检索结果-内蒙古大学图书馆

KAC-Unet: A Medical image Segmentation With the Adaptive Group Strategy and Kolmogorov-Arnold Network

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Lin, Shiying Hu, Rong Li, Zuoyong Lin, Qinghua Zeng, Kun Wu, Xiang Fujian University of Technology Fujian Provincial Key Laboratory of Big Data Mining and Applications School of Computer Science and Mathematics Fuzhou350118 China Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control School of Computer and Big Data Fuzhou350121 China Fuzhou University Affiliated Provincial Hospital Provincial Clinical Medical College Fujian Medical University Department of Urology Fuzhou350001 China

In the field of deep learning-based medical image segmentation, convolutional neural networks (CNNs) extract image features by combining linear convolutional layers with nonlinear activation functions. However, excessive stacking of linear layers in the network limits the model’s ability to capture fine-grained details. In addition, the feature distribution imbalance caused by the traditional fixed grouping strategy (FGS) can affect the deep model’s capacity to perceive the overall structure of the image. To address these challenges, we propose a medical image segmentation framework, called Kolmogorov-Arnold Network with the adaptive group strategy and contextual Transformer based on Unet (KAC-Unet). First, we propose the adaptive group strategy (AGS) to balance the grouping of different input channels, alleviating the performance degradation caused by differences in group information. Then, we propose the Shift Tokenized Kolmogorov-Arnold Network (KAN) Block to capture complex features in medical images through flexible nonlinear transformations and shift operations. Extensive experiments are conducted on three medical image segmentation datasets. The results demonstrate the effectiveness and superiority of our proposed method compared with state-of-the-art algorithms. © 1963-2012 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

STMAD:A Simple Multimodal Anomaly Detection for Thyroid Medical information

STMAD:A Simple Multimodal Anomaly Detection for Thyroid Medi...

引用

International Congress on image and Signal processing, BioMedical Engineering and Informatics (CISP-BMEI)

作者： Wentong Xu Chao Fu Jing Yu Caifeng Si Zuoyong Li Chaochao Li Haoyi Fan School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou China Department of Ultrasound First Affiliated Hospital of Zhengzhou University Zhengzhou Henan China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control School of Computer and Big Data Minjiang University Fuzhou China

ISBN: (数字)9798331507398

ISBN: (纸本)9798331507404

Anomaly detection has been widely explored by training an out-of-distribution detector with only normal data. Medical image analysis, as a common tool, faces the challenge of how to further enhance the detection performance for thyroid cancer, especially with the application of various deep learning methods in the thyroid-related field. In this paper, we validate the effectiveness of sonographic feature descriptions (textual information) for thyroid cancer diagnosis. Building on this, we propose a simple multimodal self-supervised framework that leverages both textual and image modalities for thyroid cancer anomaly detection. Results on a private dataset demonstrate the effectiveness and superiority of our proposed method compared to advanced methods.

关键词： Deep learning Training image analysis Thyroid cancer Signal processing Feature extraction Informatics Anomaly detection Medical diagnostic imaging Thyroid

来源：评论

学校读者我要写书评

暂无评论

Self-organized Criticality in C. elegans Neural Network

Self-organized Criticality in C. elegans Neural Network

引用

第42届中国控制会议

作者： Xiao Gu Jian Liu Ye Yuan Peng Zhao Kuankuan Xin Tao Fang Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education Shanghai Engineering Research Centre of Intelligent Control and Management Institute of Machine Intelligence University of Shanghai for Science and Technology Queensland Brain Institute The University of Queensland

The self-organized criticality is a fundamental property for organisms to perform normal functional *** large-scale biological neural network researches have found the existence of self-organized criticality through avalanche phenomenon, which is typical characteristic of self-organized criticality. However, such research method is not suitable for small-scale biological neural network, because number of neurons in small-scale biological neural network is not large enough to support the emergence of avalanche phenomenon. It has been demonstrated that branching parameter can also be used to describe the propagation of activity in the neural network. Here, in this paper, the C. elegans neural network composed of 302 neurons is selected to investigate the existence of self-organized criticality using branching parameter. Based on the obtained connectome of C. elegans, a directed graph model is constructed to simulate the gradient potential of neurons and the activity of C. elegans, then, the existence of self-organized criticality in the neural network of C. elegans is proved by using branching parameter method. Meanwhile, the result is further confirmed by analyzing the calcium activity data of C. elegans obtained from biological experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A depthwise separable convolution based 6D pose estimation network by efficient 2D-3D feature fusion

A depthwise separable convolution based 6D pose estimation n...

引用

2021 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2021

作者： Feng, Qi Gu, Chaochen Qin, Jiani Xu, Rui Shanghai Jiao Tong University Department of Automation Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China

ISBN: (纸本)9781665436786

Precise 6D pose estimation of the target object is an essential prerequisite for robots to understand the real world. Previous 6D pose estimation methods based on 3D data usually have problems such as long model training time, imperfect feature extraction, redundant network model parameters, and complicated follow-up processing steps. This paper proposes a 2D-3D feature fusion module that could enhance feature extraction for the 6D pose estimation network. Furthermore, we compress the size of model parameters by adopting depthwise separable convolution to accelerate training speed and to reduce memory consumption. The experiment results on LineMOD dataset show the effectiveness of our method. Our method achieves on par or better performance than the state-of-art methods for 6D pose estimation and reduces model training time and the number of model parameters simultaneously. © 2021 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Multi-Stage Goal-Driven Network for Pedestrian Trajectory Prediction

A Multi-Stage Goal-Driven Network for Pedestrian Trajectory ...

引用

Computer Vision, image and Deep Learning (CVIDL), International Conference on

作者： Xiuen Wu Tao Wang Yuanzheng Cai Lingyu Liang George Papageorgiou Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China College of Computer and Data Science Fuzhou University Fuzhou China School of Electronic and Information Engineering South China University of Technology Guangzhou China Department of Computer Science and Engineering European University Cyprus Nicosia Cyprus

ISBN: (数字)9798350373820

ISBN: (纸本)9798350373837

Pedestrian trajectory prediction plays a pivotal role in ensuring the safety and efficiency of various applications, including autonomous vehicles and traffic management systems. This paper proposes a novel method for pedestrian trajectory prediction, called multi-stage goal-driven network (MGNet). Diverging from prior approaches relying on stepwise recursive prediction and the singular forecasting of a long-term goal, MGNet directs trajectory generation by forecasting intermediate stage goals, thereby reducing prediction errors. The network comprises three main components: a conditional variational autoencoder (CVAE), an attention module, and a multi-stage goal evaluator. Trajectories are encoded using conditional variational autoencoders to acquire knowledge about the approximate distribution of pedestrians’ future trajectories, and combined with an attention mechanism to capture the temporal dependency between trajectory sequences. The pivotal module is the multi-stage goal evaluator, which utilizes the encoded feature vectors to predict intermediate goals, effectively minimizing cumulative errors in the recursive inference process. The effectiveness of MGNet is demonstrated through comprehensive experiments on the JAAD and PIE datasets. Comparative evaluations against state-of-the-art algorithms reveal significant performance improvements achieved by our proposed method.

关键词： Deep learning Pedestrians Computational modeling Predictive models Prediction algorithms Vectors Inference algorithms

来源：评论

学校读者我要写书评

暂无评论

Digital-Twin-Based Clock Synchronization in Industrial IoT Systems

Digital-Twin-Based Clock Synchronization in Industrial IoT S...

引用

IEEE International Conference on Cyber Technology in Automation, control, and intelligent Systems

作者： Ting Cheng Shuai Liu Qimin Xu Shanying Zhu Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China School of Control Science and Engineering Shandong University Jinan China

Close and efficient cooperation between devices in the Industrial Internet of Things (IIoT) requires precise clock synchronization as a prerequisite. The uncertainty of IIoT networks and the complexity of industrial environments have led to less precise clock synchronization achieved by traditional algorithms and higher network resource consumption. This paper proposes a digital-twin-based clock synchronization scheme for IIoT systems. By building the digital model for each local clock to predict their clock skew, the information interaction required to achieve synchronization is reduced. In order to model the clock accurately, this paper proposes to use the extended state Kalman filter to handle uncertain dynamics and unknown measurement bias to improve the estimation accuracy of clock skew further. The simulation results show that the proposed algorithm can achieve high- precision clock synchronization while reducing the consumption of network resources.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Polyp Segmentation Neural Network with Simple Encoding Structure and Reverse Attention Module

Polyp Segmentation Neural Network with Simple Encoding Struc...

引用

IEEE International Symposium on information (IT) in Medicine and Education, ITME

作者： Jie Wang Zuoyong Li Haiping Xu Xuesong Cheng Shenghua Teng College of Electronic and Information Engineering Shandong University of Science and Technology Qingdao China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fuzhou China Fujian Key Laboratory of Medical Big Data Engineering Fujian Provincial Hospital Fuzhou China College of Mathematics and Data Science Minjiang University Fuzhou China

Colorectal cancer is a common malignancy. In colonoscopy images, computer-assisted polyp segmentation helps doctors diagnose and treat disorders more precisely. In recent years, some methods based on deep convolutional neural networks have made significant breakthroughs in this task. However, only a few algorithms explicitly consider the effect of light intensity on segmentation performance, which results in algorithms needing to be more robust for complex samples. This paper proposes a neural network combining a simple encoding structure with a reverse attention module. Specifically, the model uses HarDNet68 as the backbone network, adds a camouflage identification module (CIM) to enhance the capture of polyp details on the underlying features, and finally utilizes adaptive feature fusion with the reverse attention module (RAM). The proposed model effectively addresses the challenge of poor segmentation quality in colonoscopy images caused by inconsistent illumination. Extensive experiments on five datasets show that the proposed model performs well in polyp segmentation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Chinese Summary Generation Algorithm Based on Contrastive Attention Mechanism

Chinese Summary Generation Algorithm Based on Contrastive At...

引用

Computer Engineering and intelligent Communications (ISCEIC), International Symposium on

作者： Liupeng Guo Yannan Xiao Yayuan Wen Peizhi Wen School of Computer and Information Security Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China School of Computer and Information Security Guilin University of Electronic Technology Guilin China School of Electronic and Information Engineering/School of Integrated Circuits GUANGXI Normal University Guilin China

Generative summarization based on the seq2seq model has gained widespread adoption due to the advancements and efficacy of the sequence-to-sequence framework. However, these models encounter challenges in handling out-of-vocabulary words and may produce summaries with factual inaccuracies. This paper addresses these issues by proposing a summarization generation model, MBC, which is built upon the Transformer as the baseline model. Additionally, it incorporates the BERT pre-trained model, pointer generation network, contrastive attention mechanism, and coverage loss. The model employs a pointer generation network to augment its vocabulary coverage capabilities by generating new terms. To enhance the representation of key information from the source text, a contrastive attention mechanism is employed during summary generation. In addition, by introducing coverage loss, the model can reduce repetitive content in the summary. To assess the model’s performance, this paper employs ROUGE values as evaluation metrics and conducts comparative experiments with other models using the LCSTS dataset. The experimental results demonstrate that, in comparison with other models, this model is more adept at attending to salient information within the source text and generating summaries of greater accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep transfer learning-based decoder calibration for intracortical brain-machine interfaces

引用

Computers in Biology and Medicine 2025年第Pt A期192卷 110231-110231页

作者： Li, Xiao Dong, Xianxin Wang, Jun Mao, Haodong Tu, Xikai Li, Wei He, Jiping Li, Qiang Zhang, Peng Hubei Key Laboratory of Modern Manufacturing Quantity Engineering School of Mechanical Engineering Hubei University of Technology Wuhan430068 China Britton Chance Center for Biomedical Photonics Wuhan National Laboratory for Optoelectronics Huazhong University of Science and Technology Hubei Wuhan China MoE Key Laboratory for Biomedical Photonics Collaborative Innovation Center for Biomedical Engineering School of Engineering Sciences Huazhong University of Science and Technology Hubei Wuhan China The Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Hubei Wuhan China Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology Beijing China

Intracortical brain-machine interfaces (iBMIs) aim to establish a communication path between the brain and external devices. However, in the daily use of iBMIs, the non-stationarity of recorded neural signals necessitates frequent recalibration of the iBMI decoder to maintain decoding performance, which requires collecting and labeling a large amount of new data. To address this challenge and minimize the time needed for decoder recalibration, we proposed an active learning domain adversarial neural network (AL-DANN). This model leveraged a substantial volume of historical data alongside a small amount of current data (four samples per category) to calibrate the decoder. By incorporating domain adversarial and active learning strategies, the model effectively transferred knowledge from historical data to new data, reducing the demand for new samples. We validated the proposed method using neural signals recorded from three monkeys performing different movements in a classification task or a regression task. The results showed that the AL-DANN outperformed existing state-of-the-art methods. Impressively, it required only four new samples per category for decoder recalibration, leading to a recalibration time reduction of over 80 %. To our knowledge, this is the first study to incorporate deep transfer learning into iBMI decoder calibration, highlighting the significant potential of applying deep learning technologies in iBMIs. © 2025

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

High-Resolution representation object pose estimation from monocular images

High-Resolution representation object pose estimation from m...

引用

2021 China Automation Congress, CAC 2021

作者： Guan, Qi Li, Wenfa Xue, Shibei Li, Dewei Department of Automation Shanghai Jiao Tong University Shanghai200240 China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai200240 China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai200240 China

ISBN: (纸本)9781665426473

This paper addresses the 6D challenge of monocular 6D pose estimation on small targets and weak texture objects. We propose a monocular object pose estimation algorithm, High Resolution Object Pose Estimation (HRPE) based on the high-resolution feature representation, which detects the 2D keypoints and uses the Perspective-n-Point (PnP) algorithm to compute the 6D pose. HRPE can maintain high-resolution feature representation through parallel convolution of multi-resolution feature branches and repeated cross-scale fusion, generating more precise pose estimation. Experimental results show that HRPE surpasses the existing state-of-the-arts, and achieves a significant accuracy improvement for small objects, which demonstrates the effectiveness of high-resolution feature representation on pose estimation. © 2021 IEEE

关键词： Textures

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：