检索结果-内蒙古大学图书馆

Advances in multi-sensor fusion for body sensor networks: algorithms, architectures, and applications

INFORMATION fusion 2019年 45卷 150-152页

作者： Fortino, Giancarlo Gravina, Raffaele Ghasemzadeh, Hassan Liu, Peter X. Poon, Carmen C. Y. Wang, Zhelong Univ Calabria Commenda Di Rende Italy Washington State Univ Pullman WA 99164 USA Carleton Univ Ottawa ON Canada Chinese Univ Hong Kong Hong Kong Hong Kong Peoples R China Dalian Univ Technol Dalian Peoples R China

来源：评论

学校读者我要写书评

暂无评论

End-to-End Multimodal sensor Dataset Collection Framework for Autonomous Vehicles

引用

sensorS 2023年第15期23卷 6783-6783页

作者： Gu, Junyi Lind, Artjom Chhetri, Tek Raj Bellone, Mauro Sell, Raivo Tallinn Univ Technol Tallinn Dept Mech & Ind Engn EE-12616 Tallinn Estonia Univ Tartu Inst Comp Sci Intelligent Transportat Syst Lab EE-51009 Tartu Estonia Univ Innsbruck Semant Technol Inst STI Innsbruck Dept Comp Sci A-6020 Innsbruck Austria Ctr Artificial Intelligence AI Res Nepal Sundarharaincha 56604 Nepal Tallinn Univ Technol FinEst Ctr Smart Cities EE-19086 Tallinn Estonia

Autonomous driving vehicles rely on sensors for the robust perception of their surroundings. Such vehicles are equipped with multiple perceptive sensors with a high level of redundancy to ensure safety and reliability in any driving condition. However, multi-sensor, such as camera, LiDAR, and radar systems raise requirements related to sensor calibration and synchronization, which are the fundamental blocks of any autonomous system. On the other hand, sensor fusion and integration have become important aspects of autonomous driving research and directly determine the efficiency and accuracy of advanced functions such as object detection and path planning. Classical model-based estimation and data-driven models are two mainstream approaches to achieving such integration. Most recent research is shifting to the latter, showing high robustness in real-world applications but requiring large quantities of data to be collected, synchronized, and properly categorized. However, there are two major research gaps in existing works: (i) they lack fusion (and synchronization) of multi-sensors, camera, LiDAR and radar;and (ii) generic scalable, and user-friendly end-to-end implementation. To generalize the implementation of the multi-sensor perceptive system, we introduce an end-to-end generic sensor dataset collection framework that includes both hardware deploying solutions and sensor fusion algorithms. The framework prototype integrates a diverse set of sensors, such as camera, LiDAR, and radar. Furthermore, we present a universal toolbox to calibrate and synchronize three types of sensors based on their characteristics. The framework also includes the fusion algorithms, which utilize the merits of three sensors, namely, camera, LiDAR, and radar, and fuse their sensory information in a manner that is helpful for object detection and tracking research. The generality of this framework makes it applicable in any robotic or autonomous applications and suitable for quick and larg

关键词： multimodal sensors autonomous driving dataset collection framework sensor calibration and synchronization sensor fusion

来源：评论

学校读者我要写书评

暂无评论

Resource-Efficient sensor fusion via System-Wide Dynamic Gated Neural Networks

Resource-Efficient Sensor Fusion via System-Wide Dynamic Gat...

引用

IEEE Communications Society Conference on sensor and Ad Hoc Communications and Networks (SECON)

作者： C. Singhal Y. Wu F. Malandrino S. Ladron de Guevara Contreras M. Levorato C. F. Chiasserini INRIA France UC Irvine USA CNR-IEIIT Italy CNIT Italy Politecnico di Torino Italy Chalmers University of Technology Sweden

ISBN: (数字)9798331519186

ISBN: (纸本)9798331519193

Mobile systems will have to support multiple AI-based applications, each leveraging heterogeneous data sources through DNN architectures collaboratively executed within the network. To minimize the cost of the AI inference task subject to requirements on latency, quality, and - crucially - reliability of the inference process, it is vital to optimize (i) the set of sensors/data sources and (ii) the DNN architecture, (iii) the network nodes executing sections of the DNN, and (iv) the resources to use. To this end, we leverage dynamic gated neural networks with branches, and propose a novel algorithmic strategy called Quantile-constrained Inference (QIC), based upon quantile-Constrained policy optimization. QIC makes joint, high-quality, swift decisions on all the above aspects of the system, with the aim to minimize inference energy cost. We remark that this is the first contribution connecting gated dynamic DNNs with infrastructure-level decision making. We evaluate QIC using a dynamic gated DNN with stems and branches for optimal sensor fusion and inference, trained on the RADIATE dataset offering Radar, LiDAR, and Camera data, and real-world wireless measurements. Our results confirm that QIC matches the optimum and outperforms its alternatives by over 80%.

关键词： Wireless communication Wireless sensor networks Costs Soft sensors Heuristic algorithms Neural networks Logic gates sensor fusion Dynamic scheduling Time measurement

来源：评论

学校读者我要写书评

暂无评论

A MULTI-sensor APPROACH TO SURVEY COMPLEX architectures SUPPORTED BY MULTI-CAMERA PHOTOGRAMMETRY 29

A MULTI-SENSOR APPROACH TO SURVEY COMPLEX ARCHITECTURES SUPP...

引用

29th CIPA Symposium on Documenting, Understanding, Preserving Cultural Heritage - Humanities and Digital Technologies for Shaping the Future

作者： Perfetti, L. Spettu, F. Achille, C. Fassi, F. Navillod, C. Cerutti, C. Politecn Milan Dept Architecture Built Environm & Construct Engn Milan Italy Univ Brescia Dept Civil Engn Architecture Terr Environm & Math Brescia Italy cNarc Fraz Avout 6 Aosta Italy

Point clouds are nowadays a standard format of three-dimensional data. Various survey techniques are available, differing in characteristics, mode of use, and target applications, nevertheless producing point clouds that are similar, comparable, and combinable. According to recent literature, combining data from multiple sensors is an established practice for large surveying projects, particularly in Cultural Heritage, where the geometric complexity of buildings encourages the employment of many sensors. This paper presents a multi-sensor approach to surveying complex architectural spaces. The case study is the Cathedral of Aosta (AO) in Italy, which is interested in a conservation project that requires investigating the two bell towers of the cathedral. The survey aimed to produce a point cloud of 5 mm resolution and 1-2 cm accuracy compatible with the 1:50 scale of representation. The following survey techniques were employed: (i) laser scanning, (ii) terrestrial photogrammetry, (iii) UAV photogrammetry, and (iv) multi-camera fisheye photogrammetry. The distinctive feature of our approach lies in the multi-camera survey, conducted using a prototype composed of five fisheye cameras. The paper describes the data acquisition phase conducted with the different techniques, the mutual verification of the data performed by cross-sections check, the segmentation, and the final assembly of the various portions until a complete point cloud with homogeneous characteristics is obtained. All the data were then collected in a web platform (FlyVast) enriched with data and info made available to the professional to plan future interventions.

关键词： Cultural heritage Data fusion Point cloud Photogrammetry Laser scanning UAV Multicamera

来源：评论

学校读者我要写书评

暂无评论

Mitigation of Motion Artifacts in Pulse Oximetry through Redundant sensors 25

Mitigation of Motion Artifacts in Pulse Oximetry through Red...

引用

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

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

Orientation Estimation Through Magneto-Inertial sensor fusion: A Heuristic Approach for Suboptimal Parameters Tuning

引用

IEEE sensorS JOURNAL 2021年第3期21卷 3408-3419页

作者： Caruso, Marco Sabatini, Angelo Maria Knaflitz, Marco Gazzoni, Marco Della Croce, Ugo Cereatti, Andrea Politecn Torino Dept Elect & Telecommun I-10129 Turin Italy Scuola Super Sant Anna BioRobot Inst I-56127 Pisa Italy Scuola Super Sant Anna Dept Excellence & AI Robot I-56127 Pisa Italy Univ Sassari Dept Biomed Sci I-07100 Sassari Italy Univ Sassari Human Neuromuscoloskeletal Syst Interunivers Ctr Bioengn I-07100 Sassari Italy

Magneto-Inertial Measurement Units (MIMUs) are a valid alternative tool to optical stereophotogrammetry in human motion analysis. The orientation of a MIMU may be estimated by using sensor fusion algorithms. Such algorithms require input parameters that are usually set using a trial- and- error (or grid- search) approach to find the optimal values. However, using trial- and- error requires a known reference orientation, a circumstance rarely occurring in real-life applications. In this article, we present a way to suboptimally set input parameters, by exploiting the assumption that two MIMUs rigidly connected are expected to show no orientation difference during motion. This approach was validated by applying it to the popular complementary filter by Madgwick et al. and tested on 18 experimental conditions including three commercial products, three angular rates, and two dimensionality motion conditions. Two main findings were observed: i) the selection of the optimal parameter value strongly depends on the specific experimental conditions considered, ii) in 15 out of 18 conditions the errors obtained using the proposed approach and the trial- and- error were coincident, while in the other cases the maximumdiscrepancy amounted to 2.5 deg and less than 1.5 deg on average.

关键词： Magnetic separation sensor fusion Optical filters Magnetometers Accelerometers Filtering algorithms MIMU filter parameter wearable sensors gait analysis

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

Comparative Analysis and Implementation of Energy-Quality Scalable Multiply-Accumulate architectures for TinyML applications

Comparative Analysis and Implementation of Energy-Quality Sc...

引用

IEEE International Conference on Electronics, Circuits and Systems (ICECS)

作者： Kenn Danielle C. Pelayo Anastacia B. Alvarez Adelson N. Chua Fredrick Angelo R. Galapon Allen Jason A. Tan Lawrence Roman A. Quizon Electrical and Electronics Engineering Institute University of the Philippines - Diliman Quezon City Philippines

ISBN: (数字)9798350377200

ISBN: (纸本)9798350377217

Recent trends in machine learning algorithms have shifted from computer vision applications to near-sensor intelligent data analytics, such as wireless sensor nodes, which are considered as ultra-low power devices. This shift presents new challenges in energy consumption, throughput, and area budgets. This work implements and optimizes Bit fusion, a 2D-scalable divide-and-conquer (D&C) MAC architecture with precisionscaling from 8 to 2 bits, through bitwidth optimizations and by trading-off complexity overheads that are not aligned with the target MobileNet-v2 model. The designs are synthesized using 22-nm FD-SOI CMOS technology. It was determined that the throughput trade-offs of 1-level architectures in $\mathbf{2 b} \times 2 \ \text{b}$ mode for $\mathbf{1 7. 3 7 \%}$ less energy per operation and $\mathbf{2 6. 8 4 \%}$ more throughput per area would be preferred. Architecture variations were also explored wherein sum-together (ST) architectures outperformed sum-apart (SA) architectures with $\mathbf{2 1. 0 3 \%}$ reduction in energy per operation and $\mathbf{3 3. 3 2 \%}$ increase in throughput per area.

关键词： Wireless communication Semiconductor device modeling Wireless sensor networks Quantization (signal) Tiny machine learning Computer architecture Throughput CMOS technology Complexity theory Reliability

来源：评论

学校读者我要写书评

暂无评论

Multi-sensor data fusion framework for energy optimization in smart homes

引用

RENEWABLE & SUSTAINABLE ENERGY REVIEWS 2024年 193卷

作者： Dasappa, Nirupam Sannagowdara Kumar, G. Krishna Somu, Nivethitha Nanyang Technol Univ Energy Res Inst NTU ERIN Singapore 637141 Singapore LITE ON Technol Corp Singapore 556741 Singapore

Advancements in Internet of Energy (IoE) technologies drive the development of several energy efficient frameworks for better energy optimization, economic savings, safety, and security in smart homes. However, certain challenges such as real-time operational data for each micro -moment, proper application of data fusion techniques, and end -to -end computing and deployment architecture prevent the establishment of an effective energy -efficient framework to provide personalized energy -saving recommendations. This work presents energy management for smart spaces (EMSS), the proposed energy efficiency framework implemented in an edge -cloud computing platform that fuses data from heterogeneous data sources (environmental sensors, camera, plug data, etc.) at appropriate data fusion levels and process them to generate actionable, explainable, personalized, and persuasive recommendations at the right moment. The user response to the generated recommendations triggers the actuators to perform respective energy -saving actions and provide more personalized future recommendations. Further, SMARTHome - a data generation framework based on configurable scenario files and a set of software codes was proposed to generate synthetic data with respect to different building types and micromoments. The functionalities of the EMSS (device and user registration), user dashboard, analytics, and energy -saving recommendations were made accessible to the user through web and mobile applications. The validation analysis of the EMSS was performed by (i) comparative analysis of the machine learning and deep learning algorithms used by the decision engine to generate energy -saving recommendations and (ii) benchmarking of EMSS based on the taxonomy of data fusion -based energy efficiency frameworks for smart homes.

关键词： Energy optimization Data fusion Micro -moments Smart spaces Smart home Recommendations

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：