检索结果-内蒙古大学图书馆

Cleaning of Multi-Source Uncertain Time Series Data Based on PageRank

Journal of Donghua University(English Edition) 2023年第6期40卷 695-700页

作者：高嘉伟孙纪舟 Faculty of Computer and Software Engineering Huaiyin Institute of TechnologyHuai’an 223003China

There are errors in multi-source uncertain time series *** discovery methods for time series data are effective in finding more accurate values,but some have limitations in their *** tackle this challenge,we propose a new and convenient truth discovery method to handle time series data.A more accurate sample is closer to the truth and,consequently,to other accurate *** the mutual-confirm relationship between sensors is very similar to the mutual-quote relationship between web pages,we evaluate sensor reliability based on PageRank and then estimate the truth by sensor ***,this method does not rely on smoothness assumptions or prior knowledge of the ***,we validate the effectiveness and efficiency of the proposed method on real-world and synthetic data sets,respectively.

关键词： big data data cleaning time series truth discovery PageRank

来源：评论

学校读者我要写书评

暂无评论

An Efficient Heterogeneous Ring Signcryption Scheme for Wireless Body Area Networks

引用

computer Systems Science & engineering 2023年第11期47卷 2061-2078页

作者： Qingqing Ning Chunhua Jin Zhiwei Chen Yongliang Xu Huaqi Lu Faculty of Computer&Software Engineering Huaiyin Institute of TechnologyHuai’an233003China

Wireless body area networks(WBANs)are an emerging technology for the real-time monitoring of physiological *** provide a mechanism for collecting,storing,and transmitting physiological data to healthcare ***,the open wireless channel and limited resources of sensors bring security *** ensure physiological data security,this paper provides an efficient Certificateless Public Key Infrastructure Heterogeneous Ring Signcryption(CP-HRSC)scheme,in which sensors are in a certificateless cryptosystem(CLC)environment,and the server is in a public key infrastructure(PKI)*** could solve the limitations of key escrow in identity-based cryptography(IBC)and certificate management for public keys in *** PKI is suited for the server because it is widely used on the ***,this paper designs a ring signcryption method that allows the controller to anonymously encrypt physiological data on behalf of a set of sensors,but the server does not exactly know who the sensor *** construction of this paper can achieve anonymity,confidentiality,authentication,non-repudiation,and integrity in a logically single *** the computational Diffie-Hellman(CDH)problem,the formal security proof is provided in the random oracle model(ROM).This paper demonstrates that this scheme has indistinguishability against adaptive chosen ciphertext attacks(IND-CCA2)and existential unforgeability against adaptive chosen message attacks(EUF-CMA).In terms of computational cost and energy usage,a comprehensive performance analysis demonstrates that the proposed scheme is the most *** to the three existing schemes,the computational cost of this paper’s scheme is reduced by about 49.5%,4.1%,and 8.4%,and the energy usage of our scheme is reduced by about 49.4%,3.7%,and 14.2%,respectively.

关键词： Wireless body area networks certificateless cryptosystem public key infrastructure security ring singncryption

来源：评论

学校读者我要写书评

暂无评论

A Semi-Anchoring Guided High-Resolution Capsule Network for Vehicle Logo Recognition

A Semi-Anchoring Guided High-Resolution Capsule Network for ...

引用

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

作者： Wang, Lanfang Yu, Zhenyang Yu, Yongtao Huaiyin Institute of Technology Faculty of Computer and Software Engineering Huaian China

ISBN: (纸本)9798350306293

As a unique identity reflecting the manufacturer of the vehicle, the vehicle logo information plays an important role in many transportation-related applications. However, due to the challenges of size variations, shape and form diversities, deformations, occlusions, and complex scenarios, it is still not an easy task to realize highly accurate vehicle logo recognition from images. This paper proposes a novel semi-anchoring guided high-resolution capsule network (SAGHR-CapsNet) for vehicle logo recognition. First, constructed with a multibranch high-resolution capsule network architecture functioned with repeated multiresolution feature fusion for feature extraction, the SAGHR-CapsNet can extract semantically strong and spatially accurate feature representations at each scale. Second, designed with a capsule-based efficient self-attention mechanism for feature semantic promotion, the SAGHRCapsNet functions excellently to attend to channel-wise informative features and target-oriented spatial features. Finally, adopted with a semi-anchoring guided strategy for vehicle logo recognition, the SAGHR-CapsNet performs promisingly to simultaneously improve the processing efficiency and guarantee the recognition accuracy. Intensive quantitative evaluations and comparative analyses on two large-scale data sets demonstrated the applicability and superiority of the SAGHR-CapsNet in vehicle logo recognition tasks. © 2023 IEEE.

关键词： Vehicles

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

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

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

Fault diagnosis of chemical process based on CNN-BiGRU 24

Fault diagnosis of chemical process based on CNN-BiGRU

引用

2024 International Conference on computer Vision and Deep Learning, CVDL 2024

作者： Sun, Chengfu Ni, Yang Du, Rui Huaiyin Institute of Technology School of Computer and Software Engineering Huaian China

ISBN: (纸本)9798400718199

targeting issues where the fault features in the chemical production process are hard to discern and the fault diagnosis method's accuracy is low. This paper proposes an improved CNN-BiGRU (Convolutional Neural Networks and Bidirectional Gated Recurrent Unit) model, which is different from the usual serial structure, and adopts a parallel structure to combine the improved CNN and Bidirectional Gated Recurrent Unit. First, CNN is used to extract local features adaptively, and a batch normalization (BN) layer is used in CNN to avoid internal covariate shift and accelerate network training. In order to prevent overfitting and minimize network calculations, the global pooling layer is introduced. Second, BiGRU is used to extract global features from the data, and by incorporating a linear layer into the conventional BiGRU network, the model's accuracy is increased. Eventually, the fusion layer fuses the features that were extracted by the two networks. The experiment's outcomes demonstrate how well the model can raise fault detection accuracy. Taking the Eastman Process of Tennessee process (TE) as the research object, experiments show that the proposed method has excellent performance. © 2024 ACM.

关键词： Failure analysis

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：