检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Zhang, Chongzhen Tang, Yang Zhao, Chaoqiang Sun, Qiyu Ye, Zhencheng Kurths, Jürgen Key Laboratory of Advanced Control and Optimization for Chemical Process Ministry of Education East China University of Science and Technology Shanghai200237 China Potsdam Institute for Climate Impact Research Potsdam14473 Germany Institute of Physics Humboldt University of Berlin Berlin12489 Germany

Semantic segmentation and depth completion are two challenging tasks in scene understanding, and they are widely used in robotics and autonomous driving. Although several studies have been proposed to jointly train these two tasks using some small modifications, like changing the last layer, the result of one task is not utilized to improve the performance of the other one despite that there are some similarities between these two tasks. In this paper, we propose multi-task generative adversarial networks (Multi-task GANs), which are not only competent in semantic segmentation and depth completion, but also improve the accuracy of depth completion through generated semantic images. In addition, we improve the details of generated semantic images based on CycleGAN by introducing multi-scale spatial pooling blocks and the structural similarity reconstruction loss. Furthermore, considering the inner consistency between semantic and geometric structures, we develop a semantic-guided smoothness loss to improve depth completion results. Extensive experiments on Cityscapes dataset and KITTI depth completion benchmark show that the Multi-task GANs are capable of achieving competitive performance for both semantic segmentation and depth completion tasks. © 2020, CC BY.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Tiny Adversarial Multi-Objective Oneshot Neural Architecture Search

arXiv

引用

arXiv 2021年

作者： Xie, Guoyang Wang, Jinbao Yu, Guo Zheng, Feng Jin, Yaochu Department of Computer Science University of Surrey Guildford SurreyGU2 7XH United Kingdom Department of Computer Science Southern University of Science and Technology Shenzhen518055 China Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of Education East China University of Science and Technology Shanghai 200237 China Faculty of Technology Bielefeld University Bielefleld D-33615 Germany

Due to limited computational cost and energy consumption, most neural network models deployed in mobile devices are tiny. However, tiny neural networks are commonly very vulnerable to attacks. Current research has proved that larger model size can improve robustness, but little research focuses on how to enhance the robustness of tiny neural networks. Our work focuses on how to improve the robustness of tiny neural networks without seriously deteriorating of clean accuracy under mobile-level resources. To this end, we propose a multiobjective oneshot network architecture search (NAS) algorithm to obtain the best trade-off networks in terms of the adversarial accuracy, the clean accuracy and the model size. Specifically, we design a novel search space based on new tiny blocks and channels to balance model size and adversarial performance. Moreover, since the supernet significantly affects the performance of subnets in our NAS algorithm, we reveal the insights into how the supernet helps to obtain the best subnet under white-box adversarial attacks. Concretely, we explore a new adversarial training paradigm by analyzing the adversarial transferability and the difference between training the subnets from scratch and fine-tuning. Finally, we make a statistical analysis for the layer-wise combination of certain blocks and channels on the first non-dominated front, which can serve as a guideline to design tiny neural network architectures for the resilience of adversarial perturbations. Copyright © 2021, The Authors. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Deep adaptive fuzzy clustering for evolutionary unsupervised representation learning

arXiv

引用

arXiv 2021年

作者： Tan, Dayu Huang, Zheng Peng, Xin Zhong, Weimin Mahalec, Vladimir Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of Education East China University of Science and Technology Shanghai200237 China School of Engineering Practice and Technology McMaster University HamiltonONL8S 4L7 Canada Shanghai Institute of Intelligent Science and Technology Tongji University Shanghai200092 China Department of Chemical Engineering McMaster University HamiltonONL8S 4L7 Canada

Cluster assignment of large and complex images is a crucial but challenging task in pattern recognition and computer vision. In this study, we explore the possibility of employing fuzzy clustering in a deep neural network framework. Thus, we present a novel evolutionary unsupervised learning representation model with iterative optimization. It implements the deep adaptive fuzzy clustering (DAFC) strategy that learns a convolutional neural network classifier from given only unlabeled data samples. DAFC consists of a deep feature quality-verifying model and a fuzzy clustering model, where deep feature representation learning loss function and embedded fuzzy clustering with the weighted adaptive entropy is implemented. We joint fuzzy clustering to the deep reconstruction model, in which fuzzy membership is utilized to represent a clear structure of deep cluster assignments and jointly optimize for the deep representation learning and clustering. Also, the joint model evaluates current clustering performance by inspecting whether the re-sampled data from estimated bottleneck space have consistent clustering properties to progressively improve the deep clustering model. Comprehensive experiments on a variety of datasets show that the proposed method obtains a substantially better performance for both reconstruction and clustering quality when compared to the other state-of-the-art deep clustering methods, as demonstrated with the in-depth analysis in the extensive experiments. Copyright © 2021, The Authors. All rights reserved.

关键词： Fuzzy clustering

来源：评论

学校读者我要写书评

暂无评论

Ternary Compression for Communication-Efficient Federated Learning

arXiv

引用

arXiv 2020年

作者： Xu, Jinjin Du, Wenli Jin, Yaochu He, Wangli Cheng, Ran The Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of Education East China University of Science and Technology Shanghai200237 China Shanghai Institute of Intelligent Science and Technology Tongji University Shanghai200092 China The Department of Computer Science University of Surrey GuildfordGU2 7XH United Kingdom Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China

Learning over massive data stored in different locations is essential in many real-world applications. However, sharing data is full of challenges due to the increasing demands of privacy and security with the growing use of smart mobile devices and IoT devices. Federated learning provides a potential solution to privacy-preserving and secure machine learning, by means of jointly training a global model without uploading data distributed on multiple devices to a central server. However, most existing work on federated learning adopts machine learning models with full-precision weights, and almost all these models contain a large number of redundant parameters that do not need to be transmitted to the server, consuming an excessive amount of communication costs. To address this issue, we propose a federated trained ternary quantization (FTTQ) algorithm, which optimizes the quantized networks on the clients through a self-learning quantization factor. Theoretical proofs of the convergence of quantization factors, unbiasedness of FTTQ, as well as a reduced weight divergence are given. On the basis of FTTQ, we propose a ternary federated averaging protocol (T-FedAvg) to reduce the upstream and downstream communication of federated learning systems. Empirical experiments are conducted to train widely used deep learning models on publicly available datasets, and our results demonstrate that the proposed T-FedAvg is effective in reducing communication costs and can even achieve slightly better performance on non-IID data in contrast to the canonical federated learning algorithms. Copyright © 2020, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Agricultural Lignocellulose Biochar Material in Wastewater Treatment: A Critical Review and Sustainability Assessment

Environmental Functional Materials

引用

Environmental Functional Materials 2025年

作者： Aqib Zahoor Xiao Liu Yuxin Liu Shengyong Liu Wang Yi Shahdev Sajnani Lingyu Tai Nadeem Tahir Boré Abdoulaye Mahaveer Yuan Liu Zia ur Rahman Martina Damizia Benedetta de Caprariis International Joint Research Center for the Control and Prevention of Environmental Pollution on Tropical lslands of Hainan Province Key Laboratory of Agro-Forestry Environmental Processes and Ecological Regulation of Hainan Province School of Environmental Science and Engineering Hainan University Haikou 570228 P. R. China Collaborative Innovation Center of Biomass Energy Henan Agricultural University Zhengzhou 450002 School of Environmental Science and Engineering Tianjin University Tianjin 300350 P. R. China Faculty of Civil and Environmental Engineering Gdańsk University of Technology ul. Narutowicza 11/12 80-233 Gdańsk Poland Interdisciplinary Research Center for Refining and Advanced Chemicals King Fahd University of Petroleum & Minerals Dhahran 31261 Saudi Arabia Department of Chemical Engineering Materials and Environment Sapienza University of Rome Via Eudossiana 18 00184 Rome Italy

Globally, roughly 380 trillion liters of wastewater are generated annually, with a significant portion remaining untreated due to expensive treatment and lack of expertise, consequently, leading severe environmental and public health problems. This research aims to identify the most environmentally sustainable and eco-friendly approach to wastewater treatment. Results shows that, agricultural lignocellulose-based biomass (ALCB) biochar is highly effective for wastewater treatment due to its abundance, cost-effectiveness, and excellent adsorption properties. The ability of sustaining high carbon content makes it a valuable carbon sink beneficial for the carbon reduction. Annually, ALCB is widely available as a byproduct in developing countries like China 716 (million tons) Mt, India 605 Mt, Brazil 451 Mt, Pakistan 285 Mt as well as in developed regions U.S.A 682 Mt, and Europe 580 Mt. Pyrolysis, gasification, and torrefaction are mostly used methods for ALCB biochar production. Physicochemical properties including surface area, porosity, functional groups, pH, and elemental composition notably affected by production methods, feedstock types and reactor designs determine the adsorption performance and environmental safety of ALCB biochar. The adsorption mechanisms of the organic and inorganic pollutant on biochar are ion exchange, complexation, electrostatic attraction, pore-filings, and physical adsorption, etc. LCA assessment revealed that the utilization of ALCB biochar on wastewater treatment offers several economic, environmental, and educational benefits through the aspect of waste management, revenue generation, job creations, pollution control, trading and skill developments.

关键词： Agricultural lignocellulose-based biochar Pyrolysis Pollutant adsorption Sustainable water treatment Environmental and economic benefits

来源：评论

学校读者我要写书评

暂无评论

A Quantized H-infinity control for networked control systems with time-varying delay and multiple packet dropouts

引用

Kongzhi Lilun Yu Yingyong/control Theory and Applications 2013年第4期30卷 469-474页

作者： Yan, Huai-Cheng Su, Zhen-Zhen Zhang, Hao Yang, Fu-Wen Key Laboratory of Advanced Control and Optimization for Chemical Processes of Ministry of Education East China University of Science and Technology Shanghai 200237 China School of Information Science and Engineering East China University of Science and Technology Shanghai 200237 China Department of Control Science and Engineering Tongji University Shanghai 200092 China

This paper is concerned with the problem of quantized H-infinity control for networked control systems (NCSs) with time-varying delay and multiple packet dropouts. The packet dropouts in both the measurement channel and the control channel are considered simultaneously, and are modeled as stochastic variables with Bernoulli random binary distribution. Both the control input and measurement output are quantized before transmission and the quantization errors are described as sector-bound uncertainties. Sufficient conditions for the existence of an observer-based, delay-dependent controller are developed to ensure the exponentially mean-square stability of the closed-loop system and to achieve the optimal H-infinity disturbance attenuation. A numerical example is given to illustrate the effectiveness of the proposed method.

关键词： Networked control systems

来源：评论

学校读者我要写书评

暂无评论

$H_{\infty}$ Output Tracking control for Networked Systems With Adaptively Adjusted Event-Triggered Scheme

引用

IEEE Transactions on Systems, Man, and Cybernetics: Systems 2019年第10期49卷 2050-2058页

作者： Huaicheng Yan Chenyang Hu Hao Zhang Hamid Reza Karimi Xiaowei Jiang Ming Liu Key Laboratory of Advanced Control and Optimization for Chemical Process of Ministry of Education East China University of Science and Technology Shanghai China School of Information Science and Engineering East China University of Science and Technology Shanghai China Department of Control Science and Engineering Tongji University Shanghai China Department of Mechanical Engineering Politecnico di Milan Milan Italy College of Mechatronics and Control Engineering Hubei Normal University Huangshi China Research Center of Satellite Technology Harbin Institute of Technology Harbin China

The H ∞ output tracking control problem of the networked control systems (NCSs) under an adaptively adjusted event-triggered scheme is investigated in this paper. Firstly, a novel adaptively adjusted event-triggered scheme developed in the NCSs with stochastic sensor faults is proposed to choose the necessary packets of sampled data to be transmitted through the networks. Then, the considered system is described as a time-delay system with a delay-distribution for investigation. Based on the established model, a novel stability criterion and the state-feedback controller design with a desired performance of H ∞ output tracking control for the systems are both derived by using Lyapunov functional. An algorithm is also presented to explain the process of adaptively adjusted event-triggered scheme method. Finally, a satellite tracking case is provided to demonstrate the effectiveness of the proposed approach.

关键词： Bandwidth Delays Actuators Communication networks Symmetric matrices Networked control systems

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to “Research on data reconciliation based on generalized T distribution with historical data” [Neurocomputing 175PA (2015) 808–815]

引用

Neurocomputing 2016年 177卷 670-670页

作者： Shengxi Wu Qiang Ye Cheng Chen Xingsheng Gu Key Laboratory of Advanced Control and Optimization for Chemical Processes Ministry of Education East China University of Science and Technology No. 130 of Meilong Road Shanghai 200237 China

来源：评论

学校读者我要写书评

暂无评论

Fuzzy-Model-Based Leader-Follower Consensus of Nonlinear Multi-Agent Systems with Input Saturation

Fuzzy-Model-Based Leader-Follower Consensus of Nonlinear Mul...

引用

International Conference on control, Automation, Robotics and Vision (ICARCV)

作者： Xiaolu Liu Duxin Chen Yan-Wu Wang Huaicheng Yan School of Automation Huazhong University of Science and Technology Wuhan P. R. China School of Mathematics Southeast University Nanjing P. R. China Key Laboratory of Advanced Control and Optimization for Chemical Process of Ministry of Education East China University of Science and Technology Shanghai P. R. China

This paper presents a fuzzy-model-based method for solving the consensus problem of a class of nonlinear multi-agent systems (MASs) with input saturation. Since each agent has nonlinear dynamics, the system is not asymptotically null controllable with bounded controls (ANCBC). Therefore, the widely-used low-gain feedback method for designing consensus protocols of MASs with input saturation can no longer work. To this end, the Takagi-Sugeno (T-S) fuzzy model is adopted to formulate the error dynamics of those nonlinear follower agents with input saturation as well as a leader with time-varying states. Accordingly, by using the properties of convex hull, a set of invariance condition in the format of linear matrix inequality (LMI) is designed. Furthermore, by enlarging the shape reference set, the estimation of the attraction domain can be obtained. Simultaneously, by viewing the control gain as an extra free parameter in the LMI optimization procedure, the leader-follower consensus algorithm is proposed, which guarantees that all followers with input saturation can track the leader, and they can asymptotically reach consensus. Finally, numerical experiments validate the effectiveness of the proposed anti-saturation consensus algorithm.

关键词： Automation Nonlinear dynamical systems STEM Actuators Symmetric matrices

来源：评论

学校读者我要写书评

暂无评论

Event-trigged control for Discrete-time Multi-agent Networks

Event-trigged Control for Discrete-time Multi-agent Networks

引用

Asian control Conference

作者： Lulu Li Daniel W. C. Ho Yuanyuan Zou Chi Huang Jianquan Lu Department of Mathematics City University of Hong Kong Hong Kong. Key Laboratory of Advanced Control and Optimization for Chemical Process Ministry of Education East China University of Science and Technology Shanghai 200237 China Department of Mathematics Taiyuan University of Technology Taiyuan 030024 China. Department of Mathematics Southeast University Nanjing 210096 China.

ISBN: (纸本)9781467357661

In this paper, a new control strategy was proposed to deal with the discrete-time multi-agent consensus problem. Two types of protocols are discussed in this paper: i) networks of single-integrators without delay under centralized eventtriggered control and ii) networks of single-integrators with delay under distributed event-triggered control. For each consensus protocol, we prove that the multi-agent network will achieve consensus asymptotically. Numerical examples are provided to demonstrate the effectiveness of the obtained theoretical results.

关键词： Multi-agent networks consensus event-triggered control time delay

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：