检索结果-内蒙古大学图书馆

conference on sensor Data fusion - Trends, Solutions, applications (SDF)

作者： Geeroms, Warre Allebosch, Gianni Kindt, Stijn Kadri, Loubna Veelaert, Peter Madhu, Nilesh Univ Ghent IMEC TELIN IPI Ghent Belgium Univ Ghent IMEC IDLab ELIS Ghent Belgium

ISBN: (数字)9781665486729

ISBN: (纸本)9781665486729

The field of speaker detection is relatively well researched. Multiple solutions focusing solely on audio or video, or a combination of both exist. On the audio side, a popular feature representation are mel-frequency cepstral coefficients, which are a sparse representation of the audio signal. On the video side, mostly pixel intensities are used, which is not sparse at all. In this paper, we take a look at a sparse video feature representation, namely facial landmarks. We first evaluate what selection of landmarks conveys the most information. Afterwards we propose several neural network architectures trained for audio-visual speaker detection. A comparison both on computational performance and accuracy is shown between the original architecture and architectures utilizing facial landmarks. For the evaluation, we introduce a new dataset to better understand the differences between the pixel and landmark features. The landmark features achieve similar accuracies for a forward oriented head position. There is a small reduction in performance for non-ideal head positions and in the case of occlusions. There is however a significant computational benefit, as there is a complexity reduction of orders two or three of magnitude due to the decreased feature dimensionality. When considering embedded devices, this is a big upside. This way we hope to provide insight and interest in a novel type of active speaker identification models.

关键词： Multimodal perception speaker localization audio-visual fusion facial landmarks Siamese neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-sensor Data fusion and Deep Machine Learning Models-Based Mental Stress Detection System 1

引用

2nd International conference on Advances in Data-driven Computing and Intelligent Systems, ADCIS 2023

作者： Gedam, Shruti Paul, Sanchita Jharkhand Mesra Ranchi India

ISBN: (数字)9789819995240

ISBN: (纸本)9789819995233

Stress is a concern in today’s paced society impacting individuals in various aspects of their lives including educational environments. It is crucial to identify and examine students’ stress levels as it offers insights into their well-being academic performance and excellence of life. The goal of this study is to develop a mental stress detection system that utilizes a combination of multiple sensor’s data fusion and deep machine learning (ML) models with the help of three physiological signals named electrocardiogram (ECG), galvanic skin response (GSR) and skin temperature (ST). Data is gathered from 200 students with the help of some stressors using a novel Internet of Medical Things (IoMT) device developed using low-cost sensors. Then the data went through pre-processed methods before being analyzed using some techniques of deep ML models like multi-layer perceptron neural networks (MLPNN), recurrent neural networks (RNN), and long short-term memory (LSTM) networks to identify stress. The results show that the RNN and LSTM models regularly outperform the MLPNN model in recognizing mental stress. These models adequately depicted the dynamic character of stress reactions while efficiently capturing temporal dependencies. The accuracy of the RNN and LSTM models was 92.34% and 93.20%, respectively. These models’ improved performance demonstrates their potential in stress detection applications. The combination of multi-sensor data fusion with deep ML algorithms allows for the precise detection of stress-related physiological changes. This has major consequences for student well-being and academic success since it enables personalized stress management tactics and interventions. Student’s mental health and academic experience can be improved by proactive efforts. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Advancing Football Game Analysis: Integrating Computer Vision, Deep Learning, and Hybrid Techniques for Enhanced Video Analytics

Advancing Football Game Analysis: Integrating Computer Visio...

引用

2024 OPJU International Technology conference on Smart Computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Benakesh, A.H. Rajeev, R. Hindustan Institute of Technology and Science Department of Computer Applications Chennai India

ISBN: (纸本)9798350373783

This research is about football analytics with the help of deep learning and computer vision, through which we can track the movement of the ball and all ball possessions a particular team has. This will assist teams in properly analyzing their game and identifying areas where they may be lacking. The fusion of YOLO which is one of the most popular model architectures and object detection algorithm and deep learning techniques like 3DCNN, CNN, Faster R-CNN, LSTM, BLSTM and computer vision has revolutionized the landscape of sports analytics, particularly in the domain of football (soccer). This abstract provides a glimpse into the exciting field of football analytics through the lens of advanced technologies. In recent years, the application of deep learning models to football data has enabled the extraction of invaluable insight from the game. This abstract serves as a gateway to the exciting world of football analytics, where deep learning and computer vision come together to revolutionize the way we perceive and engage with the beautiful game. The possibilities are limitless, as ongoing research continues to refine models and algorithms, promising even deeper insights and a richer experience for football enthusiasts worldwide. © 2024 IEEE.

关键词： Gateways (computer networks)

来源：评论

学校读者我要写书评

暂无评论

sensor fusion and Optimal Platform Trajectory Planning for Ground Target Localization with Terrain Uncertainty and Measurement Biases 25

Sensor Fusion and Optimal Platform Trajectory Planning for G...

引用

25th International conference of Information fusion (fusion)

作者： Mitra, Dipayan Tharmarasa, Ratnasingham McMaster Univ Dept Elect & Comp Engn Hamilton ON Canada

ISBN: (数字)9781737749721

ISBN: (纸本)9781665489416

A ground target can be localized using an airborne angle-only sensor. However, possible measurement bias causes a delay in error convergence. Adding measurements from a range-only sensor can improve localization by attaining faster convergence. Estimation accuracy can be improved further by optimizing the trajectories of the platforms containing the angle-only and range-only sensors. To ensure observability in 3-D localization, in most of the recent works, the height of the ground target from the sea level is assumed to be known perfectly. However, in most practical applications, target height is obtained from a Digital Terrain Elevation Database (DTED), having multiple levels of resolution. As a result, in addition to the bias uncertainty, the terrain uncertainty is required to be handled. In this work, Cramer Rao Lower Bound (CRLB) is derived for the localization problem considering the terrain and measurement bias uncertainties. A CRLB based optimization algorithm is proposed for optimal platform trajectory planning. We propose two localization approaches to handle the biases. The first approach involves bias compensation using a prior whereas the target and bias states are estimated jointly in the second approach. In both approaches, range sensor fusion is proposed to improve localization accuracy. The effectiveness of our algorithms is verified using Monte Carlo simulations.

关键词： ground target localization trajectory planning bias estimation angle-only sensor Cramer Rao lower bound terrain uncertainty sensor fusion

来源：评论

学校读者我要写书评

暂无评论

A Flexible sensor Based on PVC Gel for Detections of Robotic Grasping 17th

A Flexible Sensor Based on PVC Gel for Detections of Robotic...

引用

17th International conference on Intelligent Robotics and applications

作者： Zhong, Qiyun He, Qingsong Xie, Lin Shi, Ziyan Nanjing Univ Aeronaut & Astronaut Jiangsu Prov Key Lab Bion Funct Mat Coll Mech & Elect Engn Nanjing 210016 Peoples R China Nanjing Univ Aeronaut & Astronaut Key Lab Adv Technol Small & Medium Sized UAV Minist Ind & Informat Technol Unmanned Aerial Vehicles Res Inst Nanjing 210016 Peoples R China Nanjing Univ Aeronaut & Astronaut State Key Lab Mech & Control Aerosp Struct Nanjing 210016 Peoples R China

ISBN: (纸本)9789819607945;9789819607952

The rapid evolution of the smart industry has propelled significant advancements in both the realms of flexible electronics and robotics. The fusion of flexible sensing with intelligent robots bestows upon them the capability of tactile sensing, a critical enhancement that elevates their intelligence, digitalization, and practical applicability. We have triumphantly developed an innovative poly(vinyl chloride)/multi-walled carbon nanotubes polymer gel (PVC/MWCNTs polymer gel, PMPG), renowned for its exceptional elasticity and sensitivity. This high-performing sensing gel was crafted through a physical cross-linking method, utilizing poly(vinyl chloride) as the base matrix and multi-walled carbon nanotubes as the reinforcing fillers. Optimally, at a PVC:DBA = 1:5 (1 wt% of MWCNTs), PMPG demonstrates a remarkable response time of merely 172 ms, coupled with the capacity for sustained, continuous measurements. The material's stability is commendable, enduring up to 2,500 successive measurements without degradation. By integrating PMPG with machine learning algorithms, the soft gripper is endowed with enhanced tactile sensing and responsive feedback capabilities, heralding a new era for soft robotics across diverse settings.

关键词： Flexible sensor PMPG Tactile Sensing

来源：评论

学校读者我要写书评

暂无评论

Distributed Multi-sensor Control for Multi-Target Tracking 11

Distributed Multi-Sensor Control for Multi-Target Tracking

引用

11th International conference on Control, Automation and Information Sciences (ICCAIS)

作者： Blair, Aidan Gostar, Amirali Khodadadian Tennakoon, Ruwan Bab-Hadiashar, Alireza Li, Xiaodong Palmer, Jennifer Hoseinnezhad, Reza RMIT Univ Melbourne Vic Australia

ISBN: (数字)9781665452489

ISBN: (纸本)9781665452489

This paper proposes a new sensor control algorithm for multi-target tracking applications within distributed sensor networks. In multi-target tracking applications, most sensor control algorithms are designed for centralized sensor networks, where there is a central processing node that is computationally inefficient. This paper first provides a conceptual and mathematical overview of the multi-sensor multi-target tracking framework, using random finite set (RFS) filters and sensor fusion. We will also provide an overview of the existing sensor control methods. We then explore coordinate descent-based sensor control and introduce a fully distributed algorithm utilizing coordinate descent and an information-theoretic objective function. This method is tested on synthetic data and compared to alternative methods. The results show that the proposed method outperforms equivalent independent multi-sensor control methods.

关键词： distributed sensor network sensor control co-ordinate descent random finite sets multi-target tracking

来源：评论

学校读者我要写书评

暂无评论

Development of Real-time High-Definition 3D Mapping System with High-Accuracy Long-Range LiDAR sensor 16

Development of Real-time High-Definition 3D Mapping System w...

引用

16th International conference on Knowledge and Smart Technology, KST 2024

作者： Noppapetthongkam, Phumrawit Sutthisangiam, Nikorn King Mongkut's University of Technology North Bangkok Department of Computer and Information Science Thailand

ISBN: (纸本)9798350370737

The integration of three-dimensional 3D mapping is crucial for applications in autonomous vehicles and environmental simulations. This paper presents the development of a real-time mapping system using GPS-IMU RTK, coupled with the Velodyne UltraPuck LiDAR scanner, installed on vehicles. The system aims to generate 3D maps utilizing various devices, such as long-range LiDAR sensors, to collect distance data across a full 360-degree horizontal and vertical field of view. This results in a Point Cloud dataset, complemented by GPS-IMU data providing coordinates, motion direction, and orientation information. The processing software, developed in C#, orchestrates the fusion of Point Cloud and GPS-IMU data to create accurate 3D maps. Coordination of data in the nanosecond range ensures precise alignment between LiDAR sensor and GPS-IMU. The experiment demonstrates an achieved accuracy of 2.3 centimeters in the horizontal dimension and 2 centimeters in the vertical dimension. algorithms play a vital role in this process, requiring a profound understanding of electronics and mathematical expertise. The Point Cloud dataset is transformed into 3D maps, referencing the Universal Transverse Mercator coordinate system (UTM). This allows for future integration of additional Point Cloud datasets onto existing maps. The research focuses on the development of a real-time 3D mapping system, showcasing results in a web browser through WebGL, developed using JavaScript and C#. The processing algorithms involve mathematical calculations to produce 3D maps with customizable radii and viewing angles. Additionally, the Point Cloud data is stored in the LAS file format, and data from LiDAR sensor (PCAP) and vehicle motion (GPS-IMU) is recorded for further analysis and future improvements. © 2024 IEEE.

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

Geometric Reconstruction in Modern Remote Sensing Techniques and applications 4

Geometric Reconstruction in Modern Remote Sensing Techniques...

引用

4th International conference on Advancement in Electronics and Communication Engineering, AECE 2024

作者： Temara, Sheetal Ravindran, Sindhu Sreevidya, Nelli Krishnmoorthi, Sathya Devarasu, Neelamegam Thota, Krishna Kishore University of the Cumberlands Department of Computer and Information Sciences United States Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Chennai India Sreenidhi Institute of Science and Technology Dept. of It Telangana Hyderabad India Kongu Engineering College Dept. of Artificial Intelligence TN Erode India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Dept. of Ece TN Chennai India AP Guntur India

ISBN: (纸本)9798350364729

This paper introduces a novel method for geometric reconstruction in remote sensing, combining LiDAR, SAR, deep lea0rning algorithms, and multi-sensor fusion. The proposed approach achieves a geometric reconstruction accuracy of 0.92, significantly higher than conventional methods, which average around 0.78. The method also reduces processing time to 28 seconds from the typical 45 seconds. By integrating LiDAR and SAR data, our approach enhances spatial feature extraction and reconstruction precision, making it highly effective for applications like urban planning, disaster response, and environmental monitoring. With an Intersection over Union (IoU) score of 0.88, the method demonstrates superior performance compared to traditional techniques. © 2024 IEEE.

关键词： Urban planning

来源：评论

学校读者我要写书评

暂无评论

Research on Zero Power Communication Network Transmission Technology for fusion Perception Signals in Buried Environments

Research on Zero Power Communication Network Transmission Te...

引用

2024 International conference on Telecommunications and Power Electronics, TELEPE 2024

作者： Zhang, Xiaoyi Liu, Fuhua Zhen, Cheng Lu, Jianhua Ma, Yan Beijing Zhixin Microelectronics Technology Co. Ltd Beijing102299 China

ISBN: (纸本)9798350369212

By collecting and utilizing RF energy in the environment, zero power consumption technology breaks many limitations of traditional IoT terminals in terms of power supply, cost, and terminal volume. The access and communication of large-scale online monitoring devices have become the core issue for applications in underground environments without power supply. This paper conducts research on zero power communication network transmission technology, studies conflict avoidance algorithms for large-scale node access, and studies zero power communication lightweight protocols adapted to small data packet transmission. We design and develop an integrated communication perception device for IoT sensing, which integrates energy harvesting and communication. Based on RF energy harvesting, energy management circuits, MCU and sensor designs, and actual circuit test results, it is shown that under certain radio frequency energy or other energy conditions, the design technology in this paper can meet the requirements of IoT sensing and communication network applications in underground scenarios. © 2024 IEEE.

关键词： Radio frequency identification (RFID)

来源：评论

学校读者我要写书评

暂无评论

Data fusion for Intelligent Crowd Monitoring and Management Systems: A Survey

引用

IEEE ACCESS 2021年 9卷 47069-47083页

作者： Li, Xianzhi Yu, Qiao Alzahrani, Bander Barnawi, Ahmed Alhindi, Ahmed Alghazzawi, Daniyal Miao, Yiming Chinese Univ Hong Kong CUHK Dept Comp Sci & Engn Hong Kong Peoples R China Huazhong Univ Sci & Technol Sch Comp Sci & Technol Wuhan 430074 Peoples R China King Abdulaziz Univ Fac Comp & Informat Technol Jeddah Saudi Arabia Umm Al Qura Univ Dept Comp Sci Mecca Saudi Arabia

Intelligent Crowd Monitoring and Management Systems (ICMMSs) have become effective resources for strengthening safety and security along with enhancing early-warning capabilities to manage emergencies in crowded situations of smart cities and massive gatherings events. The main advantage of such systems is their ability to detect multiple features associated with the crowd gathering, as they enable multi-source sensors, multi-modal data, and powerful intelligent and analytical methods. Unlike traditional crowd monitoring systems, which make use of simplex forms of different data types, data and information associated with crowded scenarios can be collected, fused, processed and analyzed in large quantities for accurate global assessment and enhanced decision making processes in an ICMMS. Therefore, data fusion is introduced as an enabler to decrease data quantity, reduce data dimensions, and improve data quality. In this paper, we first survey the literature on data fusion application in crowd monitoring systems as we are developing a state-of-the-art ICMMS with data fusion as a major platform enabler. Next, we discuss some popular data fusion architectures and classifications from different perspectives. Based on this, we propose a multi-sensor, multi-modal, and dimensional ICMMS architecture based on data fusion. Then, we identify the data fusion processes in the ICMMS and classify them into sensor fusion, feature-based data fusion, and decision fusion. Relevant algorithms, applications and examples of three classes are elaborated. Finally, future data fusion research directions are discussed.

关键词： Data integration Monitoring sensor fusion sensors Cameras Intelligent sensors Temperature sensors Autonomous system crowd monitoring data fusion decision fusion sensor fusion

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：