检索结果-内蒙古大学图书馆

2023 International Conference on Cognitive Computing and Complex Data, ICCD 2023

作者： Xu, Xiang Li, Guanxiao Xiao, Shaozhang Zhang, Zheyi Huaiyin Institute of Technology School of Computer and Software Engineering Huai'an China

ISBN: (纸本)9798350306293

To achieve effective feedback and proficiency tracking of students in contemporary educational settings, we propose a methodology that integrates the RNN-GRU model and dynamic Bayesian networks for predicting students' engineering competence level based on their online learning behaviors. The approach employed utilizes the RNN-GRU model to analyze students' progression in algorithm development skills and algorithm implementation ability, resulting in the generation of a historical record of their learning features. These features are then employed to train a dynamic Bayesian network model, facilitating the prediction of students' engineering competence level. After the amount of data reaches a certain amount, it can compare the previous models such as RNN and LSTM to obtain higher accuracy. © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Research on Chemical Accident News Classification Based on CNN and BiLSTM-Self-Attention

Research on Chemical Accident News Classification Based on C...

引用

2023 International Conference on Cognitive Computing and Complex Data, ICCD 2023

作者： Zong, Hui Zhao, Yun Zhou, Heng Zhang, Le Huaiyin Institute of Technology Faculty of Computer and Software Engineering Huaian China

ISBN: (纸本)9798350306293

Chemical accident news data encompasses essential information such as news headlines, news content, and news sources, with the context of news content playing a crucial role. To enhance the accuracy of text feature extraction and improve the efficiency of chemical accident news classification, this paper introduces a feature fusion-based classification approach. The proposed model employs a multi-layer convolutional neural network (CNN) to extract local features from the text of chemical accident news. Additionally, a Bidirectional Long Short-Term Memory (BiLSTM) network is utilized to capture global features, supplemented by the integration of a Self-Attention mechanism behind the BiLSTM network to assign weights to the features and reduce noise. The local and global features are then fused to enrich the semantic information. Furthermore, the feature fusion information undergoes maximum pooling and average pooling to reduce dimensionality and enhance the training speed. Finally, the information is fed into a Softmax layer for classification. Experimental results demonstrate that the proposed neural network model, namely ABLSACNN (Add-CNN-BiLSTM-Self-Attention), outperforms the CNN-Self-Attention model. The ABLSACNN model exhibits an improvement of1.59% in accuracy, 2.46% in recall rate, and 1.93% in F1 score on the chemical accident news dataset, thereby showcasing its superiority. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Ternary-attention Capsule Feature Pyramid Network for Building Footprint Extraction from Remote Sensing Imagery

A Ternary-attention Capsule Feature Pyramid Network for Buil...

引用

2023 International Conference on Cognitive Computing and Complex Data, ICCD 2023

作者： Zhang, Haiyan Li, Yazhou Wang, Meifeng Huaiyin Institute of Technology Faculty of Computer and Software Engineering Huaian China

ISBN: (纸本)9798350306293

The up-to-date and accurate building footprint database plays a significant role in a large variety of applications. Recently, remote sensing images have provided an important data source for building footprint extraction tasks. However, due to topology variations, color diversities, and complicated rooftop and environmental scenarios, it is still a challenging task to realize fully automated and highly accurate extraction of building footprints from remote sensing images. In this paper, we propose a novel ternary-attention capsule feature pyramid network (TA-CapsFPN), which is formulated with a capsule feature pyramid network architecture and integrated with context-augmentation and feature attention modules, aiming at improving the building footprint extraction accuracy by combining the superior properties of capsule representations and the powerful capability of attention mechanisms. Quantitative evaluations and comparative analyses show that the TA-CapsFPN provides a promising and competitive performance in processing buildings of varying conditions. © 2023 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

A Surface Defect Detection Method Based on Attention Mechanism for Workpieces

A Surface Defect Detection Method Based on Attention Mechani...

引用

2023 International Conference on Cognitive Computing and Complex Data, ICCD 2023

作者： Qiu, Junlin Shen, Yongshan Feng, Wanli Zhang, Haodong Sun, Keke Qin, Yuxin Huaiyin Institute of Technology Faculty of Computer and Software Engineering Huai'an China

ISBN: (纸本)9798350306293

With the rapid development of image processing technology in recent years, faced with the issues of low detection accuracy and missed detections in the process of surface defect detection on workpieces, we propose a workpiece surface defect detection method based on attention mechanism. The model uses EfficientDet-d0 as the baseline network, mixes the Fused-MBConv structure and MBConv structure in EfficientNetv2 network as part of the feature extraction network, and uses the convolutional attention module CBAM to focus on the information of space and channel direction at the same time, and the Hardmish activation function is used in the structure. Introducing a fast spatial pyramid pooling module (SPPF) at the top of the feature extraction network increases the network's depth and enhances its expressive power. The extracted features are fed into the Improved-BiFPN (Bidirectional Feature Pyramid Network) for feature enhancement, improving the model's ability to detect defects of different sizes. Experimental results demonstrate that our proposed surface defect detection method for workpieces outperforms other advanced detectors. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Safety Helmet Detection Algorithm for Complex Scenarios Based on PConv-YOLOv8

Safety Helmet Detection Algorithm for Complex Scenarios Base...

引用

2023 International Conference on Cognitive Computing and Complex Data, ICCD 2023

作者： Wang, Yuanyuan Jiang, Feilong Li, Yazhou Zhang, Haiyan Wang, Meifeng Yan, Shaofeng Huaiyin Institute of Technology Faculty of Computer and Software Engineering Huaian China

ISBN: (纸本)9798350306293

Detecting safety helmets in complex environments is challenging due to issues like occlusion and lighting variations. Addressing the issues of slow detection speed and low object detection accuracy in complex environments with the YOLOv8 model, this paper introduces a lightweight safety helmet detection model, called PConv-YOLOv8, that is suitable for real-time applications in complex environments. Our method incorporates the PConv (Partial Convolution) module into the YOLOv8 model, reducing the complexity of the feature extraction network while enhancing feature representation accuracy. It also incorporates SimAM attention to extract and enhance the most relevant features by evaluating their similarity. Additionally, it considers category imbalance and positional regression in the target detection task, enhancing the model's performance in target category identification and positional localization. Moreover, we propose the Wise-Distribution Focal Loss function to improve bounding box selection accuracy and enhance the model's robustness. This paper introduces the Wise-Distribution Focal Loss method, which enhances the performance of target category recognition and location localization by improving the accuracy of bounding box selection and increasing the robustness of the overall model. The experimental results demonstrate that the method proposed in this paper achieves a 125% improvement in detection speed and a 1.8% increase in mAP0.5 compared to the YOLOv8 model. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

AsyCo: an asymmetric dual-task co-training model for partial-label learning

引用

Science China(Information Sciences) 2025年第5期68卷 332-347页

作者： Beibei LI Yiyuan ZHENG Beihong JIN Tao XIANG Haobo WANG Lei FENG College of Computer Science Chongqing University State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences School of Software Technology Zhejiang University School of Computer Science and Engineering Nanyang Technological University

Partial-label learning(PLL) is a typical problem of weakly supervised learning, where each training instance is annotated with a set of candidate labels. Self-training PLL models achieve state-of-the-art performance but suffer from error accumulation problems caused by mistakenly disambiguated instances. Although co-training can alleviate this issue by training two networks simultaneously and allowing them to interact with each other, most existing co-training methods train two structurally identical networks with the same task, i.e., are symmetric, rendering it insufficient for them to correct each other due to their similar limitations. Therefore, in this paper, we propose an asymmetric dual-task co-training PLL model called AsyCo,which forces its two networks, i.e., a disambiguation network and an auxiliary network, to learn from different views explicitly by optimizing distinct tasks. Specifically, the disambiguation network is trained with a self-training PLL task to learn label confidence, while the auxiliary network is trained in a supervised learning paradigm to learn from the noisy pairwise similarity labels that are constructed according to the learned label confidence. Finally, the error accumulation problem is mitigated via information distillation and confidence refinement. Extensive experiments on both uniform and instance-dependent partially labeled datasets demonstrate the effectiveness of AsyCo.

关键词： machine learning weakly supervised learning partial-label learning co-training models candidate label sets

来源：评论

学校读者我要写书评

暂无评论

Air Quality Index Prediction Based on CNN-LSTM-Attention Hybrid Modeling

Air Quality Index Prediction Based on CNN-LSTM-Attention Hyb...

引用

2023 International Conference on Cognitive Computing and Complex Data, ICCD 2023

作者： Li, Yinyin Jiang, Tao Gu, Hanzhu Lu, Weibing Wu, Qingguo Yu, Yongtao Huaiyin Institute of Technology Faculty of Computer and Software Engineering Huaian China

ISBN: (纸本)9798350306293

Air Quality Index (AQI) is an important indicator for determining good or bad air quality. The accurate and efficient prediction of AQI plays a positive role in promoting the management of air pollution. However, current algorithms for predicting AQI usually do not comprehensively consider the effects of pollutant factors and meteorological factors on the prediction performance. Therefore, taking pollutant factors and meteorological factors as the basis of the model study, a CNNLSTM-Attention hybrid model is proposed. The CNN-LSTM module is used to obtain the air quality-related features, and the attention mechanism is introduced to weigh and sum the output of the LSTM in order to obtain the final attention-weighted features. The results show that the model has better performance than the single model for the prediction of the air quality index. © 2023 IEEE.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

An Unbiased Fuzzy Weighted Relative Error Support Vector Machine for Reverse Prediction of Concrete Components

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第9期5卷 4574-4584页

作者： Fan, Zongwen Gou, Jin Weng, Shaoyuan College of Computer Science and Technology Huaqiao University Xiamen361021 China School of Software Engineering Xiamen Institute of Software Technology Xiamen361024 China

Concrete is a vital component in modern construction, prized for its strength, durability, and versatility. Accurately determining the quantities of concrete components is crucial in civil engineering applications to optimize resources (e.g., manpower and financial resources). In this article, we propose an unbiased fuzzy-weighted relative error support vector machine (UFW-RE-SVM) for reverse prediction of concrete components. First, we add an unbiased term to the target function of UFW-RE-SVM for obtaining an unbiased model. Second, we design a fuzzy-weighted operation to indicate sample importance by incorporating the fuzzy membership values into the UFW-RE-SVM. The nth root operation is introduced to address the exponential explosion issue in the fuzzy-weighted operation. Finally, considering the UFW-RE-SVM is sensitive to its hyperparameters for multioutput prediction, the whale optimization algorithm (WOA) is utilized for hyperparameter optimization for its effectiveness in optimization tasks. We design the fitness function based on the results from multiple components to balance the performance of multioutput predictions. Experimental results show that the performance of our proposed model outperforms existing works in predicting concrete components in terms of mean absolute relative error, standard deviation, and root mean square error. Further, the statistical test shows the WOA and two other metaheuristics can significantly improve the prediction performance. This indicates that the unbiased term, fuzzy-weighted operation, and WOA are effective for improving the proposed model for reverse prediction concrete components. With these promising results, the proposed model could provide decision-makers with a valuable tool for determining concrete component quantities based on desired concrete qualities. © 2020 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Application of Lightweight DSC-NET Network Model in Histopathological Images of Lung Cancer and Colon Cancer

Application of Lightweight DSC-NET Network Model in Histopat...

引用

2023 International Conference on Cognitive Computing and Complex Data, ICCD 2023

作者： An, Wenlong Zong, Hui Zhou, Heng Wang, Jian Huaiyin Institute of Technology Faculty of Computer and Software Engineering Huaian China

ISBN: (纸本)9798350306293

Classification of histopathological images is a fundamental task in the workflow of pathological diagnosis. Due to the complexity of pathological images, it is particularly important to use deep learning to improve diagnostic efficiency. This paper designs a lightweight network model DSC-NET, which consists of multi-scale feature stitching Multi-Conv, coordinate attention CA. The improved selfcalibrated convolution MSC-Conv is composed of selfcalibrated convolution SC-Conv, coordinate attention CA and depthwise DW. In addition, the DSC-NET network model converts the 1×1 convolutional layer (Conv) in the Block module into a linear layer (Linear), which reduces the computational complexity of the model while maintaining the ability of the convolution operation to capture local features. The research in this paper adopts the lung cancer and colon cancer datasets and adds Gaussian noise to these datasets to simulate the equipment shooting situation and evaluate the lightweight DSC-NET network model. Through quantitative comparisons with previous state-of-the-art methods, our experimental results demonstrate that the proposed method achieves superior accuracy. Furthermore, our method stands out with a smaller parameter count and significantly lower FLOPs, highlighting its efficiency and computational advantages. It has important potential to assist pathologists in pathological diagnosis. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Lightweight Protective Clothing Detection Algorithm Based on Ghost Convolution and GSConv Convolution

Lightweight Protective Clothing Detection Algorithm Based on...

引用

2023 International Conference on Cognitive Computing and Complex Data, ICCD 2023

作者： Guan, Qianjun Yu, Kun Wang, Haoran Li, Qiangqiang Gao, Shihong Huaiyin Institute of Technology Faculty of Computer and Software Engineering Huai'an Jiangsu China

ISBN: (纸本)9798350306293

GhostNet is proposed by Huawei Noah's Ark Laboratory in CVPR2020, which can be used with the same accuracy, with less speed and less computation than SOTA method. This convolution is a low-cost operation used to decrease the amount of computation and related parameters. Ghost convolution can be used as an alternative to traditional convolution operations because they have the same accuracy. However, utilize significantly less computation and a much smaller parameter count. GSConv(Group-Shared Convolution) is a convolution operation based on group shared weights. This operation achieves efficient parallel convolution operations by grouping convolution kernels. In this way, the parameters used and calculation complexity of the model can be reduced to some extent. This makes the network more computationally efficient and smaller in model size while maintaining accuracy. The algorithm can detect the location of protective clothing quickly and efficiently, and its accuracy and efficiency have been verified. Because the algorithm adopts lightweight network structure, real-time detection can be realized on lowpower devices efficiently. The model architecture enhances the performance based on the YOLOv5 target detection algorithm by incorporating additional features. So that the model can maintain a high precision, which is crucial for the protective clothing detection algorithm. © 2023 IEEE.

关键词： Convolution

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：