检索结果-内蒙古大学图书馆

Multi-Scale Feature Fusion Network Model for Wireless Capsule Endoscopic Intestinal Lesion Detection

computers, Materials & Continua 2025年第2期82卷 2415-2429页

作者： Shiren Ye Qi Meng Shuo Zhang Hui Wang School of Computer and Artificial Intelligence Changzhou UniversityChangzhou213164China

WCE (Wireless Capsule Endoscopy) is a new technology that combines computer vision and medicine, allowing doctors to visualize the conditions inside the intestines, achieving good diagnostic results. However, due to the complex intestinal environment and limited pixel resolution of WCE videos, lesions are not easily detectable, and it takes an experienced doctor 1–2 h to analyze a complete WCE video. The use of computer-aided diagnostic methods, assisting or even replacing manual WCE diagnosis, has significant application value. In response to the issue of intestinal lesion detection in WCE videos, this paper proposes a multi-scale feature fusion network model TSD-YOLO based on the YOLO (You Only Look Once) architecture: (I) a Tiny Detection Layer to avoid the loss of shallow feature information for tiny-scale targets;(II) integrating a simple, parameter-free attention module (SimAM) at the neck to better extract local lesion features and fuse features;(III) incorporating a new loss function DIoU (Distance Intersection over Union) to better achieve boundary box regression for target detection. This model was validated using the WCE dataset from Kyushu University Hospital. For the dataset containing 18,000 images, the evaluation metrics of our model for 12 types of lesions, outperformed existing reported results from advanced models on this dataset, and the mAP (mean Average Precision) and precision evaluation metrics improved by 3.7% and 0.9% over the benchmark model.

关键词： Deep learning wireless capsule endoscopy intestinal lesions YOLO

来源：评论

学校读者我要写书评

暂无评论

GATiT:An Intelligent Diagnosis Model Based on Graph Attention Network Incorporating Text Representation in Knowledge Reasoning

引用

computers, Materials & Continua 2024年第9期80卷 4767-4790页

作者： Yu Song Pengcheng Wu Dongming Dai Mingyu Gui Kunli Zhang School of Computer and Artificial Intelligence Zhengzhou UniversityZhengzhou450001China

The growing prevalence of knowledge reasoning using knowledge graphs(KGs)has substantially improved the accuracy and efficiency of intelligent medical ***,current models primarily integrate electronic medical records(EMRs)and KGs into the knowledge reasoning process,ignoring the differing significance of various types of knowledge in EMRs and the diverse data types present in the *** better integrate EMR text information,we propose a novel intelligent diagnostic model named the Graph ATtention network incorporating Text representation in knowledge reasoning(GATiT),which comprises text representation,subgraph construction,knowledge reasoning,and diagnostic *** the text representation process,GATiT uses a pre-trained model to obtain text representations of the EMRs and additionally enhances embeddings by including chief complaint information and numerical information in the *** the subgraph construction process,GATiT constructs text subgraphs and disease subgraphs from the KG,utilizing EMR text and the disease to be *** differentiate the varying importance of nodes within the subgraphs features such as node categories,relevance scores,and other relevant factors are introduced into the text ***-passing strategy and attention weight calculation of the graph attention network are adjusted to learn these features in the knowledge reasoning ***,in the diagnostic classification process,the interactive attention-based fusion method integrates the results of knowledge reasoning with text representations to produce the final diagnosis *** results on multi-label and single-label EMR datasets demonstrate the model’s superiority over several state-of-theart methods.

关键词： Intelligent diagnosis knowledge graph graph attention network knowledge reasoning

来源：评论

学校读者我要写书评

暂无评论

Knowledge Distillation via Hierarchical Matching for Small Object Detection

引用

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

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

来源：评论

学校读者我要写书评

暂无评论

Latent low-rank representation guided dual linear regression with different regression matrices for subspace learning

引用

Multimedia Tools and Applications 2025年 1-35页

作者： Zhang, Wentao Chen, Xiuhong School of Artificial Intelligence and Computer Science Jiangnan University Jiangsu Wuxi China

Linear regression model is one of the important learning models for classification tasks. However, the data from practical application inevitably contains some noise or is corrupted, which may lead to the decline of the learning performance of the regression model. To this end, this paper proposes two dual linear regression models based on latent low-rank representation for supervised and unsupervised cases respectively. Both models use the "clean" data to replace the original data and establish corresponding regression models, where the "clean" data learned from latent low rank representation consists of two parts, namely, the linear combination of all training samples and the linear combination of data features. It is noted that the two items in the "clean" data have different functions in reconstructing the original data matrix, so the two items in the models should have different regression coefficient matrices. Therefore, the proposed models make full use of the global structural and intrinsic feature information of the data samples, that is, the information in the row and column directions of the data matrix X, and are more robust to outliers or/and noise due to the regression of "clean" data. The iterative algorithm for solving these two models is designed by using the augmented Lagrange multiplier method based on alternating iteration method, and their convergence and computational complexity are analyzed. The comprehensive experimental results on multiple data sets also verify the effectiveness of the proposed methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Multiple linear regression

来源：评论

学校读者我要写书评

暂无评论

Deconfounded fashion image captioning with transformer and multimodal retrieval

引用

虚拟现实与智能硬件(中英文) 2025年第2期7卷 127-138页

作者： Tao PENG Weiqiao YIN Junping LIU Li LI Xinrong HU School of Computer Science and Artificial Intelligence Wuhan Textile UniversityWuhan 430200China

Background The annotation of fashion images is a significantly important task in the fashion industry as well as social media and ***,owing to the complexity and diversity of fashion images,this task entails multiple challenges,including the lack of fine-grained captions and confounders caused by dataset ***,confounders often cause models to learn spurious correlations,thereby reducing their generalization *** In this work,we propose the Deconfounded Fashion Image Captioning(DFIC)framework,which first uses multimodal retrieval to enrich the predicted captions of clothing,and then constructs a detailed causal graph using causal inference in the decoder to perform *** retrieval is used to obtain semantic words related to image features,which are input into the decoder as prompt words to enrich sentence *** the decoder,causal inference is applied to disentangle visual and semantic features while concurrently eliminating visual and language *** Overall,our method can not only effectively enrich the captions of target images,but also greatly reduce confounders caused by the *** verify the effectiveness of the proposed framework,the model was experimentally verified using the FACAD dataset.

关键词： Image caption Causal inference Fashion caption

来源：评论

学校读者我要写书评

暂无评论

Feature Extraction and Classification of Text Data by Combining Two-Stage Feature Selection Algorithm and Improved Machine Learning Algorithm

Informatica (Slovenia)

引用

Informatica (Slovenia) 2024年第8期48卷 137-150页

作者： Huang, Hua School of Computer and Artificial Intelligence Henan Finance University Zhengzhou450046 China

Efficient text classification is crucial for information processing due to the generation of massive text data. However, the uneven distribution and redundancy of text data often result in poor classification performance. To address this issue, a two-stage feature selection algorithm is proposed using the fusion of information gain and maximum correlation minimum redundancy algorithm. To improve SVM performance in text data classification, an improved SVM algorithm based on Fourier hybrid kernel function is proposed. The study found that the proposed improved algorithm achieved an accuracy of 0.82 on the IMDB dataset using only 40 feature subsets. Even when the number of features exceeded 390, the F1 value of the proposed algorithm remained 1% to 2% higher than that of other algorithms. The improved algorithm performed best when the feature dimension was around 400. The proposed algorithm, which combines the Fourier hybrid kernel function with a two-stage feature selection algorithm based on the information gain and maximum correlation minimum redundancy algorithm, achieved a 1%~3% higher F1 value and increased the number of correctly classified texts by 20 to 45. These results demonstrate the effectiveness of the algorithm as a classification tool for processing large-scale text data, which is significant for information retrieval and data mining. © 2024 Slovene Society Informatika. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Adaptive dynamic self-learning grey wolf optimization algorithm for solving global optimization problems and engineering problems

引用

Mathematical Biosciences and Engineering 2024年第3期21卷 3910-3943页

作者： Zhang, Yijie Cai, Yuhang School of Artificial Intelligence and Computer Science Jiangnan University WuXi214122 China

The grey wolf optimization algorithm (GWO) is a new metaheuristic algorithm. The GWO has the advantages of simple structure, few parameters to adjust, and high efficiency, and has been applied in various optimization problems. However, the orginal GWO search process is guided entirely by the best three wolves, resulting in low population diversity, susceptibility to local optima, slow convergence rate, and imbalance in development and exploration. In order to address these shortcomings, this paper proposes an adaptive dynamic self-learning grey wolf optimization algorithm (ASGWO). First, the convergence factor was segmented and nonlinearized to balance the global search and local search of the algorithm and improve the convergence rate. Second, the wolves in the original GWO approach the leader in a straight line, which is too simple and ignores a lot of information on the path. Therefore, a dynamic logarithmic spiral that nonlinearly decreases with the number of iterations was introduced to expand the search range of the algorithm in the early stage and enhance local development in the later stage. Then, the fixed step size in the original GWO can lead to algorithm oscillations and an inability to escape local optima. A dynamic self-learning step size was designed to help the algorithm escape from local optima and prevent oscillations by reasonably learning the current evolution success rate and iteration count. Finally, the original GWO has low population diversity, which makes the algorithm highly susceptible to becoming trapped in local optima. A novel position update strategy was proposed, using the global optimum and randomly generated positions as learning samples, and dynamically controlling the influence of learning samples to increase population diversity and avoid premature convergence of the algorithm. Through comparison with traditional algorithms, such as GWO, PSO, WOA, and the new variant algorithms EOGWO and SOGWO on 23 classical test functions, ASGW

关键词： Global optimization

来源：评论

学校读者我要写书评

暂无评论

Application of GAN-Based Data Encryption Technology in computer Communication System

引用

Informatica (Slovenia) 2024年第15期48卷 17-34页

作者： Li, Min School of Computer and Artificial Intelligence Henan Finance University Zhengzhou451464 China

With the rapid development of information technology, how to ensure the secure transmission and storage of data has become an important issue in today's society. The experiment innovatively proposes an encryption method to improve the security of computer communication systems under various attack modes. This method is based on Chosen Cipher-text Attack (CCA) and improved adversarial neural network. In the process, the adversarial neural network is first used to encrypt the data. A new symmetric encryption system structure, namely Adversarial Neural Cryptography (ANC), is introduced to merge with Generative Adversarial Network (GAN). In addition, a Chosen Cipher-text Attack-Adversarial Neural Cryptography (CCA-ANC)-based encryption method is proposed to build a computer communication data encryption system. GAN is adjusted and optimized based on the CCA test results to jointly realize the encryption of data transmission. The experiment uses two public data sets: CAIDA and UNIBS. 1520 data in the CAIDA data set are finally selected as the validation set and named as data set A by removing redundant data. 380 data in the UNIBS data set are selected as the test set and named as data set B. The experiment selects the iteration, AUC value, classification accuracy, and other performance indicators. The results showed that the research model reached a stable state with a fitness value of 0.612 after 38 iterations. Compared with existing technologies such as Blockchain technology, X-IDEA, and HS-IQRG algorithms, the AUC of the proposed method was 0.978. On dataset A, the research method had a maximum classification accuracy of 98.24% when the system iterated 75 times. The encryption time of the research method on dataset A was only 0.0424s when the system iterated 44 times. The above results all show that the research method can encrypt data. Meanwhile, this method learns a safe password generation method in the automated system, which makes certain contributions to compute

关键词： CCA-ANC computer communication data encryption technology generating adversarial network

来源：评论

学校读者我要写书评

暂无评论

Optimizing SDN Controller to Switch Latency for Controller Placement Problem

引用

Informatica (Slovenia) 2024年第8期48卷 165-176页

作者： Zobary, Firas School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China

Software-Defined Networking (SDN) updates network flexibility by decoupling the data plane from control planes, employing a logically centralized yet physically distributed multi-controller architecture. The optimal placement of controllers and their quantity presents a significant challenge known as the Controller Placement Problem (CPP). This study addresses the optimization of average propagation delay between controllers and switches, introducing an enhancement version of well-known K-Means algorithm for network partitioning and controller placement, called an Advanced K-Means algorithm. The proposed algorithm strategically minimizes the average propagation delay by situating controllers in optimal nodes within each sub-network. Evaluation through simulations on the Internet OS3E topology demonstrates the algorithm's efficacy, showcasing a 22%, 11%, 7%, and 3% reduction in average propagation delay compared to DBCP, POCO, CNPA, and HDIDS, respectively. These results establish the proposed algorithm as a competitive solution, emphasizing its capacity to achieve comparable or superior performance in mitigating latency between controllers and switches when compared to existing algorithms. © 2024 Slovene Society Informatika. All rights reserved.

关键词： Controllers

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：