检索结果-南通市图书馆

A Survey of Multi-robot Regular and Adversarial Patrolling

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2019年第4期6卷 894-903页

作者： Li Huang MengChu Zhou kuangrong hao Edwin Hou IEEE the Engineering Research Center of Digitized Textile and Apparel Technology Ministry of Educationand the College of Information Science and TechnologyDonghua UniversityShanghai 201620China the Department of Electrical and Computer Engineering New Jersey Institute of TechnologyNewarkNJ 07032 the Institute of Systems Engineering Macao University of Science and TechnologyMacao 999078China

Multi-robot systems can be applied to patrol a concerned environment for security *** to different goals,this work reviews the existing researches in a multi-robot patrolling field from the perspectives of regular and adversarial *** patrolling requires robots to visit important locations as frequently as possible and a series of deterministic strategies are proposed,while adversarial one focuses on unpredictable robots’moving patterns to maximize adversary detection *** each category,a systematic survey is done including problem statements and modeling,patrolling objectives and evaluation criteria,and representative patrolling strategies and *** problems and open questions are presented accordingly.

关键词： Multi-robot systems regular patrolling adversarial patrolling coordination methods surveillance

Crop Leaf Disease Recognition Network Based on Brain Parallel Interaction Mechanism

在线全文

学校读者我要写书评

暂无评论

Journal of Donghua University(English Edition) 2022年第2期39卷 146-155页

作者： YUAN Hui hao kuangrong WEI Bing Engineering Research Center of Digitized Textile&Apparel Technology Ministry of EducationCollege of Information Science and TechnologyDonghua UniversityShanghai 201620China

In the actual complex environment,the recognition accuracy of crop leaf disease is often not *** by the brain parallel interaction mechanism,a two-stream parallel interactive convolutional neural network(TSPI-CNN)is proposed to improve the recognition ***-CNN includes a two-stream parallel network(TSP-Net)and a parallel interactive network(PI-Net).TSP-Net simulates the ventral and dorsal ***-Net simulates the interaction between two pathways in the process of human brain visual information transmission.A large number of experiments shows that the proposed TSPI-CNN performs well on MK-D2,PlantVillage,Apple-3 leaf,and Cassava leaf ***,the effect of numbers of interactions on the recognition performance of TSPI-CNN is *** experimental results show that as the number of interactions increases,the recognition accuracy of the network also ***,the network is visualized to show the working mechanism of the network and provide enlightenment for future research.

关键词： brain parallel interaction mechanism recognition accuracy convolutional neural network crop leaf disease recognition

Compression Mechanical Performance Simulation and Parameter Optimization of Degradable Ureteral Stent Based on ABAQUS

在线全文

学校读者我要写书评

暂无评论

Journal of Donghua University(English Edition) 2023年第1期40卷 1-7页

作者：刘璐刘肖燕郝矿荣 College of Information Science and Technology Donghua UniversityShanghai 201620China Engineering Research Center of Digitized Textile&Apparel Technology Ministry of EducationDonghua UniversityShanghai 201620China

The compression performance of a degradable ureteral stent is analyzed and the parameters are optimized by a finite element modeling *** degradable ureteral stent explored in this paper is developed from poly(glycolic acid)(PGA)and poly(lactic-co-glycolic acid)(PLGA)degradable *** on the actual measurement of fabric structure parameters,the three-dimensional model of the stent is established with the help of the modeling *** finite element analysis software is used to simulate the compression process of the degradable ureteral *** parameters of materials,interactions and boundary conditions are set according to the compression environment of the stent for modeling and *** this basis,the friction coefficient of yarns,the yarn radius,and the braided angle of the stent are further *** comparison test is carried out by a single *** experimental results show that the change of yarn friction coefficient has little influence on the compressive stress,while the yarn radius and the braided angle of the stent have a great influence on the compressive stress.

关键词： degradable ureteral stent geometric model compression performance finite element modeling method

同方期刊数据库

基于集成LSTM-AE的时间序列异常检测方法

在线全文

学校读者我要写书评

暂无评论

华中科技大学学报（自然科学版） 2021年第11期49卷 35-40页

作者：陈磊秦凯郝矿荣东华大学数字化纺织服装技术教育部工程研究中心上海201620 东华大学信息科学与技术学院上海201620

针对基于LSTM-AE(长短期记忆自编码器)的时间序列异常检测方法在异常检测阶段对正常序列和异常序列的重建误差不能明显分化,致使重建误差在阈值附近的序列无法正确判断正常与异常的问题,提出一种集成LSTM-AE框架——LAEE(长短期记忆自... 详细信息

针对基于LSTM-AE(长短期记忆自编码器)的时间序列异常检测方法在异常检测阶段对正常序列和异常序列的重建误差不能明显分化,致使重建误差在阈值附近的序列无法正确判断正常与异常的问题,提出一种集成LSTM-AE框架——LAEE(长短期记忆自编码器集成框架).将训练阶段拆分为预训练和预检测两个阶段,在预训练阶段训练多个隐层维度不同的LSTM-AE,通过预检测阶段的表现挑选基检测器,并计算其各自权重;在异常检测阶段,通过对每个基检测器产生的重建误差进行加权集成获得新的重建误差矩阵,进行异常识别.通过在两类数据集上的实验结果表明:所提方法使得检测目标正常序列与异常序列重建误差分化程度加大,提高了异常检测精度.

关键词：时间序列异常检测长短期记忆自动编码器集成框架重建误差

A super-pixel slicing enhanced positional encoding for vision transformers

在线全文

学校读者我要写书评

暂无评论

A super-pixel slicing enhanced positional encoding for visio...

Attention-Guided Sparse Adversarial Attacks with Gradient Dropout

第43届中国控制会议

作者： Junchao Lu Xue-song Tang kuangrong hao College of Information Science and Technology Donghua University

Transformers have performed exceptionally well in natural language processing(NLP), prompting researchers to study their potential in computer vision. One such transformer is the Vision Transformer(ViT), which uses a pure transformer structure to classify images through a sequence of fixed-size patches. However, relying on the same patch embedding method for all images is considered an oversimplification of the process. In response to this limitation, we propose a super-pixel slicing scheme that dynamically generates a sequence of patch embeddings based on an image's features. This sequence is then utilized to create a progressive positional encoding which can bring together slices of the same object. Our method can seamlessly integrate into the existing Transformer framework to form an end-to-end Vision Transformer with Superpixel Slicing(SSVT).Our empirical results show that SSVT significantly improves the performance of transformer-based models in image classification tasks.

关键词： Image Classification Vision Transformer Super-pixel Slicing Patch Embedding Positional Encoding

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Journal of Donghua University(English Edition) 2024年第5期41卷 545-556页

作者： Zhao Hongzhi hao Lingguang hao kuangrong WEI Bing LIU Xiaoyan College of Information Science and Technology Donghua UniversityShanghai 201620China Engineering Research Center of Digitized Textile and Apparel Technology Ministry of EducationDonghua UniversityShanghai 201620China

Deep neural networks are extremely vulnerable to externalities from intentionally generated adversarial examples which are achieved by overlaying tiny noise on the clean ***,most existing transfer-based attack methods are chosen to add perturbations on each pixel of the original image with the same weight,resulting in redundant noise in the adversarial examples,which makes them easier to be *** this deliberation,a novel attentionguided sparse adversarial attack strategy with gradient dropout that can be readily incorporated with existing gradient-based methods is introduced to minimize the intensity and the scale of perturbations and ensure the effectiveness of adversarial examples at the same ***,in the gradient dropout phase,some relatively unimportant gradient information is randomly discarded to limit the intensity of the *** the attentionguided phase,the influence of each pixel on the model output is evaluated by using a soft mask-refined attention mechanism,and the perturbation of those pixels with smaller influence is limited to restrict the scale of the *** conducting thorough experiments on the NeurIPS 2017 adversarial dataset and the ILSVRC 2012 validation dataset,the proposed strategy holds the potential to significantly diminish the superfluous noise present in adversarial examples,all while keeping their attack efficacy *** instance,in attacks on adversarially trained models,upon the integration of the strategy,the average level of noise injected into images experiences a decline of 8.32%.However,the average attack success rate decreases by only 0.34%.Furthermore,the competence is possessed to substantially elevate the attack success rate by merely introducing a slight degree of perturbation.

关键词： deep neural network adversarial attack sparse adversarial attack adversarial transferability adversarial example

一种纤维生产线水浴牵伸过程的智能协同解耦控制

在线全文

学校读者我要写书评

暂无评论

化工学报 2010年第8期61卷 2144-2148页

作者：梁霄丁永生王华平郝矿荣东华大学信息科学与技术学院上海201620 东华大学材料科学与技术学院上海201620 数字化纺织服装技术教育部工程研究中心上海201620

提出了一种智能协同解耦控制器,用于纤维生产线中的水浴牵伸槽的液位-浓度复合控制。该控制器由一个控制中枢、多个控制解耦单元及相应的输出单元组成。控制中枢统一协调各控制解耦单元,多个控制解耦单元独立作用并互相交换信息进行对... 详细信息

提出了一种智能协同解耦控制器,用于纤维生产线中的水浴牵伸槽的液位-浓度复合控制。该控制器由一个控制中枢、多个控制解耦单元及相应的输出单元组成。控制中枢统一协调各控制解耦单元,多个控制解耦单元独立作用并互相交换信息进行对象解耦,控制信号经输出单元综合后作用于控制对象。仿真结果表明,该智能协同解耦控制器能够快速响应控制量的变化,实现耦合控制量的完全解耦和无超调平滑调节,对于纤维生产的牵伸过程较传统控制方法具有更好的控制性能。

关键词：纤维生产水浴牵伸槽智能协同解耦控制

基于改进NSGA-Ⅱ的涤纶长丝熔体输送过程工艺优化

在线全文

学校读者我要写书评

暂无评论

计算机与应用化学 2012年第7期29卷 825-828页

作者：徐楠丁永生郝矿荣东华大学信息科学与技术学院上海201620 数字化纺织服装技术教育部工程研究中心上海201620

涤纶纺丝生产过程中熔体输送环节具有机理复杂、受诸多因素影响、拥有多种产品性能指标等特点,对其进行工艺优化较为困难,目前往往凭借生产经验,缺乏一定的理论指导。熔体输送环节工艺优化是1个多目标优化问题,为此提出了1种智能多目标... 详细信息

涤纶纺丝生产过程中熔体输送环节具有机理复杂、受诸多因素影响、拥有多种产品性能指标等特点,对其进行工艺优化较为困难,目前往往凭借生产经验,缺乏一定的理论指导。熔体输送环节工艺优化是1个多目标优化问题,为此提出了1种智能多目标工艺优化方法:。该方法:采用以Pareto多目标最优理论为优化导向的带精英策略非支配排序遗传算法(NSGA-Ⅱ),并对其进行了一定的改进。改进之处在于,传统的NSGA-Ⅱ算法选择用于计算个体拥挤度的参考点是按各个目标分别进行选择,本文采用了多个目标综合选择法,使拥挤度的计算与筛选更为准确。本文以熔体出口处压强、温度、特性粘度3个指标为优化目标,依据工业现场数据,进行了仿真实验。实验结果:表明,该方法:运算速度较快,优化结果:准确,分布均匀,能够对实际生产的工艺优化起到一定的指导作用。

关键词： NSGA-Ⅱ Pareto最优解多目标优化熔体输送

在线全文

学校读者我要写书评

暂无评论

基于时空相似性的即时学习在线建模

仪器仪表学报 2022年第6期43卷 185-193页

作者：施锦涛陈磊秦凯李振兴郝矿荣东华大学数字化纺织服装技术教育部工程研究中心上海201620 东华大学信息科学与技术学院上海201620

流程工业数据具有较大的时变性以及非线性,传统的离线模型难以应对实际生产过程中的工况变化,而即时学习是在线建模的有效方法。已有研究对即时学习的相似度度量方法大多只侧重于样本的空间距离,忽略了工业数据时序性的特点。为此,提出... 详细信息

流程工业数据具有较大的时变性以及非线性,传统的离线模型难以应对实际生产过程中的工况变化,而即时学习是在线建模的有效方法。已有研究对即时学习的相似度度量方法大多只侧重于样本的空间距离,忽略了工业数据时序性的特点。为此,提出基于时空相似性的即时学习建模方法。首先,将样本点延拓成样本序列,结合动态时间规整计算样本间的时序距离。其次,提出时空相似性度量准则,通过对时序距离和空间距离进行非线性加权,构建时空相似性度量指标。最后,提出基于时空相似性的即时学习在线建模方法。将所提算法应用于公共数据集及聚酯纤维聚合过程,拟合优度分别达到了91.6%和98.6%,实验结果验证了算法的有效性和优越性。

关键词：时空相似性即时学习在线建模流程工业数据驱动