检索结果-内蒙古大学图书馆

Optimal Feedback control of Pedestrian Flow in Heterogeneous Corridors

ieee TRANSACTIONS ON automation SCIENCE AND ENGINEERING 2021年第3期18卷 1097-1108页

作者： Zhu, Yuanheng Zhao, Dongbin He, Haibo Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Univ Rhode Isl Dept Elect Comp & Biomed Engn Kingston RI 02881 USA

Maintaining the orderliness and efficiency of pedestrian flow through an architectural area is critical for the evacuation process. Especially, clogs and jams are easily triggered in width-changing areas. In this article, we consider pedestrian movement in heterogeneous corridors and design an optimal feedback control to regulate pedestrian flow. Flow characteristics are first studied based on microscopic social-force simulations. A Gaussian process describes the relationship between flow variables with the observation data. The macroscopic model for flow in heterogeneous corridors is developed. To avoid jams, discharges among these corridors are balanced with the narrowest corridor as the primary concern. At the equilibrium, a continuous-time nonlinear control system is formulated, and the adaptive dynamic programming learns the optimal feedback controller. Policy iteration (PI) and neural networks are combined together, and the convergence of neural-network-based PI is demonstrated by analyzing its equivalence to the Gauss-Newton method. Batch normalization is introduced to stabilize the learning process. Simulated experiments demonstrate that the control design can effectively regulate pedestrian flow for both macroscopic and microscopic models. Note to Practitioners-The development of video-processing techniques provides a powerful tool to detect human behavior in real time. In crowd events, the pedestrian movement must be regulated;otherwise, it is easy to fall into the faster-is-slower effect. It is especially important for evacuation routes with different widths. In this article, the optimal feedback control is studied to regulate pedestrian flow in heterogeneous corridors. It takes flow densities as state and produces commands that are composed of entrance influx and free-flow velocities. These commands can be executed with the support of speakers, displays, or the recently developed interactive robots. To avoid congestion, discharges of different corridors

关键词： Microscopy Feedback control Mathematical model Data models Dynamic programming Psychology computational modeling Adaptive dynamic programming (ADP) heterogeneous corridors macroscopic pedestrian dynamics optimal feedback control pedestrian flow

来源：评论

学校读者我要写书评

暂无评论

On Detecting Anomalous TLS Connections with Artificial intelligence Models

On Detecting Anomalous TLS Connections with Artificial Intel...

引用

ieee symposium on Computers and Communications (ISCC)

作者： Diana Gratiela Berbecaru Stefano Giannuzzi Department of Control and Computer Engineering Politecnico di Torino Italy Politecnico di Torino Italy Torino Italy

ISBN: (数字)9798350354232

ISBN: (纸本)9798350354249

In recent years, anomaly-based intrusion detection systems using machine learning (ML) and deep learning techniques have started to be developed to mitigate cybersecurity attacks. An anomaly-based intrusion detection system performs traffic analysis by exploiting supervised or unsupervised ML algorithms and raises alerts if a suspicious pattern is encountered. In this paper, we exploit the Autoencoder neural network model to detect variants of a very famous attack discovered in 2014, namely Heartbleed. The attack was caused by an implementation flaw in the OpenSSL library, widely used in web servers, database systems, or e-mail servers to support the Transport Layer Security (TLS) protocol. To evaluate our model, we exploited the CIC-IDS2017 dataset and a custom one created on purpose. The proposed model recognized the anomalous TLS connections containing variants of the Heartbleed attack and distinguished them from the benign traffic in 85% of the cases.

关键词： Protocols Machine learning algorithms computational modeling Supervised learning Neural networks Intrusion detection Semisupervised learning Libraries Web servers Malware

来源：评论

学校读者我要写书评

暂无评论

Introduction of a Mutual Feature between Electrodes into Support Vector Machine Based Person Verification Using Evoked Electroencephalogram by Ultrasound

Introduction of a Mutual Feature between Electrodes into Sup...

引用

ieee symposium Series on computational intelligence (SSCI)

作者： Isao Nakanishi Kotaro Mukai Faculty of Engineering Tottori Univerisity Tottori Japan Faculty of Sustainable Sciences Tottori University Tottori Japan

ISBN: (纸本)9781665487696

In user management, to realize continuous user authentication, we study the use of an electroencephalogram (EEG) evoked by ultrasound as biometrics. In previous studies, using a spectrum and four nonlinear quantities in EEG as individual features and a support vector machine (SVM) as a verification method achieved an equal error rate (EER) of 0 %. However, it required a large number of SVM models, wherein considerable amount of computation regarding learning was consumed. In this study, we introduce a mutual feature between electrodes and confirm its effectiveness in achieving EER = 0 % with a smaller number of SVM models.

关键词： Support vector machines Electrodes Ultrasonic imaging Biometrics (access control) computational modeling Frequency-domain analysis Biological system modeling

来源：评论

学校读者我要写书评

暂无评论

EELE: Exploring Efficient and Extensible LoRA Integration in Emotional Text-to-Speech

EELE: Exploring Efficient and Extensible LoRA Integration in...

引用

International symposium on Chinese Spoken Language Processing

作者： Xin Qi Ruibo Fu Zhengqi Wen Jianhua Tao Shuchen Shi Yi Lu Zhiyong Wang Xiaopeng Wang Yuankun Xie Yukun Liu Guanjun Li Xuefei Liu Yongwei Li Institute of Automation Chinese Academy of Science School of Artificial Intelligence University of Chinese Academy of Sciences Beijing National Research Center for Information Science and Technolgy Tsinghua University Department of Automation Tsinghua University Shanghai Polytechnic University School of Information and Communication Engineering Communication University of China

ISBN: (数字)9798331516826

ISBN: (纸本)9798331516833

In the current era of Artificial intelligence Generated Content (AIGC), a Low-Rank Adaptation (LoRA) method has emerged. It uses a plugin-based approach to learn new knowledge with lower parameter quantities and computational costs, and it can be plugged in and out based on the specific sub-tasks, offering high flexibility. However, the current application schemes primarily incorporate LoRA into the pre-introduced conditional parts of the speech models. This fixes the position of LoRA, limiting the flexibility and scalability of its application. Therefore, we propose the Exploring Efficient and Extensible LoRA Integration in Emotional Text-to-Speech (EELE) method. Starting from a general neutral speech model, we do not pre-introduce emotional information but instead use the LoRA plu-gin to design a flexible adaptive scheme that endows the model with emotional generation capabilities. Specifically, we initially train the model using only neutral speech data. After training is complete, we insert LoRA into different modules and fine-tune the model with emotional speech data to find the optimal in-sertion scheme. Through experiments, we compare and test the effects of inserting LoRA at different positions within the model and assess LoRA's ability to learn various emotions, effectively proving the validity of our method. Additionally, we explore the impact of the rank size of LoRA and the difference compared to directly fine-tuning the entire model.

关键词： Training Adaptation models Limiting Scalability Refining Focusing Games Motion pictures Data models Text to speech

来源：评论

学校读者我要写书评

暂无评论

Towards cloud-based control-as-a-Service for modular Process Plants

Towards cloud-based Control-as-a-Service for modular Process...

引用

International Conference on Emerging Technologies and Factory automation (ETFA)

作者： Lucas Vogt Anselm Klose Valentin Khaydarov Christian Vockeroth Christian Endres Leon Urbas Process-to-Order Lab TU Dresden Dresden Germany Sartorius Stedim Systems GmbH Guxhagen Germany Sartorius Stedim Biotech GmbH Göttingen Germany Chair of Process Control Systems TU Dresden Dresden Germany

BACKGROUND: computational and data-intensive technologies such as model predictive control and artificial intelligence have the potential to increase process yields in the process industry. In modular plant designs, the flexible and difficult-to-predict use of a particular module presents the challenge of providing the right amount of data, computing power, and storage capacity to use these technologies in each ***: Simplifying the deployment and reconfiguration of compute-intensive applications for modular ***: Reviewing the current state of the art and combining the modular plant concept with a cloud-based control-as-a-Service (CaaS) ***: A cloud-based, containerized CaaS concept that supports the deployment compute- and data-intensive methods for modular plants. The complementing communication stack consisting of standards such as APL, TSN and OPC UA ***: The proposed architecture simplifies IT/OT integration, eases the deployment of compute-intensive technologies, and allows for GMP compliant pre-qualification of software modules. However, the limiting factors like plant safety, conformity to regulations and widespread architecture adoption are not covered in detail and will be subject of future research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FPGA Validated Advanced Learning-Based Voltage control of DC/DC Converter Feeding CPL in DC Microgrid Applications

FPGA Validated Advanced Learning-Based Voltage Control of DC...

引用

ieee International symposium on Industrial Electronics (ISIE)

作者： Hussain Sarwar Khan Kimmo Kauhaniemi School of Technology and Innovations University of Vaasa Vaasa Finland

The high penetration of renewable energy distribution generations enables the concept of microgrids and is widely accepted for future power systems. In this context, the DC microgrid is preferred due to easy integration, less system losses and offer high reliability and efficiency compared to its counterparts. However, the constant power loads (CPL) are a risk to the stability of the power electronics devices due to their negative impedance characteristics and also effects the voltage quality. To overcome these conditions, this paper proposes advanced artificial intelligence-based control of DC/DC converter to regulate the DC voltage in DC microgrid (MG) applications. At the start, model predictive control is implemented as an expert to control the studied converter to extract the dataset. The extracted dataset is used to train the proposed artificial neural network (ANN). The proposed controller is tested under various operating conditions while feeding the constant power loads. The proposed controller presents a superior transient response compared to conventional model predictive control (MPC). The experimental validation of the proposed scheme is carried out by implementing the controller on the FPGA ZYBO Z7-7020 board. The results are also compared with the conventional PI control. The proposed control technique has less computational burden and mitigates destabilizing effects caused by the CPLs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Collaborative Optimization Algorithm of Deep Learning and Compliant control in Online Trajectory Planning

Collaborative Optimization Algorithm of Deep Learning and Co...

引用

International Conference on Communication Systems and Network Technologies (CSNT)

作者： Junting Liao Chunjian Zhao Hui Xie School of Computer and Artificial Intelligence Xiangnan University Chenzhou China China Telecom Hunan Chenzhou Branch Chenzhou China

ISBN: (数字)9798331531935

ISBN: (纸本)9798331531942

With the rapid development of robotics and automation, online trajectory planning faces problems such as poor adaptability to dynamic environments and low computational efficiency. This study aims to propose a collaborative optimization algorithm that combines deep learning and compliant control to improve the efficiency and accuracy of online trajectory planning. First, CNN is used for feature extraction and a prediction model is established. Then a compliant control strategy is designed to deal with dynamic obstacles to ensure the flexibility and stability of the robot in trajectory planning. The trained CNN model is then used to generate real-time trajectory predictions. The robot motion is adjusted through a fuzzy logic controller to optimize the relative position of the trajectory and obstacles. The average obstacle avoidance success rate of the algorithm in dynamic environments reaches 97%. The collaborative optimization algorithm of deep learning and compliant control effectively improves the real-time and accuracy of online trajectory planning, providing a new solution for the application of intelligent robots in complex environments.

关键词： Deep learning Trajectory planning Heuristic algorithms Collaboration Predictive models Prediction algorithms Real-time systems Trajectory Convolutional neural networks Optimization

来源：评论

学校读者我要写书评

暂无评论

Proximal Policy Optimization Based Decentralized Networked Multi-Agent Reinforcement Learning

Proximal Policy Optimization Based Decentralized Networked M...

引用

International Conference on control and automation (ICCA)

作者： Jinyi Liu Fangyu Li Jingjing Wang Honggui Han Faculty of Information Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System Engineering Research Center of Digital Community Ministry of Education and Beijing Artificial Intelligence Institute Beijing University of Technology Beijing China

ISBN: (数字)9798350354409

ISBN: (纸本)9798350354416

Networked multi-agent reinforcement learning (NMARL) is widely used in multi-agent systems (MASs). However, most existing NMARL algorithms share the global state and reward, which hinders their scalability in large-scale MASs. To make NMARL applicable to large-scale MASs, we propose a proximal policy optimization (PPO) based fully decentralized NMARL. First, we design a fully decentralized multi-agent reinforcement learning (MARL) framework, formulated as a networked partially observable multi-agent markov decision process (N-POMDP). The networked MAS is represented by a graph, where each agent communicates with and shares reward only with neighbors. Second, we design a gate recurrent unit (GRU) based communication strategy to learn the temporal communication correlation. Each agent exchanges observation information and hidden state with its neighbors. Finally, we conduct experiments using the multi-agent particle environment (MPE) and compare our algorithm with common MARL algorithms. The experimental outcomes reveal the exceptional performance of our algorithm in terms of both cumulative return and convergence speed within the extensive MAS.

关键词： Correlation Navigation Scalability Markov decision processes Redundancy Reinforcement learning Logic gates

来源：评论

学校读者我要写书评

暂无评论

Using multi-task residual network to evaluate image aesthetic quality 5

Using multi-task residual network to evaluate image aestheti...

引用

5th ieee Advanced Information Technology, Electronic and automation control Conference, IAEAC 2021

作者： Tian, Xiuling Animation and Communication College of Qingdao Agricultural University Qingdao China

ISBN: (纸本)9781728180281

With the popularity of cameras, smartphones and other devices, visual content data such as images and videos are increasing day by day, and visual content data processing technology has become a research direction in the research fields of computer vision, computational photography and artificial intelligence. Compared with the semantic features of object recognition, the mystery of human aesthetics has not yet been quantified and scientifically explained. It is difficult to determine the feature points of image aesthetics, which increases the difficulty of image aesthetics quality evaluation. In order to better obtain the feature points of image aesthetics, this paper uses a multi-task residual network model to extract features of the image, and evaluate the aesthetic level of the image according to the extracted features. Using a special aesthetic evaluation data set to test and verify the accuracy of the evaluation model proposed in this paper is 84.68%, which can more accurately evaluate the aesthetic level of images. Therefore, the evaluation model proposed in this paper promotes the development of image aesthetic value evaluation technology. © 2021 ieee.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Salp Swarm Algorithm Based Fractional Order PID controller Design for Trajectory Tracking Simulation of an Underactuated Underwater Vehicle Model

Salp Swarm Algorithm Based Fractional Order PID Controller D...

引用

International symposium on Underwater Technology

作者： Gülten Yılmaz Serhat Yılmaz Electronics and Automation Department Kocaeli University Hereke Asım Kocabıyık Vocational School Kocaeli Turkey Department of Electronics and Communication Kocaeli University Engineering Faculty Kocaeli Turkey

ISBN: (数字)9798331534189

ISBN: (纸本)9798331534196

Autonomous Underwater Vehicles (AUVs) are used in many fields, primarily in scientific, commercial, and military areas. These vehicles require various guidance and control systems to autonomously perform tasks underwater. The modeling, system identification, and control of AUVs remain active areas of research and development. In this study, modelling and trajectory tracking simulation of a low-speed, modular, symmetrical and underactuated underwater vehicle with 4DOF are evaluated. The vehicle, named RedFin is developed in Kocaeli University Laboratories. Dynamical model parameters of the AUV's are estimated by computational Fluid Dynamics (CFD) and analytical calculation techniques and the AUV mathematical model is obtained. Model validation was carried out through static and dynamic pool tests. control algorithm has been developed, offering more precise solutions. For dynamic models described by fractional differential equations, a Fractional Order PID (FOPID) control algorithm was developed, offering more precise solutions. In the study, a PID controller and a FOPID controller were designed for the trajectory tracking control of the AUV. The Salp Swarm Algorithm (SSA), one of the heuristic optimization algorithms, is used to optimize the gain parameters of both controllers. The integral of the absolute value of the position error (IAE) is selected as the fitness function. “Band Limited White Noise” with 0.5 W power and 200 Hz frequency was added to the system model control inputs. During the orbit tracking, the RMS values of depth control errors are very small, such as 0.021 m for SSA-PID, 0.0032 m for GA-KDPID, and 0.00118 m for SSA-KDPID.

关键词： Power demand Trajectory tracking Heuristic algorithms computational modeling computational fluid dynamics control systems Mathematical models Robustness Trajectory Vehicle dynamics

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：