检索结果-内蒙古大学图书馆

A Parallel Read-Write Circuit With Fast Amplitude-Adaptive Matching Scheme to Memristor Crossbar Array

学校读者我要写书评

暂无评论

IEEE Transactions on Circuits and Systems I: Regular Papers 2025年

作者： Jiang, Ningye Jiang, Mingxuan Huang, Haoen Yang, Le Huang, Yi Zeng, Zhigang Huazhong University of Science and Technology School of Artificial Intelligence and Automation Key Laboratory of Image Information Processing and Intelligent Control Ministry of Education of China Wuhan430074 China Wuhan Institute of Technology School of Electrical and Information Engineering Wuhan430205 China University of Massachusetts Amherst Department of Electrical and Computer Engineering AmherstMA01003 United States

Memristor crossbar array (MCA) is a computing-in-memory (CIM) module for computational acceleration. However, conventional read-write (R-W) circuits for MCA rely heavily on external components and have shortcoming in long writing times. To address these issues, we propose a parallel R-W circuit with a fast amplitude-adaptive matching (AAM) scheme. The fast AAM scheme is designed to accelerate time of writing memristors in MCA by adaptively adjusting the writing voltage to match an optimal amplitude. The architecture of parallel R-W circuit are outlined with the implementation of R-W processes. The design principles of parallel R-W unit, fast AAM unit, and associated control logic are described for analyzing their functions within the circuit. By integrating the parallel R-W circuit with MCA, a computing block is leveraged in a neural network for classification tasks. The experimental results demonstrate that the neural network with multiple computing blocks maintains high accuracy across various datasets (over 80%). Furthermore, the proposed AAM scheme achieves an average 54% reduction in writing time compared to that one without AAM scheme. Compared to the pulse-width scheme, the parallel R-W circuit exhibits an average 3.05× speedup in adjusting a 5×5 MCA, and the speedup efficiency is higher as the increases of MCA size. © 2025 IEEE.

关键词： Memristors

A Point Cloud Segmentation Method Based on Ground Point Cloud Removal and Multi-Scale Twin Range image

学校读者我要写书评

暂无评论

A Point Cloud Segmentation Method Based on Ground Point Clou...

Chinese control Conference (CCC)

作者： Yicheng Zhou Gang Peng Hangqi Duan Zhangang Wu Xukang Zhu School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan China Shantui Construction Machinery Co. Ltd. Jining China

Aiming at the shortcomings of traditional point cloud segmentation algorithms, this paper proposes a 3D lidar point cloud segmentation method combining ground filtering and multi-scale twin range image construction. This method fully considers the geometric space distribution characteristics of the point cloud and the randomness of the positions between objects. Based on the assumption of multi plane model, the point cloud is divided into sectors. The ground points are removed through region ground plane fitting and growth, and then the multi-scale twin range image is constructed according to non-ground points. On the basis of the twin range image, the Breadth First Search algorithm is improved, the depth-breadth joint search strategy is proposed, all the points to be clustered are traversed, and the adaptive clustering threshold is used for point cloud clustering, which realizes a point cloud segmentation method with higher accuracy and robustness. Through the experimental analysis of KITTI dataset and collected campus outdoor scene dataset, compared with the traditional point cloud segmentation algorithm, the method proposed in this paper can effectively improve the point cloud segmentation accuracy and robustness of mobile robots in complex environments.

关键词：

Difference in Uptake Pattern Heterogeneity and Reproducibility of Radiomics Features Between FAPI and FDG Pet/Ct Imaging of Tumors

学校读者我要写书评

暂无评论

Difference in Uptake Pattern Heterogeneity and Reproducibili...

IEEE International Symposium on Biomedical Imaging

作者： Tianmeng Xu Yanchao Huang Tingting Ang Shuilin Chu Peiyin Luo Shunfang Wang Yufeng Zhang Lijun Lu Ganghua Tang Wenbing Lv School of Information and Yunnan Key Laboratory of Intelligent Systems and Computing Yunnan University Kunming China Department of Nuclear Medicine Laboratory for Quality Control and Evaluation of Radiopharmaceuticals Nanfang Hospital Southern Medical University Guangzhou China School of Biomedical Engineering and Guangdong Provincial Key Laboratory of Medical Image Processing Southern Medical University Guangzhou China

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

To investigate the difference in uptake pattern heterogeneity between fluorodeoxyglucose (FDG) and fibroblast activation protein inhibitor (FAPI) PET/CT and the reproducibility of radiomics features with respect to different calculation methods of standardized uptake value (SUV). 210 patients with various tumors were involved. Among the extracted 497 radiomics features, there are only 20 features that exhibited an ICC difference of more than 0.25 between the two tracers when using different SUV calculation methods, revealing the similar influence of SUV calculation methods. In contrast, the ICC values for most texture features were generally lower (0.22-0.39) between FDG and FAPI PET images, indicating a large difference in uptake pattern heterogeneity between the two tracers. Our results demonstrated that the influence of SUV calculation methods on the reproducibility of FDG and FAPI PET features is similar. The uptake pattern heterogeneity characterized by radiomics features between FDG and FAPI PET images is significantly different.

关键词： Proteins Protein engineering Inhibitors Fibroblasts Feature extraction Reproducibility of results Radiomics

Model Predictive control Method for Multi-motor System with Dead Zone

学校读者我要写书评

暂无评论

Model Predictive Control Method for Multi-motor System with ...

作者： Genglin Fan Xiuchuan Tang Yi Shen Linan Deng China-EU Institute for Clean and Renewable Energy Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology School of Mechanical Science and Engineering Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology

The multi-motor system shows excellent performance in achieving high-precision control in the applications with large load inertia,such as large-aperture telescopes and highprecision processing machine ***,the non-linearity of gear transmission remains a key challenge that will cause the fluctuation of angular velocity and position of the load in the multi-motor *** order to compensate for the nonlinearity in the multi-motor system,this paper introduces a deadzone model into the spring-damper dynamics of the multi-motor system,based on which a model predictive control(MPC) method is proposed to control the angular velocity and angle of the *** optimization target of the proposed controller is to limit the fluctuations of input torque as much as *** effectiveness of the dead-zone based dynamic model and the MPC method are verified by simulation.

关键词： multi-motor system MPC dead zone

Semi-Supervised Class-Agnostic Motion Prediction with Pseudo Label Regeneration and BEVMix

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Kewei Wu, Yizheng Pan, Zhiyu Li, Xingyi Xian, Ke Wang, Zhe Cao, Zhiguo Lin, Guosheng S-Lab Nanyang Technological University Singapore Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China SenseTime Research Hong Kong

Class-agnostic motion prediction methods aim to comprehend motion within open-world scenarios, holding significance for autonomous driving systems. However, training a high-performance model in a fully-supervised manner always requires substantial amounts of manually annotated data, which can be both expensive and time-consuming to obtain. To address this challenge, our study explores the potential of semi-supervised learning (SSL) for class-agnostic motion prediction. Our SSL framework adopts a consistency-based self-training paradigm, enabling the model to learn from unlabeled data by generating pseudo labels through test-time inference. To improve the quality of pseudo labels, we propose a novel motion selection and re-generation module. This module effectively selects reliable pseudo labels and regenerates unreliable ones. Furthermore, we propose two data augmentation strategies: temporal sampling and BEVMix. These strategies facilitate consistency regularization in SSL. Experiments conducted on nuScenes demonstrate that our SSL method can surpass the self-supervised approach by a large margin by utilizing only a tiny fraction of labeled data. Furthermore, our method exhibits comparable performance to weakly and some fully supervised methods. These results highlight the ability of our method to strike a favorable balance between annotation costs and performance. Code will be available at https://***/kwwcv/SSMP. Copyright © 2023, The Authors. All rights reserved.

关键词： Forecasting

Lifetime Extension control for Multi-Stack SOFC System with Inconsistent Stacks

学校读者我要写书评

暂无评论

Lifetime Extension Control for Multi-Stack SOFC System with ...

Chinese control Conference (CCC)

作者： Zexin Li Guoqiang Liu Wei Zhao Xi Li Key Laboratory of Image Processing and Intelligent Control of Education Ministry School of Artificial Intelligence and Automation Huazhong University of Science & Technology Wuhan Hubei China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen Guangdong China

The multi-stack fuel cell system (MFCS) is an important basis for the application of solid oxide fuel cell (SOFC) technology to large-scale power generation systems. MFCS can provide higher power, longer lifetime and better reliability. Different from the single-stack fuel cell system (SFCS), there may be some inconsistencies among the stacks in the MFCS. If the inconsistencies are ignored, they will significantly affect the lifetime of the MFCS. This study focuses on the lifetime extension of multi-stack SOFC power generation systems with inconsistent stacks. Since the multi-stack system of SOFC generally cannot control the flow rate of each stack respectively, it brings a difficulty to the control of the MFCS with inconsistencies among the stacks. In order to overcome this difficulty, this paper built a multi-stack SOFC system model, which can characterize the degradation and inconsistencies among SOFC stacks. And then designed a power distribution strategy based on fuzzy control to extend the lifetime of the MFCS. The strategy was verified by simulations. The simulation results show that the strategy can effectively control the inconsistencies among the stacks and significantly extend the lifetime of the MFCS.

关键词：

Constraining Depth Map Geometry for Multi-View Stereo: A Dual-Depth Approach with Saddle-shaped Depth Cells

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ye, Xinyi Zhao, Weiyue Liu, Tianqi Huang, Zihao Cao, Zhiguo Li, Xin Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Department of Computer Science University of Albany AlbanyNY12222 United States

Learning-based multi-view stereo (MVS) methods deal with predicting accurate depth maps to achieve an accurate and complete 3D representation. Despite the excellent performance, existing methods ignore the fact that a suitable depth geometry is also critical in MVS. In this paper, we demonstrate that different depth geometries have significant performance gaps, even using the same depth prediction error. Therefore, we introduce an ideal depth geometry composed of Saddle-Shaped Cells, whose predicted depth map oscillates upward and downward around the ground-truth surface, rather than maintaining a continuous and smooth depth plane. To achieve it, we develop a coarse-to-fine framework called Dual-MVSNet (DMVSNet), which can produce an oscillating depth plane. Technically, we predict two depth values for each pixel (Dual-Depth), and propose a novel loss function and a checkerboard-shaped selecting strategy to constrain the predicted depth geometry. Compared to existing methods,DMVSNet achieves a high rank on the DTU benchmark and obtains the top performance on challenging scenes of Tanks and Temples, demonstrating its strong performance and generalization ability. Our method also points to a new research direction for considering depth geometry in MVS. Copyright © 2023, The Authors. All rights reserved.

关键词： Geometry

Transmission-Constrained Consensus of Multiagent Networks

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wang, Xiaotian Su, Housheng School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan430074 China

This paper studies the consensus problem for multiagent systems with transmission constraints. A novel model of multiagent systems is proposed where the information transmissions between agents are disturbed by irregular distortions or interferences (named transmission constraint functions), and this model is universal which can be applied in many cases, such as interval consensus and discarded consensus. In the transmission-constrained consensus problem, we obtain the necessary and sufficient condition that agents can converge to state consensus. Furthermore, a more general case is studied in which the system reaches an equilibrium. Based on some techniques of algebraic topology and stability theory, the existence, uniqueness and stability of the system equilibrium point can be proven, which means the system can reach an asymptotically stable equilibrium. Moreover, the state values of the equilibrium are only decided by the network structure and transmission constraint functions, but not the agents’ initial states. Finally, numerical simulations are presented to illustrate the proposed theorems and corollaries. © 2022, CC BY-NC-SA.

关键词： Directed graphs

Fast Full-frame Video Stabilization with Iterative Optimization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhao, Weiyue Li, Xin Peng, Zhan Luo, Xianrui Ye, Xinyi Lu, Hao Cao, Zhiguo Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Department of Computer Science University of Albany AlbanyNY12222 United States

Video stabilization refers to the problem of transforming a shaky video into a visually pleasing one. The question of how to strike a good trade-off between visual quality and computational speed has remained one of the open challenges in video stabilization. Inspired by the analogy between wobbly frames and jigsaw puzzles, we propose an iterative optimization-based learning approach using synthetic datasets for video stabilization, which consists of two interacting submodules: motion trajectory smoothing and full-frame outpainting. First, we develop a two-level (coarse-to-fine) stabilizing algorithm based on the probabilistic flow field. The confidence map associated with the estimated optical flow is exploited to guide the search for shared regions through backpropagation. Second, we take a divide-and-conquer approach and propose a novel multiframe fusion strategy to render full-frame stabilized views. An important new insight brought about by our iterative optimization approach is that the target video can be interpreted as the fixed point of nonlinear mapping for video stabilization. We formulate video stabilization as a problem of minimizing the amount of jerkiness in motion trajectories, which guarantees convergence with the help of fixed-point theory. Extensive experimental results are reported to demonstrate the superiority of the proposed approach in terms of computational speed and visual quality. The code will be available on GitHub. Copyright © 2023, The Authors. All rights reserved.

关键词： Iterative methods