检索结果-内蒙古大学图书馆

International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC)

作者： S. Kolangiammal S. Prabha P. Sivalakshmi Narayanasamy P S. Kalaichelvi S. Sujatha Department of Electronics and Communication Engineering SRM Institute of Science and Technology Kattankulathur Chennai Tamil Nadu India Department of Computer Science Jawaharlal Nehru College for Women ( Arts & Science ) Ulundurpet Kallakuruchi Tamil Nadu India Department of Electronics and Communication Engineering R.M.K. College of Engineering and Technology Chennai Tamil Nadu India Department of Mathematics Vel Tech Rangarajan Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India PG and Research Department of Computer Science and Applications Vivekanandha College of Arts and Sciences for Women (Autonomous) Elayampalayam Tiruchengode Tamil Nadu India Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

ISBN: (数字)9798350376425

ISBN: (纸本)9798350376432

This research study explores how yard management methods can be transformed using Artificial Intelligence (AI) algorithms and Internet of Things (IoT) technology. Problems with manual procedures, lack of transparency, and inefficient use of resources are common with older yard management systems. To improve operational efficiency, cost-effectiveness, and flexibility, this research proposes a new way that uses IoT sensors to collect data in real-time and AI algorithms to make predictions and decisions. IoT sensor deployment, data processing infrastructure, and optimization approaches powered by AI make up the three main components of the integrated system. Data on the location, condition, and environmental factors of assets is continually gathered via the strategic placement of IoT sensors across yard facilities. AI algorithms that can predict outcomes, spot trends, and maximize resource use in ever-changing settings are subsequently employed to process and analyze this data. Yard throughput, inventory correctness, labor productivity, and overall operational performance were all improved in various industrial settings, as shown in case studies and empirical data, demonstrating the advantages of this integrated technique. For complicated decision-making, supplementary data sources like traffic patterns or weather predictions should be incorporated, and decentralized architectures for resilient and scalable IoT deployments should be investigated. To revolutionize supply chain operations, enhance efficiency, and encourage innovation in logistics methods.

关键词： Productivity Technological innovation Supply chains Weather forecasting Companies Transforms Prediction algorithms Internet of Things Artificial intelligence Optimization

来源：评论

学校读者我要写书评

暂无评论

Multi-sensor aided deep pose tracking

引用

IFAC-PapersOnLine 2022年第37期55卷 326-332页

作者： Hojun Lee Tyler Toner Dawn Tilbury Kira Barton Department of Robotics University of Michigan Ann Arbor MI 48109 USA Department of Mechanical Engineering University of Michigan Ann Arbor MI 48109 USA

Accurate pose estimation of nearby objects is critical for robots to dynamically interact with their surroundings. The complexity of this task has led researchers to explore deep learning methods. Nowadays, many works have solely focused on developing complicated neural network architectures to estimate pose from a simple monocular camera. However, most of these methods struggle with inherent limitations of a single sensor system, like occlusion, which are commonly encountered in mobile robotics applications. Online, occlusion-robust pose estimation is extremely important in such cases, as mobility of a robot introduces major uncertainty that complicates manipulation. Hence, we present Multi-sensor aided Deep Pose Tracking (MS-DPT), a framework for online object pose estimation to enable robust mobile manipulation. A Convolutional Neural Network (CNN) identifies key objects in an RGB-D image, from which object pose estimates are generated using a variant of the Iterative Closest Point (ICP) algorithm. An extended Kalman filter is used to fuse this pose estimate with onboard motion sensors to compensate for occlusion and robot motion during manipulation. This three stage method focuses on cohering different modalities and algorithms to improve the pose tracking stability and continuity in cases where the target object becomes heavily occluded by an obstacle or a mobile robot itself. The proposed approach accurately tracks textureless objects with high symmetries while operating at 10 FPS during experiments.

关键词： Object pose estimation Neural-network model Robot vision Data fusion Tracking

来源：评论

学校读者我要写书评

暂无评论

An Improved Algorithm for Universal sensor Registration 23

An Improved Algorithm for Universal Sensor Registration

引用

23rd International conference on Information fusion (fusion)

作者： Sigalov, Daniel Gal, Aharon Vigdor, Boaz Rafael Adv Def Syst Haifa Israel

ISBN: (纸本)9780578647098

We revise the ideas presented in a previous paper and propose an improved method for absolute sensor registration in target tracking applications. The approach uses targets of opportunity and, without making assumptions on their dynamical models, allows simultaneous calibration of multiple three- and two-dimensional sensors. The idea is representing the sensor angular misalignments as rotations of the actual position vectors by some rotation matrices. We formulate the registration task as a Maximum Likelihood (ML) estimation problem where the parameters to be estimated as the unknown rotation matrices as well as the unknown ground truth positions. Whereas for two-sensor scenarios only relative registration is possible, in practical cases with three or more sensors unambiguous absolute calibration may be achieved. The derived algorithm, as opposed to its previous version, is ensured to converge for three-dimensional scenarios. The derived algorithms are straightforward to implement and do not require tuning of parameters. The performance of the algorithms is tested in a numerical study.

关键词： sensor registration bias calibration sensor misalignment

来源：评论

学校读者我要写书评

暂无评论

3rd International conference on Wireless Communications and applications,ICWCA 2019

3rd International Conference on Wireless Communications and ...

引用

3rd International conference on Wireless Communications and applications,ICWCA 2019

ISBN: (纸本)9789811556968

The proceedings contain 28 papers. The special focus in this conference is on Wireless Communications and applications. The topics include: Application of the Several Common algorithms for Corner Detection to Sonar Image Registration;performance Analysis of Interleaver for Polar Coding in Bit-Interleaved Coded Modulation System;research on Technology of Wireless sensor Network;characteristics of Scholte Wave for Target Detection;visible and Infrared Image fusion Based on Online Convolutional Dictionary Learning with Sparse Matrix Computation;optimization of Maintenance Force Dispatch of Artillery Command Information System Based on Mission Success;application of an Improved Genetic Algorithm in Tourism Route Planning;classification of Medical Symptoms Based on Social sensors;research on Method and Technology of Emergency Logistics Intelligent System Engineering;research on Radio Base Station Distribution Technology in Transrapid System Communication;a Technical Survey on Approaches for Detecting Rogue Access Points;A Matching Algorithm Based on the fusion of SAD and Census;evaluation Method of Vehicle Technology Status Based on Big Data Analysis Technology;bay Number Recognition Based on Deep Convolutional Recurrent Neural Network;Deep Reinforcement Learning-Based Resource Allocation for Smart Grid in RAN Network Slice;identification of e-Nose Wine Varieties Based on Feature Extraction and Classification Modeling;comparison of Contrast Enhancement Methods for Underwater Target Sonar Images;region Contraction-Based Sparse Approach for Magnetocardiography Current Source Imaging;the Differential Properties of the Metric Projector Over a Class of Closed Convex Cones;a Novel Node Scheduling Algorithm for Solar-Powered Wireless sensor Networks;A USRP-Based Testbed of Multi-agent Reinforcement Learning for Dynamic Spectrum Anti-Jamming.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluation of a Wireless sensor Network for the Detection of Forest Fires

Evaluation of a Wireless Sensor Network for the Detection of...

引用

International conference on Edge Computing and applications (ICECAA)

作者： Anuradha. T A. Suganya R. Muthalagu M. Narender Jose Anand A. Department of Electrical and Electronics Engineering KCG College of Technology Chennai Department of IT Tagore Engineering College Rathinamangalam Kancheepuram District Tamilnadu Department of Electronics and Communication Engineering Agni College of Technology Chennai Tamil Nadu Department of CSE TKR College of Engineering & Technology Hyderabad India Department of Electronics and Communication Engineering KCG College of Technology Chennai Tamil Nadu India

The objective of the study is to assess the effectiveness and reliability of the WSN in detecting forest fires accurately and providing timely alerts to the authorities. Field experiments in a forested area are conducted with controlled fire scenarios to simulate real-world fire conditions. The WSN sensors were deployed, and data from the sensors were collected and analyzed. Proposed result demonstrate that the WSN is capable of detecting forest fires with high accuracy and providing timely alerts. The sensors effectively captured changes in environmental parameters associated with fire events. Through data fusion and intelligent algorithms, the WSN system accurately differentiated between normal environmental variations and fire-related anomalies. The wireless communication capability of the network enabled real-time transmission of data to a central monitoring station, allowing for immediate analysis and decision-making. Additionally, the WSN system demonstrated robustness and fault tolerance, as it could continue functioning even if individual sensors were damaged or lost. The evaluation of the WSN for forest fire detection showed promising results, highlighting its potential as an effective tool for early fire detection and prevention. The use of such a wireless sensor network can enhance the efficiency of fire management strategies, enabling timely responses, reducing response times, and minimizing the impact of forest fires on ecosystems and communities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Humanoid Robots that Move on Two Feet and Are Led by Vision Systems

Humanoid Robots that Move on Two Feet and Are Led by Vision ...

引用

Technological Advancements in Computational Sciences (ICTACS), International conference on

作者： Kamred Udham Singh Ankit Kumar Gaurav Kumar Teekam Singh Santosh Kumar Satya Prakash Yadav School of Computing Graphic Era Hill University Dehradun India Department of Computer Engineering & Applications GLA University Mathura UP India Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun Department of Management Jaipuria Institute of Management Jaipur India Department of Computer Science and Engineering GLBITM Greater Noida UP India

At the convergence of robotics and computer vision lies a crucial research field that focuses on the development of vision-guided walking for humanoid robots. The ability of humanoid robots to walk independently while simultaneously seeing and comprehending their surroundings via the use of visual inputs offers tremendous potential. Humanoid robots are developed to reproduce human-like qualities and skills. This abstract discusses current developments in the area of vision-guided walking for humanoid robots as well as the approaches that have been used. Through the use of computer vision methods in conjunction with walking algorithms, humanoid robots are given the capacity to traverse situations that are both complex and dynamic while exhibiting increased flexibility. For this, real-time sensing of the environment, object identification and avoidance of obstacles, as well as analysis of the terrain, are required in order to arrive at intelligent judgements while moving. Vision-guided walking not only makes robotic locomotion more secure and effective, but it also paves the way for a wide range of potential applications, including exploration, human-robot interaction, search and rescue, and many more. Visual sensing systems, sensor fusion procedures, gait generation methods, motion planning, and control strategies. These topics are discussed in relation to vision-guided walking. Different types of sensors, such as cameras, depth sensors, and LiDAR, are being investigated to see how they can best provide a holistic understanding of the surrounding environment. In addition, the abstract draws attention to the difficulties caused by sensor noise, occlusions, fluctuations in illumination, and the need for real-time processing. In places an emphasis on the role that methods of machine learning play in the improvement of vision-guided walking. The use of deep learning algorithms gives robots the ability to learn from data, hence enhancing their capacity to understand and r

关键词：

来源：评论

学校读者我要写书评

暂无评论

Autonomous Driving architectures, Perception and Data fusion: A Review 16

Autonomous Driving Architectures, Perception and Data Fusion...

引用

IEEE 16th International conference on Intelligent Computer Communication and Processing (ICCP)

作者： Velasco-Hernandez, Gustavo Yeong, De Jong Barry, John Walsh, Joseph Inst Technol Tralee Irish Software Res Ctr IMaR Res Ctr Lero Tralee Ireland

ISBN: (纸本)9781728190808

Over the last 10 years, huge advances have been made in the areas of sensor technologies and processing platforms, pushing forward developments in the field of autonomous vehicles, mostly represented by self-driving cars. However, the complexity of these systems has been also increased in terms of the hardware and software within them, especially for the perception stage in which the goal is to create a reliable representation of the vehicle and the world. In order to manage this complexity. several architectural models have been proposed as guidelines to design, develop, operate and deploy self-driving solutions for real applications. In this work, a review on autonomous driving architectures is presented, classifying them into technical or functional architectures depending on the domain of their definition. In addition, the perception stage of self-driving solutions is analysed as a component of the architectures, detailing into the sensing part and how data fusion is used to perform localisation, mapping and object detection. Finally, the paper is concluded with additional thoughts on the actual status and future trends in the field.

关键词： Architecture Autonomous Driving Autonomous Vehicles Data fusion Localisation Mapping Perception Self-Driving Car sensor fusion

来源：评论

学校读者我要写书评

暂无评论

Soft body sensor networks: architectures and applications

Soft body sensor networks: Architectures and Applications

引用

2020 IEEE International conference on Networking, Sensing and Control, ICNSC 2020

作者： Dong, Wentao Cheng, Xiao Yao, Daojin School of Electrical and Automation Engineering East China Jiaotong University Nanchang China Rail Transportation Technology Innovation Center East China Jiaotong University Nanchang China

ISBN: (纸本)9781728168531

Body sensor networks (BSNs) are designed to collect, process, and transmit the biological data from different parts of human body from wearable electronics with limited resources. Conventional BSN node is also designed and fabricated by the rigid sensors, printed circuit board (PCB), and integrated chip (IC), which are not compatible with the soft human skin. The concepts of soft body sensor networks (SBSNs) are given in the manuscript based on wireless sensor networks and flexible electronics. SBSN node is composed of soft sensors, flexible data modulation and process unit and flexible wireless communication unit, and all the components of SBSN node are designed to be bended and be compatible with soft skin surface by flexible electronic. The architecture of SBSNs are built with several layers: soft sensors, data collection, wireless communication, body could, data fusion algorithm and monitoring interface for further online healthy monitoring. Multisensory decision fusion algorithm has been presented with biometric and medical monitoring applications which is subsequently analyzed for medical diagnosis. Emotion recognitions are realized to predict healthy state based on SBSNs using the intelligent data fusion algorithms. © 2020 IEEE.

关键词： sensor nodes

来源：评论

学校读者我要写书评

暂无评论

DV-Hop localization Based on parameter correction and Improved zebra optimization algorithm

DV-Hop localization Based on parameter correction and Improv...

引用

International conference on Information, Communication and Networks (ICICN)

作者： Xun Wang Xiuwu Yu Yong Liu School of Electrical Engineering University of South China Heng Yang China College of Physics and Optoelectronic Engineering Shenzhen University Shen Zhen China

ISBN: (数字)9798350355802

ISBN: (纸本)9798350355819

The Internet of Things (IoT) makes extensive use of wireless sensor networks to monitor the physical environment. Since location data is the foundation of network applications in wireless sensor networks, precise node localization is essential to the operation of the entire system. An improved DV-Hop localization algorithm (IZDV) based on the fusion of Chaos, Flight, and Wandering strategies for zebra optimization is proposed in order to improve the localization accuracy of the widely used Distance Vector Hopping (DV-Hop) localization algorithm. The DV-Hop localization algorithm relies solely on network connectivity for localization, which results in a large error in the localization result. First, various communication radii are used to substitute the original integer hop information with fractional hop information. Second, the average hop distance information of the unknown nodes is corrected using the mean square weighted average error plus additional beacon node information. Lastly, the original least squares approach for node position estimation is replaced with the improved zebra optimization algorithm, which optimizes the classical zebra algorithm by combining chaotic, dynamic weighting and Levy. This accelerates the algorithm's convergence and strengthens its global and local search capabilities to keep the algorithm from prematurely entering the local optimum while still maintaining the algorithm's time complexity. The simulation results indicate that the average localization error of this paper's algorithm is reduced by about 60.51%, 22.65% and 19.32% in comparison with the classical DV-Hop algorithm, GDV-Hop algorithm and ISSADV-Hop algorithm in default network conditions, which verifies the better localization accuracy and stability of the proposed algorithm.

关键词： Location awareness Wireless communication Wireless sensor networks Accuracy Heuristic algorithms Vectors Stability analysis Internet of Things Time complexity Optimization

来源：评论

学校读者我要写书评

暂无评论

An Optimization of Deep sensor fusion Based on Generalized Intersection over Union 20th

An Optimization of Deep Sensor Fusion Based on Generalized I...

引用

20th International conference on algorithms and architectures for Parallel Processing (ICA3PP)

作者： Meng, Lianxiao Yang, Lin Tang, Gaigai Ren, Shuangyin Yang, Wu Harbin Engn Univ Informat Secur Res Ctr Harbin Peoples R China Chinese Acad Mil Sci Inst Syst Engn Natl Key Lab Sci & Technol Informat Syst Secur Beijing Peoples R China

ISBN: (纸本)9783030602390;9783030602383

3D object detection is a major topic in unmanned driving and robotics, which is suffering from the low accuracy recently. We found that the loss function of 3D object detection network is the main cause to the low accuracy. For this, we proposed an optimized realization of deep sensor fusion network model (DSFN) based on Generalized Intersection over Union (GIoU). In DSFN, the designed backbone network is used to fuse point cloud features and image features, making full use of heterogeneous sensor information. Specifically, we introduced the GIoU as the loss function of the backbone network. We evaluated our model on KITTI dataset which is resulted from a LIDAR-camera setup. Compared with similar models, our model shows a higher accuracy.

关键词： Deep sensor fusion Network (DSFN) 3D bounding box estimation Loss function Deep learning Camera and Lidar

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：