检索结果-内蒙古大学图书馆

Multi-Modal Domain Adaptation Variational Autoencoder for EEG-Based Emotion Recognition

IEEE/CAA Journal of Automatica Sinica 2022年第9期9卷 1612-1626页

作者： Yixin Wang Shuang Qiu Dan Li Changde Du Bao-Liang Lu Huiguang He the Research Center for Brain-inspired Intelligence National Laboratory of Pattern RecognitionInstitute of AutomationChinese Academy of ScienceBeijing 100190 the University of Chinese Academy of Sciences Beijing 100049 the Beijing Institute of Control and Electronic Technology Beijing 100038China the School of Mathematics and Information Sciences Yantai UniversityYantai 264003China the Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of ScienceBeijingChina the Department of Computer Science and Engineering Shanghai Jiao Tong UniversityShanghai 200240China

Traditional electroencephalograph(EEG)-based emotion recognition requires a large number of calibration samples to build a model for a specific subject,which restricts the application of the affective brain computer interface(BCI)in *** attempt to use the multi-modal data from the past session to realize emotion recognition in the case of a small amount of calibration *** solve this problem,we propose a multimodal domain adaptive variational autoencoder(MMDA-VAE)method,which learns shared cross-domain latent representations of the multi-modal *** method builds a multi-modal variational autoencoder(MVAE)to project the data of multiple modalities into a common *** adversarial learning and cycle-consistency regularization,our method can reduce the distribution difference of each domain on the shared latent representation layer and realize the transfer of *** experiments are conducted on two public datasets,SEED and SEED-IV,and the results show the superiority of our proposed *** work can effectively improve the performance of emotion recognition with a small amount of labelled multi-modal data.

关键词： Cycle-consistency domain adaptation electroencephalograph(EEG) multi modality variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Oral Cancer Classification Using a Hybrid Attention-Aided Deep Learning Model 5th

Oral Cancer Classification Using a Hybrid Attention-Aided D...

引用

5th International Conference on Medical Imaging and computer Aided Diagnosis, MICAD 2024

作者： Dutta, Srinjan Roy, Jibesh Mandal, Diptarka Kaplun, Dmitrii Shpakovskaya, Irina Sarkar, Ram Department of Computer Science and Engineering Jalpaiguri Government Engineering College Jalpaiguri India School of Computer Engineering and Mathematical Sciences Defence Institute of Advanced Technology Pune India Artificial Intelligence Research Institute China University of Mining and Technology Xuzhou China Department of Automation and Control Process Saint Petersburg Electrotechnical University "LETI" Saint Petersburg Russia Department of Computer Science and Engineering Jadavpur University West Bengal Kolkata India I.P. Pavlov Saint Petersburg First State Medical University St. Petersburg Russia

ISBN: (纸本)9789819638628

Oral cancer remains a critical global health challenge, characterized by high morbidity and mortality due to late-stage diagnosis. This paper addresses the need for improved diagnostic accuracy by introducing a novel hybrid-attention aided deep learning model for oral cancer classification. Our approach integrates the EfficientNetB0 model for feature extraction with a customized hybrid attention module, combining self, spatial, and soft attention mechanisms to emphasize crucial features. The model has been trained and evaluated on both microscopic and macroscopic oral cancer datasets, demonstrating its generalizability. Our proposed model achieves an accuracy of 96.97% on a macroscopic dataset and 92% on a microscopic dataset, with respective F1-scores of 0.97 and 0.89, outperforming baseline models. This hybrid attention-aided deep learning model shows significant potential in improving early detection and treatment planning of oral cancer. Source code and additional results of this work can be found at the GitHub repository. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

How grey wolf optimization affects remanufacturing 17

How grey wolf optimization affects remanufacturing

引用

17th CIRP Conference on Intelligent Computation in Manufacturing Engineering, CIRP ICME 2023

作者： Gal, Barna Zeh, Christine Szaller, Adam Fraunhofer Austria Research GmbH Theresianumgasse 7 WienA-1040 Austria Institute for Computer Science and Control Kende str. 13-17 Budapest1111 Hungary EPIC InnoLabs Nonprofit Ltd. Kende str. 13-17 Budapest1111 Hungary

While in 1971 the Earth Overshoot Day was on December 25th, in 2022 this day for Austria was already reached on July 28th. And since uncertainties in the remanufacturing production planning occur, companies are forced to take in trade-offs like increased production capacity available at short notice. These uncertainties result in financial losses and production waste, as well as bottlenecks in the supply of materials for gas engine assembly. For this reason, this paper explores the use of a grey wolf optimizer for the reduction of the cycle time of a gas engine remanufacturer. A discrete event simulation is used for evaluation purposes and the results from the scheduler are compared with benchmarks of the current production planning of manufacturers. © 2024 Elsevier B.V.. All rights reserved.

关键词： Circular Economy Grey Wolf Optimizer Production Planning Remanufacturing Sustainable Manufacturing

来源：评论

学校读者我要写书评

暂无评论

Technological Machines Diagnostics of Grain Processing Enterprises as the Object of Automation

Technological Machines Diagnostics of Grain Processing Enter...

引用

2023 International Conference Automatics and Informatics, ICAI 2023

作者： Kalandarov, Palvan I. Ubaydullayeva, Shakhnoza R. Nikolov, Nikola N. Hayitov, Aziz Sharifov, Husen 'Tashkent Institute of Irrigation and Agricultural Mechanization Engineers' National Research University Department 'Automation and Control of Technology Process in Production' Tashkent Uzbekistan Technical University of Varna Faculty of Computer Science and Automation Department of Automation Varna Bulgaria Bukhara Institute of Natural Resource Management of the National Research University 'Tashkent Institute of Irrigation and Agricultural Mechanization Institute' Tashkent Uzbekistan

ISBN: (纸本)9798350312911

The article gives the basic concepts of reliability, performance, durability, considers the issues of changing the technical state of the machine during operation. The models under consideration have the ability to introduce various perturbations in order to simulate physical defects, and numerical simulation on a computer made it possible to obtain solutions in the form of temporary realizations of oscillations for different states of the simulation object. The cooperative use of the full-scale method and mathematical modeling made it possible to reduce the volume of full-scale experiments and apply statistical methods of analysis in the problem of classifying the technical condition by constructing mathematical models of the probability of failure and uptime during their operating time. The content of the main types of machine states is revealed, considerable attention is paid to the issues of identifying and influencing failures and the causes of failures in the machine, the reasons for the loss of performance during operation. © 2023 IEEE.

关键词： Deterioration

来源：评论

学校读者我要写书评

暂无评论

Learning discretized neural networks under Ricci flow

The Journal of Machine Learning Research

引用

The Journal of Machine Learning research 2024年第1期25卷 18901-18944页

作者： Jun Chen Hanwen Chen Mengmeng Wang Guang Dai Ivor W. Tsang Yong Liu Institute of Cyber-Systems and Control Zhejiang University China and School of Computer Science and Technology Zhejiang Normal University China Institute of Cyber-Systems and Control Zhejiang University China SGIT AI Lab State Grid Corporation of China China Centre for Frontier Artificial Intelligence Research Agency for Science Technology and Research (A*STAR) Singapore and Institute of High Performance Computing Agency for Science Technology and Research (A*STAR) Singapore and College of Computing and Data Science Nanyang Technological University Singapore

In this paper, we study Discretized Neural Networks (DNNs) composed of low-precision weights and activations, which suffer from either infinite or zero gradients due to the nondifferentiable discrete function during training. Most training-based DNNs in such scenarios employ the standard Straight-Through Estimator (STE) to approximate the gradient w.r.t. discrete values. However, the use of STE introduces the problem of gradient mismatch, arising from perturbations in the approximated gradient. To address this problem, this paper reveals that this mismatch can be interpreted as a metric perturbation in a Riemannian manifold, viewed through the lens of duality theory. Building on information geometry, we construct the Linearly Nearly Euclidean (LNE) manifold for DNNs, providing a background for addressing perturbations. By introducing a partial differential equation on metrics, i.e., the Ricci flow, we establish the dynamical stability and convergence of the LNE metric with the L2-norm perturbation. In contrast to previous perturbation theories with convergence rates in fractional powers, the metric perturbation under the Ricci ow exhibits exponential decay in the LNE manifold. Experimental results across various datasets demonstrate that our method achieves superior and more stable performance for DNNs compared to other representative training-based methods.

关键词： discretized neural networks gradient perturbation information geometry ricci flow riemannian manifold

来源：评论

学校读者我要写书评

暂无评论

Climate Downscaling Using Neural Operator: Spatiotemporal Multimodal Fusion Operator with State-Query Coupled Kernel

Climate Downscaling Using Neural Operator: Spatiotemporal Mu...

引用

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

作者： Zhang, Haodi Wang, Yichi Jian, Yifan Jiang, Jiahui Bai, Zhaohai Ma, Lin College of Computer Science and Software Engineering Shenzhen University China Center for Agricultural Resources Research Institute of Genetic and Developmental Biology Chinese Academy of Sciences China State Key Laboratory of Pollution Control and Resource Reuse School of the Environment Nanjing University China

ISBN: (纸本)9798350368741

Climate downscaling is crucial for detailed small-scale analysis and for acquiring climate data in regions without weather stations. Operator learning has proven potential for this task. However, several challenges remain in operator learning, such as multimodal fusion, spatiotemporal fusion and input state and query adaptation. To address these challenges, we propose a Spatiotemporal Multimodal Fusion Operator with a State-Query Coupled Kernel (SMCK). This framework includes a latent space fusion encoder that encodes climate variables using position-wise multihead attention for multimodal fusion and integrates historical information to generate robust and precise representation. Additionally, we introduce a state-query coupled kernel that combines radial basis functions and discrete fourier encoding to enhance query location representation, while also adapting to the state to obtain the coupled kernel. Extensive experiments demonstrate that our method achieves state-ofthe-art performance and provides strong support for climate downscaling and the planning of climate-related strategies. © 2025 IEEE.

关键词： Climate downscaling Deep Learning Multimodal fusion Operator learning Time series forecasting

来源：评论

学校读者我要写书评

暂无评论

Fuzzy System of Wind Turbine Defect Image Processing 14

Fuzzy System of Wind Turbine Defect Image Processing

引用

14th International Conference on Advanced computer Information Technologies, ACIT 2024

作者： Dubchak, Lesia Sachenko, Anatoliy Wolff, Carsten Vasylkiv, Nadia West Ukrainian National University Department of Computer Engineerin Ternopil Ukraine West Ukrainian National University Research Institute for Intelligent Computer Systems Ternopil Ukraine Kazimierz Pulaski University of Technology and Humanities in Radom Department of Tele-Informatics Radom Poland Dortmund University of Applied Science and Arts Dortmund Germany West Ukrainian National University Department of Information Computer Systems and Control Ternopil Ukraine

ISBN: (纸本)9798350350036

Wind turbines are an important component of the global strategy for the transition to renewable energy sources and the fight against climate change. Their implementation contributes to sustainable development and to improving the ecological situation of the planet. Detecting and elimination of defects helps reduce the wear of the components and prevent premature failure. This can significantly extend the life of wind turbines, which is economically beneficial for owners and operators. The use of UAVs allows for minimizing the risks for personnel, as inspection and diagnosis of defects can be carried out without the need to lift people to great heights or stay in dangerous areas. This is especially important for turbines located in places of difficult access. The images taken by the UAV contain many extraneous objects and fuzzy data. Fuzzy logic allows you to create models for pattern recognition and object classification in images, taking into account uncertainty and variation in the data. This increases the accuracy and reliability of pattern recognition systems. This article proposes an image processing system to detect wind turbine defects, with a fuzzy system module that selects images from a video stream for further processing. © 2024 IEEE.

关键词： Windmill

来源：评论

学校读者我要写书评

暂无评论

Benchmarking the Full-Order Model Optimization Based Imitation in the Humanoid Robot Reinforcement Learning Walk

Benchmarking the Full-Order Model Optimization Based Imitati...

引用

International Conference on Advanced Robotics (ICAR)

作者： Ekaterina Chaikovskaya Inna Minashina Vladimir Litvinenko Egor Davydenko Dmitry Makarov Yulia Danik Roman Gorbachev Moscow Institute of Physics and Technology Federal Research Center “Computer Science and Control” of Russian Academy of Sciences

When a gait of a bipedal robot is developed using deep reinforcement learning, reference trajectories may or may not be used. Each approach has its advantages and disadvantages, and the choice of method is up to the control developer. This paper investigates the effect of reference trajectories on locomotion learning and the resulting gaits. We implemented three gaits of a full-order anthropomorphic robot model with different reward imitation ratios, provided sim-to-sim control policy transfer, and compared the gaits in terms of robustness and energy efficiency. In addition, we conducted a qualitative analysis of the gaits by interviewing people, since our task was to create an appealing and natural gait for a humanoid robot. According to the results of the experiments, the most successful approach was the one in which the average value of rewards for imitation and adherence to command velocity per episode remained balanced throughout the training. The gait obtained with this method retains naturalness (median of 3.6 according to the user study) compared to the gait trained with imitation only (median of 4.0), while remaining robust close to the gait trained without reference trajectories.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Asymptotic Approximations of a Regulator and a Convergent Iteration Process for a Singularly Perturbed Problem

Asymptotic Approximations of a Regulator and a Convergent It...

引用

International Conference on Management of Large-Scale System Development (MLSD)

作者： Mikhail Dmitriev Dmitry Makarov Federal Research Center "Computer Science and Control" of RAS Moscow Institute of Physics and Technology Moscow Russia

The paper considers the construction of asymptotic expansions in a singularly perturbed weakly nonlinear control problem to design an approximate controller. The asymptotic expansions are used to construct interpolation and extrapolation procedures and are obtained by applying the SDRE technique and analyzing a convergent iterative process. The experiments performed showed the efficiency of the proposed approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Character Recognition of Vedic Sanskrit using Deep Learning Algorithms 3

Character Recognition of Vedic Sanskrit using Deep Learning ...

引用

3rd IEEE International Conference on Computing, Communication, and Intelligent Systems, ICCCIS 2022

作者： Pandey, Mrinal Pandey, Rashmikiran Nazarov, Alexey Moscow Institute of Physics and Technology Department of Radio Engineering and Cybernetics Moscow Russia Federal Research Center Computer Science and Control Russian Academy of Sciences Moscow Russia

ISBN: (纸本)9781665462006

One of the applications of deep learning is deciphering the unscripted text over the walls and pillars of historical monuments is the major source of information extraction. This information gives us an idea about the art and the culture of that respective era. In this paper we proposed a model for digital recognition of textual characters written in Sanskrit language using the 4-fold Convolutional Neural Network (CNN) architecture. At the first stage we remove the noise and subsequently segmentation of characters from the input image is performed, later we convert the image into binary image format by the help of image processing techniques. The research is performed over the Devanagari script which was developed during 1st to the 4th century CE and is common to many languages from the Indian subcontinent. © 2022 IEEE.

关键词： Character recognition

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：