检索结果-内蒙古大学图书馆

Journal of Network Intelligence 2024年第2期9卷 790-803页

作者： Liu, Shu-Tang Fan, Ji-Jie Wang, Rui-Dong Han, Han Zhang, De-Yang Faculty of Humanities and Arts Macau University of Science and Technology 999078 China Academic Affairs Office Minjiang University Fuzhou350108 China Kyrgyz National University Named after Jusup Balasagyn Bishkek720033 Kyrgyzstan School of Computer Science and Technology Harbin University of Science and Technology Harbin150080 China School of Measurement and Control Technology and Communication Engineering Harbin University of Science and Technology Harbin150080 China Henan Provincial Institute of Scientific and Technical Information Zhengzhou450003 China

Anomaly detection in time series is challenging for machine learning due to the uncertainty and complex pattern in time series. In this paper, we propose a Kalman filter-based cycle-consistent adversarial learning framework (KFCGAN) for time series anomaly detection, assuming that the abnormal pattern prevents the model from reconstructing the original and filtered signals. Specifically, KFCGAN comprises a Kalman filter module and a cycle-consistent adversarial learning module that utilizes an autoencoder as its generator. Firstly, the Kalman filter module generates the filtered signals from the original signals as the target domain. Then, the forward direction of the cycleconsistent adversarial learning module learns the transformation of the original time series domain to the filtered time series domain. At the same time, the backward direction optimizes it by transforming the target domain to the original domain. Finally, anomaly detection can be modeled as the signal reconstruction problem between the original and target domains. The experimental results on five real-world datasets show that the proposed method outperforms the start-of-the-art, demonstrating that KFCGAN can effectively capture abnormal time series patterns. © 2024, J. Network Intell. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Empowered,Collaborative,and Co-Evolving AI Models:The Post-LLM Roadmap

引用

工程（英文） 2025年第1期44卷 87-100页

作者： Fei Wu Tao Shen Thomas Bäck Jingyuan Chen Gang Huang Yaochu Jin Kun Kuang Mengze Li Cewu Lu Jiaxu Miao Yongwei Wang Ying Wei Fan Wu Junchi Yan Hongxia Yang Yi Yang Shengyu Zhang Zhou Zhao Yueting Zhuang Yunhe Pan College of Computer Science and Technology Zhejiang UniversityHangzhou 310027China Leiden Institute of Advanced Computer Science Leiden UniversityLeiden 2333 CCNetherlands College of Electrical Engineering Zhejiang UniversityHangzhou 310027China School of Engineering Westlake UniversityHangzhou 310024China Department of Computer Science and Engineering Hong Kong University of Science and TechnologyHong Kong 999077China Department of Computer Science and Engineering Shanghai Jiao Tong UniversityShanghai 200240China School of Cyber Science and Technology Sun Yat-Sen UniversityShenzhen 518107China Department of Computing The Hong Kong Polytechnic UniversityHong Kong 999077China

Large language models(LLMs)have significantly advanced artificial intelligence(AI)by excelling in tasks such as understanding,generation,and reasoning across multiple *** these achieve-ments,LLMs have inherent limitations including outdated information,hallucinations,inefficiency,lack of interpretability,and challenges in domain-specific *** address these issues,this survey explores three promising directions in the post-LLM era:knowledge empowerment,model collaboration,and model ***,we examine methods of integrating external knowledge into LLMs to enhance factual accuracy,reasoning capabilities,and interpretability,including incorporating knowledge into training objectives,instruction tuning,retrieval-augmented inference,and knowledge ***,we discuss model collaboration strategies that leverage the complementary strengths of LLMs and smaller models to improve efficiency and domain-specific performance through techniques such as model merging,functional model collaboration,and knowledge ***,we delve into model co-evolution,in which multiple models collaboratively evolve by sharing knowledge,parameters,and learning strategies to adapt to dynamic environments and tasks,thereby enhancing their adaptability and continual *** illustrate how the integration of these techniques advances AI capabilities in science,engineering,and society—particularly in hypothesis development,problem formulation,problem-solving,and interpretability across various *** conclude by outlining future pathways for further advancement and applications.

关键词： Artificial intelligence Large language models Knowledge empowerment Model collaboration Model co-evolution

来源：评论

学校读者我要写书评

暂无评论

Prompt Learning for Few-Shot Question Answering via Self-Context Data Augmentation

IEEE Transactions on Artificial Intelligence

引用

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

Two-view attention-guided convolutional neural network for mammographic image classification

引用

CAAI Transactions on Intelligence technology 2023年第2期8卷 453-467页

作者： Lilei Sun Jie Wen Junqian Wang Yong Zhao Bob Zhang Jian Wu Yong Xu College of Computer Science and Technology Guizhou UniversityGuiyangChina Shenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of TechnologyShenzhenChina Harbin Institute of Technology ShenzhenChina School of Electronic and Computer Engineering Shenzhen Graduate School of Peking UniversityShenzhenChina Department of Computer and Information Science University of MacaoTaipaChina Science for Life Laboratory KTH Royal Institute of TechnologyStockholmSweden

Deep learning has been widely used in the field of mammographic image classification owing to its superiority in automatic feature ***,general deep learning models cannot achieve very satisfactory classification results on mammographic images because these models are not specifically designed for mammographic images and do not take the specific traits of these images into *** exploit the essential discriminant information of mammographic images,we propose a novel classification method based on a convolutional neural ***,the proposed method designs two branches to extract the discriminative features from mammographic images from the mediolateral oblique and craniocaudal(CC)mammographic *** features extracted from the two-view mammographic images contain complementary information that enables breast cancer to be more easily ***,the attention block is introduced to capture the channel-wise information by adjusting the weight of each feature map,which is beneficial to emphasising the important features of mammographic ***,we add a penalty term based on the fuzzy cluster algorithm to the cross-entropy function,which improves the generalisation ability of the classification model by maximising the interclass distance and minimising the intraclass distance of the *** experimental results on The Digital database for Screening Mammography INbreast and MIAS mammography databases illustrate that the proposed method achieves the best classification performance and is more robust than the compared state-ofthe-art classification methods.

关键词： convolutional neural network deep learning medical image processing mammographic image

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Low-Light Image Enhancement Based on Explicit Denoising and Knowledge Distillation

引用

computers, Materials & Continua 2025年第2期82卷 2537-2554页

作者： Wenkai Zhang Hao Zhang Xianming Liu Xiaoyu Guo Xinzhe Wang Shuiwang Li College of Computer Science and Engineering Guilin University of TechnologyGuilin541006China Guangxi Key Laboratory of Embedded Technology and Intelligent System Guilin University of TechnologyGuilin541004China

Under low-illumination conditions, the quality of image signals deteriorates significantly, typically characterized by a peak signal-to-noise ratio (PSNR) below 10 dB, which severely limits the usability of the images. Supervised methods, which utilize paired high-low light images as training sets, can enhance the PSNR to around 20 dB, significantly improving image quality. However, such data is challenging to obtain. In recent years, unsupervised low-light image enhancement (LIE) methods based on the Retinex framework have been proposed, but they generally lag behind supervised methods by 5–10 dB in performance. In this paper, we introduce the Denoising-Distilled Retine (DDR) method, an unsupervised approach that integrates denoising priors into a Retinex-based training framework. By explicitly incorporating denoising, the DDR method effectively addresses the challenges of noise and artifacts in low-light images, thereby enhancing the performance of the Retinex framework. The model achieved a PSNR of 19.82 dB on the LOL dataset, which is comparable to the performance of supervised methods. Furthermore, by applying knowledge distillation, the DDR method optimizes the model for real-time processing of low-light images, achieving a processing speed of 199.7 fps without incurring additional computational costs. While the DDR method has demonstrated superior performance in terms of image quality and processing speed, there is still room for improvement in terms of robustness across different color spaces and under highly resource-constrained conditions. Future research will focus on enhancing the model’s generalizability and adaptability to address these challenges. Our rigorous testing on public datasets further substantiates the DDR method’s state-of-the-art performance in both image quality and processing speed.

关键词： Deep learning low-light image enhancement real-time processing knowledge distillation

来源：评论

学校读者我要写书评

暂无评论

The quantum Ising model for perfect matching and solving it with variational quantum eigensolver

引用

science China(Information sciences) 2024年第9期67卷 306-320页

作者： Qilin ZHENG Pingyu ZHU Chao WU Miaomiao YU Weihong LUO Ping XU Institute for Quantum Information and State Key Laboratory of High Performance Computing College of Computer Science and Technology National University of Defense Technology Hefei National Laboratory

Obtaining all perfect matchings of a graph is a tough problem in graph theory, and its complexity belongs to the #P-Complete class. The problem is closely related to combinatorics, marriage matching problems, dense subgraphs, the Gaussian boson sampling, chemical molecular structures, and dimer *** this paper, we propose a quadratic unconstrained binary optimization formula of the perfect matching problem and translate it into the quantum Ising model. We can obtain all perfect matchings by mapping them to the ground state of the quantum Ising Hamiltonian and solving it with the variational quantum eigensolver. Adjusting the model's parameters can also achieve the maximum or minimum weighted perfect matching. The experimental results on a superconducting quantum computer of the Origin Quantum Computing technology Company show that our model can encode 2~n dimensional optimization space with only O（n） qubits consumption and achieve a high success probability of the ground state corresponding to all perfect matchings. In addition, the further simulation results show that the model can support a scale of more than 14 qubits, effectively resist the adverse effects of noise, and obtain a high success probability at a shallow variational depth. This method can be extended to other combinatorial optimization problems.

关键词： perfect matching Ising model quantum Hamiltonian variational quantum eigensolver quadratic unconstrained binary optimization

来源：评论

学校读者我要写书评

暂无评论

A Novel Energy and Communication Aware Scheduling on Green Cloud Computing

引用

computers, Materials & Continua 2023年第12期77卷 2791-2811页

作者： Laila Almutairi Shabnam Mohamed Aslam Department of Computer Engineering Computer Science and Information Technology CollegeMajmaah UniversityAl Majmaah11952Saudi Arabia Department of Information Technology Computer Science and Information Technology CollegeMajmaah UniversityAl Majmaah11952Saudi Arabia

The rapid growth of service-oriented and cloud computing has created large-scale data centres *** data centres’operating costs mostly come from back-end cloud infrastructure and energy *** cloud computing,extensive communication resources are ***,cloud applications require more bandwidth to transfer large amounts of data to satisfy end-user *** is also essential that no communication source can cause congestion or bag loss owing to unnecessary switching *** paper proposes a novel Energy and Communication(EC)aware scheduling(EC-scheduler)algorithm for green cloud computing,which optimizes data centre energy consumption and traffic *** primary goal of the proposed EC-scheduler is to assign user applications to cloud data centre resources with minimal utilization of data *** first introduce a Multi-Objective Leader Salp Swarm(MLSS)algorithm for task sorting,which ensures traffic load balancing,and then an Emotional Artificial Neural Network(EANN)for efficient resource ***-scheduler schedules cloud user requirements to the cloud server by optimizing both energy and communication delay,which supports the lower emission of carbon dioxide by the cloud server system,enabling a green,unalloyed *** tested the proposed plan and existing cloud scheduling methods using the GreenCloud simulator to analyze the efficiency of optimizing data centre energy and other scheduler *** EC-scheduler parameters Power Usage Effectiveness(PUE),Data Centre Energy Productivity(DCEP),Throughput,Average Execution Time(AET),Energy Consumption,and Makespan showed up to 26.738%,37.59%,50%,4.34%,34.2%,and 33.54%higher efficiency,respectively,than existing state of the art schedulers concerning number of user applications and number of user requests.

关键词： EC-scheduler green cloud energy efficiency task scheduling task sorting resource allocation

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Signal Detection for Quadrature Spatial Modulation System

引用

China Communications 2024年第10期21卷 78-85页

作者： Shu Dingyun Peng Yuyang Yue Ming Fawaz AL-Hazemi Mohammad Meraj Mirza School of Computer Science and Engineering Macao University of Science and TechnologyMacaoChina Department of Computer and Network Engineering University of JeddahSaudi Arabia Department of Computer Science College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif 21944Saudi Arabia

With the development of communication systems, modulation methods are becoming more and more diverse. Among them, quadrature spatial modulation(QSM) is considered as one method with less capacity and high efficiency. In QSM, the traditional signal detection methods sometimes are unable to meet the actual requirement of low complexity of the system. Therefore, this paper proposes a signal detection scheme for QSM systems using deep learning to solve the complexity problem. Results from the simulations show that the bit error rate performance of the proposed deep learning-based detector is better than that of the zero-forcing(ZF) and minimum mean square error(MMSE) detectors, and similar to the maximum likelihood(ML) detector. Moreover, the proposed method requires less processing time than ZF, MMSE,and ML.

关键词： bit error rate complexity deep learning quadrature spatial modulation

来源：评论

学校读者我要写书评

暂无评论

Stochastic Augmented-Based Dual-Teaching for Semi-Supervised Medical Image Segmentation

引用

computers, Materials & Continua 2025年第1期82卷 543-560页

作者： Hengyang Liu Yang Yuan Pengcheng Ren Chengyun Song Fen Luo School of Computer Science and Engineering Chongqing University of TechnologyChongqing400054China College of Artificial Intelligence Chongqing Technology and Business UniversityChongqing400067China

Existing semi-supervisedmedical image segmentation algorithms use copy-paste data augmentation to correct the labeled-unlabeled data distribution ***,current copy-paste methods have three limitations:(1)training the model solely with copy-paste mixed pictures from labeled and unlabeled input loses a lot of labeled information;(2)low-quality pseudo-labels can cause confirmation bias in pseudo-supervised learning on unlabeled data;(3)the segmentation performance in low-contrast and local regions is less than *** design a Stochastic Augmentation-Based Dual-Teaching Auxiliary Training Strategy(SADT),which enhances feature diversity and learns high-quality features to overcome these *** be more precise,SADT trains the Student Network by using pseudo-label-based training from Teacher Network 1 and supervised learning with labeled data,which prevents the loss of rare labeled *** introduce a bi-directional copy-pastemask with progressive high-entropy filtering to reduce data distribution disparities and mitigate confirmation bias in *** the mixed images,Deep-Shallow Spatial Contrastive Learning(DSSCL)is proposed in the feature spaces of Teacher Network 2 and the Student Network to improve the segmentation capabilities in low-contrast and local *** this procedure,the features retrieved by the Student Network are subjected to a random feature perturbation *** two openly available datasets,extensive trials show that our proposed SADT performs much better than the state-ofthe-art semi-supervised medical segmentation *** only 10%of the labeled data for training,SADT was able to acquire a Dice score of 90.10%on the ACDC(Automatic Cardiac Diagnosis Challenge)dataset.

关键词： Semi-supervised medical image segmentation contrastive learning stochastic augmented

来源：评论

学校读者我要写书评

暂无评论

Inhibiting plastic tensile instability of non-symmetric thin-walled shell component via increasing regional metal inflow based on heterogeneous pressure-carrying medium

引用

Chinese Journal of Aeronautics 2024年第1期37卷 391-413页

作者： Nan XIANG Yiquan SHU Pengyi WANG Menghan YANG Haoran WANG Tao HUANG Junqing GUO Fuxiao CHEN School of Materials Science and Engineering Henan University of Science and TechnologyLuoyang 471023China National Key Laboratory for Precision Heat Processing of Metals School of Materials Science and EngineeringHarbin Institute of TechnologyHarbin 150001China College of Mechanical&Electrical Engineering Shaanxi University of Science&TechnologyXi’an 710021China Provincial and Ministerial Co-construction of Collaborative Innovation Center for Non-ferrous Metal new Materials and Advanced Processing Technology Luoyang 471023China

Heterogeneous pressure-carrying medium was employed to establish a differentiated pressure field on sheet metal in flexible die forming process in this work,which aimed at matching the non-symmetric shape of target component and improving metal inflow to avoid local tensile ***,metal inflow corresponding to the differentiated pressure field was analytically *** of a typical non-symmetric shell component was experimentally and numerically studied based on the proposed *** with forming processes based on the uniform pressure,difference of metal inflow in two sides of the non-symmetric component increased from 2.16 mm to 3.36 mm and metal inflow in critical region increased by 11.9%when differentiated pressure field(taking heterogeneous elastomer#4–3 for example)was *** resultant maximum thinning ratio decreased by 4.2% and the uniformity of shell thickness increased by 16.9%.With the decrease of Shore hardness of elastomer in the formed region,stress path in the ready-to-form region transferred towards the bi-axial tension stress state,i.e.,stress ratio(a)***,stress triaxiality(η)in characteristic regions were regulated appropriately,which decreased the risk of tensile *** was attributed to the decreased normal pressure and frictional resistance at sheet/elastomer interface in the formed region.

关键词： Aluminum alloys Finite element method Metal forming Plastic deformation Sheet metal

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：