检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Mo, Shurong Wu, Nailong Qi, Jie Pan, Anqi Feng, Zhiguang Yan, Huaicheng Wang, Yueying College of Information Science and Technology Donghua University Shanghai201620 China Engineering Research Center of Digitized Textile and Fashion Technology Ministry of Education Donghua University Shanghai201620 China College of Intelligent Systems Science and Engineering Harbin Engineering University Harbin150056 China School of Information Science and Engineering East China University of Science and Technology Shanghai200237 China School of Mechatronic Engineering and Automation Shanghai University Shanghai200444 China

In this paper, a delay compensation feedback controller based on reinforcement learning is therefore proposed to adjust the time interval of the adaptive cruise control (ACC) vehicle agents in traffic congestion by introducing the proximal policy optimization (PPO) scheme. The high-speed traffic flow is characterized by two-by-two Aw Rasle Zhang (ARZ) nonlinear first-order partial differential equations (PDEs). Unlike the backstepping delay compensation control1, the PPO controller proposed in this paper consists of the current traffic flow velocity, the current traffic flow density, and the previous one-step control input. Since the system dynamics of the traffic flow are difficult to be expressed mathematically, the control gains of the three feedback can be determined via learning from the interaction between the PPO and the digital simulator of the traffic system. The performance of Lyapunov control, backstepping control and PPO control are compared with numerical simulation. The results demonstrate that PPO control is superior to Lyapunov control in terms of the convergence rate and control efforts for the traffic system without delay. As for the traffic system with an unstable input delay value, the performance of the PPO controller is also equivalent to that of the backstepping controller. Besides, PPO is more robust than backstepping controller when the parameter is sensitive to Gaussian noise. © 2022, CC BY.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Smart online charging algorithm for electric vehicles via customized actor-critic learning

arXiv

引用

arXiv 2021年

作者： Cao, Yongsheng Wang, Hao Li, Demin Zhang, Guanglin College of Information Science and Technology Donghua University Engineering Research Center of Digitized Textile and Apparel Technology Ministry of Education Shanghai201620 China The Department of Data Science and Artificial Intelligence Faculty of Information Technology Monash University MelbourneVIC3800 Australia The Stanford Sustainable Systems Lab Stanford University StanfordCA94305 United States

With the advances in the Internet of Things technology, electric vehicles (EVs) have become easier to schedule in daily life, which is reshaping the electric load curve. It is important to design efficient charging algorithms to mitigate the negative impact of EV charging on the power grid. This paper investigates an EV charging scheduling problem to reduce the charging cost while shaving the peak charging load, under unknown future information about EVs, such as arrival time, departure time, and charging demand. First, we formulate an EV charging problem to minimize the electricity bill of the EV fleet and study the EV charging problem in an online setting without knowing future information. We develop an actor-critic learning-based smart charging algorithm (SCA) to schedule the EV charging against the uncertainties in EV charging behaviors. The SCA learns an optimal EV charging strategy with continuous charging actions instead of discrete approximation of charging. We further develop a more computationally efficient customized actor-critic learning charging algorithm (CALC) by reducing the state dimension and thus improving the computational efficiency. Finally, simulation results show that our proposed SCA can reduce EVs' expected cost by 24.03%, 21.49%, 13.80%, compared with the Eagerly Charging Algorithm, Online Charging Algorithm, RL-based Adaptive Energy Management Algorithm, respectively. CALC is more computationally efficient, and its performance is close to that of SCA with only a gap of 5.56% in the cost. Copyright © 2021, The Authors. All rights reserved.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Optimizing deep neural networks through neuroevolution with stochastic gradient descent

arXiv

引用

arXiv 2020年

作者： Zhang, Haichao Hao, Kuangrong Gao, Lei Wei, Bing Tang, Xuesong College of Information Science and Technology Engineering Research Center of Digitized Textile and Apparel Technology Ministry of Education Donghua University Shanghai201620 China CSIRO Waite Campus UrrbraeSA5064 Australia

Deep neural networks (DNNs) have achieved remarkable success in computer vision;however, training DNNs for satisfactory performance remains challenging and suffers from sensitivity to empirical selections of an optimization algorithm for training. Stochastic gradient descent (SGD) is dominant in training a DNN by adjusting neural network weights to minimize the DNN’s loss function. As an alternative approach, neuroevolution is more in line with an evolutionary process and provides some key capabilities that are often unavailable in SGD, such as the heuristic black-box search strategy based on individual collaboration in neuroevolution. This paper proposes a novel approach that combines the merits of both neuroevolution and SGD, enabling evolutionary search, parallel exploration, and an effective probe for optimal DNNs. A hierarchical cluster-based suppression algorithm is also developed to overcome similar weight updates among individuals for improving population diversity. We implement the proposed approach in four representative DNNs based on four publicly-available datasets. Experiment results demonstrate that the four DNNs optimized by the proposed approach all outperform corresponding ones optimized by only SGD on all datasets. The performance of DNNs optimized by the proposed approach also outperforms state-of-the-art deep networks. This work also presents a meaningful attempt for pursuing artificial general intelligence. Copyright © 2020, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Optimal Resources Allocation of Bidirectional Relay Communication

Optimal Resources Allocation of Bidirectional Relay Communic...

引用

International Conference on Artificial Intelligence in Information and Communication (ICAIIC)

作者： Caixia Cai Runhe Qiu Xue-Qin Jiang College of Information Sciences and Technology Engineering Research Center of Digitized Textile & Fashion Technology Ministry of Education Donghua University Shanghai China

ISBN: (数字)9781728149851

ISBN: (纸本)9781728149868

This paper is aiming at solving a joint optimization of transmit powers (TPs) and transmit time (TT) allocation problem. The joint optimization problem needs to consider nonideal power amplifiers (PAs) efficiency, non-negligible circuit powers (CPs) consumption and direct links (DLs) in relaying transmission (RT) simultaneously. Firstly, transmission models, spectral-efficiency (SE) analysis, and total energy consumption (TEC) models with the existence of DLs in RT are given. Secondly, minimizing TEC analysis with joint optimization of TPs and TT under non-negligible CPs consumption and nonideal PAs efficiency is given. In addition, the gradient-descent algorithm which is used to solve the joint optimization problem is given. Furthermore, optimal relay position (ORP) problems are analyzed. Simulations are presented to validate the theoretical analysis. Results reveal that the relay technique and DLs in RT can improve the system's SE and energy-efficiency (EE).

关键词： Relays Optimization Resource management Energy consumption Analytical models Protocols Fading channels

来源：评论

学校读者我要写书评

暂无评论

Exposing image forgery using Lambert model and shadows 3

Exposing image forgery using Lambert model and shadows

引用

3rd Annual International Conference on Network and Information Systems for Computers, ICNISC 2017

作者： Hou, Yang-Yu Ge, Hua-Yong Fang, Shu-Juan Xu, Cai-Xia College of Information Sciences and Technology Donghua University China Engineering Research Center of Digitized Textile and Fashion Technology Ministry of Education Shanghai China

ISBN: (纸本)9781538616185

In view of the rapid development of the modern science and technology, image processing technology is also widely used in various fields. More and more digital images are tampered, which brings a lot of difficulties and troubles. This paper analyzes the shadows of objects which are produced by the point light source or the line light source, and makes a preliminary judgment by calculating the grey level. Based on Lambert illumination model and optical properties of consistency, this paper proposes a new technique to judge whether an image is tampered or not. At last, the experimental results are obtained by analyzing the shadows of a lot of images. © 2019 IEEE.

关键词： Light sources

来源：评论

学校读者我要写书评

暂无评论

Delay-Compensated Distributed PDE Control of Traffic with Connected/Automated Vehicles

arXiv

引用

arXiv 2021年

作者： Qi, Jie Mo, Shurong Krstic, Miroslav The College of Information Science and Technology Engineering Research Center of Digitized Textile and Fashion Technology Ministry of Education Donghua University Shanghai201620 China The College of Information Science and Technology Donghua University Shanghai201620 China The Department of Mechanical Aerospace Engineering University of California San DiegoCA92093-0411 United States

We develop an input delay-compensating design for stabilization of an Aw-Rascle-Zhang (ARZ) traffic model in congested regime which is governed by a 2×2 first-order hyperbolic nonlinear PDE. The traffic flow consists of both adaptive cruise control-equipped (ACC-equipped) and manually-driven vehicles. The control input is the time gap of ACC-equipped and connected vehicles, which is subject to delays resulting from communication lag. For the linearized system, a novel three-branch bakcstepping transformation with explicit kernel functions is introduced to compensate the input delay. The transformation is proved to be bounded, continuous and invertible, with explicit inverse transformation derived. Based on the transformation, we obtain the explicit predictor-feedback controller. We prove exponential stability of the closed-loop system with the delay compensator in L2 norm. The performance improvement of the closed-loop system under the proposed controller is illustrated in simulation. © 2021, CC BY.

关键词： Feedback

来源：评论

学校读者我要写书评

暂无评论

Cost Minimization for Geo-Distributed Data centers with Renewable Resources and Energy Storages

Cost Minimization for Geo-Distributed Data Centers with Rene...

引用

IEEE Global Communications Conference

作者： Shun Zhang Zhirong Shen Guanglin Zhang College of Information Science and Technology Donghua University Engineering Research Center of Digitized Textile and Apparel Technology Ministry of Education

ISBN: (数字)9781728109626

ISBN: (纸本)9781728109633

With the rapid development of cloud computing, data centers are increasing in quantity and scale for large Internet service providers to provide global Internet services. The enormous operation cost of data centers attracts lots of researchers' attention and their huge energy consumption have brought great challenges to the sustainable development of green data centers. In this paper, we investigate the workload scheduling and energy management issues of geo-distributed data centers with renewable resources and energy storages. We formulate the minimization problem of operation cost including electricity cost, water consumption and carbon emission as a stochastic optimization problem. For minimizing the long-term operation cost, we adopt the Lyapunov optimization technique to design an online algorithm which achieves a delicate tradeoff between system cost and performance of delay tolerant workloads. Moreover, extensive simulation results show the correctness and effectiveness of proposed online algorithm based on the real-world traces.

关键词： Data centers Carbon dioxide Renewable energy sources Delays Batteries Servers

来源：评论

学校读者我要写书评

暂无评论

Hydrogen bond network study of cellulose ⅱ based on molecular dynamics simulation 12

Hydrogen bond network study of cellulose ⅱ based on molecul...

引用

12th textile Bioengineering and Informatics Symposium, TBIS 2019

作者： Chen, Yu Jiang, Xue-Wei Wuhan Textile and Apparel Digital Engineering Technology Research Center School of Fashion Wuhan Textile University No.1 Fangzhi Road Wuhan Hubei430073 China

Hydrogen bonds play an important role in the structure and properties of cellulose Ⅱ. In this paper, the initial atom coordinates and molecular model were obtained from experimental data. The molecular structural and hydrogen bonds of cellulose Ⅱ were analysed, based on the molecular dynamics simulation at 300 K. The discussions were divided into center and origin chains. The properties of the cellulose structure indicate that the initial model and force field are suitable. The results show that bond lengths and angles of cellulose Ⅱ do not change, except for the hydroxyl groups. The dihedral angles affect the hydrogen bonds formation. These angles in the center chain are 32.963%, 14.890% and 26.052%, respectively, which are larger than those in the origin chain. The gt conformation participating in O6-H…O6' hydrogen bonds in the origin chain is 16.558% larger than in the center chain. However, the gg conformational structure is mainly involved in the O3-H…O5 hydrogen bond in the origin chain. Importantly, the formed O3-H…O5 hydrogen bond fluctuates greatly in the origin chain, but hardly exists in the center chain. Interestingly, O2-H…O6' has the shortest bond length and the largest proportion. These results can help us to comprehensive understand the stability and structure of cellulose Ⅱ properties more accurately. © (2019) textile Bioengineering and Informatics Symposium Proceedings 2019 - 12th textile Bioengineering and Informatics Symposium, TBIS 2019. All rights reserved.

关键词： Molecular dynamics

来源：评论

学校读者我要写书评

暂无评论

Image Inpainting Using Double Discriminator Generative Adversarial Networks

引用

Journal of Physics: Conference Series 2021年第1期1732卷

作者： Chao Zhang Tong Wang Engineering Research Center of Digitized Textile & Apparel Technology Ministry of Education College of Information Science and Technology Donghua University Shanghai 201620 P. R. China

The image inpainting algorithms based on GAN have problems such as color inconsistencies of the inpainted region with the surrounding part and the mode collapse during the training. This paper proposes an inpainting algorithm based on double discriminator generative adversarial networks (GANs). This algorithm introduces the loss function of WGAN-GP into a global discriminator and local discriminator independently. It combines the Mean-Square Error (MSE) and feature reconstruction loss function to train the inpainting model and repair the missing area. The algorithm uses more dilated convolutions instead of standard convolutions to obtain a larger receptive field and the skip connection to enhance the structural prediction ability of the generator. The experiment results on the labeled faces in the wild dataset show that our algorithm improves the quality of image inpainting and the stability of the training process.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On textile biomedical engineering

引用

Science China(Technological Sciences) 2019年第6期62卷 945-957页

作者： LI Yi ZHANG Xin YING BaoAn College of Textile Science and Engineering Xi'an Polytechnic University Xi'an 710048 China School of Materials The University of Manchester Manchester Ml3 9PL United Kingdom Research Center of Clothing Engineering and Technology Apparel and Art Design College Xi'an Polytechnic University Xi'an 710048 China

The demand for advanced fiber biomaterials and medical devices has risen rapidly with the increasing of aging population in the world. To address this grand societal challenge, textile biomedical engineering(TBE) has been defined as a holistic and integrative approach of designing and engineering advanced fiber materials for fabricating textile structures and devices to achieve various functions such as drug delivery, tissue engineering and artificial implants, pressure therapy and thermal therapy,bioelectric/magnetic detection and stimulation for the medical treatment and rehabilitation of human body. TBE is multidisciplinary in nature and needs integration of cross disciplinary expertise in medical science, healthcare professionals, physiologists, scientists and engineers in chemistry, materials, mechanics, electronics, computing, textile and designers. engineering fiber materials and designing textile devices for biomedical applications involve the integration of the fundamental research in physics, chemistry, mathematics, and computational science with the development of engineering principles and understanding on the relationship between textile materials/devices and human physiology, behaviour, medicine and health. Theoretical concepts have been advanced together with creating new knowledges created from molecules to cells, organs and body-textile systems, and developing advanced fiber materials, innovative textile devices and functional apparel products for healthcare,comfort, protection against harmful external environment, diseases prevention, diagnosis and treatment, as well as rehabilitations. A holistic, integrative and quantitative approach has been adopted for deriving the technical solutions of how to engineer fibers and textiles for the benefits of human health. This paper reviews the theoretical foundations for textile biomedical engineering and advances in the recent years.

关键词： biomaterials fibers textile biomedical engineering healthcare smart functions nano

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：