检索结果-内蒙古大学图书馆

A New Method of Image Restoration technology Based on WGAN

computer Systems Science & engineering 2022年第5期41卷 689-698页

作者： Wei Fang Enming Gu Weinan Yi Weiqing Wang Victor S.Sheng School of Computer&Software Engineering Research Center of Digital ForensicsMininstry of EducationNanjing University of Information Science&TechnologyNanjing210044China Provincial Key Laboratory for Computer Information Processing Technology Soochow UniversitySuzhou215325China Texas Tech University USA

With the development of image restoration technology based on deep learning,more complex problems are being solved,especially in image semantic inpainting based on ***,image semantic inpainting techniques are becoming more ***,due to the limitations of memory,the instability of training,and the lack of sample diversity,the results of image restoration are still encountering difficult problems,such as repairing the content of glitches which cannot be well integrated with the original ***,we propose an image inpainting network based on Wasserstein generative adversarial network(WGAN)*** the corresponding technology having been adjusted and improved,we attempted to use the Adam algorithm to replace the traditional stochastic gradient descent,and another algorithm to optimize the training used in recent *** evaluated our algorithm on the ImageNet *** obtained high-quality restoration results,indicating that our algorithm improves the clarity and consistency of the image.

关键词： Image restoration WGAN DCGAN context semantic

来源：评论

学校读者我要写书评

暂无评论

AI-Inspired Algorithm for the Automated Recognition of the World’s Oldest Script “Brahmi”

引用

SN computer Science 2025年第1期6卷 1-12页

作者： Jain, Trang Jain, Arpit Dwivedi, Rakesh Kumar Saxena, Rakhi College of Computing Sciences and Information Technology Teerthanker Mahaveer University UP Moradabad India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Vijayawada India Department of Computer Science Deshbandhu College University of Delhi New Delhi India

One of the internationally known oldest script is Brahmi whose digitisation may be helpful for the archaeologists as well as it may help in the digitisation of other languages. Optical character recognition techniques with genetic algorithms will be quite useful for this purpose. In this paper, a review of the work, done on the images of Brahmi letters using CNN till now, is presented. It will be useful to check the possibility of improvement in the performance of a model used for character recognition. A model is designed where tuning of hyper parameters is done using genetic algorithms which improves the accuracy of recognition to 97%. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Ashok shilalekh Brahmi script CNN Kharavela shilalekh OCR

来源：评论

学校读者我要写书评

暂无评论

Predicting the tasks of disabled persons using deep learning-based motor imagery model in BCI applications

引用

Research on Biomedical engineering 2023年第4期39卷 977-989页

作者： Nayak, Pinki Meenakshi, S. Medikondu, Nageswara Rao Department of Information Technology Dr Akhilesh Das Gupta Institute of Technology and Management Delhi India Department of Computer Applications SDNB Vaishnav College for Women Chennai India Department of Mechanical Engineering Koneru Lakshmaiah Education Foundation Guntur Vaddeswaram India

Purpose: In order to support the disabled persons, researchers developed a motor imagery concept as an important tool. By using this concept, the disabled persons can do daily activities with the help of brain-computer interface (BCI) applications. However, the motor imagery movements of simple limb discrimination in BCI is a challenging concept, even though various machine learning (ML)/deep learning (DL) techniques are developed. The MI model plays a crucial role in BCI systems designed for various applications, such as assistive technologies, neurorehabilitation, and controlling external devices. Here are some key purposes of the MI model in BCI applications. Methods: According to the DL concepts, this research work constructs a system model based on motor imagery electroencephalogram (EEG) signals. Two datasets such as BCI-Competition-III-IVa (Dataset A) and BCI-Competition-IV-1 (Dataset B) are considered as input for proposed model, where pre-processing plays a major role in this work. Conclusion: In conclusion, the motor imagery (MI) model is a fundamental component of brain-computer interface (BCI) applications that harnesses the power of the brain’s motor imagery to enable communication, control, and interaction for individuals with diverse abilities. By interpreting the brain signals associated with imagined movements, the MI model transforms mental intentions into actionable commands, facilitating a range of practical and impactful applications The Common Average Reference (CAR) filter and Laplace spatial filtering (LSF) are used as pre-processing model to remove noise and filters the components of frequency, which are not considered in the motor imagery function. Result: Then, this pre-processed signal is given as an input to the new pre-trained model of convolutional neural network (CNN) for prediction tasks. The experimental analysis provided that the proposed model of CNN achieved 83.83% of average accuracy on Dataset A and 83.88% of average accuracy o

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Adaptive Sensor Scheduling for Federated Learning over 6G in-X Subnetworks 2

Adaptive Sensor Scheduling for Federated Learning over 6G in...

引用

2nd International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2023

作者： Wu, Qiaoli Gao, Bo Xiong, Ke Beijing Jiaotong University Engineering Research Center of Network Management Technology for High-Speed Railway Ministry of Education School of Computer and Information Technology Beijing China

ISBN: (纸本)9798350348002

In the upcoming 6G era, various end devices with data and computing resources can collaborate through federated learning (FL) to achieve the goal of ubiquitous intelligence. Inside any of those 'X' (i.e. everything) devices, however, a6G in-X subnetwork that wirelessly uploads training data from onboard sensors to an embedded access point (AP) may become a communication bottleneck during the process of FL. To support communication-efficient FL over in-X subnetworks, this paper proposes an adaptive sensor scheduling algorithm that jointly solves a queue stability problem and an age of information (AoI) optimization problem, based on Lyapunov optimization and MaxRatio scheduling methods. Simulations show that the proposed algorithm achieves higher FL accuracy, while guaranteeing queue stability at APs and better data freshness (quality) for data uploading over in-X subnetworks. © 2023 IEEE.

关键词： Scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Detection of Melanoma Insitu Using Trained CNN Model

引用

SN computer Science 2024年第8期5卷 984页

作者： SethuMadhavi, R. Premkumar, Anitha Satheesha, T.Y. Bhasker, B. DharmaTheja, M. Asha, P.N. School of Computer Science Engineering REVA University Bengaluru 560064 India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education (MAHE) Karnataka Bangalore 560064 India School of Science and Technology Department of Engineering University of London London United Kingdom School of Computing and Information Technology REVA University Bengaluru 560064 India Department of Computer Science and Engineering Vel Tech Rangarajan Dr.Sagunthala R & amp D Institute of Science and Technology Chennai India

Being the most deadly kind of skin cancer, melanoma presents a serious risk to life and is increasingly prevalent, particularly among men. It is characterized by aggressive cell multiplication that can spread within the body if left untreated, making early detection crucial for successful treatment. While machine learning techniques have been used for melanoma diagnosis, they often have limitations in performance. To address this, we propose an advanced deep learning framework incorporating a novel hybrid architecture that combines Convolutional Neural Networks (CNNs) with attention mechanisms. This framework also incorporates advanced techniques for model interpretability, such as visualizing the areas of the image that the model focuses on for its decision-making, to enhance transparency and trustworthiness for medical professionals and leverages transfer learning with pre-trained networks to boost performance. We utilized a range of optimization techniques, including AdaBelief and dynamic learning rates, to enhance model training. Our evaluation metrics included accuracy, sensitivity, specificity, and precision. Comparative results demonstrated that our model outperformed traditional techniques, with the ResNet50 architecture combined with the Adam optimizer achieving an accuracy of 92%, sensitivity of 90%, and specificity of 94%. These findings demonstrate the efficacy of our deep learning strategy by showing a notable improvement in melanoma detection performance. It is imperative to underscore that actual clinical trials or pilot studies are required to validate the model's effectiveness and reliability in real-world scenarios. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Cancer detection Convolutional Neural Network (CNN) Deep learning Dermatology Melanoma Skin cancer detection Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Learning Label Shift Correction for Test-Agnostic Long-Tailed Recognition 41

Learning Label Shift Correction for Test-Agnostic Long-Taile...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Wei, Tong Mao, Zhen Zhou, Zi-Hao Wan, Yuanyu Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China School of Software Technology Zhejiang University Ningbo China

Long-tail learning primarily focuses on mitigating the label distribution shift between long-tailed training data and uniformly distributed test data. However, in real-world applications, we often encounter a more intricate challenge where the test label distribution is agnostic. To address this problem, we first theoretically establish the substantial potential for reducing the generalization error if we can precisely estimate the test label distribution. Motivated by the theoretical insight, we introduce a simple yet effective solution called label shift correction (LSC). LSC estimates the test label distribution within the proposed framework of generalized black box shift estimation, and adjusts the predictions from a pre-trained model to align with the test distribution. Theoretical analyses confirm that accurate estimation of test label distribution can effectively reduce the generalization error. Extensive experimental results demonstrate that our method significantly outperforms previous state-of-the-art approaches, especially when confronted with non-uniform test label distribution. Notably, the proposed method is general and complements existing long-tail learning approaches, consistently improving their performance. The source code is available at https://***/Stomach-ache/label-shift-correction. Copyright 2024 by the author(s)

关键词： Black-box testing

来源：评论

学校读者我要写书评

暂无评论

A structural equation model for cyber academic dishonesty in higher education: Evidence from Taiwan

引用

Accountability in Research 2024年第7期31卷 724-750页

作者： Cheng, Yao-Chung Ho, Wei-Sho Chang, Shao-Hsun Yao, Kai-Chao Lo, Chih-Cheng Center for Teacher Education National Changhua University of Education Changhua Taiwan Department of Computer Science and Information Engineering National Changhua University of Education Changhua Taiwan Department of Industrial Education and Technology National Changhua University of Education Changhua Taiwan NCUE Alumni Association National Changhua University of Education Changhua Taiwan Kenda Cultural and Educational Foundation Yuanlin Taiwan

With the continued spread of the rise of online teaching, and the massive use of 3C products (computer, communication, and consumer electronics), the cases of academic plagiarism or using others’ works as own works caused by inappropriate use of the Internet are occurring all the time. However, very little research has been conducted on the cyber ethical climate in relation to cyber academic dishonesty. This study investigates the structural relationship between cyber ethical climate, cyber self-efficacy, cyber ethical attitude and cyber academic dishonesty, among university and graduate students, and develops a multiple mediation model. A total of 812 university and graduate students from 32 universities in Taiwan completed the online questionnaire. The results of the study show that the multiple mediation model is valid and find that the cyber ethical climate creates a favorable context for organizing members to demonstrate cyber ethical behavior, demonstrating the importance of mutual influence on cyber academic dishonesty between the cyber ethical climate created by teachers and the cyber ethical climate of class peers. Based on these results, we deeply examine the practical implications and make specific recommendations to improve the cyber ethical behavior of university and graduate students. © 2023 Informa UK Limited, trading as Taylor & Francis Group.

关键词： cyber academic dishonesty the multiple mediation model cyber ethical attitude Cyber ethical climate cyber self-efficacy

来源：评论

学校读者我要写书评

暂无评论

Secure RFID-Assisted Authentication Protocol for Vehicular Cloud Computing Environment

引用

IEEE Transactions on Intelligent Transportation Systems 2024年第9期25卷 12528-12537页

作者： Saleem, Muhammad Asad Li, Xiong Mahmood, Khalid Tariq, Tayyaba Alenazi, Mohammed J. F. Das, Ashok Kumar University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu611731 China Institute for Cyber Security School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China Sichuan University Key Laboratory of Data Protection and Intelligent Management Ministry of Education Chengdu610065 China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Shenzhen518000 China National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Yunlin Douliu64002 Taiwan National Yunlin University of Science and Technology Graduate School of Engineering Science and Technology Yunlin Douliu64002 Taiwan King Saud University College of Computer and Information Sciences Department of Computer Engineering Riyadh11451 Saudi Arabia International Institute of Information Technology Center for Security Theory and Algorithmic Research Hyderabad500032 India

Vehicular network technology has made substantial advancements in recent years in the field of Intelligent Transportation Systems. Vehicular Cloud Computing (VCC) has emerged as a novel paradigm with a substantial increase in data exchange within Vehicular ad-hoc networks (VANETs). VCC integrates cloud computing, vehicular networking, and Internet of Things (IoT) technologies. It enables Infrastructure-to-Vehicle (I2V), Vehicle-to-Vehicle (V2V), and Vehicle-to-Device (V2D) communication. VCC optimizes vehicle, cloud infrastructure, and IoT resources while addressing significant communication security and vehicle-user privacy challenges. To address these issues, we developed an RFID-based authentication protocol for VCC based on a Henon map using a hash function. In addition, we also incorporated a Physical Unclonable Function (PUF) to resist physical tampering attacks. We validate the protocol's security formally and informally. The formal security analysis is conducted through a widely used RoR model. We use the Scyther simulation tool to verify the proposed protocol's security against various attacks. Moreover, we compare the performance of our protocol with similar existing protocols across important performance parameters such as communication and computation overheads and security attributes. The proposed protocol yields substantial improvements, demonstrating a 40.74% reduction in computation overhead and a 13.03% decrease in communication overhead as compared to related protocols, delivering both enhanced performance and resource efficiency. The analysis demonstrates its capacity to support secure communication in the VCC environment and satisfy desirable security attributes. © 2024 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Automated Learning Engines and their Potential to Enhance information Retrieval Accuracy 3

Automated Learning Engines and their Potential to Enhance In...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Sakhare, Nitin N. Thangarasu, N. Rajarajeswari, S. Dedgaonkar, Suruchi G. Rengarajan, A. Pareek, Ravi Kant Vishwakarma Institute of Information Technology Department of Computer Engineering Pune India Karpagam Academy of Higher Education Department of Computer Science Coimbatore India Prince Shri Venkateshwara Padmavathy Engineering College Department of Science and Humanities Chennai India Vishwakarma Institute of Information Technology Department of Information Technology Pune India Department of Computer Science and Information Technology Karnataka Bangalore India Vivekananda Global University Department of Civil Engineering Jaipur India

ISBN: (纸本)9798350319125

Latest advances in artificial intelligence (AI) have given upward push to automated mastering engines which can be capable of leveraging big quantities of records to become aware of and extract applicable information with top notch accuracy. This has enabled more green records retrieval strategies, which has capability to revolutionize how human beings use and get admission to facts. computerized studying engines are capable of acting complex duties consisting of natural language processing, sentiment analysis, and object recognition, all of which require extensive computation strength. because of this possibilities for more suitable statistics retrieval systems are getting an increasing number of available to *** automatic mastering engine is particularly beneficial in situations wherein there's an abundance of statistics. The engine is able to filter and narrow down the facts to identify and extract simplest the most beneficial data. This allows to keep away from clutter and false positives from the hunt consequences, accordingly main to greater accurate and reliable results. moreover, their capacity to examine from the records they process way that they can be tailor-made to particular use instances, thereby making searches greater green and powerful. furthermore, automated mastering engines can perform at a miles quicker fee than traditional seek techniques. through automating the technique of statistics collection, evaluation, and usage, time is stored and the efficiency of the whole information retrieval system is substantially improved. this may have a ways-reaching implications. © 2023 IEEE.

关键词： information positives quicker system traditional

来源：评论

学校读者我要写书评

暂无评论

Asymptotics-Aware Multi-View Subspace Clustering

引用

IEEE Transactions on Multimedia 2025年 27卷 3650-3663页

作者： Xu, Yesong Chen, Shuo Li, Jun Yang, Jian Anhui Polytechnic University School of Computer and Information Wuhu241000 China RIKEN Center for Advanced Intelligence Project Tokyo103-0027 Japan Nanjing University of Science and Technology PCA Laboratory Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing210094 China Nanjing University of Science and Technology Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing210094 China

Recently, multi-view subspace clustering has attracted extensive attention due to the rapid increase of multi-view data in many real-world applications. The main goal of this task is to learn a common representation of multiple subspaces from the given multi-view data, and most existing methods usually directly merge multiple groups of features by the single-step integration. However, there may exist large disparities among different views of the data, and thus the conventional single-step practice can hardly obtain a generally consistent feature representation for the multi-view data. To overcome this challenge, we present a novel approach dubbed "Asymptotics-Aware Multi-view Subspace Clustering (A2 MSC)"to pursue a consistent feature representation in a multi-step way, which iteratively conducts the data recovery to gradually reduce the differences between pairwise views. Specifically, we construct an asymptotic learning rule to update the feature representation, and the iteration result converges to a consistent feature vector for characterizing each instance of the original multi-view data. After that, we utilize such a new feature representation to learn a clustering-oriented similarity matrix via minimizing a self-expressive objective, and we also design the corresponding optimization algorithm to solve it with convergence guarantees. Theoretically, we prove that the learned asymptotic representation effectively integrates multiple views, thereby ensuring the effective handling of multi-view data. Empirically, extensive experimental results demonstrate the superiority of our proposed A2 MSC over the state-of-the-art multi-view subspace clustering approaches. © 2025 IEEE.

关键词： Data assimilation

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：