检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2025年第3期6卷 589-603页

作者： Qiu, Jian-Qiang Zhang, Chun-Yang Chen, C. L. Philip Fuzhou University College of Computer and Data Science Fuzhou350108 China South China University of Technology School of Computer Science and Engineering Guangzhou510006 China

Pretrained language models (PLMs) have shown remarkable performance on question answering (QA) tasks, but they usually require fine-tuning (FT) that depends on a substantial quantity of QA pairs. Therefore, improving the performance of PLMs in scenarios with only a small number of training examples, also known as a few-shot setting, is of great practical significance. Current mitigation strategies for the few-shot QA task largely rely on pretraining a QA task-specific language model from scratch, overlooking the potential of foundational PLMs to generate QA pairs, particularly in the few-shot setting. To address this issue, we propose a prompt-based QA data augmentation method aimed at automating the creation of high-quality QA pairs. It employs the PFT method, adapting the question generation process of PLMs to the few-shot setting. Additionally, we introduce a dynamic text filling training strategy. This strategy simulates the progressive human learning process, thereby alleviating overfitting of PLMs in the few-shot setting and enhancing their reasoning capability to tackle complex questions. Extensive experiments demonstrate that the proposed method outperforms existing approaches across various few-shot configurations. 2691-4581 © 2024 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission. See https://***/publications/rights/*** for more information.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

DeepSwarm:towards swarm deep learning with bi-directional optimization of data acquisition and processing

引用

Frontiers of Computer science 2025年第3期19卷 125-127页

作者： Sicong LIU Bin GUO Ziqi WANG Lehao WANG Zimu ZHOU Xiaochen LI Zhiwen YU School of Computer Science and Engineering Northwestern Polytechnical UniversityXi’an 710072China School of Data Science City University of Hong KongHong Kong 999077China College Of Computer Science And Technology Harbin Engineering UniversityHarbin 150001China

1 Introduction On-device deep learning(DL)on mobile and embedded IoT devices drives various applications[1]like robotics image recognition[2]and drone swarm classification[3].Efficient local data processing preserves privacy,enhances responsiveness,and saves ***,current ondevice DL relies on predefined patterns,leading to accuracy and efficiency *** is difficult to provide feedback on data processing performance during the data acquisition stage,as processing typically occurs after data acquisition.

关键词： drone swarm classification efficient local data processing data processing deep learning dl device deep learning bi directional optimization iot devices swarm deep learning

来源：评论

学校读者我要写书评

暂无评论

Optimised EfficientNet for multi-class skin cancer diagnosis: integrating chaotic grey wolf algorithms

引用

Current science 2025年第7期128卷 728-736页

作者： Rama, P. Angayarkanni, V. Theresa, W. Gracy Pandiaraj, A. Department of Computing Technologies College of Engineering and Technology Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur603 203 India Department of Artificial Intelligence and Data Science Panimalar Engineering College Chennai600 123 India

The detection of skin cancer holds paramount importance worldwide due to its impact on global health. While deep convolutional neural networks (DCNNs) have shown potential in this domain, current approaches often struggle with fine-grained variability in skin lesion features, imbalanced datasets and inadequate augmentation. The objectives of our study encompass building a model that not only enhances accuracy but also reduces training time and cost, improves dimensionality reduction during classification and segmentation, and is evaluated on larger datasets for robustness. We enhance the learning process using an improved nature-inspired optimisation algorithm tailored specifically for skin cancer classification tasks. This algorithm optimises model parameters to maximise classification accuracy while minimising computational overhead. Our proposed architecture leverages a gold standard dermatological image dataset meticulously curated and validated by experts. This dataset spans eight distinct classes, including actinic keratosis, basal cell carcinoma, melanoma, nevus, and others, ensuring a diverse representation of skin conditions. The balanced class distribution in the training and test sets enables fair evaluation and robustness assessment of our deep learning models. The developed algorithm showcases novelty in its approach, contributing to advancements in early skin cancer detection technologies. This study introduces an optimised deep learning model designed for the early detection of skin cancer, achieving a notable accuracy of 97.48%. Our study aims to contribute significantly to the medical field by providing a reliable and efficient tool for dermatologists and healthcare practitioners to assist in diagnosing skin conditions accurately and promptly, ultimately improving patient outcomes and healthcare efficiency. © (2025), (Indian Academy of sciences). All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Effi-CNN: real-time vision-based system for interpretation of sign language using CNN and transfer learning

引用

Multimedia Tools and Applications 2025年第6期84卷 3137-3159页

作者： Pranav Katarya, Rahul Big Data Analytics and Web Intelligence Laboratory Computer Science & Engineering Department Delhi Technological University New Delhi India

The deaf and mute population has difficulty conveying their thoughts and ideas to others. Sign language is their most expressive mode of communication, but the general public is callow of sign language;therefore, the mute and deaf have difficulty communicating with others. A system that can correctly translate sign language motions to speech and vice versa in real time is required to overcome this communication barrier. Effi-CNN, a vision-based Sign Language Recognition (SLR) system employing transfer learning with EfficientNetB2, is proposed in this paper. We have also developed a system covering sign gestures to text in real time. Our approach was evaluated on eight publicly available datasets, including the Massey University gesture dataset, the ArSL2018 dataset, the MNIST-ASL dataset, and others. When comparing our results to state-of-the-art algorithms, the experimental findings showed that our proposed work is more successful than existing models. Our proposed model delivered an accuracy of 99.90 on MNIST dataset. The results show that our Effi-CNN surpasses most currently existing solutions and can categorize many gestures with a low error rate. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Novel MITM attack scheme based on built-in negotiation for blockchain-based digital twins

引用

Digital Communications and Networks 2025年第1期11卷 256-267页

作者： Xin Liu Rui Zhou Shohei Shimizu Rui Chong Qingguo Zhou Xiaokang Zhou School of Information Science and Engineering Lanzhou UniversityLanzhou 730000China Faculty of Data Science Shiga UniversityHikone 522-8522Japan Beijing Zhongxin Xingkong Network Technology Co Beijing 100005China

As smart contracts,represented by Solidity,become deeply integrated into the manufacturing industry,blockchain-based Digital Twins(DT)has gained momentum in recent *** of the blockchain infrastructures in widespread use today are based on the Proof-of-Work(PoW)mechanism,and the process of creating blocks is known as“mining”.Mining becomes increasingly difficult as the blockchain grows in size and the number of on-chain business systems *** lower the threshold of participation in the mining process,“mining pools”have been *** can cooperate and share the mining rewards according to the hashrate they contributed to the *** is the most widely used communication protocol between miners and mining *** security is essential for the *** this paper,we propose two novel Man-In-The-Middle(MITM)attack schemes against Stratum,which allow attackers to steal miners'hashrate to any mining pool using hijacked TCP *** with existing attacks,our work is more secretive,more suitable for the real-world environment,and more *** Proof-of-Concept(PoC)shows that our schemes work perfectly on most mining softwares and ***,we present a lightweight AI-driven approach based on protocol-level feature analysis to detect Stratum MITM for blockchain-based *** detection model consists of three layers:feature extraction layer,vectorization layer,and detection *** prove that our detection approach can effectively detect Stratum MITM traffic with 98%*** work alerts the communities and provides possible mitigation against these more hidden and profitable attack schemes.

关键词： Digital twins MITM Blockchain Stratum Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

STBA: Towards Evaluating the Robustness of DNNs for Query-Limited Black-box Scenario

引用

IEEE Transactions on Multimedia 2025年 27卷 2666-2681页

作者： Liu, Renyang Lam, Kwok-Yan Zhou, Wei Wu, Sixing Zhao, Jun Hu, Dongting Gong, Mingming Yunnan University School of Information Science and Engineering Kunming650500 China Nanyang Technological University College of Computing and Data Science 639798 Singapore Yunnan University School of Software Engineering Research Center of Cyberspace Kunming650500 China University of Melbourne Melbourne Centre for Data Science School of Mathematics and Statistics ParkvilleVIC3010 Australia

Extensive studies have revealed that deep neural networks (DNNs) are vulnerable to adversarial attacks, especially black-box ones, which can heavily threaten the DNNs deployed in the real world. Many attack techniques have been proposed to explore the vulnerability of DNNs and further help to improve their robustness. Despite the significant progress made recently, existing black-box attack methods still suffer from unsatisfactory performance due to the vast number of queries needed to optimize desired perturbations. Besides, the other critical challenge is that adversarial examples built in a noise-adding manner are abnormal and struggle to successfully attack robust models, whose robustness is enhanced by adversarial training against small perturbations. There is no doubt that these two issues mentioned above will significantly increase the risk of exposure and result in a failure to dig deeply into the vulnerability of DNNs. Hence, it is necessary to evaluate DNNs' fragility sufficiently under query-limited settings in a non-additional way. In this paper, we propose the Spatial Transform Black-box Attack (STBA), a novel framework to craft formidable adversarial examples in the query-limited scenario. Specifically, STBA introduces a flow field to the high-frequency part of clean images to generate adversarial examples and adopts the following two processes to enhance their naturalness and significantly improve the query efficiency: a) we apply an estimated flow field to the high-frequency part of clean images to generate adversarial examples instead of introducing external noise to the benign image, and b) we leverage an efficient gradient estimation method based on a batch of samples to optimize such an ideal flow field under query-limited settings. Compared to existing score-based black-box baselines, extensive experiments indicated that STBA could effectively improve the imperceptibility of the adversarial examples and remarkably boost the attack success rate u

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Advanced Parkinson’s Disease Classification using Hybrid Model: SVM and Random Forest 3

Advanced Parkinson’s Disease Classification using Hybrid Mo...

引用

3rd International Conference on Intelligent data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Archana, S.H. Rajeshkannan, M. Anish, M.J. Sandeep, Pasupuleti Artificial Intelligence and Data Science Saveetha Engineering College Chennai India

ISBN: (纸本)9798331527549

Parkinson’s disease (PD) is a progressive and chronic neurodegenerative condition that significantly impairs motor and cognitive functions, posing a considerable burden on global healthcare systems. Early and precise diagnosis is vital to improving patient outcomes, yet traditional diagnostic techniques often encounter limitations due to overlapping symptoms with other neurological disorders and the subtle nature of early PD indicators. This research introduces a machine learning-driven approach that employs a hybrid ensemble model integrating Support Vector Machine (SVM) and Random Forest classifiers to enhance diagnostic accuracy by analyzing vocal and acoustic features. To address dataset imbalance, the Synthetic Minority Over-sampling Technique (SMOTE) is applied, enabling the model to identify meaningful patterns within underrepresented data. Principal Component Analysis (PCA) is utilized to reduce dimensionality, preserving critical data variance while minimizing computational complexity and mitigating overfitting. Hyperparameter tuning further optimizes each classifier, bolstering the model’s accuracy and robustness. Comparative analyses demonstrate that this hybrid ensemble model effectively distinguishes PD patients from healthy individuals, showcasing its potential as a reliable predictive tool in clinical applications. This study highlights the promise of advanced machine learning methodologies in supporting early PD detection, offering clinicians a valuable resource for timely intervention and improved patient care. © 2025 IEEE.

关键词： hybrid classification Machine learning models Parkinson’s Disease principal component analysis (PCA) random forest algorithm support vector machine (SVM)

来源：评论

学校读者我要写书评

暂无评论

Guidelines for dopant selection in Cu catalysts to promote the electrochemical CO2 reduction reaction for ethylene production

引用

Journal of Energy Chemistry 2025年第4期103卷 674-681页

作者： Dogyeong Kim Seohyeon Ka Man Ho Han Woong Kim Seung-Ho Yu Jae-Young Choi Keun Hwa Chae Hyung-Suk Oh Woong Hee Lee Clean Energy Research Center Korea Institute of Science and Technology (KIST) Department of Chemical and Biological Engineering Korea University Department of Materials Science and Engineering Korea University School of Advanced Materials Science and Engineering Sungkyunkwan University KIST-SKKU Carbon-Neutral Research Center Sungkyunkwan University Analysis &Data Center Korea Institute of Science and Technology Division of Energy and Environmental Technology KIST School Korea University of Science and Technology (UST)

To develop an efficient electrochemical CO2reduction reaction（CO2RR） for the production of C2chemicals,improvements in the Cu catalyst are *** is widely used for catalyst enhancement;however,only a few elements have been *** study proposes guidelines for the selection of Cu catalyst dopants to promote ethylene *** was hypothesized that the dopant chemical state highly influences the CO2RR catalytic *** the case of dopants possessing a standard reduction potential within the CO2RR potential region（e.g.,Mn and Ni）,low Faradaic efficiency（FE） toward ethylene production was obtained owing to the presence of a metallic dopant（10.7% for Ni dopant）.In contrast,a low standard reduction potential led to a stable high oxidation state for the dopant,yielding abundant Cuδ+species with modified electronic structures and enhancing the CO2RR catalytic activity for ethylene production（42.1% for Hf dopant）.We expected that a dopant with a low standard reduction potential is difficult to reduce,which leads to a stable Cu-O-X bond and induces a stable Cuδ+*** study provides insights into how to select dopant for various catalyst to enhance CO2RR catalytic activity.

关键词： CO 2 reduction reaction Catalytic selectivity Dopant Cu species Ethylene production

来源：评论

学校读者我要写书评

暂无评论

Knowledge Probabilization in Ensemble Distillation: Improving Accuracy and Uncertainty Quantification for Object Detectors

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第1期6卷 221-233页

作者： Yang, Yang Wang, Chao Gong, Lei Wu, Min Chen, Zhenghua Li, Xiang Chen, Xianglan Zhou, Xuehai University of Science and Technology of China School of Computer Science and Technology Hefei230026 China 138632 Singapore East China Normal University School of Data Science and Engineering Shanghai200062 China

Ensemble object detectors have demonstrated remarkable effectiveness in enhancing prediction accuracy and uncertainty quantification. However, their widespread adoption is hindered by significant computational and storage demands, limiting their feasibility in resource-constrained settings. To overcome this, researchers have focused on distilling the knowledge from ensemble object detectors into a single model. In this article, we introduce probabilization based ensemble distillation (ProbED), an innovative ensemble distillation framework that consolidates knowledge from multiple object detectors into a single, resource-efficient model. Unlike traditional ensemble distillation methods that average the outputs of subteachers, ProbED captures comprehensive outcome distributions from all subteachers, providing a more nuanced approach to knowledge transfer. ProbED employs knowledge probabilization to achieve a sophisticated and refined aggregation of teacher knowledge, including feature knowledge, semantic knowledge, and localization knowledge, resulting in dual improvements in prediction accuracy and uncertainty quantification for the student model. In particular, ProED's novel knowledge probabilization-based approach to aggregating teacher knowledge is inspired by our empirical observations, which demonstrate that knowledge probabilization excels in effectively representing uncertainty, improving prediction, and facilitating robust knowledge transfer. Furthermore, we introduce a random smoothing perturbation technique to modify inputs within ProbED, further enhancing the distillation process. Extensive experiments highlight ProbED's ability to significantly enhance the prediction accuracy and uncertainty quantification of various object detectors, demonstrating its superior performance compared to other state-of-the-art techniques. © 2024 IEEE.

关键词： Teaching

来源：评论

学校读者我要写书评

暂无评论

Transverse Velocity Field Measurement of Solar High-resolution Images Based on Unsupervised Deep Learning

引用

Research in Astronomy and Astrophysics 2025年第3期25卷 236-248页

作者： Zhen-Hong Shang Long Chen Zhen-Ping Qiang Yi Bi Run-Xin Li Faculty of Information Engineering and Automation Kunming University of Science and Technology Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and Technology College of Big Data and Intelligent Engineering Southwest Forestry University Yunnan Observatories Chinese Academy of Sciences

Measuring the transverse velocity field in high-resolution solar images is essential for understanding solar *** paper introduces an innovative unsupervised deep learning optical flow model designed to calculate the transverse velocity field,addressing the challenges of missing optical flow labels and the limited accuracy of velocity field measurements in high-resolution solar *** proposed method converts the transverse velocity field computation problem into an optical flow computation problem,using two forward propagations of features to get rid of the reliance on optical flow ***,it reduces the impact of the“Brightness Consistency”constraint on optical flow accuracy by identifying and handling optical flow *** apply this method to compute the transverse velocity fields of high-resolution solar image sequences from the Hαand TiO bands,observed by the New Vacuum Solar *** experiments with several wellestablished optical flow methods,including those based on supervised deep learning models,show that our approach outperforms the comparison methods according to key evaluation metrics such as Residual Map Mean,Residual Map Variance,Cross Correlation,and Structural Similarity Index ***,since optical flow captures the fundamental motion information in image sequences,the proposed method can be applied to a variety of research areas,including solar image registration,sequence alignment,image super-resolution,magnetic field calibration,and solar activity *** code is available at https://***/jackie-willianm/Transverse-Velocity-Field-Measurement-of-Solar-High-Resolution-Images.

关键词： methods: data analysis Sun: fundamental parameters techniques: image processing

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：