检索结果-内蒙古大学图书馆

4th International Conference on Information Science, Parallel and Distributed Systems, ISPDS 2023

作者： Wang, Qinfen Li, Yifei Xia, Yong School of Computer Science and Engineering Northwestern Polytechnical University Natl. Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi'an710072 China

ISBN: (纸本)9798350337181

Generative adversarial networks (GAN) have been successful in demonstrating the efficiency of generative time series. In this paper, we proposed a novel end-to-end supervised and unsupervised coupled generative adversarial networks (SUC-GAN) framework that consists of a gated recurrent unit (GRU) for generating multivariate time series. We test SUC-GAN on three datasets (i.e. Sines, Energy, Stocks) to investigate the efficacy and properties. The preliminary results show the potential power of supervised, unsupervised, and coupled learning for data generation. © 2023 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Exploring the Capabilities and Limitations of Generative AI applications, Challenges, and Future Directions

Exploring the Capabilities and Limitations of Generative AI ...

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Singh, Gulbir Meenakshi Sharma, Poonam Bhardwaj, Anjul Graphic Era Hill University Department of Computer Science and Engineering Haldwani Campus Uttarakhand Nanital India Mmict&bm Mullana Haryana Ambala India Divine Institute of Management & Studies Dept. of Computer Application Ziradei Bihar Siwan India

ISBN: (纸本)9798331508685

Unprecedented capabilities for content generation, predictive analytics, and automation are made available by the introduction of Generative Artificial Intelligence (AI) technologies, which uses in a new age of industrial innovation. The purpose of this study is to investigate the transformational potential of generative AI from the perspective of exploring its capabilities and limitations and highlighting its role in the development of future technological developments. With the help of this study, we want to highlight important unsolved issues in contemporary generative AI paradigms. These challenges need to be addressed in order to further improve the capabilities, variety, and dependability of these concepts. Our goal is to give researchers with significant insights that will allow them to explore successful research areas, which will ultimately lead to the creation of generative AI systems that are more robust and accessible. © 2025 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

An Assessment of Analysis Techniques

An Assessment of Analysis Techniques

引用

2023 International Conference on Artificial Intelligence and Smart Communication, AISC 2023

作者： Salaria, Amita Balu, Vincent Chandigarh School of Business Department of Master of Computer Application Jhanjeri India Sanskriti University Hod Department of Mechanical Engineering Uttar Pradesh Mathura India

ISBN: (纸本)9798350322309

The Supervised Learning in Organizations (PPDM) method, data analysis, mining and data, and subjects related to data mining have all been covered in this page. Due to the enormous quantity of readily viewable info and the urgent need to transform it into useful skills and data, data analysis has grown in popularity both in the data business and the general public in past years. To convert collected data into usable research and wisdom, innovative technology and methods are needed to keep up with the ever-growing data amounts. Some many data analysis techniques are required in the offering of information facilities, including cloud computing and Wifi services, in in order to better comprehend user behaviour, ease congestion, and increase cash flow. To meet this need, information mining strategies will be contrasted from the perspective of a file scientist. The report classifies and compares these data mining methods. © 2023 IEEE.

关键词： Data warehouses

来源：评论

学校读者我要写书评

暂无评论

An end-to-end repair-based joint training framework for weakly supervised pavement crack segmentation

引用

Multimedia Tools and applications 2025年第16期84卷 16281-16299页

作者： Zhou, Hui Tao, Huanjie Duan, Qianyue Hu, Zhenwu Deng, Yishi School of Computer Science Northwestern Polytechnical University Xi’an710129 China School of Cyberspace Security Northwestern Polytechnical University Xi’an710129 China Engineering Research Center of Embedded System Integration Ministry of Education Xi’an710129 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi’an710129 China

Weakly supervised pavement crack segmentation aims to assign each pixel of pavement surface images a category label (crack or non-crack) using limited annotation information. Most existing methods adopt the multi-stage approach based on the class activation map (CAM), which outputs from a pre-trained crack classification model, to generate the pixel-level pseudo labels, and then train a segmentation model using these pseudo labels. However, these methods have two notable drawbacks: (i) CAM focuses primarily on the most discriminative regions of the image, potentially resulting in an incomplete estimation of crack regions, and (ii) the process of obtaining pixel-level pseudo labels from CAM is complex and may introduce noise. To avoid these issues, we propose an end-to-end repair-based joint training framework for weakly supervised pavement crack segmentation. Specifically, to better guide the model to pay more attention to the repair process of crack regions, we introduce the segmentation loss, which assigns different weights for crack regions and background regions, through the Residual Project Network. Additionally, to alleviate the impact of the domain gap between synthetic and real datasets, we introduce the consistency loss through the joint training paradigm of unpaired data that incorporates both crack and non-crack images into the training process simultaneously. Furthermore, to enable the model to effectively extract local features and reduce the model's computational complexity, we introduce the Lightweight Multi-head Self-attention module. The experiment results on the CRACK500 Dataset, the CFD Dataset, and the AEL Dataset demonstrate that our model achieves better performance than some existing weakly supervised pavement segmentation methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Repair

来源：评论

学校读者我要写书评

暂无评论

Improved Speaker-Emotion Voice Conversion with Limited Corpus based on Large Language Model and Pre-trained Model 6

Improved Speaker-Emotion Voice Conversion with Limited Corpu...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Fanchang TangYaLing Yadav, Amit Sah, Abhishek Pratap Khan, Asif Department of Software Engineering Chengdu Neusoft University Chengdu China College of Engineering IT and Environment Charles Darwin University NT Australia School of Management Science and Engineering University of Electronic Science and Technology of China Chengdu China Department of Computer Application Integral University Lucknow India

ISBN: (纸本)9798331522667

Existing research on speaker and emotional voice conversion often focuses on separate tasks, neglecting their joint exploration. Furthermore, the limited availability of emotional corpora for target speakers poses a significant challenge for training robustness and generalized models. This paper proposes an improved scheme for speaker-emotion voice conversion with limited target speaker's emotional corpus, integrating a large language model and a pre-trained emotional speech synthesis model. It introduces several enhancements to enhance the quality of converted speech in terms of speaker similarity and emotional expressiveness. First, emotionally tagged text is generated using a large language model and emotional speech is synthesized from this text using a fine-tuned pre-trained emotional speech synthesis model. Then, a speaker-emotion voice conversion model is co-trained with both synthesized and real target emotional speech. Finally, the model is fine-tuned with the real target emotional speech to further boost the speaker and emotional similarity. © 2025 IEEE.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

application of Developmental Services based on IoT Efficiency 6

Application of Developmental Services based on IoT Efficienc...

引用

6th International Conference on Inventive Computation Technologies, ICICT 2023

作者： Rawat, Vandana Singh, Neelam Bijalwan, Rahul Verma, Poonam Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India Department of Computer Application Graphic Era Deemed to be University Dehradun India Department of Computer Applications Graphic Era Hill University Dehradun India

ISBN: (纸本)9798350398496

Internet of things (IoT) is a fast and conforming technology, having a standard emergence primarily connected to the wireless communication between actuators, gadgets, and electrical services all in general referred to as instructions. Developmental services refer to the activities and services promoting community development and are considered as an integral part of developmental services, which include seamless and coherent experience. It is a phenomenon rich in technical skills and broader experiences consisting of mechanical frameworks and platforms, which aim towards selecting the most efficient and cost-effective tools. The collection of valuable information and relaying on them accurately are the two most important features provided by the efficient IoT services. © 2023 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Exploring Deep Learning Techniques for Automated Cataract Detection in Digital Camera Imagery

Exploring Deep Learning Techniques for Automated Cataract De...

引用

2024 International Conference on Advances in Modern Age Technologies for Health and engineering Science, AMATHE 2024

作者： Kamepalli, Sujatha Veeranjaneyulu, N. Bodapati, Jyostna Devi Vignan's Foundation For Science Technology And Research Dept. Department Of Information Technology And Computer Application Guntur India Vignan's Foundation For Science Technology And Research Dept. Department Of Advnced Computer Science And Engineering Guntur India

ISBN: (纸本)9798350371567

Cataracts, a prevalent eye condition impacting vision, demand accurate and prompt identification for effective risk reduction and blindness prevention. Traditional methods of cataract diagnosis rely heavily on manual examination by ophthalmologists, which can be time-consuming and subject to human error. With the advent of digital imaging technology, there is an opportunity to enhance the efficiency of cataract detection. The deep neural network models VGG19 and ResNet-50 are recommended in this paper for automatic cataract identification on digital camera images. To optimize network performance, adjustments to loss and activation functions were made, incorporating minimal kernels, reduced training parameters, and layers. This resulted in a ResNet-50 model with significantly decreased computational cost and average operating time compared to the cutting-edge models. The proposed ResNet 50 model achieved an average accuracy of 93.41%, outperforming the VGG 19 model, which had an accuracy of 91.13%. This research contributes to the evolution of cataract detection methodologies, emphasizing the potential of deep learning models, particularly ResNet-50, in improving diagnostic accuracy and operational efficiency for enhanced eye health outcomes. © 2024 IEEE.

关键词： Digital cameras

来源：评论

学校读者我要写书评

暂无评论

Healthcare management in Bigdata with Blockchain and IOT integrated System 1

Healthcare management in Bigdata with Blockchain and IOT int...

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Kaliyahan, Shalini Bhatnagar, Prachi Gupta, Shilpi Jain, Archana Malik, Suraj Gochhait, Saikat Sharma, Aditi Pandey, Mahima Shankar IIMT University Department of Computer Science and Application Uttar Pradesh Meerut India Meerut Institute of Technology Department of Computer Science and Engineering Uttar Pradesh Meerut India IIMT University Department of Computer Science and Engineering Uttar Pradesh Meerut India Constituent of Symbiosis International Deemed University Symbiosis Institute of Digital and Telecom Management Pune India Galgotia College of Engineering and Technology Department of Computer Science and Engineering Uttar Pradesh Greater Noida India

ISBN: (纸本)9798350356816

In 21st decade, healthcare is one of the biggest challenges, and the current scenario very flexible to adapt the effective execution technology solutions like internet of things (IoT). Through this a patient may access the treatment remotely and rapidly. Most suitable and effective applications need complex data of personal care, and reliability among the entire participated component or parties. Blockchain technology has been captured the industry domain with its computation and trusted model among participated parties. This paper presents a data storage decision framework for managing blockchain storage using on-chain and off-chain methods. There is a need for making balanced decisions between the very expensive on-chain storage methods and the less secure off-chain storage, towards optimizing blockchain storage costs. © 2024 IEEE.

关键词： Cloud computing architecture

来源：评论

学校读者我要写书评

暂无评论

A Data Commercialization Evaluation Model Based on Fuzzy Multi-attribute Group Decision Making 4

A Data Commercialization Evaluation Model Based on Fuzzy Mul...

引用

4th International Conference on Big Data Economy and Information Management, BDEIM 2023

作者： Zhao, Bin Cao, Li Gao, Yilong Zhai, Peng School of Information Science and Engineering Linyi University Shandong Linyi China School of Mathematics and Computer Application Technology Jining University Shandong Jining China

ISBN: (纸本)9798400716669

The core purpose of data commoditization transformation is to lower the threshold of data utilization and facilitate data analysis and mining at the user end. In this paper, we propose a data commoditization degree evaluation model for data trading websites. First, the evaluation index system of data commercialization is constructed, combining the abstract indexes reflecting data commonality and industry-specific data commercialization standards to assess the degree of data commercialization;second, the fuzzy multi-attribute group decision-making method is utilized to conduct fuzzy evaluation of the indexes in response to the issue of user evaluation preference;and the fuzzy function corresponding to the fuzzy evaluation is calculated based on the fuzzy structured element afterwards. The degree of superiority of the program is calculated by fuzzy compromise group decision-making method. Finally, the simplicity, convenience, and effectiveness of the data commoditization assessment model are demonstrated through a speech data case study. © 2023 ACM.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Feature Fusion for Enhanced Person Re-identification 3rd

Multi-scale Feature Fusion for Enhanced Person Re-identific...

引用

3rd International Conference on Machine Learning, Cloud Computing and Intelligent Mining, MLCCIM 2024

作者： Wang, XiaoHui Sun, Yulin Zou, Zhipeng Liang, Xiaoyang Sun, Zhenyu Liu, Wei Shandong Business Institute Yantai China Shandong Xuewen Information Technology Co. Ltd. Jining China Technology of Computer Application Yantai Engineering and Technology College Yantai China School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou China

ISBN: (纸本)9789819624676

In the realm of surveillance and security, person re-identification (Re-ID) stands as a critical challenge, particularly across non-overlapping camera networks. The essence of this challenge lies in the accurate and efficient identification of individuals by leveraging features captured from multiple perspectives. Addressing this, we introduce the Contextual Multi-Scale Network (Asy-CMSNet), a novel framework designed to enhance the Re-ID process through the integration of asymmetrical convolution and an innovative loss function, the Enhanced TriHard (E-TriHard). Unlike traditional approaches that rely on the stacking of convolutional layers, Asy-CMSNet employs a sophisticated mechanism that allows for the nuanced extraction and integration of multi-scale features, thereby optimizing the identification process across diverse pedestrian appearances. Central to our framework is the notion that effective person Re-ID necessitates the consideration of both global and localized pedestrian details, ranging from broad clothing characteristics to subtle accessories, which our model adeptly captures and utilizes. Through extensive experimentation across several benchmark datasets, Asy-CMSNet demonstrates superior performance in person Re-ID challenges, highlighting a substantial progression in the area. Our findings not only set new performance benchmarks but also pave the way for future research into more efficient, scalable, and robust person Re-ID systems. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Benchmarking

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：