检索结果-内蒙古大学图书馆

IAENG International Journal of Computer Science 2024年第9期51卷 1385-1392页

作者： Yang, Zhen Zhou, Ziwei Wang, Chaoyang Xu, Liang School of Applied Technology University of Science and Technology Liaoning Anshan China School of Computer and Software Engineering University of Science and Technology Liaoning Anshan China School of Computer and Software Engineering University of Science and Technology Liaoning Anshan China

This paper introduces a new network model - the Image Guidance Encoder-Decoder Model (IG-ED), designed to enhance the efficiency of image captioning and improve predictive accuracy. IG-ED, a fusion of the convolutional network VGGNet-16 and the long short-term memory network (LSTM), is designed based on the encoder-decoder structure. The image captioning performance sees significant enhancements when leveraging the IG-ED network model. The network training process unfolds in a series of steps. Initially, the input image undergoes convolution via the VGGNet-16 network, producing a 512-dimensional vector. Concurrently, each word in the image's caption is encoded to generate a corresponding 512-dimensional vector consistent with the image feature dimension. These two vectors form the input for the decoding process. Subsequently, the vectors are fed into the redesigned fusion LSTM (F-LSTM) network at different time steps to gradually train the parameters of the IG-ED framework. The training process is completed by utilizing a loss function for determining convergence. Evaluation of the IG-ED model's performance is conducted using CIDEr and seven other evaluation metrics on the MSCOCO 2014 dataset. The results exhibit substantial improvements over the "Adaptive Attention Mode" network and "Neural Talk" network. Additionally, the parameter count of the IG-ED architecture is significantly reduced compared to the "Adaptive Attention Mode" network, leading to decreased computational resource requirements and enabling edge computing on the neural network. © (2024), (International Association of Engineers). All Rights Reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Adaptive-basis decomposition-based low-rank network for efficient non-uniform motion deblurring

引用

Optoelectronics Letters 2025年第1期21卷 43-50页

作者： CHEN Lei XIONG Qingbo ZHANG Wei LI Runde School of Software Henan UniversityKaifeng 475004China School of Applied Technology China University of Labor RelationsBeijing 100048China

In this study,we present a unified sparsity-driven framework that significantly enhances motion deblurring performance by integrating two key components:a custom-designed dataset and a low-rank module(LRM).This framework leverages the inherent sparsity of per-pixel blur kernels to bolster both deblurring accuracy and model ***,we propose an adaptive-basis decomposition-based deblurring(ADD)approach,which constructs a tailored training dataset to enhance the generalization capacity of the deblurring *** ADD framework adaptively decomposes motion blur into sparse basis elements,effectively addressing the intricacies associated with non-uniform ***,an LRM is proposed to improve the interpretability of deblurring models as a plug-and-play module,primarily designed to identify and harness the intrinsic sparse features in sharp images.A series of ablation studies have been conducted to substantiate the synergistic advantages of combining the proposed ADD with the LRM for overall improvement in deblurring ***,we empirically demonstrate through rigorous experimentation that incorporating the LRM into an existing Uformer network leads to substantial enhancement in reconstruction *** integration yields a sparsity-guided low-rank network(SGLRN).Operating under the overarching principle of sparsity,SGLRN consistently outperforms state-of-the-art methods across multiple standard deblurring *** experimental results,assessed through quantitative metrics and qualitative visual evaluations,provide compelling evidence of its *** overall deblurring results are available at Google Drive.

关键词： network motion uniform

来源：评论

学校读者我要写书评

暂无评论

A Neural Network Slab Quality Prediction Analysis Based on a Hybrid Intelligent Optimisation Algorithm

IAENG International Journal of Computer Science

引用

IAENG International Journal of Computer Science 2025年第3期52卷 673-683页

作者： Li, Yiran Zhang, Chunna School of Applied Technology University of Science and Technology Liaoning Liaoning Anshan114051 China School of Computer Science and Software Engineering University of Science and Technology Liaoning Liaoning Anshan114051 China

To address the problem of inaccurate prediction of slab quality in continuous casting, an algorithm based on particle swarm optimisation and differential evolution is proposed. The algorithm combines BP neural network prediction method. Firstly, the factors affecting the quality of the slab are analysed and a sufficient number of sample sets are extracted for training;Secondly, the particle swarm optimisation algorithm is optimised, and then the BP neural network is optimised and the chaos mechanism is introduced to increase the continuity of motion of the particles. The population is partitioned hierarchically, and different types of particles are processed separately to improve the global search capability of the algorithm. The differential evolution algorithm is also integrated to optimise cross-selection and increase particle diversity. Finally, a prediction model is built to predict and analyse the sample data. In the experiment, three algorithms are tested for different benchmark functions, namely the comparison of convergence, stability and searchability. The optimisation time comparison is completed, the target curve fit test is performed and the slab quality test results are checked. The experimental results show that the PSO-EIDE algorithm has strong optimisation ability, fast convergence speed and obvious improvement in stability and accuracy. © (2025), (International Association of Engineers). All rights reserved.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Classifying extended,localized and critical states in quasiperiodic lattices via unsupervised learning

引用

Chinese Physics B 2025年第1期34卷 422-427页

作者： Bohan Zheng Siyu Zhu Xingping Zhou Tong Liu School of Computer Science and Technology School of SoftwareNanjing University of Posts and TelecommunicationsNanjing 210023China Institute of Quantum Information and Technology Nanjing University of Posts and TelecommunicationsNanjing 210003China Department of Applied Physics School of ScienceNanjing University of Posts and TelecommunicationsNanjing 210003China

Classification of quantum phases is one of the most important areas of research in condensed matter *** this work,we obtain the phase diagram of one-dimensional quasiperiodic models via unsupervised ***,we choose two advanced unsupervised learning algorithms,namely,density-based spatial clustering of applications with noise(DBSCAN)and ordering points to identify the clustering structure(OPTICS),to explore the distinct phases of the Aubry–André–Harper model and the quasiperiodic p-wave *** unsupervised learning results match well with those obtained through traditional numerical ***,we assess similarity across different algorithms and find that the highest degree of similarity between the results of unsupervised learning algorithms and those of traditional algorithms exceeds 98%.Our work sheds light on applications of unsupervised learning for phase classification.

关键词： quantum phase quasiperiodic machine learning

来源：评论

学校读者我要写书评

暂无评论

Advancing Evasion: Distributed Backdoor Attacks in Federated Learning 25th

Advancing Evasion: Distributed Backdoor Attacks in Federate...

引用

25th International Conference on Parallel and Distributed Computing, Applications and Technologies, PDCAT 2024

作者： Wang, Jian Shen, Hong Ke, Wei Faculty of Applied Sciences Macao Polytechnic University China School of Engineering and Technology Central Queensland University Rockhampton Australia School of Software Technology Guangzhou Institute of Software Guangzhou China

ISBN: (纸本)9789819642069

Federated Learning (FL) is vulnerable to backdoor attacks through data poisoning if the data is not scrutinized, as malicious participants can inject backdoor triggers in normal samples, leading to poisoned updates. Distributed backdoor attacks pose a greater threat than centralized ones, as they often use fixed pixel blocks as triggers, increasing the risk of detection. This paper presents a novel distributed backdoor attack strategy that leverages edge structure poisoning to circumvent existing defense mechanisms, employing a distributed poisoning strategy to evade current defense mechanisms, thereby enhancing the stealth of the attack. Experimental results on multiple benchmark datasets demonstrate that this method is more effective and stealthy compared to other backdoor attack methods. Furthermore, this paper also proposes targeted defense strategies based on the experimental results, offering a new perspective on the security of FL systems. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

ONNXPruner: ONNX-Based General Model Pruning Adapter

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第7期47卷 5806-5817页

作者： Ren, Dongdong Li, Wenbin Ding, Tianyu Wang, Lei Fan, Qi Huo, Jing Pan, Hongbing Gao, Yang Nanjing University School of Electronic Science and Engineering China Nanjing University State Key Laboratory for Novel Software Technology School of Intelligence Science and Technology China Microsoft Corporation Applied Sciences Group RedmondWA98052 United States University of Wollongong School of Computing and Information Technology NSW2522 Australia

Recent advancements in model pruning have focused on developing new algorithms and improving upon benchmarks. However, the practical application of these algorithms across various models and platforms remains a significant challenge. To address this challenge, we propose ONNXPruner, a versatile pruning adapter designed for the ONNX format models. ONNXPruner streamlines the adaptation process across diverse deep learning frameworks and hardware platforms. A novel aspect of ONNXPruner is its use of node association trees, which automatically adapt to various model architectures. These trees clarify the structural relationships between nodes, guiding the pruning process, particularly highlighting the impact on interconnected nodes. Furthermore, we introduce a tree-level evaluation method. By leveraging node association trees, this method allows for a comprehensive analysis beyond traditional single-node evaluations, enhancing pruning performance without the need for extra operations. Experiments across multiple models and datasets confirm ONNXPruner's strong adaptability and increased efficacy. Our work aims to advance the practical application of model pruning. © 1979-2012 IEEE.

关键词： Adaptation Models Training Filters Deep Learning Computational Modeling software Interoperability Load Modeling software Algorithms Electronic Mail General Model Pruning ONNX Tree Level Evaluation Deep Neural Network Model Pruning Deep Learning Model Architecture Deep Learning Framework Hardware Platform Superior Performance Deep Neural Network Feature Maps Py Torch Image Net Training Images Sparse Matrix Root Node Type Of Operation Single Node Deep Neural Network Model Validation Images Extra Components Importance Of Filtering Pruning Method Squeeze Net

来源：评论

学校读者我要写书评

暂无评论

Numerical study on micro-fracture mechanism of rock dynamic failureinduced by abrupt unloading under high in-situ stresses

引用

Theoretical & applied Mechanics Letters 2024年第6期14卷 486-495页

作者： Yuezong Yang Anye Li Zhushan Shao Kui Wu Wei Wei Wenhui Du Yujie Wang School of Science Xi’an University of Architecture and TechnologyXi’an 710055China CAEP Software Center for High Performance Numerical Simulation Institute of Applied Physics and Computational Mathematics BeijingBeijing 100088China

Rock burst is a kind of severe engineering disaster resulted from dynamic fracture process of *** macrofailure behaviors of rocks are primarily formed after experiencing the initiation,propagation,and coalescenceof *** this paper,the grain-based discretized virtual internal bond model is employed to investigatethe fracturing process of unloaded rock under high in-situ stresses from the micro-fracture *** micro-fracturing process reveals that the longitudinal stress waves induced by unloading lead to thevisible unloading *** influences of in-situ stresses,mineral grain sizes,and grain heterogeneity on rockmacro and micro fracture are ***-crack areas of tensile and shear cracks and micro-crack anglesare statistically analyzed to reveal the rock micro-fracture *** simulated results indicate thatthe combined effect of the stress state transition and the unloading effect dominates the rock unloading *** vertical and horizontal in-situ stresses determine the stress state of surrounding rock after unloading andthe unloading effect,*** the vertical stress increases,the stress level after unloading is higher,andthe shear failure characteristics become more *** the horizontal stress increases,the unloading effectincreases,leading to the intensification of tensile *** mineral grain size and grain heterogeneity alsohave nonnegligible influences on rock unloading *** micro-fracture perspective provides further insightinto the unloading failure mechanism of deep rock excavation.

关键词： Rock burst Micro-fracture Dynamic failure Unloading effect

来源：评论

学校读者我要写书评

暂无评论

A Review on Air-Ground Coordination in Mobile Edge Computing:Key Technologies,Applications and Future Directions

引用

清华大学学报自然科学版（英文版） 2025年第3期30卷 1359-1386页

作者： Siqi Li Guoqiang Liu Li Li Zhongyuan Zhang Wenhao Fei Haolong Xiang School of Art Nanjing University of Information Science and TechnologyNanjing 210044China School of Software Nanjing University of Information Science and TechnologyNanjing 210044China College of Computer Science and Technology China University of Petroleum(East China)Qingdao 266555China School of Math and Applied Mathematics Nanjing University of Information Science and TechnologyNanjing 210044China

In recent years,Mobile Edge Computing(MEC)has received extensive research attention due to its characteristics,such as real-time data processing and flexible application ***,traditional MEC server deployment relies on the terrestrial Base Stations(BSs),resulting in high deployment costs and limited coverage *** response to these challenges,air-ground coordination has emerged,which effectively combines the advantages of edge computing and Unmanned Aerial Vehicles(UAVs),providing an effective architecture for edge *** utilizing the flexibility of UAVs and empowering them into edge nodes with computing resources,the coverage range of MEC can be expanded,thereby reducing the reliance of edge devices on terrestrial ***,leveraging terrestrial BSs as supplements to the computing power compensates for relatively limited computational capabilities of *** extensive studies have been conducted on air-ground coordination,there are few related summaries of application technologies and ***,the key technologies of air-ground coordination and applications are comprehensively reviewed in this ***,to provide guidance for interested researchers,the development trends and potential applications of air-ground coordination are explored.

关键词： air-ground coordination air-ground control air-ground perception emergency management resource management

来源：评论

学校读者我要写书评

暂无评论

Heterologous Image Matching Based on Salience Region

IAENG International Journal of Computer Science

引用

IAENG International Journal of Computer Science 2025年第4期52卷 894-900页

作者： Zhai, Jinlong Xu, Yang Yan, Xiaohu Computer Science and Software Engineering University of Science and Technology LiaoNing Anshan114051 China School of Computer Science and Software Engineering University of Science and Technology LiaoNing Anshan114051 China Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong-Macao Greater Bay Area Shenzhen Polytechnic University Shenzhen518055 China

To address the matching problem caused by the significant differences in spatial features, spectrum and contrast between heterologous images, a heterologous image matching method based on salience region is proposed in this paper. Firstly, texture features and corner features are detected. Secondly, the epanechnikov kernel function is used to calculate the point with the maximum kernel function value among all feature points, which is then defined as E-point. Thirdly, the salience region is defined and extracted according to the position of the E-point. Finally, six groups of heterologous images are used as data sources, and compared with HAPCG, HOWP, SIFT, and PSO_SIFT algorithms respectively. The results show that the comprehensive matching performance of the proposed method is better than the original algorithm without salience region processing. The root mean square error and the matching time are less than the original method while ensuring a similar number of matching points, which greatly improves the accuracy and speed of heterologous image matching. © (2025.0), (International Association of Engineers). All Rights Reserved.

关键词： Image matching

来源：评论

学校读者我要写书评

暂无评论

Boosting Adversarial Training with Learnable Distribution

引用

Computers, Materials & Continua 2024年第3期78卷 3247-3265页

作者： Kai Chen Jinwei Wang James Msughter Adeke Guangjie Liu Yuewei Dai School of Electronics and Information Engineering Nanjing University of Information Science and TechnologyNanjing210044China Key Laboratory of Intelligent Support Technology for Complex Environments Ministry of EducationNanjing210044China School of Computer and Software Nanjing University of Information Science and TechnologyNanjing210044China Nanjing Center for Applied Mathematics Nanjing211135China

In recent years,various adversarial defense methods have been proposed to improve the robustness of deep neural *** training is one of the most potent methods to defend against adversarial ***,the difference in the feature space between natural and adversarial examples hinders the accuracy and robustness of the model in adversarial *** paper proposes a learnable distribution adversarial training method,aiming to construct the same distribution for training data utilizing the Gaussian mixture *** distribution centroid is built to classify samples and constrain the distribution of the sample *** natural and adversarial examples are pushed to the same distribution centroid to improve the accuracy and robustness of the *** proposed method generates adversarial examples to close the distribution gap between the natural and adversarial examples through an attack algorithm explicitly designed for adversarial *** algorithm gradually increases the accuracy and robustness of the model by scaling ***,the proposed method outputs the predicted labels and the distance between the sample and the distribution *** distribution characteristics of the samples can be utilized to detect adversarial cases that can potentially evade the model *** effectiveness of the proposed method is demonstrated through comprehensive experiments.

关键词： Adversarial training feature space learnable distribution distribution centroid

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：