检索结果-内蒙古大学图书馆

16th International Conference on Digital Image Processing, ICDIP 2024

作者： Zhang, Yudongfeng Zhou, Zhaoyi Zhao, Mingbo Li, Dawei Engineering Research Center of Digitized Textile & Fashion Technology Ministry of Education Donghua University Shanghai201620 China College of Information Sciences and Technology Donghua University Shanghai201620 China State Key Laboratory for Modification of Chemical Fibers and Polymer Materials College of Information Sciences and Technology Donghua University Shanghai201620 China

ISBN: (数字)9781510682917

ISBN: (纸本)9781510682900

Current plant organ analysis algorithms are mostly based on two-dimensional images. There is an issue of overlapping in plant organs in the 2D space, and only specific species of plants can be well handled in 2D. Therefore, we propose a method for propagating labels of plant organs by using a modified Graph Neural Network on three-dimensional plant point clouds. We first convert the three-dimensional point cloud files of plants into a dataset with a graph data structure, and then input it into an improved GCNII for training. Only a few sampled points of the plant are needed for label propagation, then it can lift the efficiency of plant organ segmentation and classification. The accuracy of label propagation results for maize, sorghum, tomato, and tobacco can reach over 95%. The research is of great significance to reducing the amount of manual labeling work load for 3D plant phenotyping. © 2024 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

MS-FTSCNN: An EEG Emotion Recognition Method from the Combination of Multi-Domain Features

SSRN

引用

SSRN 2023年

作者： Li, Feifei Hao, Kuangrong Wei, Bing Hao, Lingguang Ren, Lihong Engineering Research Center of Digitized Textile and Apparel Technology Ministry of Education Donghua University Shanghai202120 China College of Information Sciences and Technology Donghua University Shanghai201620 China

Electroencephalography (EEG), as a physiological cue, is more objective and reliable in identifying emotions than non-physiological cues. Previous methods only consider one or two relationships among frequency, time and spatial domain features of EEG signals, and the designed models may still be relatively large in terms of parameters. Meanwhile, the training process of the previous networks is troublesome during algorithm optimization. To address these challenges, we design a simple and efficient feature preprocessing method to obtain a 3D feature structure that contains EEG signal information in the frequency, time and spatial domains simultaneously. Then, we propose a multiscale frequency-time-spatial convolutional model, MS-FTSCNN, which is able to capture frequency, time and spatial features from the input signals and fuse three features more efficiently. Moreover, the multi-scale one-dimensional convolutional kernel in our method can reduce network parameters, providing possibilities for real-time online applications. Finally, the recognition accuracies of arousaland valence of our proposed model are 93.82%, 94.48% on DEAP dataset and 92.64%, 92.15% on MOHNOB-HCI dataset, which is higher than most existing methods. © 2023, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Muscle fatigue identification and prediction in motion using wearable device with power and torque-based features

Wearable Electronics

引用

Wearable Electronics 2025年 2卷 62-68页

作者： Zhangding Li Xi Wang Qiao Li Fei Wang Xiaoming Tao College of Information Science & Technology Donghua University Shanghai China Engineering Research Center of Digitized Textile & Apparel Technology Ministry of Education Donghua University Shanghai China College of Textiles Donghua University Shanghai China Key Laboratory of Textile Science & Technology Ministry of Education Donghua University Shanghai 201620 China School of Textile Science and Engineering Wuyi University Jiangmen 529020 China School of Fashion and Textiles The Hong Kong Polytechnic University Kowloon Hong Kong China

Monitoring muscle fatigue is a critical area of research in both the fields of rehabilitation medicine and sports science. Despite its importance, practical measurement remains challenging due to constraints in equipment size and cost. This study leverages a commercially available, wearable high-resolution goniometer to capture joint angles during single-degree-of-freedom curling movements. From these data, we can deduce the torque and power of the biceps in the upper arm using an elbow musculoskeletal model. We proposed nine fatigue indicators, all of which showed significant correlations with the Root Mean Square (RMS) and Median Frequency (MDF) indicators derived from Electromyography (EMG) signals. Spectral clustering was utilized for the identification and classification of fatigue. Subsequently, we employed a K-Nearest Neighbors (KNN) model to predict muscular fatigue, achieving an impressive overall accuracy of 95%, an effective recall rate of 95%, an F1-score of 95%, and an Area Under the Curve (AUC) of 99%. This research presents an innovative and comprehensive approach to the identification and prediction of muscle fatigue.

关键词： Muscle fatigue detection Muscle power Torque of flexion Machine learning

来源：评论

学校读者我要写书评

暂无评论

Convergence Analysis of Epidemic Models over Contact and Migration Graphs

Convergence Analysis of Epidemic Models over Contact and Mig...

引用

Chinese Automation Congress (CAC)

作者： Fei Niu Xiaofeng Wang School of Information Science & Technology Donghua University Shanghai China Department of Automation School of Information Science & Technology Donghua University Shanghai China Engineering Research Center of Digitized Textile & Apparel Technology (Ministry of Education) Donghua University Shanghai China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

In this paper, we study the susceptible-infected-susceptible (SIS) epidemic spreading model under population migration on multilayer networks. Specifically, we consider two-layer contact-migration networks, in which one layer of the multilayer networks describes the contact patterns between different populations and the other one captures the possible migration paths between any two sites. By using Lyapunov methods as well as Markov chain theory, we study convergence properties of the SIS epidemic dynamics on the two-layer contact-migration networks either by establishing the structural conditions under which the multilayer networked system always evolves into the disease-free equilibrium or by deriving the algebraic conditions below which the system converges to the disease-free equilibrium. Finally, two simulation examples are given to verify our theoretical results.

关键词： Epidemics Sufficient conditions Network topology Infectious diseases Simulation Nonhomogeneous media Solids Topology Convergence Lyapunov methods

来源：评论

学校读者我要写书评

暂无评论

A Modified Self-Adaptive Sparrow Search Algorithm for Robust Multi-UAV Path Planning

引用

Journal of Donghua University(English Edition) 2024年第6期41卷 630-643页

作者： SUN Zhiyuan SHEN Bo PAN Anqi XUE Jiankai MA Yuhang College of Information Science and Technology Donghua UniversityShanghai 201620China Engineering Research Center of Digitized Textile&Fashion Technology Ministry of EducationDonghua UniversityShanghai 201620China

With the advancement of technology,the collaboration of multiple unmanned aerial vehicles(multi-UAVs)is a general trend,both in military and civilian *** planning is a crucial step for multi-UAV mission execution,it is a nonlinear problem with *** optimization algorithms have difficulty in finding the optimal solution that minimizes the cost function under various *** the same time,robustness should be taken into account to ensure the reliable and safe operation of the *** this paper,a self-adaptive sparrow search algorithm(SSA),denoted as DRSSA,is *** optimization,a dynamic population strategy is used to allocate the searching effort between exploration and exploitation;a t-distribution perturbation coefficient is proposed to adaptively adjust the exploration range;a random learning strategy is used to help the algorithm from falling into the vicinity of the origin and local *** convergence of DRSSA is tested by 29 test functions from the Institute of Electrical and Electronics Engineers(IEEE)Congress on Evolutionary Computation(CEC)2017 benchmark ***,a stochastic optimization strategy is introduced to enhance safety in the path by accounting for potential *** sets of simulation experiments on multi-UAV path planning in three-dimensional environments demonstrate that the algorithm exhibits strong optimization capabilities and robustness in dealing with uncertain situations.

关键词： multiple unmanned aerial vehicle(multi-UAV) path planning sparrow search algorithm(SSA) stochastic optimization

来源：评论

学校读者我要写书评

暂无评论

An Edge-Specific Message Graph Convolution Network Based on Community Graph Structure Generation for Polymerization Process Prediction

SSRN

引用

SSRN 2024年

作者： Li, Jinpeng Hao, Kuangrong Chen, Lei Shi, Xun Xie, Ruimin College of Information Sciences and Technology Donghua University Shanghai 201620 China College of Materials Science and Engineering Donghua University Shanghai201620 China Engineering Research Center of Digitized Textile and Apparel Technology Ministry of Education Donghua University Shanghai201620 China

The monitoring and prediction of key process variables play a crucial role in the stability of the polyester fiber production processes. In the process of esterification, there are multiple types of strong nonlinear dependencies among many sensor variables, which has always been a challenge in non-diffusive system modeling and control. Therefore, an Edge-Specific Message Graph Convolution Network (ESMGCN) is proposed to achieve separate modeling of specific dependencies between each pair of sensors individually, and to describe more accurately non-diffusive polyester fiber production systems. In addition, to address the problem of different degrees of dependencies between different sensor community clusters, a community graph structure generation method is proposed to construct the graph structure within and between sensor communities, respectively. Finally, a multivariate time series prediction model for the polyester fiber polymerization process is constructed. Experiments are conducted in a real industrial system, and the results verify the model's effectiveness. © 2024, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Wi-Fi harvesting enabled energy optimization scheme for smart clothing 4

A Wi-Fi harvesting enabled energy optimization scheme for sm...

引用

4th IEEE International Conference on Electronic Information and Communication technology, ICEICT 2021

作者： Lin, Panyue Wang, Luyao Huang, Gan Chu, Xin Zhang, Lei College ofInformation Science and Technology Donghua University Shanghai201620 China Engineering Research Center o f Digitized Textile and Apparel Technology Ministry of Education Shanghai201620 China

ISBN: (纸本)9781665432030

The outbreak of the COVID-19 and the rapid aging population have made isolated medical treatment and home based care become the new norm. As a distributed wireless body sensor network (WBSN), smart clothing is of great importance for the monitoring of infectious diseases and chronic diseases. Yet, limited energy supply and real-time data transmission are challenging for regular use. In this paper, we propose an energy harvesting powered smart clothing architecture, which is optimized by reinforcement learning, PSO and static transferring algorithm to extend battery life while balancing the time delay of data transmission. To evaluate the optimization performance, the reinforcement learning, the static transferring algorithm and the particle swarm optimization(PSO) with two kinds of weight are conducted. The simulation results show that reinforcement learning has the optimal performance in terms of total cost, energy consumption and battery loss without considering the time delay. ©2021 IEEE

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Clothing Style Recommendation System based on Interactive Genetic Algorithm

Clothing Style Recommendation System based on Interactive Ge...

引用

作者： Kai Sun Long Wu Jing Qi Jun-Tao Ding Yue Wang Jun Zhang School of Apparel&Art Design Xi'an Polytechnic University Shaanxi Research Center of Clothing Engineering and Technology Xi'an Polytechnic University Shaanxi "Four Subjects and One Union" Clothing Intelligent Design and Manufacturing Engineering Technology Research Center Wuhan Textile and Apparel Digital Engineering Technology Research Center

Given consumers' increasing demand for personalized recommendations of clothing styles,this study proposes a recommendation system based on an interactive genetic algorithm for women's *** interactive genetic algorithm as the core,the system interacts with users through the interface to obtain preference information in realtime,and then integrates the user's implicit decision factors,such as emotions and preferences,into the system through the adaptive function and uses the genetic algorithm to optimize the recommendation results to meet the personalized needs of *** can then be optimized based on user experience and feedback.

关键词： Clothing Style Recommendation Interactive Genetic Algorithm Personalized Recommendation System User Preference Recommendation Satisfaction

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning in Maximum Entropy Framework with Automatic Adjustment of Mixed Temperature Parameters for Path Planning

Deep Reinforcement Learning in Maximum Entropy Framework wit...

引用

Robotics, Control and Automation (ICRCA), International Conference on

作者： Yingying Chen Fengkang Ying Xiangjian Li Huashan Liu College of Information Science and Technology Donghua University China Engineering Research Center of Digitized Textile & Fashion Technology Ministry of Education Shanghai China

Deep reinforcement learning in maximum entropy framework is sample-efficient and has a strong exploration capacity, making it effective and favorable to solve problems like path planning. Properly tuning the temperature parameters can improve the performance of policy learning, but manual tuning is inefficient. In this paper, we propose a mixed algorithm named SAC-M which is inspired by adaptive soft actor-critic (A-SAC) and soft actor-critic with automatic entropy (SAC-A). The proposed method achieves automatic adjustment of temperature parameters so that the entropy can vary among different states to control the degree of exploration, reducing the possibility of learning suboptimal policies to some extent. The experimental results illustrate that the proposed SAC-M outperforms A-SAC and SAC-A in path planning tasks in different scenes, especially when A-SAC and SAC-A are mixed in a proper ratio.

关键词： Deep learning Reinforcement learning Manuals Entropy Path planning Temperature control Task analysis

来源：评论

学校读者我要写书评

暂无评论

Expert-guided Triple-memory Deep Reinforcement Learning for Robotic Motion Planning

Expert-guided Triple-memory Deep Reinforcement Learning for ...

引用

WRC Symposium on Advanced Robotics and Automation (WRC SARA)

作者： Huashan Liu Guojing Zhang Xiangjian Li Xinjie Xiao College of Information Science and Technology Donghua University Engineering Research Center of Digitized Textile & Fashion Technology Ministry of Education Shanghai China

Off-policy deep reinforcement learning (DRL) mostly use memory to improve the processes of data sampling. However, it is difficult for DRL to obtain positive feedback in the early stage of the training. Although an expert memory can solve the problem of sparse rewards in the early stage of training, it can not ensure to obtain the optima, and even leads to overfitting, which affects the performance of the agent in the later stage. In this paper, an expert-guided triple-memory (ETM) framework is proposed to be applied in off-policy DRL, so as to enhance the convergence performance and enhance the stability of the algorithm. Experimental results show that, the proposed approach is feasible and superior in the obstacle-avoidance motion planning tasks for robots.

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：