检索结果-内蒙古大学图书馆

IFAC-PapersOnLine 2023年第2期56卷 5518-5524页

作者： Zoltán Szabó József Bokor Péter Gáspár Systems and Control Laboratory Institute for Computer Science and Control (SZTAKI) Eötvös Loránd Research Network (ELKH) Budapest Hungary Systems and Control Laboratory Institute for Computer Science and Control (SZTAKI) Eotvos Loránd Research Network (ELKH) Budapest Hungary

The paper proposes a system representation formed by a minimal collection of sufficiently long restricted trajectories generated by an observable discrete time LTI system. Conditions are given under which such a collection is a system representation and also an exhaustive parametrization of these representations is provided. These can be also interpreted as a generalized persistency condition which complements the results encountered for the controllable case. In terms of the proposed representation some system properties are investigated and a controllable-autonomous decomposition is given. Finally it is shown how the representation associated to the inverse system, to the parallel and cascade connection, respectively, can be derived.

关键词： Modeling LTI system representation data based

来源：评论

学校读者我要写书评

暂无评论

EEG-based comparative measurement of visual fatigue caused by stereoscopic depth perception

EEG-based comparative measurement of visual fatigue caused b...

引用

The 2023 International Conference on Display Technology, (ICDT 2023)

作者： Jia, Lixiu Huang, Sheng Ding, Yiquan Feng, Lihang Huang, Xiaohua School of Computer Engineering Nanjing Institute of Technology Jiangsu Nanjing China School of Electrical Engineering and Control Science Nanjing Tech University Jiangsu Nanjing China

In this study, we investigated the influence of stereoscopic depth on visual fatigue based on subjective and EEG measurement. 19 channels of EEG data of 17 subjects before and after watching 3D movie with different depth ranges were recorded, and the power of δ, θ, α, β, power spectral parameters (gravity frequency, power spectral entropy) were calculated and analyzed. The results showed that visual fatigue caused by 3D enhanced movies with larger negative disparity was more significantly severe than that of 3D normal movies. © 2023, John Wiley and Sons Inc. All rights reserved.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Back-ends for Online Speaker Recognition and Clustering 48

Probabilistic Back-ends for Online Speaker Recognition and C...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Sholokhov, Alexey Kuzmin, Nikita Lee, Kong Aik Chng, Eng Siong Federal Research Center "Computer Science and Control"of the Russian Academy of Sciences Moscow Russia Nanyang Technological University Singapore A∗STAR Institute for Infocomm Research Singapore

ISBN: (纸本)9781728163277

This paper focuses on multi-enrollment speaker recognition which naturally occurs in the task of online speaker clustering, and studies the properties of different scoring back-ends in this scenario. First, we show that popular cosine scoring suffers from poor score calibration with a varying number of enrollment utterances. Second, we propose a simple replacement for cosine scoring based on an extremely constrained version of probabilistic linear discriminant analysis (PLDA). The proposed model improves over the cosine scoring for multi-enrollment recognition while keeping the same performance in the case of one-to-one comparisons. Finally, we consider an online speaker clustering task where each step naturally involves multi-enrollment recognition. We propose an online clustering algorithm allowing us to take benefits from the PLDA model such as the ability to handle uncertainty and better score calibration. Our experiments demonstrate the effectiveness of the proposed algorithm. © 2023 IEEE.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

On the reduction of Linear Parameter-Varying State-Space models

arXiv

引用

arXiv 2024年

作者： Olucha, E. Javier Terzin, Bogoljub Das, Amritam Tóth, Roland Control Systems Group Eindhoven University of Technology Netherlands Systems and Control Laboratory Institute for Computer Science and Control Budapest Hungary

This paper presents an overview and comparative study of the state of the art in state-order reduction (SOR) and scheduling dimension reduction (SDR) for linear parameter-varying (LPV) state-space (SS) models, comparing and benchmarking their capabilities, limitations and performance. The use case chosen for these studies is an interconnected network of nonlinear coupled mass spring damper systems with three different configurations, where some spring coefficients are described by arbitrary user-defined static nonlinear functions. For SOR, the following methods are compared: linear time-invariant (LTI), LPV and LFR-based balanced reductions, moment matching (MM) and parameter-varying oblique projection. For SDR, the following methods are compared: principal component analysis (PCA), trajectory PCA, Kernel PCA and LTI balanced truncation, autoencoders and deep neural network. The comparison reveals the most suitable reduction methods for the different benchmark configurations, from which we provide use case SOR and SDR guidelines that can be used to choose the best reduction method for a given LPV-SS model. © 2024, CC BY.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Study on Landslide Susceptibility Evaluation Based on Improved Multivariable Weighted Model: A Case Study of Lushan County, China 3

Study on Landslide Susceptibility Evaluation Based on Improv...

引用

3rd IEEE International Conference on Software Engineering and Artificial Intelligence, SEAI 2023

作者： Zhao, Li Duan, Gonghao Wuhan Institute of Technology School of Computer Science and Engineering Wuhan China Automation for Complex Systems Hubei Key Laboratory of Advanced Control and Intelligent Wuhan China

ISBN: (纸本)9798350337952

The evaluation of regional geological hazard susceptibility is of great significance to the prevention and control of geological hazard. In this paper, the "4-20"Lushan earthquake disaster area as the research area, combined with GIS and characteristics of the research area, through correlation analysis, selected 9 influencing factors as the evaluation factors. The study was conducted using a weighted information volume-logistic regression model (WI-LR). The results were classified into five sensitivity levels: very low, low, medium, high and very high. The results show that the landslide prone areas in Lushan County are concentrated in the area below the middle of the county seat, mostly near rivers, faults and areas with peak acceleration greater than 0.4. Among them, WI-LR model (AUC=0.918) > deterministic factor model (CF =0.908) > weighted information quantity model (WI) (AUC=0.896) > information quantity model I (AUC=0.853) > information quantity logistic regression model I-LR (AUC=0.799). It indicates that WI-LR model has high evaluation accuracy. © 2023 IEEE.

关键词： Hazards

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Modeling of the Behavior of a Computing Node in the Absence of Tasks on the Project Server 9th

Probabilistic Modeling of the Behavior of a Computing No...

引用

9th Russian Supercomputing Days International Conference, RuSCDays 2023

作者： Nikolay, Khrapov Mikhail, Posypkin Institute for Information Transmission Problems of the Russian Academy of Sciences Moscow Russia Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences Moscow Russia

ISBN: (纸本)9783031494345

There may be situations where there are no tasks on the BOINC project for a number of reasons. If a computing node does not receive a task as a response to a request, then it goes into an idle state for a while. This publication proposes a probabilistic model of the behavior of a single computing node in the absence of jobs on the server. The proposed model best describes the processes associated with computing in local infrastructures, but it is also possible to generalize the methodology for large-scale voluntary computing projects. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

AutYOLO-ATT: an attention-based YOLOv8 algorithm for early autism diagnosis through facial expression recognition

引用

Neural Computing and Applications 2024年第27期36卷 17199-17219页

作者： Hosney, Reham Talaat, Fatma M. El-Gendy, Eman M. Saafan, Mahmoud M. Computers and Control Systems Engineering Department Faculty of Engineering Mansoura University Mansoura Egypt Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh33516 Egypt Faculty of Computer Science and Engineering New Mansoura University Gamasa35712 Egypt Nile Higher Institute for Engineering and Technology Mansoura Egypt

Autism Spectrum Disorder (ASD) is a developmental condition resulting from abnormalities in brain structure and function, which can manifest as communication and social interaction difficulties. Conventional methods for diagnosing ASD may not be effective in the early stages of the disorder. Hence, early diagnosis is crucial to improving the patient's overall health and well-being. One alternative and effective method for early autism diagnosis is facial expression recognition since autistic children typically exhibit distinct facial expressions that can aid in distinguishing them from other children. This paper provides a deep convolutional neural network (DCNN)-based real-time emotion recognition system for autistic kids. The proposed system is designed to identify six facial emotions, including surprise, delight, sadness, fear, joy, and natural, and to assist medical professionals and families in recognizing facial expressions in autistic children for early diagnosis and intervention. In this study, an attention-based YOLOv8 (AutYOLO-ATT) algorithm for facial expression recognition is proposed, which enhances the YOLOv8 model's performance by integrating an attention mechanism. The proposed method (AutYOLO-ATT) outperforms all other classifiers in all metrics, achieving a precision of 93.97%, recall of 97.5%, F1-score of 92.99%, and accuracy of 97.2%. These results highlight the potential of the proposed method for real-world applications, particularly in fields where high accuracy is essential. © The Author(s) 2024.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Diffusion-based framework for weakly-supervised temporal action localization

引用

Pattern Recognition 2025年 160卷

作者： Zou, Yuanbing Zhao, Qingjie Sarker, Prodip Kumar Li, Shanshan Wang, Lei Liu, Wangwang School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China Beijing Institute of Control Engineering Beijing100190 China

Weakly supervised temporal action localization aims to localize action instances with only video-level supervision. Due to the absence of frame-level annotation supervision, how effectively separate action snippets and backgrounds from semantically ambiguous features becomes an arduous challenge for this task. To address this issue from a generative modeling perspective, we propose a novel diffusion-based network with two stages. Firstly, we design a local masking mechanism module to learn the local semantic information and generate binary masks at the early stage, which (1) are used to perform action-background separation and (2) serve as pseudo-ground truth required by the diffusion module. Then, we propose a diffusion module to generate high-quality action predictions under the pseudo-ground truth supervision in the second stage. In addition, we further optimize the new-refining operation in the local masking module to improve the operation efficiency. The experimental results demonstrate that the proposed method achieves a promising performance on the publicly available mainstream datasets THUMOS14 and ActivityNet. The code is available at https://***/Rlab123/action_diff. © 2024

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Multimodal Large Models are Effective Action Anticipators

引用

IEEE Transactions on Multimedia 2025年 27卷 2949-2960页

作者： Wang, Binglu Tian, Yao Wang, Shunzhou Yang, Le Xi'an University of Architecture and Technology College of Information and Control Engineering Xi'an710055 China Northwestern Polytechnical University School of Astronautics Xi'an710072 China Peking University School of Electronic and Computer Engineering Shenzhen Graduate School Shenzhen518055 China Hefei Comprehensive National Science Center Institute of Artificial Intelligence Hefei230022 China University of Science and Technology of China School of Information Science and Technology Hefei230022 China

The task of long-term action anticipation demands solutions that can effectively model temporal dynamics over extended periods while deeply understanding the inherent semantics of actions. Traditional approaches, which primarily rely on recurrent units or Transformer layers to capture long-term dependencies, often fall short in addressing these challenges. Large Language Models (LLMs), with their robust sequential modeling capabilities and extensive commonsense knowledge, present new opportunities for long-term action anticipation. In this work, we introduce the ActionLLM framework, a novel approach that treats video sequences as successive tokens, leveraging LLMs to anticipate future actions. Our baseline model simplifies the LLM architecture by setting future tokens, incorporating an action tuning module, and reducing the textual decoder layer to a linear layer, enabling straightforward action prediction without the need for complex instructions or redundant descriptions. To further harness the commonsense reasoning of LLMs, we predict action categories for observed frames and use sequential textual clues to guide semantic understanding. In addition, we introduce a Cross-Modality Interaction Block, designed to explore the specificity within each modality and capture interactions between vision and textual modalities, thereby enhancing multimodal tuning. Extensive experiments on benchmark datasets demonstrate the superiority of the proposed ActionLLM framework, encouraging a promising direction to explore LLMs in the context of action anticipation. © 1999-2012 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Learning-based model augmentation with LFRs

arXiv

引用

arXiv 2024年

作者： Hoekstra, Jan H. Verhoek, Chris Tóth, Roland Schoukens, Maarten Control Systems Group Eindhoven University of Technology Netherlands Systems and Control Laboratory Institute for Computer Science and Control Budapest Hungary

Nonlinear system identification (NL-SI) has proven to be effective in obtaining accurate models for highly complex systems. Especially, recent encoder-based methods for artificial neural networks state-space (ANN-SS) models have achieved state-of-the-art performance on various benchmarks, while offering consistency and computational efficiency. The inclusion of prior knowledge of the system can be exploited to increase (i) estimation speed, (ii) accuracy, and (iii) interpretability of the resulting models. This paper proposes an encoder based model augmentation method incorporating prior knowledge from first-principles (FP) models. We introduce a novel linear-fractional-representation (LFR) model structure that allows for the unified representation of various augmentation structures including the ones that are commonly used in the literature, and an identification algorithm for estimating the proposed structure together with appropriate initialization methods. The performance and generalization capabilities of the proposed method are demonstrated on a hardening mass-spring-damper simulation. © 2024, CC BY-NC-SA.

关键词： Nonlinear systems

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：