检索结果-内蒙古大学图书馆

25th IEEE Conference on Signal Processing - algorithms, architectures, Arrangements, and applications (IEEE SPA)

作者： Alkhoury, Ludvik Choi, Jiwon Wang, Chizhong Mahoney, Sean Shender, Barry S. Hrebien, Leonid Kam, Moshe New Jersey Inst Technol Dept Elect & Comp Engn Newark Coll Engn Newark NJ 07102 USA Athena GTX Regulatory Affairs Dept Athena IA 50113 USA Naval Air Warfare Ctr Aircraft Div Human Syst Dept Patuxent River MD 20670 USA Drexel Univ Dept Elect & Comp Engn Philadelphia PA 19104 USA

ISBN: (数字)9788362065424

ISBN: (纸本)9788362065424

Photoplethysmography (PPG) signals are used in pulse oximetry to calculate peripheral capillary oxygen saturation (SpO(2)) levels. It is well known that the accuracy of the calculated SpO(2) is susceptible to motion noise. Using field data collected from human subjects during rest and while exhibiting medium to high-intensity physical exercises, we show how sensor redundancy can mitigate motion effects by employing two channels of red and infrared PPG signals. We demonstrate the advantage of redundancy using two SpO(2) calculation methods. These methods are widely used "Red over Infrared" (RoI) method and the Discrete Saturation Transform (DST) algorithm both, assisted by pre-filtering by a heart-rate tuned comb filter. The data were collected from individuals at rest and while exercising. SpO(2) levels are calculated for two channels, each using a red and an infrared PPG signal. We integrated the SpO(2) computed from the two channels with a Kalman filter (KF) and computed the SpO(2) mean absolute error (MAE) from each channel individually and after integrating the two channels. The SpO(2) MAEs of each one of the two channels separately were greater (and statistically significant) than the SpO(2) MAE obtained from the two channels integrated with a KF. We observed that when two channels of PPG (red and infrared) signals were available, then combining SpO(2) levels obtained from these two channels exhibited a smoother and more reliable estimate of the blood oxygen saturation level as compared the SpO(2) levels computed from each channel separately. The reason is that if the data for the two channels are collected at sufficient physical distance from one another, the motion artifacts affecting the two channels are uncorrelated. The KF is then able to use past measurements and modeling of the dynamics to attenuate the effect of the motion artifacts.

关键词： pulse oximetry peripheral capillary oxygen saturation (SpO(2)) electrocardiography (ECG) motion artifact motion resistant oximetry data fusion comb filter red over infrared Discrete Saturation Transform (DST) Kalman Filter wearable unit multiple photoplethysmography (PPG) channels

来源：评论

学校读者我要写书评

暂无评论

A Wearable sensor Network With Embedded Machine Learning for Real-Time Motion Analysis and Complex Posture Detection

引用

IEEE sensorS JOURNAL 2022年第8期22卷 7868-7876页

作者： Mascret, Q. Gagnon-Turcotte, G. Bielmann, M. Fall, C. L. Bouyer, L. J. Gosselin, B. Univ Laval Dept Elect & Comp Engn Quebec City PQ G1V 0A6 Canada Ctr Interdisciplinary Res Rehabil & Social Integr Quebec City PQ G1M 2S8 Canada

This work presents an embedded system driven by a wearable sensor network and machine learning to perform complex posture detection and high-precision human activity recognition (HAR) in real time. The presented prototype performs real-time HAR using raw data collected from three wireless wearable motion sensor nodes in parallel. The sensors communicate the measured inertial data to a Raspberry Pi 3 running a pre-trained classifier, which performs motion detection and classification in real-time. Our approach based on raw data and machine learning provides more efficiency and simplicity by decreasing the computation cost and the latency. Our detection and classification algorithm utilizes a new custom preconditioning method called Multi-Mapping Spherical Normalization (MMSN), in combination with a Support vector Machine with Radial Basis Function Kernel (RBF-SvM). This new preconditioning algorithm allows to sparse the raw inertial data to increase successful classification results without adding any computational burden. The presented approach achieves a motion classification accuracy of 98.28% for 12 body motions, while allowing for real-time prediction with low latency output (< 20 ms which is 50% less than some studies) for preconditioning and processing thanks to the new MMSN preconditioning method and the use of raw data. We tested our approach with 10 able-bodied subjects.

关键词： sensors Real-time systems Wearable sensors Machine learning Wireless sensor networks sensor phenomena and characterization Wireless communication Activity recognition embedded systems machine learning real-time systems sensor systems and applications sensor fusion signal processing algorithms supervised learning support vector machines wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Evaluating Lightweight GAN- and Adapted CTGAN-Based Data Synthesis for Predictive Maintenance in High-Radiation Environments 11

Evaluating Lightweight GAN- and Adapted CTGAN-Based Data Syn...

引用

11th IEEE/ACM International Conference on Big Data Computing, applications and Technologies, BDCAT 2024

作者： Al-Hasan, Tamim M. Zhai, Xiaojun Mcdonald-Maier, Klaus D. Bensaali, Faycal Cryer, Alice University of Essex Colchester School of Computer Science and Electrical Engineering EssexCO4 3SQ United Kingdom Qatar University Al Tarfa College of Engineering Department of Electrical Engineering Doha Qatar United Kingdom Atomic Energy Authority Culham Science Centre Abingdon Remote Applications in Challenging Environments OxfordshireOX14 3DB United Kingdom

ISBN: (纸本)9798350367300

This paper presents a comparative analysis of two developed Generative Adversarial Network (GAN) architectures for synthesizing sensor data in predictive maintenance (PdM) applications within high-radiation environments. The study ad-dresses the challenge of data scarcity in such settings, where experimental runs are constrained by the risk of device failure and economic considerations. The two GAN models: GAN-1 uses the Conditional Tabular GAN (CTGAN) architecture, and GAN-2 employs a custom network. These models generated synthetic datasets that were used to train and evaluate three machine learning algorithms: Random Forest, k-Nearest Neighbours, and eXtreme Gradient Boosting. The performance of these PdM models trained on synthetic data was compared against models trained on the original limited dataset. Results demonstrate that GAN-1 produced synthetic data closely mirroring the characteristics of the original dataset, enabling PdM models to achieve comparable performance levels. This study highlights the potential of GAN-based data synthesis in enhancing PdM model development for high-radiation environments, offering a viable solution to the challenges of limited data availability in such harsh settings. The findings have significant implications for improving operational reliability and safety in nuclear and other extreme environments where electronic systems are deployed. © 2024 IEEE.

关键词： Gamma rays

来源：评论

学校读者我要写书评

暂无评论

Data fusion in Wireless sensor Network: An Overview

Data Fusion in Wireless Sensor Network: An Overview

引用

CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies (CHILECON)

作者： Daniel Fernando Quintero Bernal Héctor Kaschel John Kern Departamento de Ingeniería Eléctrica Universidad de Santiago de Chile Santiago Chile

Due to the massive increase in data sets in contemporary applications and the difficulty of their processing in various approaches, data fusion remains a predominant way to obtain outstanding results, in terms of reliability, efficiency, and precision. The following document presents an overview of data fusion in wireless sensor networks; in which, various concepts to applications are considered to generate a base document for future research. This article gives a comprehensive and current view of models or architectures, techniques, methodologies or algorithms, and a current review of applications in different areas.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Precise indoor localization and mapping using mobile laser scanners: a scoping review

引用

Geomatica 2022年第4期75卷 165-177页

作者： Gharebaghi, Amin Mostafavi, Mir Abolfazl Larouche, Christian Esmaeili, Kamran Genon, Martin Center for Research in Geospatial Data and Intelligence Université Laval Quebec CityQCG1V 0A6 Canada Department of Civil & Mineral Engineering University of Toronto TorontoONM5S 1A4 Canada Department of Mining Metallurgy and Materials Engineering Université Laval Quebec CityQCG1V 0A6 Canada

Indoor localization and mapping are essential for a wide range of applications. The absence of GPS signals in indoor environments such as buildings, caves, and tunnels brings significant challenges for applications where accurate positioning (i.e., centimeter-level accuracy) is required. This paper presents a scoping review of the most recent studies on precise indoor localization and mapping using mobile technologies, specifically, mobile laser scanners. The scoping review allows for a comprehensive and structured review of the literature to maximize the capture of relevant information and provide reproducible results. We extracted and reported a range of information from the selected articles published since 2009, with the goal of identifying the most frequently used sensors and methods of fusing their collected observations. The results show that in the majority of studies, LiDAR is the core sensor and IMUs with 75% and odometers with 67% magnitude are the main sensors integrated with the LiDAR system to enhance the localization precision. In addition, the classical iterative closest point (ICP) algorithm with approxi-mately 60% frequency and the extended Kalman filter (EKF) method with over 40% frequency are the main algorithms used for the scan matching and fusion of different sensor data, respectively. This scoping review also revealed the lack of mapping-systems calibration as the main limitation in over 70% of the papers analyzed. © 2022 The Author(s).

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Multiple IMU fusion Algorithm Comparison for Sounding Rocket Attitude applications 35

Multiple IMU Fusion Algorithm Comparison for Sounding Rocket...

引用

35th International Technical Meeting of the Satellite Division of the Institute of Navigation, ION GNSS+ 2022

作者： Gómez, M.A. García, Laura Train Rico, Alberto Solera Gómez-Pérez, Ignacio Sánchez, Eusebio valero Universidad Politécnica de Madrid Spain Universidad Carlos III de Madrid Spain Instituto Nacional de Técnica Aeroespacial Spain

ISBN: (纸本)9781713871361

Micro-electro-mechanical (MEMS) technology is known to offer a wide variety of advantages for navigation and guidance purposes in terms of cost, size and weight. However, sensor accuracy limits its applications. The use of a Redundant Inertial Measurement Unit (RIMU) configuration allows combining inertial observations not only to obtain a better performances for attitude estimation, but also to be able to detect and isolate a sensor not properly working. The output signals of uncorrelated IMU sensors can be integrated using a data fusion algorithm (e.g Extended Kalman Filter, EKF). The aim of this study is to present the implementation of several filters for an array of consumer grade IMUs placed on a "skew-redundant" configuration in a sounding rocket vehicle. The filtering method allows designing an attitude estimator capable of improving the kinematic predictions from gyroscope measurement integration by applying a correction method from accelerometer and magnetometer data. Moreover, simulations are performed to analyze the resilience and fault detection, while laboratory tests check the performance of the two proposed architectures. With the aim of testing accuracy of the algorithms for the RIMU a software simulation tool and laboratory tests are presented. © 2022 35th International Technical Meeting of the Satellite Division of the Institute of Navigation, ION GNSS+ 2022. All rights reserved.

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

A Field-Programmable Gate Array-Based Adaptive Sleep Posture Analysis Accelerator for Real-Time Monitoring

引用

sensorS 2024年第22期24卷 7104页

作者： Sravanthi, Mangali Gunturi, Sravan Kumar Chinnaiah, Mangali Chinna Lam, Siew-Kei vani, G. Divya Basha, Mudasar Janardhan, Narambhatla Krishna, Dodde Hari Dubey, Sanjay Koneru Lakshmaiah Educ Fdn Dept Elect & Commun Engn Hyderabad 500075 Telangana India Malla Reddy Inst Engn & Technol Dept Elect & Commun Engn Hyderabad 500014 Telangana India BV Raju Inst Technol Dept Elect & Commun Engn Narsapur 502313 Telangana India Nanyang Technol Univ Coll Comp & Data Sci CCDS Singapore 639798 Singapore Chaitanya Bharati Inst Technol Dept Mech Engn Hyderabad 500075 Telangana India

This research presents a sleep posture monitoring system designed to assist the elderly and patient attendees. Monitoring sleep posture in real time is challenging, and this approach introduces hardware-based edge computation methods. Initially, we detected the postures using minimally optimized sensing modules and fusion techniques. This was achieved based on subject (human) data at standard and adaptive levels using posture-learning processing elements (PEs). Intermittent posture evaluation was performed with respect to static and adaptive PEs. The final stage was accomplished using the learned subject posture data versus the real-time posture data using posture classification. An FPGA-based Hierarchical Binary Classifier (HBC) algorithm was developed to learn and evaluate sleep posture in real time. The IoT and display devices were used to communicate the monitored posture to attendant/support services. Posture learning and analysis were developed using customized, reconfigurable vLSI architectures for sensor fusion, control, and communication modules in static and adaptive scenarios. The proposed algorithms were coded in verilog HDL, simulated, and synthesized using vIvADO 2017.3. A Zed Board-based field-programmable gate array (FPGA) Xilinx board was used for experimental validation.

关键词： sleep posture recognition adaptive posture analysis FPGA sensor fusion

来源：评论

学校读者我要写书评

暂无评论

Cotton Jassid Infestation Monitoring Using Sentinel-2 MSI, Landsat 9 TIRS, and PlanetScope Imagery with Machine Learning and Data fusion

Cotton Jassid Infestation Monitoring Using Sentinel-2 MSI, L...

引用

2024 International Conference on Computer and applications, ICCA 2024

作者： Bah, Souleymane Houegbe, M.D. Tanguy Mesreil Megnigbeto, Emmanuel Wilfried G. Houndji, vinasetan Ratheil Kouton, Bignon Nicanor Gouwakinnou, N. Gérard Ezin, C. Eugène Institut de Mathématiques et de Sciences Physiques Université d'Abomey-Calavi Dangbo Benin Laboratoire d'Ecologie de Botanique et de Biologie végétate BiPLAC Parakou Benin Institut de Recherche sur le Coton Division protection phytosanitaire Parakou Benin Institut de Formation et de Recherche en Informatique Université d'Abomey-Calavi Abomey-Calavi Benin

ISBN: (纸本)9798350367560

The excessive use of synthetic pesticides in the fields is the cause of numerous problems to human health and biodiversity. Knowing the location and severity of the emergence of pests enables targeted treatment, helping to reduce the use of pesticides. Given that traditional field inspection requires considerable effort with limited effectiveness, remote sensing combined with machine learning is an essential complement for large-scale, efficient monitoring. This study therefore aims to develop a machine learning-based solution for detecting cotton jassids from free satellite imagery data in Alibori, northern Benin. Multispectral and thermal infrared images respectively from the Sentinel-2 and Landsat 9 satellites were fused in the most correlated bands using signal processing algorithms Pseudo Wigner Distribution (PWD), Nonsubsampled Contourlet Transform (NSCT), and Discrete wavelet transform (DWT). Two configurations, in terms of data augmentation, were used. Areas infested by jassids were identified in merged and unmerged satellite images (Sentinel-2, Landsat 9, and PlanetScope, a commercial satellite) using Support vector Machine (SvM), Random Forest (RF), and CatBoost supervised machine learning algorithms. The green and Thermal Infrared sensor 1 (TIRS1) bands are the most correlated in configuration 1 and the blue and TIRSI bands in configuration 2 for respectively Sentinel-2 and Landsat 9. The DWT and NSCT signal processing algorithms produced the least Root Mean Square Deviation (RMSE) for image fusion (0.46 for DWT and 0.33 for NSCT). The best result in terms of detecting performance was obtained with the composite treatment of Landsat 9 images and the RF algorithm, with an overall accuracy of 88.23%, an Fl-score of 82%, and a Kappa index of 79.92% in configuration 1 and in configuration 2 for composite treatment of Sentinel-2 an overall accuracy of 92.36%, an Fl-score of 90.75% and a Kappa index of 86.36% with CatBoost algorithm. © 2024 IEEE.

关键词： Cotton

来源：评论

学校读者我要写书评

暂无评论

Robust sensor fusion algorithms for IoT

Robust Sensor Fusion Algorithms for IoT

引用

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

作者： Sakthitharan Subramanian Gandrakoti Lokeshwari S. Jagadeesan S. Leela v. G Pratheep Murugesan venkatasudhahar Department of Computational Intelligence Faculty of Engineering and Technology SRM Institute of Science and Technology School of Computing Chennai Tamil Nadu India Department of Cybersecurity Geethanjali College of Engineering and Technology Hyderabad Telangana India Department of Computer Science and Engineering Nandha Engineering college(Autonomous) Erode Tamil Nadu India Department of Computer Science and Business Systems Sri Eshwar College of Engineering Coimbatore Tamil Nadu India Department of Mechatronics Engineering Kongu Engineering College Perundurai Tamil Nadu India Department of Mechanical Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India

ISBN: (数字)9798331543624

ISBN: (纸本)9798331543631

sensor fusion is a critical component of the IoT ecosystem, as it combines a variety of data streams from multiple sensors to enhance the accuracy, reliability, and real-time decision-making. This research concentrates on the development of robust sensor fusion algorithms that are capable of effectively managing the heterogeneity, noise, and uncertainty that are inherent in data from Internet of Things (IoT) sensors. Our primary focus is on the ability of these algorithmic methodologies to manage data from multi-modal sensors. We investigate algorithms that are based on deep learning, Bayesian inference, and Kalman filtering. The proposed solutions aim to improve the performance of systems in sectors that are influenced by the Internet of Things (IoT), including healthcare, smart cities, industrial automation, and autonomous cars. This investigation investigates the scalability, energy efficiency, and computational burden of the Internet of Things (IoT) in the context of limited resources. Through simulations and practical applications, we demonstrate the enhancement of data precision, defect tolerance, and overall system dependability by these robust sensor fusion techniques.

关键词： Deep learning Uncertainty Smart cities sensor fusion Inference algorithms Bayes methods Internet of Things Reliability Kalman filters Streams

来源：评论

学校读者我要写书评

暂无评论

Flow-Based Programming for Real-Time Multi-sensor Data fusion 35

Flow-Based Programming for Real-Time Multi-Sensor Data Fusio...

引用

35th International Technical Meeting of the Satellite Division of the Institute of Navigation, ION GNSS+ 2022

作者： Topp, Thomas Hobiger, Thomas Institute of Navigation University of Stuttgart Germany

ISBN: (纸本)9781713871361

Flow-based programming (FBP) splits software functionality into modules which are triggered by data elements flowing from one module to the next. Thus, modules, which are not directly dependent on data from each other, can run independently and applications can be parallelized on a basic level what is a major improvement for the performance of multi-sensor data fusion algorithms. This paper discusses the flow-based software INSTINCT, which is a solid framework for implementing PNT algorithms and helps to reduce development times by making algorithms reusable. It provides an intuitive graphical user interface (GUI) that makes it usable in research and teaching. Inside the software, a variety of file formats and sensors for IMU und GNSS data processing are implemented. The realization of an INS/GNSS loosely-coupled Kalman filter flow is discussed and the results are compared to a flow representing a single point positioning (SPP) solution. Finally, a performance study of the algorithm on a 4th generation Intel CPU is presented, demonstrating that real-time capabilities can be ensured even on older systems. © 2022 by Institute of Navigation. All rights reserved.

关键词： Graphical user interfaces

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：