检索结果-南通市图书馆

Knowledge Distillation via Hierarchical Matching for Small Object Detection

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of computer science & Technology 2024年第4期39卷 798-810页

作者： Yong-Chi Ma Xiao Ma Tian-Ran Hao Li-Sha Cui Shao-Hui Jin Pei Lyu School of computer science and artificial intelligence Zhengzhou UniversityZhengzhou 450000China

Knowledge distillation is often used for model compression and has achieved a great breakthrough in image classification,but there still remains scope for improvement in object detection,especially for knowledge extraction of small *** main problem is the features of small objects are often polluted by background noise and not prominent due to down-sampling of convolutional neural network(CNN),resulting in the insufficient refinement of small object features during *** this paper,we propose Hierarchical Matching Knowledge Distillation Network(HMKD)that operates on the pyramid level P2 to pyramid level P4 of the feature pyramid network(FPN),aiming to intervene on small object features before *** employ an encoder-decoder network to encapsulate low-resolution,highly semantic information,akin to eliciting insights from profound strata within a teacher network,and then match the encapsulated information with high-resolution feature values of small objects from shallow layers as the *** this period,we use an attention mechanism to measure the relevance of the inquiry to the feature *** in the process of decoding,knowledge is distilled to the *** addition,we introduce a supplementary distillation module to mitigate the effects of background *** show that our method achieves excellent improvements for both one-stage and twostage object ***,applying the proposed method on Faster R-CNN achieves 41.7%mAP on COCO2017(ResNet50 as the backbone),which is 3.8%higher than that of the baseline.

关键词： knowledge distillation object detection small object detection machine learning

RepBoTNet-CESA:An Alzheimer’s Disease computer Aided Diagnosis Method Using Structural Reparameterization BoTNet and Cubic Embedding Self Attention

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

computers, Materials & Continua 2024年第5期79卷 2879-2905页

作者： Xiabin Zhang Zhongyi Hu Lei Xiao Hui Huang college of computer science and artificial intelligence Wenzhou UniversityWenzhou325035China Key Laboratory of intelligence Image Processing and Analysis Wenzhou UniversityWenzhou325035China

Various deep learning models have been proposed for the accurate assisted diagnosis of early-stage Alzheimer’s disease(AD).Most studies predominantly employ Convolutional Neural Networks(CNNs),which focus solely on local features,thus encountering difficulties in handling global *** contrast to natural images,Structural Magnetic Resonance Imaging(sMRI)images exhibit a higher number of channel ***,during the Position Embedding stage ofMulti Head Self Attention(MHSA),the coded information related to the channel dimension is *** tackle these issues,we propose theRepBoTNet-CESA network,an advanced AD-aided diagnostic model that is capable of learning local and global features *** combines the advantages of CNN networks in capturing local information and Transformer networks in integrating global information,reducing computational costs while achieving excellent classification ***,it uses the Cubic Embedding Self Attention(CESA)proposed in this paper to incorporate the channel code information,enhancing the classification performance within the Transformer ***,the RepBoTNet-CESA performs well in various AD-aided diagnosis tasks,with an accuracy of 96.58%,precision of 97.26%,and recall of 96.23%in the AD/NC task;an accuracy of 92.75%,precision of 92.84%,and recall of 93.18%in the EMCI/NC task;and an accuracy of 80.97%,precision of 83.86%,and recall of 80.91%in the AD/EMCI/LMCI/NC *** demonstrates that RepBoTNet-CESA delivers outstanding outcomes in various AD-aided diagnostic ***,our study has shown that MHSA exhibits superior performance compared to conventional attention mechanisms in enhancing ResNet ***,the Deeper RepBoTNet-CESA network fails to make further progress in AD-aided diagnostic tasks.

关键词： Alzheimer CNN structural reparameterization multi head self attention computer aided diagnosis

Expression Recognition Method Based on Convolutional Neural Network and Capsule Neural Network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

computers, Materials & Continua 2024年第4期79卷 1659-1677页

作者： Zhanfeng Wang Lisha Yao School of computer science and artificial intelligence Chaohu UniversityHefei238000China School of Big Data and artificial intelligence Anhui Xinhua UniversityHefei230088China

Convolutional neural networks struggle to accurately handle changes in angles and twists in the direction of images,which affects their ability to recognize patterns based on internal feature levels. In contrast, CapsNet overcomesthese limitations by vectorizing information through increased directionality and magnitude, ensuring that spatialinformation is not overlooked. Therefore, this study proposes a novel expression recognition technique calledCAPSULE-VGG, which combines the strengths of CapsNet and convolutional neural networks. By refining andintegrating features extracted by a convolutional neural network before introducing theminto CapsNet, ourmodelenhances facial recognition capabilities. Compared to traditional neural network models, our approach offersfaster training pace, improved convergence speed, and higher accuracy rates approaching stability. Experimentalresults demonstrate that our method achieves recognition rates of 74.14% for the FER2013 expression dataset and99.85% for the CK+ expression dataset. By contrasting these findings with those obtained using conventionalexpression recognition techniques and incorporating CapsNet’s advantages, we effectively address issues associatedwith convolutional neural networks while increasing expression identification accuracy.

关键词： Expression recognition capsule neural network convolutional neural network

Retrieval-and-alignment based large-scale indoor point cloud semantic segmentation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

science China(Information sciences) 2024年第4期67卷 164-180页

作者： Zongyi XU Xiaoshui HUANG Bo YUAN Yangfu WANG Qianni ZHANG Weisheng LI Xinbo GAO School of computer science and Technology Chongqing University of Posts and Telecommunications Shanghai artificial intelligence Laboratory School of Electronic Engineering and computer science Queen Mary University of London

Current methods for point cloud semantic segmentation depend on the extraction of descriptive features. However, unlike images, point clouds are irregular and often lack texture information, making it demanding to extract discriminative features. In addition, noise, outliers, and uneven point distribution are commonly present in point clouds, which further complicates the segmentation task. To address these problems, a novel architecture is proposed for direct and accurate large-scale point cloud segmentation based on point cloud retrieval and alignment. The proposed approach involves using a feature-based point cloud retrieval method for searching for reference point clouds with annotations from a dataset. In the following segmentation stage, an overlap-based point cloud registration method has been developed to align the target and reference point clouds. For accurate and robust alignment, an overlap region estimation module is trained to locate the optimal overlap region between two pieces of point clouds in a coarse-to-fine manner. In the detected overlap region, the global and local features of the points are extracted and combined for featuremetric registration to obtain accurate transformation parameters between the target and reference point clouds. After alignment, the annotated segmentation of the reference is transferred to the target point clouds to obtain accurate segmentation results. Extensive experiments are conducted to show that the developed method outperforms the state-of-the-art approaches in terms of both accuracy and robustness against noise and outliers.

关键词： point cloud semantic segmentation large-scale indoor point clouds point cloud alignment overlap estimation label transfer

A novel graph oversampling framework for node classification in class-imbalanced graphs

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

science China(Information sciences) 2024年第6期67卷 214-229页

作者： Riting XIA Chunxu ZHANG Yan ZHANG Xueyan LIU Bo YANG Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University college of artificial intelligence Jilin University college of computer science and Technology Jilin University college of Communication Engineering Jilin University

Graph neural network(GNN) is a promising method to analyze graphs. Most existing GNNs adopt the class-balanced assumption, which cannot deal with class-imbalanced graphs well. The oversampling technique is effective in alleviating class-imbalanced problems. However, most graph oversampling methods generate synthetic minority nodes and their edges after applying GNNs. They ignore the problem that the representations of the original and synthetic minority nodes are dominated by majority nodes caused by aggregating neighbor information through GNN before oversampling. In this paper, we propose a novel graph oversampling framework, termed distribution alignment-based oversampling for node classification in classimbalanced graphs(named Graph-DAO). Our framework generates synthetic minority nodes before GNN to avoid the dominance of majority nodes caused by message passing in GNNs. Additionally, we introduce a distribution alignment method based on the sum-product network to learn more information about minority nodes. To our best knowledge, it is the first to use the sum-product network to solve the class-imbalanced problem in node classification. A large number of experiments on four real datasets show that our method achieves the optimal results on the node classification task for class-imbalanced graphs.

关键词： graph neural network class-imbalanced graphs sum-product network oversampling node classification

Formal Verification of Data Modifications in Cloud Block Storage Based on Separation Logic

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2024年第1期33卷 112-127页

作者： Bowen ZHANG Zhao JIN Hanpin WANG Yongzhi CAO Key Laboratory of High Confidence Software Technologies (MOE) School of Computer Science Peking University School of computer and artificial intelligence Zhengzhou University School of computer science and Cyber Engineering Guangzhou University

Cloud storage is now widely used, but its reliability has always been a major concern. Cloud block storage(CBS) is a famous type of cloud storage. It has the closest architecture to the underlying storage and can provide interfaces for other types. Data modifications in CBS have potential risks such as null reference or data *** verification of these operations can improve the reliability of CBS to some extent. Although separation logic is a mainstream approach to verifying program correctness, the complex architecture of CBS creates some challenges for verifications. This paper develops a proof system based on separation logic for verifying the CBS data modifications. The proof system can represent the CBS architecture, describe the properties of the CBS system state, and specify the behavior of CBS data modifications. Using the interactive verification approach from Coq, the proof system is implemented as a verification tool. With this tool, the paper builds machine-checked proofs for the functional correctness of CBS data modifications. This work can thus analyze the reliability of cloud storage from a formal perspective.

关键词： Cloud computing Behavioral sciences Reliability Formal verification

A Novel Predictive Model for Edge Computing Resource Scheduling Based on Deep Neural Network

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

computer Modeling in Engineering & sciences 2024年第4期139卷 259-277页

作者： Ming Gao Weiwei Cai Yizhang Jiang Wenjun Hu Jian Yao Pengjiang Qian School of artificial intelligence and computer science Jiangnan UniversityWuxi214122China The Center for Intelligent Systems and Applications Research School of Artificial Intelligence and Computer ScienceJiangnan UniversityWuxi214122China School of Information Engineering Huzhou UniversityHuzhou313000China

Currently,applications accessing remote computing resources through cloud data centers is the main mode of operation,but this mode of operation greatly increases communication latency and reduces overall quality of service(QoS)and quality of experience(QoE).Edge computing technology extends cloud service functionality to the edge of the mobile network,closer to the task execution end,and can effectivelymitigate the communication latency ***,the massive and heterogeneous nature of servers in edge computing systems brings new challenges to task scheduling and resource management,and the booming development of artificial neural networks provides us withmore powerfulmethods to alleviate this ***,in this paper,we proposed a time series forecasting model incorporating Conv1D,LSTM and GRU for edge computing device resource scheduling,trained and tested the forecasting model using a small self-built dataset,and achieved competitive experimental results.

关键词： Edge computing resource scheduling predictive models

A multi-stream network for retrosynthesis prediction

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of computer science 2024年第2期18卷 231-233页

作者： Qiang ZHANG Juan LIU Wen ZHANG Feng YANG Zhihui YANG Xiaolei ZHANG Institute of artificial intelligence School of Computer ScienceWuhan UniversityWuhan 430072China college of Informatics Huazhong Agricultural UniversityWuhan 430072China

1 Introduction Retrosynthesis aims to predict a set of reactants for producing given molecules[1],which plays a significant part in the biochemistry field,such as molecular pathway design and drug *** existing methods perform better in solving this problem,most of these methods[2,3]only describe the molecules from one kind of perspective,such as they use Simplified Molecular Input Line Entry System(SMILES)strings[4]to represent the atomic components and the relationship between atoms of molecules or leverage Extended Connectivity Fingerprints(ECFPs)represent the information of the molecular sub-structure composition via binary vectors[5].

关键词： synthesis reactant hough

Internet of Things Enabled DDoS Attack Detection Using Pigeon Inspired Optimization Algorithm with Deep Learning Approach

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

computers, Materials & Continua 2024年第9期80卷 4047-4064页

作者： Turki Ali Alghamdi Saud S.Alotaibi Department of computer science and artificial intelligence College of ComputingUmm Al-Qura UniversityMakkah21955Saudi Arabia

Internet of Things(IoTs)provides better solutions in various fields,namely healthcare,smart transportation,home,*** Denial of Service(DoS)outbreaks in IoT platforms is significant in certifying the accessibility and integrity of IoT *** learning(DL)models outperform in detecting complex,non-linear relationships,allowing them to effectually severe slight deviations fromnormal IoT activities that may designate a DoS *** uninterrupted observation and real-time detection actions of DL participate in accurate and rapid detection,permitting proactive reduction events to be executed,hence securing the IoT network’s safety and ***,this study presents pigeon-inspired optimization with a DL-based attack detection and classification(PIODL-ADC)approach in an IoT *** PIODL-ADC approach implements a hyperparameter-tuned DL method for Distributed Denial-of-Service(DDoS)attack detection in an IoT ***,the PIODL-ADC model utilizes Z-score normalization to scale input data into a *** handling the convolutional and adaptive behaviors of IoT,the PIODL-ADCmodel employs the pigeon-inspired optimization(PIO)method for feature selection to detect the related features,considerably enhancing the recognition’s ***,the Elman Recurrent Neural Network(ERNN)model is utilized to recognize and classify DDoS ***,reptile search algorithm(RSA)based hyperparameter tuning is employed to improve the precision and robustness of the ERNN method.A series of investigational validations is made to ensure the accomplishment of the PIODL-ADC *** experimental outcome exhibited that the PIODL-ADC method shows greater accomplishment when related to existing models,with a maximum accuracy of 99.81%.

关键词： Internet of things denial of service deep learning reptile search algorithm feature selection