检索结果-内蒙古大学图书馆

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Chiyang Liu Xinxing Chen Jian Huang Hubei Key Laboratory of Brain-inspired Intelligent Systems and the Key Laboratory for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Southern University of Science and Technology Shenzhen China

ISBN: (数字)9798350385724

ISBN: (纸本)9798350385731

Mobile robots for Gas Source Localization (GSL) tasks are a safer alternative than human and animal rescuers in hazardous scenarios. Existing research primarily concentrates on rule-based algorithms or conventional artificial neural networks (ANNs). However, these approaches are either inapplicable in cluttered environments or undeployable due to their high energy consumption and the demand for substantial computational resources. This paper introduces the application of energy-efficient spiking neural networks (SNNs) to address robotic GSL tasks. A pipeline is proposed to train SNNs with deep Q learning and a pretrain-finetune paradigm. To facilitate the training process, a small dataset of gas dispersion is generated utilizing openFoam and GADEN, a high-fidelity simulator for gas dispersion. Data from a simplified plume model are leveraged to pretrain an ANN, the activation function of which gradually transitions from a bounded rectified linear unit (bReLU) to a step function. Subsequently, an SNN initialized with the ANN parameters undergoes finetuning on the GADEN-based dataset. The training pipeline significantly reduces training time compared to direct training of SNNs. The trained SNN is validated within the GADEN simulation environment and compared to three different models, demonstrating promising performance and superior generalization despite limited training data.

关键词： Training Location awareness Q-learning Mechatronics Pipelines Training data Spiking neural networks Data models Mobile robots Dispersion

来源：评论

学校读者我要写书评

暂无评论

Hybrid Data-Free Knowledge Distillation

arXiv

引用

arXiv 2024年

作者： Tang, Jialiang Chen, Shuo Gong, Chen School of Computer Science and Engineering Nanjing University of Science and Technology China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education China Jiangsu Key Laboratory of Image and Video Understanding for Social Security China Center for Advanced Intelligence Project RIKEN Japan Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

Data-free knowledge distillation aims to learn a compact student network from a pre-trained large teacher network without using the original training data of the teacher network. Existing collection-based and generation-based methods train student networks by collecting massive real examples and generating synthetic examples, respectively. However, they inevitably become weak in practical scenarios due to the difficulties in gathering or emulating sufficient real-world data. To solve this problem, we propose a novel method called Hybrid Data-Free Distillation (HiDFD), which leverages only a small amount of collected data as well as generates sufficient examples for training student networks. Our HiDFD comprises two primary modules, i.e., the teacher-guided generation and student distillation. The teacher-guided generation module guides a Generative Adversarial Network (GAN) by the teacher network to produce high-quality synthetic examples from very few real-world collected examples. Specifically, we design a feature integration mechanism to prevent the GAN from overfitting and facilitate the reliable representation learning from the teacher network. Meanwhile, we drive a category frequency smoothing technique via the teacher network to balance the generative training of each category. In the student distillation module, we explore a data inflation strategy to properly utilize a blend of real and synthetic data to train the student network via a classifier-sharing-based feature alignment technique. Intensive experiments across multiple benchmarks demonstrate that our HiDFD can achieve state-of-the-art performance using 120 times less collected data than existing methods. Code is available at https://***/tangjialiang97/HiDFD. Copyright © 2024, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

CR-Famba: A Frequency-Domain Assisted Mamba for Thin Cloud Removal in Optical Remote Sensing imagery

引用

IEEE Transactions on Multimedia 2025年

作者： Liu, Jiao Pan, Bin Shi, Zhenwei Nankai University TKLNDST College of Computer Science Tianjin300350 China Nankai University School of Statistics and Data Science KLMDASR LEBPS LPMC Tianjin300071 China Beihang University Image Processing Center School of Astronautics the State Key Laboratory of Virtual Reality Technology and Systems Beijing100191 China

Optical remote sensing images are inevitably affected by cloud cover. To remove clouds from optical remote sensing images, a series of deep learning-based thin cloud removal methods have been developed. However, these methods have not explored the long-range modeling ability of state space models in optical remote sensing image thin cloud removal. In this paper, we propose a frequency-domain assisted Mamba for thin cloud removal, which is called CR-Famba. In CR-Famba, to better extract global and local features of images, we design a frequency-domain assisted state space layer (FDA-SSL). The FDA-SSL consists of two core components: residual state space block (RSSB) and frequency domain detail enhancement block (FDDEB). The RSSB utilizes the visual state space module (VSSM) to extract long-range dependencies of images from a spatial perspective while adding convolutional layers to overcome local pixel forgetting. Due to the rich detailed information of remote sensing images, we present FDDEB equipped with discrete wavelet transform (DWT) to supplement the extracted local information from the frequency domain perspective. We conduct experiments on different types of cloud-containing datasets, and the results show that our method can recover images with clearer texture details compared to other methods. https://***/Lab-PANbin/ © 2025 IEEE.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

ENHANCING KERNEL FLEXIBILITY VIA LEARNING ASYMMETRIC LOCALLY-ADAPTIVE KERNELS

arXiv

引用

arXiv 2023年

作者： He, Fan He, Mingzhen Shi, Lei Huang, Xiaolin Suykens, Johan A.K. STADIUS Center for Dynamical Systems Signal Processing and Data Analytics KU Leuven Belgium Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China Shanghai Key Laboratory for Contemporary Applied Mathematics School of Mathematical Sciences Fudan University China

The lack of sufficient flexibility is the key bottleneck of kernel-based learning that relies on manually designed, pre-given, and non-trainable kernels. To enhance kernel flexibility, this paper introduces the concept of Locally-Adaptive-Bandwidths (LAB) as trainable parameters to enhance the Radial Basis Function (RBF) kernel, giving rise to the LAB RBF kernel. The parameters in LAB RBF kernels are data-dependent, and its number can increase with the dataset, allowing for better adaptation to diverse data patterns and enhancing the flexibility of the learned function. This newfound flexibility also brings challenges, particularly with regards to asymmetry and the need for an efficient learning algorithm. To address these challenges, this paper for the first time establishes an asymmetric kernel ridge regression framework and introduces an iterative kernel learning algorithm. This novel approach not only reduces the demand for extensive support data but also significantly improves generalization by training bandwidths on the available training data. Experimental results on real datasets underscore the remarkable performance of the proposed algorithm, showcasing its superior capability in handling large-scale datasets compared to Nyström approximation-based algorithms. Moreover, it demonstrates a significant improvement in regression accuracy over existing kernel-based learning methods and even surpasses residual neural networks. Copyright © 2023, The Authors. All rights reserved.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

USV Path Planning Based on ACO-SA Algorithm

USV Path Planning Based on ACO-SA Algorithm

引用

Chinese Control Conference (CCC)

作者： Chuanshang Luo Yifeng Tang Zhihui Huang Yifan Xu Bin Liu Hai-Tao Zhang the Engineering Research Center of Autonomous Intelligent Unmanned Systems the Key Laboratory of Image Processing and Intelligent Control and the State Key Laboratory of Digital Manufacturing Equipment and Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

This paper solves USV path planning problem constrained by multiple factors via ant-colony optimization algorithm. First, this paper uses the ways of multi-objective optimization to model the USV path planning problem. An improved ant colony algorithm named ACO-SA is put forward afterwards to effectively solve the problem. The algorithm is a combination of ACO algorithm(ant colony algorithm) and SA algorithm(simulated annealing algorithm), which has three improments: change the initial distribution of pheromone to guide the search when the algorithm has just started running; change the heuristic function and state transition probability taking three factors into consideration; change the pheromone update rule and make the ants compete for the right to update pheromone by simulated annealing algorithm, and update the best solution by the same algorithm. Finally, simulation experiment and field experiment are conducted to check the validity of ACO-SA algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

WDNet: A Water Depth Perception Network with Global Information

WDNet: A Water Depth Perception Network with Global Informat...

引用

Chinese Control Conference (CCC)

作者： Zhihui Huang Yifeng Tang Chuancong Tang Yifan Xu ChuanShang Luo Bin Liu Hai-Tao Zhang the Key Laboratory of Image Processing and Intelligent Control and the State Key Laboratory of Digital Manufacturing Equipment and Technology School of Artificial Intelligence and Automation the Engineering Research Center of Autonomous Intelligent Unmanned Systems Huazhong University of Science and Technology Wuhan China

Deep perception of the unmanned surface vehicle's surroundings is an inaccessible part of its fully autonomous navigation mission. The existing methods, whether based on traditional stereo matching or deep learning, do not fully consider the characteristics of water environment, resulting in severe error depths in weak textures (sky, calm lake) and water reflections regions, that increases the risk of running aground or collision. What is worse that there is not a public dataset for depth estimation in the water environment. Therefore, this work proposes a self-supervised model for depth estimation named Water Depth Perception Network (WDNet) to address these problems. The decoder of this network has a wider receptive field and can effectively handle the depth error in the weak texture region. Besides, the WDNet is trained with a novel and effective loss function which assist the network to reduce errors in sky and water region, and some indexes are proposed to evaluate the model's performances in sky and water region. Finally, our proposed WDNet achieves a 0.1056 absolute relative error in ranging, the average number of error pixels in the sky area drops from 15803.87 to 580.91, which only accounted for 0.29% of the image, and the error in water region drops from 51.04 to 6.75, all of them are superior to the performance of baseline model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Koopman Operator Learning Control of the Piezoelectric Actuator

Koopman Operator Learning Control of the Piezoelectric Actua...

引用

Chinese Control Conference (CCC)

作者： Xiang Huang Hai-Tao Zhang Engineering Research Center of Autonomous Intelligent Unmanned Systems the Key Laboratory of Image Processing and Intelligent Control and the State Key Laboratory of Digital Manufacturing Equipment and Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

The piezoelectric actuator is one kind of device that can drive nanoscale motion. However, the nonlinear hysteresis effect induced by its natural material greatly degrades its positioning accuracy. To handle this challenging issue, this work develops a Koopman model predict control (Koopman- MPC) framework for the piezoelectric actuator. Specifically, the Koopman operator theory is adapted for modeling the piezoelectric actuator dynamics. A simple yet powerful linear model spanned in a high-dimensional space is thus constructed to characterize the hysteresis dynamics. Subsequently, upon the established Koopman model, an MPC scheme is put forward for tracking control of piezoelectric actuators. Therein, by sustained optimizing a cost function containing future outputs and control increments, the control input is obtained. Moreover, extensive tracking simulations are carried out on a simulated piezoelectric actuator for verifying the feasibility and effectiveness of the Koopman- Mpc scheme.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Graph Dismantling with Reinforcement Supervised Learning

Dynamic Graph Dismantling with Reinforcement Supervised Lear...

引用

Chinese Control Conference (CCC)

作者： Yumei Wang Chuancong Tang Hai-Tao Zhang the Engineering Research Center of Autonomous Intelligent Unmanned Systems the Key Laboratory of Image Processing and Intelligent Control and the State Key Laboratory of Digital Manufacturing Equipment and Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

There are always some “key” nodes in a big complex network, which can joint the most connected subgraphs. How to identify these nodes, finding a minimum set of nodes to attack for reducing the size of residual network's Largest Connected Component(LCC) to break up the original network, has become a research hotspot. Therefore, a method for determining the “key” nodes based on reinforcement learning framework and supervised learning model is proposed. This algorithm can not only utilize the dynamic exploration ability of reinforcement learning to collect a rich training dataset, but also take advantage of the characteristics that supervised learning is adaptive and has strong generalization ability to possess high efficiency and strong robustness. In order to further improve the algorithm's performance, $\epsilon$ -greedy mechanism is used to explore more network states. The experiment results show that given the same fraction of removed nodes, our algorithm can make the residual LCC smaller in various networks which is superior to the state-of-the-art algorithms in terms of effectiveness and generalization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Canine EEG Helps Human: Cross-Species and Cross-Modality Epileptic Seizure Detection via Multi-Space Alignment

arXiv

引用

arXiv 2024年

作者： Wang, Ziwei Li, Siyang Wu, Dongrui Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Hubei Key Laboratory of Brain-inspired Intelligent Systems School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

Epilepsy significantly impacts global health, affecting about 65 million people worldwide, along with various animal species. The diagnostic processes of epilepsy are often hindered by the transient and unpredictable nature of seizures. Here we propose a multi-space alignment approach based on cross-species and cross-modality electroencephalogram (EEG) data to enhance the detection capabilities and understanding of epileptic seizures. By employing deep learning techniques, including domain adaptation and knowledge distillation, our framework aligns cross-species and cross-modality EEG signals to enhance the detection capability beyond traditional within-species and within-modality models. Experiments on multiple surfaces and intracranial EEG datasets of humans and canines demonstrated substantial improvements in detection accuracy, achieving over 90% AUC scores for cross-species and cross-modality seizure detection with extremely limited labeled data from the target species/modality. To our knowledge, this is the first study that demonstrates the effectiveness of integrating heterogeneous data from different species and modalities to improve EEG-based seizure detection performance. This is a pilot study that provides insights into the challenges and potential of multi-species and multi-modality data integration, offering an effective solution for future work to collect huge EEG data to train large brain models. © 2024, CC BY.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Memristor-Based Circuit of Sequential Associative Memory with Memory Interactions and Stimulus Similarity Effect

引用

IEEE Transactions on Cognitive and Developmental systems 2025年

作者： Xiong, Dongdong Wang, Xiaoping Jiang, Yiming Yang, Chao Jiang, Man Lai, Jingang Zeng, Zhigang Huazhong University of Science and Technology School of Artificial Intelligence and Automation Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan430074 China Hubei Key Laboratory of Braininspired Intelligent Systems Wuhan430074 China Huazhong University of Science and Technology Institute of Artificial Intelligence School of Artificial Intelligence and Automation Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan430074 China Guangxi University of Science and Technology School of Computer Science and Technology Liuzhou545006 China Huazhong University of Science and Technology Department of Physiology School of Basic Medicine and Tongji Medical College Wuhan430030 China

Most proposed memristor-based circuits of associative memory consider various mechanisms in only one associative memory. Few works on circuit design of sequential associative memory have been reported. In this paper, a memristor-based circuit of sequential associative memory with memory interactions and stimulus similarity effect is designed. Two associative memories, the prior associative memory (PAM) and the later associative memory (LAM), are formed successively. The PAM modifies the rate of the formation of the LAM, and the LAM, in turn, affects the strength of the PAM, which are two interactions in sequential associative memory, called transfer and retroaction. In addition, the magnitudes of transfer and retroaction are determined by the similarity of the conditioned stimuli. The above functions are realized by the ring input processing module, memory module, transfer module and retroaction module. It has been identified in circuit analysis that the proposed circuit is power efficient and has good robustness. Furthermore, the proposed circuit has promising applications for fire rescue robots. © 2016 IEEE.

关键词： Associative storage

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：