检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Qiao, Xiaoyu Li, Weisheng Xiao, Bin Huang, Yuping Yang, Lijian Chongqing Key Laboratory of Image Cognition Chongqing University of Posts and Telecommunications Chongqing China Key Laboratory of Cyberspace Big Data Intelligent Security Chongqing University of Posts and Telecommunications Ministry of Education Chongqing China

ISBN: (纸本)9798350368741

In accelerated MRI reconstruction problem, directly recovering all the missing k-space data from undersampled measurements is highly ill-posed and often leads to suboptimal performance. To address the problem, we propose a novel deep unfolding network (DUN) with subsampling decomposition (SD) based k-space refinement to mitigate the ill-posedness. Our method employs a parallel network architecture with a primary branch unfolded by gradient descent-inspired optimization process (GD-PB) for reconstruction. Additionally, we introduce an SD-based auxiliary branch (SD-AB) that decompose the inverse problem into moderately corrupted subproblems. We design a novel subsampling mask predictor that captures both global and local spatial correlations in k-space, ensuring the SD-AB effectively preserves the most well-reconstructed subsets as reliable region (RR). The RR in SD-AB is used to periodically refine the intermediate outputs of the GD-PB, achieving improved accuracy. Experimental results reveal that our method significantly outperforms conventional and SD-based DUN techniques, achieving superior PSNR and SSIM results compared with cutting-edge methods. © 2025 IEEE.

关键词： compressed sensing deep unfolded network MRI reconstruction parallel imaging subsampling decomposition

来源：评论

学校读者我要写书评

暂无评论

DualConv: Dual Convolutional Kernels for Lightweight Deep Neural Networks

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2023年第11期34卷 9528-9535页

作者： Zhong, Jiachen Chen, Junying Mian, Ajmal South China Univ Technol Sch Software Engn Guangzhou 510006 Peoples R China Minist Educ Key Lab Big Data & Intelligent Robot SCUT Guangzhou 510006 Peoples R China Univ Western Australia Dept Comp Sci Crawley WA 6009 Australia

Convolutional neural network (CNN) architectures are generally heavy on memory and computational requirements which make them infeasible for embedded systems with limited hardware resources. We propose dual convolutional kernels (DualConv) for constructing lightweight deep neural networks. DualConv combines 3x 3 and 1x 1 convolutional kernels to process the same input feature map channels simultaneously and exploits the group convolution technique to efficiently arrange convolutional filters. DualConv can be employed in any CNN model such as VGG-16 and ResNet-50 for image classification, you only look once (YOLO) and R-CNN for object detection, or fully convolutional network (FCN) for semantic segmentation. In this work, we extensively test DualConv for classification since these network architectures form the backbone for many other tasks. We also test DualConv for image detection on YOLO-V3. Experimental results show that, combined with our structural innovations, DualConv significantly reduces the computational cost and number of parameters of deep neural networks while surprisingly achieving slightly higher accuracy than the original models in some cases. We use DualConv to further reduce the number of parameters of the lightweight MobileNetV2 by 54% with only 0.68% drop in accuracy on CIFAR-100 dataset. When the number of parameters is not an issue, DualConv increases the accuracy of MobileNetV1 by 4.11% on the same dataset. Furthermore, DualConv significantly improves the YOLO-V3 object detection speed and improves its accuracy by 4.4% on PASCAL visual object classes (VOC) dataset.

关键词： Convolution Kernel Standards Computational modeling Network architecture Convolutional neural networks Feature extraction Dual convolution lightweight deep neural network parameter reduction performance improvement

来源：评论

学校读者我要写书评

暂无评论

Stacking U-Nets in U-shape: Redesigning the Information Flow in Model-based Networks for MRI Reconstruction

Stacking U-Nets in U-shape: Redesigning the Information Flow...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

ISBN: (纸本)9798350368741

Model-based networks have shown convincing performance in MRI reconstruction. However, the unrolled cascades within the networks are constrained to solely obtain information from the preceding counterpart, resulting in potential error accumulation. Moreover, the linear structure fails to address the challenge of recovering fine-grained details. To tackle these problems, we propose to redesign the information flow in model-based networks. Our method features a large U-shaped network, where the nodes are built with unrolled cascades and U-Net-based regularizers. We design an input-level integration module to help the cascades acquire information from adjacent and skip-connected counterparts, building robust mappings to the target. We further design a coarse-to-fine feature-level integration module, aiming at guiding the network to progressively recover fine details. Intermediate reconstructions produced by subnetworks of different scales are integrated, enabling the extraction of complementary information to enhance the final performance. Compared with cutting-edge methods on different datasets, our method exhibits superior performances. © 2025 IEEE.

关键词： compressed sensing deep learning model-based MRI reconstruction U-Net

来源：评论

学校读者我要写书评

暂无评论

Predictive control for greenhouse temperature and humidity and energy optimization by improved NMPC objective function algorithm

引用

International Journal of Agricultural and Biological Engineering 2024年第5期17卷 128-136页

作者： Lina Wang Ying Zhang Mengjie Xu Qiuhui Liu Binrui Wang Institute of Mechanical and Electrical Engineering China Jiliang UniversityHangzhou 310018China Zhejiang Province Key Laboratory of On-line Testing Equipment Calibration Technology Research China Jiliang UniversityHangzhou 310018China Zhejiang Provincial Key Laboratory of Intelligent Manufacturing Quality Big Data Traceability and Application China Jiliang UniversityHangzhou 310018China

Persistent low temperatures in autumn and winter have a huge impact on crops,and greenhouses rely on solar radiation and heating equipment to meet the required indoor *** the energy cost of frequent operation of the actuators is exceptionally *** relationship between greenhouse environmental control accuracy and energy consumption is one of the key issues faced in greenhouse *** this study,a non-linear model predictive control method with an improved objective function was *** improved objective function used tolerance intervals and boundary constraints to optimize the objective *** nonlinear model predictive control(NMPC)controller design was based on the wavelet neural network(WNN)data-driven model and applied the interior point method to solve the optimal solution of the objective function control,thus balancing the contradiction between energy consumption and control *** simulation results showed that the improved NMPC method reduced energy consumption by 21.02%and 9.54%compared with the model predictive control and regular NMPC,which proved the method achieved good results in a low-temperature *** research can provide an important reference for the field as it offers a more efficient approach to managing greenhouse climates,potentially leading to substantial energy savings and enhanced sustainability in agricultural practices.

关键词： greenhouse environmental control greenhouse energy optimization nonlinear model predictive control objective function improvement

来源：评论

学校读者我要写书评

暂无评论

Learning Preconditioners in Gates-controlled Deep Unfolding Networks based on Quasi-Newton Methods For Accelerated MRI Reconstruction

Learning Preconditioners in Gates-controlled Deep Unfolding ...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

ISBN: (纸本)9798350368741

Deep unfolding networks (DUNs) have made significant progress in MRI reconstruction, successfully tackling the problem of prolonged imaging time. However, the ill-conditioned nature of MRI reconstruction often causes slow convergence in iterative optimization, potentially compromising the performance of DUNs. In this study we propose a preconditioned and gates-controlled DUN (PGDUN) to address these challenges. Our approach starts with optimizing the step size of proximal gradient descent (PGD) through a preconditioner. To improve flexibility and adaptability, we relax the constrains on quasi-newton-based optimization procedure. We design ConvLSTM-based modules, where the gate units automatically preserve necessary long- and short-term information, facilitating the learning of optimized variables and their combinations. Furthermore, we design gate units to modulate the features fed to regularizers across different iterations, boosting their robustness against potential accumulated errors. Evaluations using PSNR and SSIM metrics reveal that our approach outperforms existing state-of-the-art methods, achieving superior reconstruction results across various sequences. © 2025 IEEE.

关键词： Compressed Sensing LSTM MRI reconstruction Preconditioner Quasi-Newton

来源：评论

学校读者我要写书评

暂无评论

Image denoising based on residual network 3

Image denoising based on residual network

引用

3rd International Conference on Electronic Information Engineering, big data, and Computer Technology, EIBDCT 2024

作者： Ma, Lihe Wang, Yan Sha, Ning Ma, Lin School of Information Engineering Harbin University Harbin China Heilongjiang Government Affairs Big Data Center3 Harbin China Heilongjiang Provincial Key Laboratory of the Intelligent Perception and Intelligent Software Harbin China

ISBN: (纸本)9781510680449

Image denoising has always been a hot research topic in the field of computer vision, playing an important role in improving image quality and accuracy. In this paper, a method for image denoising based on residual network is proposed, which uses deep learning technology to improve the effect of image processing. This method can automatically learn useful features in the image and effectively remove noise in the image, achieving automatic removal of image noise. Finally, experiments were conducted on standard image datasets for evaluation. The experimental results show that the image denoising method based on residual network has better performance compared to traditional methods. It can effectively remove various types of noise, improve image quality and clarity, and has broad application prospects in image processing. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Overcoming Debye length limitations:Three-dimensional wrinkled graphene field-effect transistor for ultra-sensitive adenosine triphosphate detection

引用

Frontiers of physics 2023年第5期18卷 183-192页

作者： Yue Ding Chonghui Li Meng Tian Jihua Wang Zhenxing Wang Xiaohui Lin Guofeng Liu Wanling Cui Xuefan Qi Siyu Li Weiwei Yue Shicai Xu School of Physics and Electronics Shandong Normal UniversityJinan 250014China Shandong Key Laboratory of Biophysics Institute of BiophysicsDezhou UniversityDezhou 253023China Shandong Engineering Laboratory of Swine Herd Health Big Data and Intelligent Monitoring Dezhou UniversityDezhou 253023China

Adenosine triphosphate(ATP)is closely related to the pathogenesis of certain diseases,so the detection of trace ATP is of great significance to disease diagnosis and drug *** field-effect transistors(GFETs)have been proven to be a promising platform for the rapid and accurate detection of small molecules,while the Debye shielding limits the sensitive detection in real ***,a three-dimensional wrinkled graphene field-effect transistor(3D WG-FET)biosensor for ultra-sensitive detection of ATP is *** lowest detection limit of 3D WG-FET for analyzing ATP is down to 3.01 aM,which is much lower than the reported *** addition,the 3D WG-FET biosensor shows a good linear electrical response to ATP concentrations in a broad range of detection from 10 aM to 10 ***,we achieved ultra-sensitive(LOD:10 aM)and quantitative(range from 10 aM to 100 fM)measurements of ATP in human *** 3D WG-FET also exhibits high *** work may provide a novel approach to improve the sensitivity for the detection of ATP in complex biological matrix,showing a broad application value for early clinical diagnosis and food health monitoring.

关键词： ATP in complex human serum three-dimensional wrinkled graphene field effect transistor Debye shielding ultra-sensitive

来源：评论

学校读者我要写书评

暂无评论

Research on Multi-AGVs dynamic scheduling based on deep reinforcement learning 19

Research on Multi-AGVs dynamic scheduling based on deep rein...

引用

19th IEEE International Conference on e-Business Engineering, ICEBE 2023

作者： Qin, Zhuorui Wu, Xiaoqian Zheng, Yimin Wu, Qingyao South China University of Technology School of Software Engineering Guangzhou China Key Laboratory of Big Data and Intelligent Robot Ministry of Education China Shenzhen Bangqi Technology Intelligent Development Co. Ltd Shenzhen China Pazhou Lab Guangzhou China

ISBN: (纸本)9798350325553

Driven by the latest advances in industrial artificial intelligence, automatic guided vehicles (AGVs) have been widely used for material handling in flexible workshops. In the pursuit of agile and flexible production transportation planning, the ability to handle unpredictable and dynamic events is becoming increasingly important. In order to achieve this real-time dynamic control, this study proposes a distributed multi-agent architecture to solve the dynamic Multi-AGVs scheduling problem. Double Deep Q-Network algorithm is used to train the scheduling agent, capture the relationship between production transportation operation information and scheduling goals, and make real-time scheduling decisions for flexible jobs with constant arrival intervals. Specialized state, action, and reward representations are proposed to handle variable specifications of dynamic scheduling problems. The performance of this method under different scene scales was verified through simulation studies. Numerical results show that compared with existing traditional heuristic scheduling strategies, this method not only has superior performance, but also its advantages persist even if the manufacturing system job scale changes. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Gradient-Based Differential kWTA Network With Application to Competitive Coordination of Multiple robots

引用

IEEE/CAA Journal of Automatica Sinica 2022年第8期9卷 1452-1463页

作者： Mei Liu Xiaoyan Zhang Mingsheng Shang Long Jin School of Information Science and Engineering Lanzhou UniversityLanzhou 730000 State Key Laboratory of Tibetan Intelligent Information Processing and Application Xining 810016China Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent TechnologyChinese Academy of SciencesChongqing 400714China Shenzhen Research Institute Lanzhou UniversityShenzhen 518063China

Aiming at the k-winners-take-all(kWTA)operation,this paper proposes a gradient-based differential kWTA(GDk WTA)*** obtaining the network,theorems and related proofs are provided to guarantee the exponential convergence and noise resistance of the proposed GD-kWTA ***,numerical simulations are conducted to substantiate the preferable performance of the proposed network as compared with the traditional ***,the GD-k WTA network,backed with a consensus filter,is utilized as a robust control scheme for modeling the competition behavior in the multi-robot coordination,thereby further demonstrating its effectiveness and feasibility.

关键词： Consensus filter k-winners-take-all(kWTA) multirobot coordination noise resistance

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Pre-Training for Detection Transformers

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2023年第11期45卷 12772-12782页

作者： Dai, Zhigang Cai, Bolun Lin, Yugeng Chen, Junying South China Univ Technol Sch Software Engn Guangzhou 510650 Guangdong Peoples R China Minist Educ Key Lab Big Data & Intelligent Robot SCUT Guangzhou 510006 Guangdong Peoples R China Tencent Wechat AI Guangzhou 510630 Guangdong Peoples R China

DEtection TRansformer (DETR) for object detection reaches competitive performance compared with Faster R-CNN via a transformer encoder-decoder architecture. However, trained with scratch transformers, DETR needs large-scale training data and an extreme long training schedule even on COCO dataset. Inspired by the great success of pre-training transformers in natural language processing, we propose a novel pretext task named random query patch detection in Unsupervised Pre-training DETR (UP-DETR). Specifically, we randomly crop patches from the given image and then feed them as queries to the decoder. The model is pre-trained to detect these query patches from the input image. During the pre-training, we address two critical issues: multi-task learning and multi-query localization. (1) To trade off classification and localization preferences in the pretext task, we find that freezing the CNN backbone is the prerequisite for the success of pre-training transformers. (2) To perform multi-query localization, we develop UP-DETR with multi-query patch detection with attention mask. Besides, UP-DETR also provides a unified perspective for fine-tuning object detection and one-shot detection tasks. In our experiments, UP-DETR significantly boosts the performance of DETR with faster convergence and higher average precision on object detection, one-shot detection and panoptic segmentation. Code and pre-training models: https://***/dddzg/up-detr.

关键词： Transformers Task analysis Object detection Feature extraction Training Location awareness Decoding Object detection one-shot detection self-supervised learning transformer unsupervised pre-training

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：