检索结果-内蒙古大学图书馆

Proceedings of the12th International Conference on Information technology and its Applications, CITA 2023

作者： Tran, Ngoc-Du Nguyen, Dinh-Quoc-Dai Nguyen, Ngoc-Linh-Chi Pham, Van-Truong Tran, Thi-Thao Department of Automation Engineering School of Electrical and Electronic Engineering Hanoi University of Science and Technology Hanoi Viet Nam

ISBN: (纸本)9783031368851

Polyp Segmentation is important in helping doctors diagnose and provide an accurate treatment plan. With the emerging of deep learning technology in the last decade, deep learning models especially Unet and its evolved versions, for medical segmentation task have achieved superior results compared to previous traditional methods. To preserve location information, Unet-based models use connections between feature maps of the same resolution of encoder and decoder. However, using the same resolution connections has two problems: 1) High-resolution feature maps on the encoder side contain low-level information. In contrast, high-resolution feature maps on the decoder side contain high-level information that leads to an imbalance in terms of semantic information when connecting. 2) In medical images, objects such as tumours and cells often have diverse sizes, so to be able to segment objects correctly, the use of context information on a scale of the feature map encoder during the decoding process is not enough, so it is necessary to use context information on full-scale. In this paper, we propose a model called CTDCFormer that uses the PvitV2_B3 model as the backbone encoder to extract global information about the object. In order to exploit the full-scale context information of the encoder, we propose the GCF module using the lightweight attention mechanism between the decoder’s feature map and the encoder’s four feature maps. Our model CTDCFormer achieves superior results compared to other state of the arts, with the Dice scores up to 94.1% on the Kvasir-SEG set, and 94.7% on the CVC-ClinicDB set. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

MixerFormer-Covariance Metric Neural Network: A New Few-shot Learning Model for Bearing Fault Diagnosis 12

MixerFormer-Covariance Metric Neural Network: A New Few-shot...

引用

12th IEEE International Conference on Control, automation and Information Sciences, ICCAIS 2023

作者： Vu, Manh-Hung Pham, Van-Truong Hanoi University of Science and Technology School of Electrical and Electronic Engineering Department of Automation Engineering Hanoi Viet Nam

ISBN: (纸本)9798350328783

Deep inside the electrical machine, bearings are a delicate and easily injured component. Consequently, identifying bearing failures is a highly informative and crucial area. Instead of using manual methods, deep learning models were applied to diagnose bearing failures from abnormal signals returned from electrical machines. However, the weakness of modern end-to-end models is that they require a large amount of data to train in order to give highly accurate diagnostic results. Some studies have shown that Few-shot models are very suitable for diagnosis under limited data conditions, but few-shot models require many steps to make the diagnosis. Therefore, to overcome those disadvantages, the Mixer-former Covariance Metric Neural Network model is proposed. This is a few-shot training model but only needs 1 stage to diagnose the fault instead of more than 2 stages like other few-shot models. On the Case Western Reverse University (CWRU) and HUST-Bearing datasets, two open-access datasets, several experiments and ablation investigations were performed. The results demonstrate that the proposed model outperforms other modern deep learning models when there is limited data available. In addition, this model still satisfies the requirements and produces excellent results when trained with a significant quantity of data. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Framework for Mass-Forming Chronic Pancreatitis and Pancreatic Ductal Adenocarcinoma Classification Based on Magnetic Resonance Imaging

引用

Computers, Materials & Continua 2024年第4期79卷 409-427页

作者： Luda Chen Kuangzhu Bao Ying Chen Jingang Hao Jianfeng He Faculty of Information Engineering and Automation Kunming University of Science and TechnologyKunming650504China Department of Radiology Second Affiliated Hospital of Kunming Medical UniversityKunming650101China School of Physics and Electronic Engineering Yuxi Normal UniversityYuxi653100China

Pancreatic diseases, including mass-forming chronic pancreatitis (MFCP) and pancreatic ductal adenocarcinoma(PDAC), present with similar imaging features, leading to diagnostic complexities. Deep Learning (DL) methodshave been shown to perform well on diagnostic tasks. Existing DL pancreatic lesion diagnosis studies basedon Magnetic Resonance Imaging (MRI) utilize the prior information to guide models to focus on the lesionregion. However, over-reliance on prior information may ignore the background information that is helpful fordiagnosis. This study verifies the diagnostic significance of the background information using a clinical ***, the Prior Difference Guidance Network (PDGNet) is proposed, merging decoupled lesion andbackground information via the Prior Normalization Fusion (PNF) strategy and the Feature Difference Guidance(FDG) module, to direct the model to concentrate on beneficial regions for diagnosis. Extensive experiments inthe clinical dataset demonstrate that the proposed method achieves promising diagnosis performance: PDGNetsbased on conventional networks record an ACC (Accuracy) and AUC (Area Under the Curve) of 87.50% and89.98%, marking improvements of 8.19% and 7.64% over the prior-free benchmark. Compared to lesion-focusedbenchmarks, the uplift is 6.14% and 6.02%. PDGNets based on advanced networks reach an ACC and AUC of89.77% and 92.80%. The study underscores the potential of harnessing background information in medical imagediagnosis, suggesting a more holistic view for future research.

关键词： Pancreatic cancer pancreatitis background region prior normalization fusion feature difference guidance

来源：评论

学校读者我要写书评

暂无评论

AMG-Mixer: A Multi-Axis Attention MLP-Mixer Architecture for Biomedical Image Segmentation 12th

AMG-Mixer: A Multi-Axis Attention MLP-Mixer Architecture for...

引用

Proceedings of the12th International Conference on Information technology and its Applications, CITA 2023

作者： Le, Hoang-Minh-Quang Le, Trung-Kien Pham, Van-Truong Tran, Thi-Thao Department of Automation Engineering School of Electrical and Electronic Engineering Hanoi University of Science and Technology Hanoi Viet Nam

ISBN: (纸本)9783031368851

Previously, Multi-Layer Perceptrons (MLPs) were primarily used in image classification tasks. The emergence of the MLP-Mixer architecture has demonstrated the continued efficacy of MLPs in other visual tasks. To obtain superior results, it is imperative to have pre-trained weights from large datasets, and the Cross-Location (Token Mix) operation must be adaptively modified to suit the specific task at hand. Inspired by this, we proposed AMG-Mixer, an MLP-based architecture for image segmentation. In particular, recognizing the importance of positional information, we proposed AxialMBconv Token Mix utilizing Axial Attention. Additionally, to reduce Axial Attention’s receptive field constraints, we proposed Multi-scale Multi-axis MLP Gated (MS-MAMG) block which employs Multi-Axis MLP. The proposed AMG-Mixer architecture outperformed State-of-the-Art (SOTA) methods on benchmark datasets including GLaS, Data Science Bowl 2018, and Skin Lesion Segmentation ISIC 2018, even without pre-training. The proposed AMG-Mixer architecture has been confirmed effective and high performing in our study. The code is available at https://***/quanglets1fvr/amg_mixer. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A New ConvMixer-Based Approach for Diagnosis of Fault Bearing Using Signal Spectrum 12th

A New ConvMixer-Based Approach for Diagnosis of Fault Bear...

引用

Proceedings of the12th International Conference on Information technology and its Applications, CITA 2023

作者： Vu, Manh-Hung Nguyen, Van-Quang Tran, Thi-Thao Pham, Van-Truong Department of Automation Engineering School of Electrical and Electronic Engineering Hanoi University of Science and Technology Hanoi Viet Nam

ISBN: (纸本)9783031368851

It has been reported that nearly 40 % of electrical machine failures are caused by bearing problems. That is why identifying bearing failure is crucial. Deep learning for diagnosing bearing faults has been widely used, like WDCNN, Conv-mixer, and Siamese models. However, good diagnosis takes a significant quantity of training data. In order to overcome this, we propose a new approach that can dramatically improve training performance with a small data set. In particular, we propose to integrate the ConvMixer models to the backbone of Siamese network, and use the few-short learning for more accurate classification even with limited training data. Various experimental results with raw signal inputs and signal spectrum inputs are conducted, and compared with those from traditional models using the same data set provided by Case Western Reserve University (CWRU). © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Mixers (machinery)

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach based on MLP-mixer Models for Bearing Fault Diagnosis

A Deep Learning Approach based on MLP-mixer Models for Beari...

引用

2023 International Conference on system Science and engineering, ICSSE 2023

作者： Nguyen, Van-Quang Vu, Manh-Hung Pham, Van-Truong Tran, Thi-Thao Hanoi University of Science and Technology School of Electrical and Electronic Engineering Department of Automation Engineering Hanoi Viet Nam

ISBN: (纸本)9798350322941

Bearing fault diagnosis plays an important role in monitoring activities of rotating machinery, especially electrical machine failures. Identifying bearing failure, therefore, is getting more and more attention. With the successes of deep learning techniques, various approaches based on convolutional neural networks (CNNs) have been developed for diagnosing bearing faults. Deep learning models can be effective for accurate diagnosis;nevertheless, in order to achieve this, a substantial amount of training data is typically required. To overcome this, we propose a new deep neural network approach based on the MLP-mixer model and CNN model that can dramatically improve training performance even with a small amount of data set. Various experiments and ablation studies have been conducted on the public Case Western Reserve University (CWRU) database. Evaluation results show that the proposed approach still obtains high accuracy when reducing the number of training samples. The promising performance of the proposed model when compared with another state of arts proved the advantages of the proposed approach. © 2023 IEEE.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

ConvmixFormer-Unet: A New Approach for Medical Image Segmentation based on Convmixer and Transformer 12

ConvmixFormer-Unet: A New Approach for Medical Image Segment...

引用

12th IEEE International Conference on Control, automation and Information Sciences, ICCAIS 2023

作者： Nguyen, Van-Quang Nguyen, Quang-Huy Tran, Thi-Thao Hanoi University of Science and Technology School of Electrical and Electronic Engineering Department of Automation Engineering Hanoi Viet Nam

ISBN: (纸本)9798350328783

The research community has shown a great interest in transformer-based structures because of their capacity to understand contextual data and dependencies over long distances, even though they demand substantial computational resources. To overcome this challenge, the MLP-mixer approach offers an alternative to attention token-mix by employing MLP and transpose operations and the results are promising. This approach also showed advantages over the CNN-based models that utilize local information but often neglect global contexts. In the current study, we introduce a novel segmentation model called ConvmixFormer Unet, which leverages the strengths of the Former structure and a CNN-based network. Our model incorporates the ConvmixFormer block in the encoder stage, where the Former structure is utilized by substituting the token-mix layer with a Multi-scale ConvMixer token-mix block while retaining the channel-mix layer. The Convmix Transpose blocks are also proposed in the decoder stage. We assess the effectiveness of our proposed method by employing three distinct datasets, namely GlaS, Data Science Bowl 2018, and ISIC 2018. Additionally, we evaluate our approach against the most advanced models. The findings demonstrate that our proposed model achieves a significant improvement in performance while reducing remarkably the overall number of model parameters. © 2023 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Exploring Motor Imagery EEG: Enhanced EEG Microstate Analysis with GMD-Driven Density Canopy Method

引用

Computers, Materials & Continua 2024年第6期79卷 4659-4681页

作者： Xin Xiong Jing Zhang Sanli Yi Chunwu Wang Ruixiang Liu Jianfeng He Faculty of Information Engineering and Automation Kunming University of Science and TechnologyKunming650500China College of Physics and Electronic Engineering Hanshan Normal UniversityChaozhou521041China Department of Clinical Psychology Second People’s Hospital of YunnanKunming650021China

The analysis of microstates in EEG signals is a crucial technique for understanding the spatiotemporal dynamics of brain electrical *** methods such as Atomic Agglomerative Hierarchical Clustering(AAHC),K-means clustering,Principal Component Analysis(PCA),and Independent Component Analysis(ICA)are limited by a fixed number of microstate maps and insufficient capability in cross-task feature *** these limitations,this study introduces a Global Map Dissimilarity(GMD)-driven density canopy K-means clustering *** innovative approach autonomously determines the optimal number of EEG microstate topographies and employs Gaussian kernel density estimation alongside the GMD index for dynamic modeling of EEG *** this advanced algorithm,the study analyzes the Motor Imagery(MI)dataset from the GigaScience database,*** findings reveal six distinct microstates during actual right-hand movement and five microstates across other task conditions,with microstate C showing superior performance in all task *** imagined movement,microstate A was significantly *** with existing algorithms indicates a significant improvement in clustering performance by the refined method,with an average Calinski-Harabasz Index(CHI)of 35517.29 and a Davis-Bouldin Index(DBI)average of ***,an information-theoretical analysis of the microstate sequences suggests that imagined movement exhibits higher complexity and disorder than actual *** utilizing the extracted microstate sequence parameters as features,the improved algorithm achieved a classification accuracy of 98.41%in EEG signal categorization for motor imagery.A performance of 78.183%accuracy was achieved in a four-class motor imagery task on the BCI-IV-2a *** results demonstrate the potential of the advanced algorithm in microstate analysis,offering a more effective tool for a deeper understanding of the spatiotemporal features of EE

关键词： EEG microstate motor imagery K-means clustering algorithm gaus sian kernel function shannon entropy Lempel-Ziv complexity

来源：评论

学校读者我要写书评

暂无评论

Energy and Time-Efficient Scheduling of Automated Guided Vehicles system: A Hybrid Artificial Bee Colony Algorithm and Improved Ant Colony Optimization Approach 12

Energy and Time-Efficient Scheduling of Automated Guided Veh...

引用

12th IEEE International Conference on Control, automation and Information Sciences, ICCAIS 2023

作者： Nguyen, Hoang Anh Nguyen, Duc Minh Pham, Quoc Huy Pham, Quang Dai Hoang, Duc Chinh Hanoi University of Science and Technology School of Electrical and Electronic Engineering Department of Automation Engineering Hanoi Viet Nam

ISBN: (纸本)9798350328783

In this paper, a hybrid implementation of the Artificial Bee Colony (ABC) algorithm and Ant Colony Optimization (ACO) is applied for optimal scheduling and path-planning for an automated guided vehicle system (AGVS), in terms of energy consumption and service tardiness. AGVS is an essential component in the modern flexible manufacturing complex for transporting materials and goods. High efficiency in the operation of the AGVS contributes to an increase in the stability of the whole manufacturing process, improving total production efficiency and profit. ABC and ACO algorithms are swarm intelligence methods based on the foraging behavior of honeybees and ants colonies in real-life. The proposed strategy is the combination of the local search ability of ACO and global search ability of ABC to avoid the local optimum trap of solutions. The approach demonstrates satisfactory performance based on different case studies in simulation for a large-scale AGV system, in comparison with other optimization methods. Results show that while the proposed method may not be the best in terms of the total travel distance, it allows for the safe travel of the AGV while still outperforming the original solutions in terms of time and energy cost. © 2023 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Resilient Event-Triggered Control of Vehicle Platoon Under DoS Attacks and Parameter Uncertainty

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-9页

作者： Han, Qiaoni Ma, Jianguo Zuo, Zhiqiang Wang, Xiaocheng Yang, Bo Guan, Xinping Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System School of Electrical and Information Engineering Tianjin University Tianjin China Tianjin Key Laboratory of Wireless Mobile Communications and Power Transmission College of Electronic and Communication Engineering Tianjin Normal University Tianjin China Department of Automation Shanghai Jiao Tong University Shanghai China

This paper investigates the problem of dynamic event-triggered platoon control for intelligent vehicles (IVs) under denial of service (DoS) attacks and parameter uncertainty. DoS attacks disrupt vehicle-to-vehicle (V2V) communications, leading to the destabilization of vehicle formations. To alleviate the burden of the V2V communication network and enhance the tracking performance in the presence of DoS attacks and parameter uncertainty, a resilient and dynamic event-triggered mechanism is proposed. In contrast to the static event-triggering mechanism (STEM), this approach leverages the internal dynamic variable to further save communication resources. Subsequently, a method is developed for designing the desired triggering mechanism. Following this, a co-design framework is constructed to guarantee robust and resilient control against DoS attacks, with the analysis of eliminating Zeno behavior. Lastly, extensive simulations are presented to show the superiority of the proposed method in terms of enhancing platoon resilience and robustness and improving communication efficiency. IEEE

关键词： Vehicular ad hoc networks

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：