检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zhang, Zejia Yang, Bo Chen, Xinxing Shi, Weizhuang Wang, Haoyuan Luo, Wei Huang, Jian Hubei Key Laboratory of Brain-Inspired Intelligent Systems Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China State key laboratory of intelligent vehicle safety technology chongqing changan automobile co ltd Chongqing400023 China Science and technology innovation center China ship development and design centre Wuhan430060 China

A promising effective human-robot interaction in assistive robotic systems is gaze-based control. However, current gaze-based assistive systems mainly help users with basic grasping actions, offering limited support. Moreover, the restricted intent recognition capability constrains the assistive system’s ability to provide diverse assistance functions. In this paper, we propose an open implicit intention recognition framework powered by Large Language Model (LLM) and Vision Foundation Model (VFM), which can process gaze input and recognize user intents that are not confined to predefined or specific scenarios. Furthermore, we implement a gaze-driven LLM-enhanced assistive robot system (MindEye-OmniAssist) that recognizes user’s intentions through gaze and assists in completing task. To achieve this, the system utilizes open vocabulary object detector, intention recognition network and LLM to infer their full intentions. By integrating eye movement feedback and LLM, it generates action sequences to assist the user in completing tasks. Real-world experiments have been conducted for assistive tasks, and the system achieved an overall success rate of 41/55 across various undefined tasks. Preliminary results show that the proposed method holds the potential to provide a more user-friendly human-computer interaction interface and significantly enhance the versatility and effectiveness of assistive systems by supporting more complex and diverse task. Copyright © 2025, The Authors. All rights reserved.

关键词： Eye movements

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Transfer Boosting (SS-TrBoosting)

arXiv

引用

arXiv 2024年

作者： Deng, Lingfei Zhao, Changming Du, Zhenbang Xia, Kun Wu, Dongrui The 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 Shenzhen Huazhong University Science and Technology Research Institute Shenzhen518063 China

Semi-supervised domain adaptation (SSDA) aims at training a high-performance model for a target domain using few labeled target data, many unlabeled target data, and plenty of auxiliary data from a source domain. Previous works in SSDA mainly focused on learning transferable representations across domains. However, it is difficult to find a feature space where the source and target domains share the same conditional probability distribution. Additionally, there is no flexible and effective strategy extending existing unsupervised domain adaptation (UDA) approaches to SSDA settings. In order to solve the above two challenges, we propose a novel fine-tuning framework, semi-supervised transfer boosting (SS-TrBoosting). Given a well-trained deep learning-based UDA or SSDA model, we use it as the initial model, generate additional base learners by boosting, and then use all of them as an ensemble. More specifically, half of the base learners are generated by supervised domain adaptation, and half by semi-supervised learning. Furthermore, for more efficient data transmission and better data privacy protection, we propose a source data generation approach to extend SS-TrBoosting to semi-supervised source-free domain adaptation (SS-SFDA). Extensive experiments showed that SS-TrBoosting can be applied to a variety of existing UDA, SSDA and SFDA approaches to further improve their performance. © 2024, CC BY.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A New Multi-Scale Model for Medium-Term Load Forecasting

A New Multi-Scale Model for Medium-Term Load Forecasting

引用

Chinese Control and Decision Conference, CCDC

作者： Peng Liu Hongliang Fang Jiang-Wen Xiao Yan-Wu Wang Xiao-Kang Liu School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Ministry of Education Key Laboratory of Image Processing and Intelligent Control (Huazhong University of Science and Technology) Wuhan China

When a large number of distributed power and renewable energy are connected to the smart grid, the volatility and intermittency of renewable energy bring some challenges to the smart grid. Therefore, accurate medium-term load forecasting is essential because it is conducive to the stability of the power grid and can provide data support for the power generating plan. Many factors affect medium-term load forecasting and the real-time electricity price is a very important factor among them. In this paper, a multi-scale model based on LSTM model is proposed to extracts features from 3 different time scales including half-hourly time scale, daily time scale and monthly time scale. At first, the half-hourly data is processed by a half-hourly data processing layer to extract the half-hourly features. Then, its output is concatenated with the daily load data and is input into a daily data processing layer. Finally, the daily features are concatenated with the monthly load data and they are input into a monthly data processing layer to extract the monthly features and get the final forecasting results. The case study results demonstrate that the proposed multi-scale model has better performance than the single-scale models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Speech Cryptosystem Using the New Chaotic System with a Capsule-Shaped Equilibrium Curve

引用

Computers, Materials & Continua 2023年第6期75卷 5987-6006页

作者： Mohamad Afendee Mohamed Talal Bonny Aceng Sambas Sundarapandian Vaidyanathan Wafaa Al Nassan Sen Zhang Khaled Obaideen Mustafa Mamat Mohd Kamal Mohd Nawawi Faculty of Informatics and Computing Universiti Sultan Zainal AbidinMalaysia Department of Computer Engineering University of SharjahSharjah26666UAE Department of Mechanical Engineering Universitas Muhammadiyah TasikmalayaIndonesia Research and Development Centre Vel Tech UniversityAvadiChennaiIndia School of Artificial Intelligence and Automationand Key Laboratory of Image Processingand Intelligent Control of Education Ministry of ChinaHuazhong University of Scienceand TechnologyWuhan430074China Institute of Strategic Industrial Decision Modeling School of Quantitative SciencesUniversiti Utara Malaysia06010UUM SintokKedahMalaysia

In recent years,there are numerous studies on chaotic systems with special equilibrium curves having various shapes such as circle,butterfly,heart and *** paper describes a new 3-D chaotic dynamical system with a capsule-shaped equilibrium *** proposed chaotic system has two quadratic,two cubic and two quartic nonlinear *** is noted that the proposed chaotic system has a hidden attractor since it has an infinite number of equilibrium *** is also established that the proposed chaotic system exhibits multi-stability with two coexisting chaotic attractors for the same parameter values but differential initial states.A detailed bifurcation analysis with respect to variations in the system parameters is portrayed for the new chaotic system with capsule equilibrium *** have shown MATLAB plots to illustrate the capsule equilibrium curve,phase orbits of the new chaotic system,bifurcation diagrams and *** an engineering application,we have proposed a speech cryptosystem with a numerical algorithm,which is based on our novel 3-D chaotic system with a capsule-shaped equilibrium *** proposed speech cryptosystem follows its security evolution and implementation on Field Programmable Gate Array(FPGA)*** results show that the proposed encryption system utilizes 33%of the FPGA,while the maximum clock frequency is 178.28 MHz.

关键词： Chaos chaotic systems hidden attractors multi-stability bifurcation speech cryptosystem FPGA design

来源：评论

学校读者我要写书评

暂无评论

RP-MSTC*: Multi-Agent Coverage Path Planning Algorithm Emphasizing Local Area Updates

RP-MSTC*: Multi-Agent Coverage Path Planning Algorithm Empha...

引用

Neuromorphic Computing (ICNC), International Conference on

作者： Yong Yang Dingxin He Huantao Mao Hong Chen Hongtao Wu Zhi-Wei Liu 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 Huazhong University of Science and Technology Wuhan China

Compared to traditional area coverage algorithms, this paper proposes a re-plannable multi-agent coverage path planning algorithm to address issues such as low coverage rate of multiple agents in large-scale scenarios like warehouses and inability to cope with local environmental changes. Initially, the MSTC * algorithm is utilized to create the coverage path based on the available map information. To address scenarios like idle areas for material placement, the method introduces local area detection and path re-planning to enhance the coverage rate. This paper verifies the feasibility and effectiveness of the algorithm under different maps through simulation experiments. Compared with the coverage situation of other coverage path planning algorithms in environments with local area updates, the algorithm proposed in this paper has a higher coverage rate in this scenario.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Motor imagery Classification for Asynchronous EEG-Based Brain-Computer Interfaces

arXiv

引用

arXiv 2024年

作者： Wu, Huanyu Li, Siyang Wu, Dongrui The 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 Shenzhen Huazhong University of Science Technology Research Institute Shenzhen518063 China

Motor imagery (MI) based brain-computer interfaces (BCIs) enable the direct control of external devices through the imagined movements of various body parts. Unlike previous systems that used fixed-length EEG trials for MI decoding, asynchronous BCIs aim to detect the user's MI without explicit triggers. They are challenging to implement, because the algorithm needs to first distinguish between resting-states and MI trials, and then classify the MI trials into the correct task, all without any triggers. This paper proposes a sliding window prescreening and classification (SWPC) approach for MI-based asynchronous BCIs, which consists of two modules: a prescreening module to screen MI trials out of the resting-state, and a classification module for MI classification. Both modules are trained with supervised learning followed by self-supervised learning, which refines the feature extractors. Within-subject and cross-subject asynchronous MI classifications on four different EEG datasets validated the effectiveness of SWPC, i.e., it always achieved the highest average classification accuracy, and outperformed the best state-of-the-art baseline on each dataset by about 2%. © 2024, CC BY.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

CSP-Net: Common Spatial Pattern Empowered Neural Networks for EEG-Based Motor imagery Classification

arXiv

引用

arXiv 2024年

作者： Jiang, Xue Meng, Lubin Chen, Xinru Xu, Yifan Wu, Dongrui Key Laboratory of The Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518063 China

Electroencephalogram-based motor imagery (MI) classification is an important paradigm of non-invasive brain-computer interfaces. Common spatial pattern (CSP), which exploits different energy distributions on the scalp while performing different MI tasks, is very popular in MI classification. Convolutional neural networks (CNNs) have also achieved great success, due to their powerful learning capabilities. This paper proposes two CSP-empowered neural networks (CSP-Nets), which integrate knowledge-driven CSP filters with data-driven CNNs to enhance the performance in MI classification. CSP-Net-1 directly adds a CSP layer before a CNN to improve the input discriminability. CSP-Net-2 replaces a convolutional layer in CNN with a CSP layer. The CSP layer parameters in both CSP-Nets are initialized with CSP filters designed from the training data. During training, they can either be kept fixed or optimized using gradient descent. Experiments on four public MI datasets demonstrated that the two CSP-Nets consistently improved over their CNN backbones, in both within-subject and cross-subject classifications. They are particularly useful when the number of training samples is very small. Our work demonstrates the advantage of integrating knowledge-driven traditional machine learning with data-driven deep learning in EEG-based brain-computer interfaces. © 2024, CC BY.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Csp-Net: Common Spatial Pattern Empowered Neural Networks for Eeg-Based Motor imagery Classification

SSRN

引用

SSRN 2024年

作者： Jiang, Xue Meng, Lubin Chen, Xinru Xu, Yifan Wu, Dongrui Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518063 China

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Complementary Learning Subnetworks for Parameter-Efficient Class-Incremental Learning

arXiv

引用

arXiv 2023年

作者： Li, Depeng Zeng, Zhigang The School of Artificial Intelligence and Automation The Institute of Artificial Intelligence Huazhong University of Science and Technology China The Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan430074 China

In the scenario of class-incremental learning (CIL), deep neural networks have to adapt their model parameters to non-stationary data distributions, e.g., the emergence of new classes over time. However, CIL models are challenged by the well-known catastrophic forgetting phenomenon. Typical methods such as rehearsal-based ones rely on storing exemplars of old classes to mitigate catastrophic forgetting, which limits real-world applications considering memory resources and privacy issues. In this paper, we propose a novel rehearsal-free CIL approach that learns continually via the synergy between two Complementary Learning Subnetworks. Our approach involves jointly optimizing a plastic CNN feature extractor and an analytical feed-forward classifier. The inaccessibility of historical data is tackled by holistically controlling the parameters of a well-trained model, ensuring that the decision boundary learned fits new classes while retaining recognition of previously learned classes. Specifically, the trainable CNN feature extractor provides task-dependent knowledge separately without interference;and the final classifier integrates task-specific knowledge incrementally for decision-making without forgetting. In each CIL session, it accommodates new tasks by attaching a tiny set of declarative parameters to its backbone, in which only one matrix per task or one vector per class is kept for knowledge retention. Extensive experiments on a variety of task sequences show that our method achieves competitive results against state-of-the-art methods, especially in accuracy gain, memory cost, training efficiency, and task-order robustness. Furthermore, to make the non-growing backbone (i.e., a model with limited network capacity) suffice to train on more incoming tasks, a graceful forgetting implementation on previously learned trivial tasks is empirically investigated. Copyright © 2023, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

A Recipe for Scaling up Text-to-Video Generation with Text-free Videos

arXiv

引用

arXiv 2023年

作者： Wang, Xiang Zhang, Shiwei Yuan, Hangjie Qing, Zhiwu Gong, Biao Zhang, Yingya Shen, Yujun Gao, Changxin Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Alibaba Group China Zhejiang University China Ant Group China

Diffusion-based text-to-video generation has witnessed impressive progress in the past year yet still falls behind text-to-image generation. One of the key reasons is the limited scale of publicly available data (e.g., 10M video-text pairs in WebVid10M vs. 5B image-text pairs in LAION), considering the high cost of video captioning. Instead, it could be far easier to collect unlabeled clips from video platforms like YouTube. Motivated by this, we come up with a novel text-to-video generation framework, termed TF-T2V, which can directly learn with text-free videos. The rationale behind is to separate the process of text decoding from that of temporal modeling. To this end, we employ a content branch and a motion branch, which are jointly optimized with weights shared. Following such a pipeline, we study the effect of doubling the scale of training set (i.e., video-only WebVid10M) with some randomly collected text-free videos and are encouraged to observe the performance improvement (FID from 9.67 to 8.19 and FVD from 484 to 441), demonstrating the scalability of Copyright © 2023, The Authors. All rights reserved.

关键词：

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：