者： Xuanzhe Li Wenjun Ke Jianhong Feng Shaotong Liu Zhewei Xu Xiaojuan Sheng School of Computer Science and Engineering Southeast University Nanjing China Unit 32366 of the Chinese People's Liberation Army Beijing China Beijing Institute of Computer Technology and Application Beijing China

ISBN: (数字)9798350354621

ISBN: (纸本)9798350354638

With the continual accumulation of data and advances in machine learning technology, it has become feasible to construct generalized estimation models based on sets of indicators. Viewing complexity indicators as independent variables and model generalizability as the dependent variable, the scenario transforms into a regression problem. Hence, this chapter examines the application of regression prediction models grounded in machine learning for the purpose of estimating the generalizability of deep convolutional networks. Given the construction risks present in generalizability measurements toward test datasets, this study proposes a generalizability measurement method that relies solely on the intrinsic attributes of the model. Several common machine learning models-SVR, RF, XGBoost, and FCNN-are employed to establish regression models between model complexity and generalization gap. To address the difficulty of manually designing hyperparameters in machine learning models, Bayesian optimization is utilized for hyperparameter tuning. The regression effectiveness of the four machine learning models, post hyperparameter optimization, is analyzed experimentally, selecting the model with the best performance as the generalizability estimation model for this study. The results indicate that the BO-XGBoost generalizability estimation model achieved the best regression outcomes, with R 2 values of 0.994 and 0.997 in two model sets respectively.

关键词： Radio frequency Measurement Deep learning Analytical models Estimation Predictive models Complexity theory Bayes methods Indexes Optimization

来源：评论

学校读者我要写书评

暂无评论

FedDAG: Federated Domain Adversarial Generation Towards Generalizable Medical Image Analysis

arXiv

引用

arXiv 2025年

作者： Che, Haoxuan Wu, Yifei Jin, Haibo Xia, Yong Chen, Hao Department of Computer Science and Engineering Hong Kong University of Science and Technology University Hong Kong National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an710072 China Department of Computer Science and Engineering Department of Chemical and Biological Engineering Division of Life Science Hong Kong University of Science and Technology Hong Kong

Federated domain generalization aims to train a global model from multiple source domains and ensure its generalization ability to unseen target domains. Due to the target domain being with unknown domain shifts, attempting to approximate these gaps by source domains may be the key to improving model generalization capability. Existing works mainly focus on sharing and recombining local domain-specific attributes to increase data diversity and simulate potential domain shifts. However, these methods may be insufficient since only the local attribute recombination can be hard to touch the out-of-distribution of global data. In this paper, we propose a simple-yet-efficient framework named Federated Domain Adversarial Generation (FedDAG). It aims to simulate the domain shift and improve the model generalization by adversarially generating novel domains different from local and global source domains. Specifically, it generates novel-style images by maximizing the instance-level feature discrepancy between original and generated images and trains a generalizable task model by minimizing their feature discrepancy. Further, we observed that FedDAG could cause different performance improvements for local models. It may be due to inherent data isolation and heterogeneity among clients, exacerbating the imbalance in their generalization contributions to the global model. Ignoring this imbalance can lead the global model’s generalization ability to be sub-optimal, further limiting the novel domain generation procedure. Thus, to mitigate this imbalance, FedDAG hierarchically aggregates local models at the within-client and across-client levels by using the sharpness concept to evaluate client model generalization contributions. Extensive experiments across four medical benchmarks demonstrate FedDAG’s ability to enhance generalization in federated medical scenarios. © 2025, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Medical CT Image Super-resolution Algorithm based on GAN

Medical CT Image Super-resolution Algorithm based on GAN

引用

computer, Vision and Intelligent Technology (ICCVIT), International Conference on

作者： Saihu Tian Taile Peng Zhongan Wang Zhengfeng Li School of Computer Science and Technology Anhui Engineering Research Center for Intelligent Computing and Application on Cognitive Behavior Huaibei Normal University Huaibei China

ISBN: (数字)9798331540043

ISBN: (纸本)9798331540050

Computed Tomography (CT) images are essential for visualizing the internal structures of the human body and are widely applied in the diagnosis of various diseases. However, during the processes of generating, storing, and transmitting medical CT images, the clarity of these images can be degraded by non-human factors, resulting in issues such as reduced resolution and blurred texture details, thereby compromising image fidelity. In this study, we present an approach utilizing Generative Adversarial Networks (GANs). that incorporates a grayscale value loss as an additional constraint while maintaining the original loss function constraints. We conduct experiments for 4x super-resolution reconstruction. To evaluate the reconstruction performance, we compare the Peak Signal-to-Noise Ratio (PSNR) and the Structural Similarity Index (SSIM) of the reconstructed images. The experimental results demonstrate ,which the proposed method exhibits promising performance in both quantitative metrics and visual quality.

关键词： Visualization PSNR Computed tomography Computational modeling Superresolution Noise Gray-scale Generative adversarial networks Image reconstruction Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Exploring Consumer Behavior in E-Commerce with AI Personalization and Market Trends Analysis Models 3

Exploring Consumer Behavior in E-Commerce with AI Personaliz...

引用

3rd International Conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Kumar, Gaurav Devayani, G. Saraswathi, C. Melba Kani, R. Dongre, Sandeep Mallick, M. S. Mohamed School of Computer Application Lovely Professional University Phagwara India M.Kumarasamy College of Engineering Department of Computer Science and Business Systems Karur India School of Management Studies Bannari Amman Institute of Technology Erode India Mar Ephraem college of Engineering and Technology Kanyakumari India Nagpur India Department of Computer Science Engineering Chennai India

ISBN: (纸本)9798331508456

Online retailers must monitor and respond to changing consumer trends to stay competitive. AI-driven customization's revolutionary impact on market trends is the focus of this study on online buying and customer behavior. As AI advances, e-commerce platforms will be able to customize user experiences. Preprocessing, feature extraction, and model training comprise the AI-driven personalization process. Customer data from online marketplaces is collected first. It manages missing values, balance the data, encode categorical variables, scale the features, and minimize the dimensions as part of our thorough data preprocessing to ensure fair and applicable results. To trained the algorithms with CNN and Convolutional LSTM Based on key criteria, the AI model beat LSTM and CNN. It provides personalized insights and recommendations with an average accuracy of 92.03%. Personalized experiences and product suggestions enabled by AI-powered personalization have transformed e-commerce. It's important to use smart algorithms to engage customers and examine large databases. This proposed approach to shows that AI can transform online shopping and improve customer experiences. © 2025 IEEE.

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

Constructing Complexity Metrics for Measuring Generalization Ability of Deep Learning Models

Constructing Complexity Metrics for Measuring Generalization...

引用

International Conference on Big Data and Information Analytics (BigDIA)

作者： Wantao Wen Wenjun Ke Jianhong Feng Shaotong Liu Zhewei Xu Xiaojuan Sheng School of Computer Science and Engineering Southeast University Nanjing China Unit 32366 of the Chinese People's Liberation Army Beijing China Beijing Institute of Computer Technology and Application Beijing China

ISBN: (数字)9798350354621

ISBN: (纸本)9798350354638

Deep neural networks have achieved tremendous success in many applications, but their generalization ability remains unexplained. Understanding this can enhance their use in safety-critical applications and guide better model design. A key aspect of this is studying model complexity, which is related to generalization. This paper proposes a technique for constructing complexity metrics to measure the generalization of deep learning models, focusing on convolutional neural networks for image classification tasks. Firstly, we consider complexity metrics based on model structure from statistical learning theory and use them as baseline metrics. Secondly, we summarize and generalize previous metrics based on model parameter norms and outputs. Thirdly, we propose a complexity metric based on the sharpness of model solutions, combining PAC-Bayesian theory to measure the expected sharpness of model local minima. Finally, experiments on two model sets are conducted to verify the effectiveness of each metric by examining the relationship between complexity and model generalization, thereby constructing the final set of model complexity metrics. We then analyze the correlation between these candidate metrics and the model's generalization gap, selecting highly correlated metrics to construct a complexity indicator set. Experimental results demonstrate that the proposed metrics based on sharpness and PAC-Bayes theory achieve the best correlation results on two model sets, PGDL-CIFAR10 and PGDL-SVHN.

关键词： Measurement Deep learning Analytical models Correlation Statistical learning Focusing Data models Complexity theory Convolutional neural networks Image classification

来源：评论

学校读者我要写书评

暂无评论

Vector angle-based and ISDE+ indicator selection for many-objective evolutionary optimization 3

Vector angle-based and ISDE+ indicator selection for many-ob...

引用

3rd International Conference on Electronic Information engineering, Big Data, and computer Technology, EIBDCT 2024

作者： Liu, Peng Chen, Hanning Liu, Keyi Wang, Guopeng Song, Lizhe Xia, Yelin Jia, Kun School of Computer Science and Technology Tiangong University Tianjin300387 China College of Artificial Intelligence Tianjin University of Science and Technology Tianjin300457 China School of Mechanical and Electrical Engineering Xinjiang Institute of Engineering Xinjiang Wulumuqi830023 China The Open University of China Beijing100039 China Engineering Research Center of Integration and Application of Digital Learning Technology Ministry of Education Beijing100039 China Jingwei Textile Machinery Beijing00176 China

ISBN: (纸本)9781510680449

Many-objective optimization problems are challenging for the majority of extant multi-objective evolutionary algorithms to solve because they are unable to strike a balance between diversity and convergence in the high-dimensional objective space. Therefore, for many-objective evolutionary optimization, this paper proposes a vector angle-based and ISDE+ indicator selection strategies. Using these two strategies, the worst individual are repeatedly removed from the population through environmental selection. More specially, the first one is aimed at finding any two individuals that have the smallest vector angle, which indicates that they are looking in the same research direction. The latter considers the individuals with poor convergence and diversity, which are eliminated according to the value of ISDE+ indicator one by one. Experimental results revel that the proposed algorithm obtains competitive advantages on various benchmark problems with up to 10 objectives, when the proposed algorithm is compared with several state-of-the-art many-objective algorithms. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Construction of PCOS Prediction Model Based on BP Neural Network

Construction of PCOS Prediction Model Based on BP Neural Net...

引用

Mobile Computing and Sustainable Informatics (ICMCSI), International Conference on

作者： Xianqing Hu Amit Yadav Asif Khan Abhishek Pratap Sah Sami Azam School of Computer and Software Chengdu Neusoft University Chengdu China Faculty of Science and Technology Charles Darwin University NT Australia Department of Computer Application Integral University Lucknow India School of Management Science and Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

Polycystic ovary syndrome (PCOS), a common endocrine-metabolic disorder affecting about 10-13% of women during reproductive age worldwide, often leads to irregular menstruation, infertility, obesity, and long-term health risks such as diabetes and cardiovascular disease. In this paper, clinical data from PCOS patients and healthy control group were collected from ten hospitals containing 37 key indicators such as age, weight, BMI, menstrual cycle, etc. BP (Back Propagation) Neural Network prediction models were constructed and compared using the collected data and the cross-validation method was used for parameter tuning. It was found that BP N eural Network performed particularly well on the test set, and both demonstrated high prediction accuracy and generalization ability which provided strong evidence for the early identification and early valuable intervention opportunities for PCOS patients.

关键词： Training Adaptation models Accuracy Biological system modeling Computational modeling Neural networks Predictive models Data models Robustness Tuning

来源：评论

学校读者我要写书评

暂无评论

Research on Tensor Multi-Clustering Distributed Incremental Updating Method for Big Data

引用

computers, Materials & Continua 2024年第10期81卷 1409-1432页

作者： Hongjun Zhang Zeyu Zhang Yilong Ruan Hao Ye Peng Li Desheng Shi School of Computer Science Nanjing University of Posts and TelecommunicationsNanjing210023China Ministry of Science and Technology Innovation China Communications Services Corporation LimitedBeijing100071China School of Artificial Intelligence The University of ManchesterManchesterM139PLUK Ministry of Technology Innovation China Telecom Artificial Intelligence Technology(Beijing)Corporation LimitedBeijing100032China Ministry of Science and Technology Innovation Zhongbo Information Technology Research Institute Corporation LimitedNanjing210012China Jiangsu Postal Big Data Technology and Application Engineering Research Center Nanjing University of Posts and TelecommunicationsNanjing210003China

The scale and complexity of big data are growing continuously,posing severe challenges to traditional data processing methods,especially in the field of clustering *** address this issue,this paper introduces a new method named Big Data Tensor Multi-Cluster Distributed Incremental Update(BDTMCDIncreUpdate),which combines distributed computing,storage technology,and incremental update techniques to provide an efficient and effective means for clustering ***,the original dataset is divided into multiple subblocks,and distributed computing resources are utilized to process the sub-blocks in parallel,enhancing ***,initial clustering is performed on each sub-block using tensor-based multi-clustering techniques to obtain preliminary *** new data arrives,incremental update technology is employed to update the core tensor and factor matrix,ensuring that the clustering model can adapt to changes in ***,by combining the updated core tensor and factor matrix with historical computational results,refined clustering results are obtained,achieving real-time adaptation to dynamic *** experimental simulation on the Aminer dataset,the BDTMCDIncreUpdate method has demonstrated outstanding performance in terms of accuracy(ACC)and normalized mutual information(NMI)metrics,achieving an accuracy rate of 90%and an NMI score of 0.85,which outperforms existing methods such as TClusInitUpdate and TKLClusUpdate in most ***,the BDTMCDIncreUpdate method offers an innovative solution to the field of big data analysis,integrating distributed computing,incremental updates,and tensor-based multi-clustering *** not only improves the efficiency and scalability in processing large-scale high-dimensional datasets but also has been validated for its effectiveness and accuracy through *** method shows great potential in real-world applications where dynamic data growth is common,and it is of significant imp

关键词： Tensor incremental update distributed clustering processing big data

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：