检索结果-内蒙古大学图书馆

Empirical Evaluation of Video Surveillance based Crime and Anomaly Detection System using Hybrid Deep Learning Strategy

Empirical Evaluation of Video Surveillance based Crime and A...

引用

2023 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2023

作者： Kishore Kumar, A. Suganthi, P. Sakthi Saravanan, N. Joel, T. Shanmugam, Sathish Sri Ramakrishna Engineering College Department of Robotics and Automation Vattamalaipalayam Coimbatore India Sri Sai Ram Institute of Technology Department of CSE Chennai India S. A. Engineering College Department of EEE Chennai India R.M.K. Engineering College Department of ECE Chennai India Everi India Private Limited Chennai India

ISBN: (纸本)9798350319200

In the realm of urban safety and security, the development of efficient and accurate crime detection systems is of paramount importance. This study presents an empirical evaluation of a cutting-edge Video Surveillance-based Crime and Anomaly Detection System (CADS) that harnesses the power of Hybrid Deep Learning, integrating Artificial Neural Networks (ANN) and Recurrent Neural Networks (RNN). CADS has been meticulously designed to detect and analyze criminal activities and abnormal behaviors in real-time video surveillance data. It employs a hybrid approach that combines the capabilities of ANN for feature extraction and pattern recognition with the temporal analysis prowess of RNN for identifying sequential anomalies. Through rigorous empirical evaluation, CADS demonstrates remarkable performance in urban crime detection scenarios. The system excels in detecting both overt and subtle criminal activities, providing valuable insights for enhanced safety measures. Notable achievements include the recognition of suspicious behaviors such as crowd contraflow, prolonged parking lot scouting, and even direct assaults. This research delves into the intricate workings of CADS, elucidating its design and implementation in Python on a Windows platform. The proposed model represents a significant advancement in the field of crime and anomaly detection when compared to existing models. In rigorous comparative evaluations, the proposed model has demonstrated its superiority by consistently outclassing all existing models, achieving an impressive accuracy rate of 97.77%. By leveraging CADS, law enforcement agencies and urban security stakeholders can proactively respond to potential threats and anomalies, ultimately contributing to safer and more secure urban environments. © 2023 IEEE.

关键词： Artificial Neural Networks (ANN) Crime and Anomaly Detection System (CADS) Recurrent Neural Networks (RNN)

来源：评论

学校读者我要写书评

暂无评论

Autonomous Cost-Effective Robotic Exploration and Mapping for Disaster Reconnaissance 10

Autonomous Cost-Effective Robotic Exploration and Mapping fo...

引用

10th International Conference on Emerging Trends in engineering and Technology - Signal and Information Processing, ICETET-SIP-22 2022

作者： Seenu, N. Manohar, Lokeshwaran Stephen, Nikhit Mathew Ramanathan, Kuppan Chetty Ramya, M.M. Centre for Automation and Robotics Hindustan Institute of Technology and Science Chennai India Technische Universität Dortmund Department of Electrical Engineering and Information Technology Dortmund Germany École Centrale de Nantes Automatic Control and Robotics Department Nantes France

ISBN: (纸本)9781665467414

Natural calamities like earthquake and tsunami wreak havoc on life of so many people and the infrastructure, thus saving people who are trapped in the affected region has been a very difficult task for rescuers. This work aims to develop a system which will ease this task for the rescuers by using behavior based multiple robots that will explore, map, localize, path plan and navigate in an unknown environment. Various incarnations of pre-existing meta-heuristic algorithms are used to develop a cost-effective solution in this work. A random walk exploration is used to explore the entire environment effectively which reduces the computational cost and time. To reduce the complexities of mapping, binary occupancy grid is used for the map layout, which is not as efficient as compared to its counterparts but better, where time is the crucial factor. To identify the efficient path to navigate from source to destination positions in the environment, Particle Swarm Optimization algorithm is used in this paper. The last and the most crucial step of the system is navigation towards the destination. By integrating INS and GPS algorithms, the robot can get an almost perfect algorithm for navigation which is not prone to errors. Autonomous robot exploration, mapping and navigation are achieved by integrating the proposed algorithms to work simultaneously. The effectiveness of the proposed algorithms is analyzed through simulations in Webots virtual simulator environment, and the results are presented. Adapting the proposed exploration technique for swarm of robots is a prospective future research direction of this paper. © 2022 IEEE.

关键词： Legged locomotion Navigation Robot sensing systems Tsunami Sensors Particle swarm optimization Task analysis

来源：评论

学校读者我要写书评

暂无评论

A Conceptual Framework Towards the Realization of In situ Monitoring and Control of End-to-End Additive Manufacturing Process

引用

Micro and Nanosystems 2023年第2期15卷 92-101页

作者： Karadgi, Sachin Bhovi, Prabhakar M. Patil, Arun Y. Ramaiah, Keshavamurthy Venka-Teswarlu, K. Langdon, Terence G. Department of Automation & Robotics KLE Technological University Karnataka Hubballi580031 India School of Mechanical Engineering KLE Technological University Karnataka Hubballi580031 India B.V.B. College of Engineering and Technology Mechanical Engineering KLE Technological University Karnataka Hubballi580031 India Department of Mechanical Engineering Dayananda Sagar College of Engineering and Technology Karnataka Bengaluru560078 India Benga-luru Karnataka India Materials Research Group School of Engineering Sciences University of Southampton SouthamptonSO17 1BJ United Kingdom

Additive Manufacturing (AM) is considered one of the key technologies for realizing Industry 4.0. There are numerous stages in the end-to-end AM process, including component design, material design, build, and so on. An enormous amount of data is generated along the end-to-end AM process that can be acquired from the 3D printer in real-time, micro-characterization studies, and process plan details, among others. For instance, these data can be employed to predict the printed compo-nents’ quality and, at the same time, proactively adapt the 3D printer parameters to achieve better qual-ity. This end-to-end AM process can be mapped onto the digital thread. The current article elaborates on a conceptual framework to acquire the data from various sources associated with the end-to-end AM process and realize monitoring and control of the end-to-end AM process, leading to an intelligent AM process. © 2023, Bentham Science Publishers. All rights reserved.

关键词： 3D printing

来源：评论

学校读者我要写书评

暂无评论

Integrating Expert Guidance for Efficient Learning of Safe Overtaking in Autonomous Driving Using Deep Reinforcement Learning

arXiv

引用

arXiv 2023年

作者： Lu, Jinxiong Alcan, Gokhan Kyrki, Ville The Intelligent Robotics Group Department of Electrical Engineering and Automation Aalto University Espoo02150 Finland

Overtaking on two-lane roads is a great challenge for autonomous vehicles, as oncoming traffic appearing on the opposite lane may require the vehicle to change its decision and abort the overtaking. Deep reinforcement learning (DRL) has shown promise for difficult decision problems such as this, but it requires massive number of data, especially if the action space is continuous. This paper proposes to incorporate guidance from an expert system into DRL to increase its sample efficiency in the autonomous overtaking setting. The guidance system developed in this study is composed of constrained iterative LQR and PID controllers. The novelty lies in the incorporation of a fading guidance function, which gradually decreases the effect of the expert system, allowing the agent to initially learn an appropriate action swiftly and then improve beyond the performance of the expert system. This approach thus combines the strengths of traditional control engineering with the flexibility of learning systems, expanding the capabilities of the autonomous system. The proposed methodology for autonomous vehicle overtaking does not depend on a particular DRL algorithm and three state-of-the-art algorithms are used as baselines for evaluation. Simulation results show that incorporating expert system guidance improves state-of-the-art DRL algorithms greatly in both sample efficiency and driving safety. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Method for Predicting River Water Height Based on GRU-RNN Method

An Intelligent Method for Predicting River Water Height Base...

引用

2023 International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2023

作者： Kavitha, K. Singh, Kavita Shakya, Priyanka Parasar, Vatsal Kumar Kaushal, Deepak Kalra, Gourav Aditya Institute of Technology and Management Department of Information Technology Tekkali India Institute of Aeronautical Engineering Department of Civil Engineering Hyderabad Telangana Dundigal India University of Allahabad Department of Atmospheric and Ocean Science Studies India Robotics & Automation Noida India Graphic Era Deemed to Be University Department of Management Studies Uttarakhand Dehradun India Department of Mechanical Engineering Ambala Mullana India

ISBN: (纸本)9798350300857

It is vital in hydrology to be able to predict the magnitude of a flood, and this is often done using a number of conceptual and deterministic models. Such models may require highly specialized data that is not always easily accessible, such as soil moisture, soil type, evaporation rate, characteristic and slope of the land use, soil surface, and management issues in the catchment region, etc. It's crucial to be able to predict when and how much rain will fall. Additional constraints on the effectiveness of such models include the necessity to make simplifying assumptions and a required response time. Preprocessing, feature extraction, and model training are the first three steps of the proposed strategy. Preprocessing makes use of a time and frequency representation obtained by wavelet analysis. The recursive feature elimination approach was employed for the feature extraction. After using information gain to choose useful features, the models are trained with GRU-RNN. The proposed method outperforms the two most popular alternatives, GRU and RNN. © 2023 IEEE.

关键词： SWAT

来源：评论

学校读者我要写书评

暂无评论

On Rapid Parallel Tuning of Controllers of a Swarm of MAVs – Distribution Strategies of the Updated Gains

On Rapid Parallel Tuning of Controllers of a Swarm of MAVs ...

引用

International Conference on Control, automation, robotics and Vision (ICARCV)

作者： Dariusz HorIa Wojciech Giernacki Vít Krátký Petr Štibinger Tomáš Báča Martin Saska Faculty of Automation Robotics and Electrical Engineering Institute of Robotics and Machine Intelligence Poznan University of Technology Poznan Poland Department of Cybernetics Faculty of Electrical Engineering Czech Technical University in Prague Prague Czechia

ISBN: (数字)9798331518493

ISBN: (纸本)9798331518509

In this paper, we present a reliable, scalable, time deterministic, model-free procedure to tune swarms of Micro Aerial Vehicles (MAVs) using basic sensory data. Two approaches to taking advantage of parallel tuning are presented. First, the tuning with averaging of the results on the basis of performance indices reported from the swarm with identical gains to decrease the negative effect of the noise in the measurements. Second, the tuning with parallel testing of varying set of gains across the swarm to reduce the tuning time. The presented methods were evaluated both in simulation and real-world experiments. The achieved results show the ability of the proposed approach to improve the results of the tuning while decreasing the tuning time, ensuring at the same time a reliable tuning mechanism.

关键词： automation Distribution strategy Noise Gain measurement Robot sensing systems Data models Reliability Noise measurement Tuning Testing

来源：评论

学校读者我要写书评

暂无评论

Improved Contact Stability for Admittance Control of Industrial Robots with Inverse Model Compensation

Improved Contact Stability for Admittance Control of Industr...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Kangwagye Samuel Kevin Haninger Sami Haddadin Sehoon Oh Chair of Robotics and Systems Intelligence Munich Institute of Robotics and Machine Intelligence (MIRMI) Technical University Munich Munich Germany Department of Mechanical and Production Engineering Kyambogo University Kampala Uganda Department of Automation Fraunhofer IPK Berlin Germany Department of Robotics and Mechatronics Engineering DGIST Daegu Korea

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Industrial robots have increased payload, repeatability, and reach compared to collaborative robots, however, they have a fixed position controller and low intrinsic admittance. This makes realizing safe contact challenging due to large contact force overshoots in contact transitions and contact instability when the environment and robot dynamics are coupled. To improve safe contact on industrial robots, we propose an admittance controller with inverse model compensation, designed and implemented outside the position controller. By including both the inner loop and outer loop dynamics in its design, the proposed method achieves expanded admittance in terms of increasing both gain and cutoff frequency of the desired admittance. Results from theoretical analyses and experiments on a commercial industrial robot show that the proposed method improves rendering of the desired admittance while maintaining contact stability. We further validate this by conducting actual assembly tasks of plug insertion with fine positioning, switch insertion onto the rail, and colliding the robot end effector with random objects and surfaces, as seen at https://***/8XfkdHEdWDs.

关键词： Service robots Contacts Dynamics Cutoff frequency Observers Industrial robots Stability analysis Admittance Thermal stability Payloads

来源：评论

学校读者我要写书评

暂无评论

Video Stabilization using RAFT-based Optical Flow

Video Stabilization using RAFT-based Optical Flow

引用

International Conference on robotics and Artificial Intelligence (ICRAI)

作者： Rana Ashar Burhan Sadiq Hira Mohiuddin Saniya Ashraf Muhammad Imran Anayat Ullah Control Automotive and Robotics Lab National Centre of Robotics and Automation Rawalpindi Pakistan Department of Electronic Engineering Balochistan University of IT Engineering and Management Sciences Quetta Pakistan

Video Stabilization is the basic need for modern-day video capture. Many methods have been proposed throughout the years including 2D and 3D-based models as well as models that use optimization and deep neural networks. This work describes the implementation of cutting-edge Recurrent All-Pairs Field Transforms (RAFT) for optical flow estimation in video stabilization. we use a pipeline that accommodates the large motion. It then passes the results to the optical flow for better accuracy. After that, it satisfies the inaccuracies of the optical flow and makes it robust to occlusion, Parallax, and moving objects. Our approach yields better results (visually and quantitatively) compared to other optimization and deep learning-based visual stabilization techniques.

关键词： Industries Deep learning Visualization Pipelines Neural networks Estimation Transforms

来源：评论

学校读者我要写书评

暂无评论

Dynamic Neural Curiosity Enhances Learning Flexibility for Autonomous Goal Discovery

arXiv

引用

arXiv 2024年

作者： Houbre, Quentin Pieters, Roel Tampere University Tampere Finland Department of Automation Technology and Mechanical Engineering Cognitive Robotics Tampere University Tampere33720 Finland

The autonomous learning of new goals in robotics remains a complex issue to address. Here, we propose a model where curiosity influence learning flexibility. To do so, this paper proposes to root curiosity and attention together by taking inspiration from the Locus Coeruleus-Norepinephrine system along with various cognitive processes such as cognitive persistence and visual habituation. We apply our approach by experimenting with a simulated robotic arm on a set of objects with varying difficulty. The robot first discovers new goals via bottom-up attention through motor babbling with an inhibition of return mechanism, then engage to the learning of goals due to neural activity arising within the curiosity mechanism. The architecture is modelled with dynamic neural fields and the learning of goals such as pushing the objects in diverse directions is supported by the use of forward and inverse models implemented by multilayer perceptrons. The adoption of dynamic neural fields to model curiosity, habituation and persistence allows the robot to demonstrate various learning trajectories depending on the object. In addition, the approach exhibits interesting properties regarding the learning of similar goals as well as the continuous switch between exploration and exploitation. © 2024, CC BY-NC-SA.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

UAV Swarm Confrontation Based on Multi-agent Deep Reinforcement Learning 41

UAV Swarm Confrontation Based on Multi-agent Deep Reinforcem...

引用

第41届中国控制会议

作者： Zhi Wang Fan Liu Jing Guo Chen Hong Ming Chen Ershen Wang Yunbo Zhao Department of General Aviation Civil Aviation Management Institute of China School of Electronic and Information Engineering Shenyang Aerospace University College of Robotics Beijing Union University Department of Automation University of Science and Technology of China

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Multi-agent deep reinforcement learning(MADRL) has attracted a tremendous amount of interest in recent *** this paper,we introduce MADRL into the confrontation scene of Unmanned Aerial Vehicle(UAV) *** analysis the dynamic game process of UAV swarm confrontation,we build two non-cooperative game models based on MADRL *** using the multi-agent deep deterministic policy gradient(MADDPG) and the centralized training with decentralized execution method,we achieve the Nash equilibrium under 5 vs.5 UAV confrontation *** also introduce multi-agent soft actor critic(MASAC) method into the UAV swarm confrontation,simulation results indicate that the MASAC-based model outperforms the MADDPG-based model on exploring the UAV swarm combat environment,and more effectively converges to the Nash *** work will provide new insights into the confrontation of UAV swarm.

关键词： UAV Swarm Non-cooperative Game Multi-agent Deep Reinforcement Learning

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：