检索结果-内蒙古大学图书馆

IEEE Instrumentation and Measurement Technology Conference

作者： Claudio De Capua Stefano De Falco Rosario Morello Dept. of Computer Science and Electrical Technologies University “Mediterranea” of Reggio Calabria Reggio Calabria Italy Department of Electrical Engineering University of Naples “Federico II” Naples Italy

This paper proposes an innovative design of a Web-sensor network for environmental monitoring of the electromagnetic pollution. A remote control application allows to process acquired data and available information by an original data fusion procedure. The aim is to verify the compliance of the exposure levels to electromagnetic field with the limits established from law. The measurement system is a configurable network of wireless and smart Web-sensors distributed along an urban area. The implemented sensing units measure the electromagnetic field in high and low frequency ranges and, by General Packet Radio Service (GPRS) communication, acquired data are transmitted to WEB pages. By means of an original algorithm the whole area is divided in several local zones, where an equal number of sensors has the task to monitor specific zones. The clustering algorithm uses environmental and topographical information in order to configure the network and the monitoring map. So, the number and size of the zones are variable according to the desired resolution. A proposed Statistical Model allows to estimate the reliability curve over time of each sensor in order to get knowledge on its operating state. Starting from the available information, a remote workstation performs the data fusion procedure. Alarm and warning occurrences are singled out. A final report shows the zones which require greater attention so to plan suitable interventions on the area. Quality indexes provide indication on reliability and consistency of the result.

关键词： Remote monitoring Electromagnetic fields Pollution measurement Electromagnetic measurements Clustering algorithms Area measurement Wireless sensor networks Urban areas Frequency measurement Measurement units

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

arXiv

引用

arXiv 2024年

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

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%. Copyright © 2024, The Authors. All rights reserved.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Low complexity track initialization from a small set of non-invertible measurements

引用

EURASIP JOURNAL ON ADVANCES IN SIGNAL PROCESSING 2008年第unknown期000卷 1-15页

作者： Berger, Christian R. Daun, Martina Koch, Wolfgang Univ Connecticut Dept Elect & Comp Engn Storrs CT 06269 USA Fgan Ev Informat Proc & Pattern Recognit Fim Res I Sensor Network & Data Fus Grp D-53343 Wachtberg Germany

Target tracking from non-invertible measurement sets, for example, incomplete spherical coordinates measured by asynchronous sensors in a sensor network, is a task of data fusion present in a lot of applications. Difficulties in tracking using extended Kalman filters lead to unstable behavior, mainly caused by poor initialization. Instead of using high complexity numerical batch-estimators, we offer an analytical approach to initialize the filter from a minimum number of observations. This directly pertains to multi-hypothesis tracking (MHT), where in the presence of clutter and/or multiple targets (i) low complexity algorithms are desirable and (ii) using a small set of measurements avoids the combinatorial explosion. Our approach uses no numerical optimization, simply evaluating several equations to find the state estimates. This is possible since we avoid an over-determined setup by initializing only from the minimum necessary subset of measurements. Loss in accuracy is minimized by choosing the best subset using an optimality criterion and incorporating the leftover measurements afterwards. Additionally, we provide the possibility to estimate only sub-sets of parameters, and to reliably model the resulting added uncertainties by the covariance matrix. We compare two different implementations, differing in the approximation of the posterior: linearizing the measurement equation as in the extended Kalman filter (EKF) or employing the unscented transform ( UT). The approach will be studied in two practical examples: 3D track initialization using bearingsonly measurements or using slant-range and azimuth only. Copyright (c) 2008 Christian R. Berger et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Smart Environmental Architecture for Node Localization in a Wireless sensor Network

Smart Environmental Architecture for Node Localization in a ...

引用

International Conference on Intelligent Environments (IE)

作者： Salvador Jauregui-Ortiz Mario Siller Felix Ramos Edson Scalabrin Electrical Engineering and Computer Science Department Center of Research and Advanced Studies of the IPN Guadalajara Jalisco Mexico Graduate Program in Computer Science Pontifical Catholic University Parana Brazil Curitiba Parana Brazil

As far as we know, there is not a Node Localization Algorithm (NLA) that presents the same accuracy for all possible scenarios. We believe that a NLA should be able to "interpret" the dynamic information of the environment. In this sense, simple NLAs are rather focused and might perform well for specific scenarios and applications. Therefore, information fusion and context awareness seems to be an appropriate approach to address this issue. We propose the Smart Environmental Architecture for Node Localization (SEA-NL), which is composed by two main elements: (i) the Smart Beacon Nodes (SBNs) and (ii) the Logical Position of Nodes (LPN). In (i) the obstruction level indicator is estimated and can improve the estimation of distances among nodes. In (ii) environment information and a one to one relation between a node and an object are used and can also improve location estimation. Via simulation, our architecture was tested indoors and outdoors considering three localization algorithms: the Weighed Centroid Localization (WCL), the Centroid Localization, and the Triangular Centroid Localization. Finally, we present an accuracy comparison among NLAs used in isolated way, and by using the SBNs, the LPN, and the SEA-NL, where our architecture improves WCL up to ~30.88%.

关键词： Wireless sensor networks Accuracy Estimation Computer architecture Buildings Attenuation Monitoring

来源：评论

学校读者我要写书评

暂无评论

A Constraint Sufficient Statistics based Distributed Particle Filter for Bearing Only Tracking

A Constraint Sufficient Statistics based Distributed Particl...

引用

IEEE International Conference on Communications

作者： Arash Mohammadi Amir Asif Computer Science and Engineering York University

ISBN: (纸本)9781457720529

A constrained sufficient statistic based distributed implementation of the particle filter (CSS/DPF) is proposed for angle/bearing-only tracking (BOT) applications. The CSS/DPF runs localized particle filters at each sensor node and computes the global sufficient statistics (GSS) of the overall system as a function (summation) of the local sufficient statistics (LSS). The CSS/DPF is, therefore, a two stage procedure: (i) First, the means of LSS at local nodes are computed by running average consensus algorithms to derive the GSS, and;(ii) Each node then updates its localized particle filter using the modified GSS. Simulation results show that the CSS/DPF is near-optimal with its performance almost identical to that of the centralized particle filter. The number of average consensus runs in the CSS/DPF are reduced by an order of magnitude of the dimension of the state vector, thereby, reducing the communication complexity and bandwidth requirement of the distributed implementation.

关键词： Consensus Algorithm Data fusion Distributed Estimation Bearing-only Tracking Particle Filters Particle filters Aerospace ground services PRNP gene communication complexity LSS gene bandwidth requirement Sufficient Distribute dimensions

来源：评论

学校读者我要写书评

暂无评论

Multisensor fusion-based object detection and tracking using Active Shape Model

Multisensor fusion-based object detection and tracking using...

引用

International Conference on Digital Information Management (ICDIM)

作者： Dongeun Lee Sunghoon Choi Information Technology Research Center LG CNS Company Limited Seoul South Korea

This paper proposes automatic target detection and tracking system using Active Shape Model (ASM). Existing model based approaches for tracking are either manually initiated or need some form of user interaction to locate the object in images. Also the low light environmental conditions for surveillance systems make the tracking further harder. Hence the proposed system makes use of multiple sensors in the form of IR and visible cameras to enable tracking in degraded and low light environments. The proposed algorithm consists of the following stages: (i) input image evaluation for obtaining the conditions under which the camera is placed, (ii) an integrated motion detector and target tracker, (iii) active shape tracker (AST) for performing tracking, (iv) update of tracking results for real time tracking of targets. In the first stage the input image is evaluated for the lighting conditions. If the lighting conditions are poor then IR sensor is integrated with the CCD sensor for tracking applications. In the second stage the motion detector and region tracker are used to provide feedback to AST for automatic initialization of tracking. Tracking is carried out in the third stage using ASM. The final stage extracts the parameters and tracking information and applies it to the next frame if the tracking is carried out in real time. The major contribution this work lies in the integration for a completed system, which covers from image processing to tracking algorithms. The approach of combining multiple algorithms succeeds in overcoming fundamental limitations of tracking and at the same time realizes real time implementation. Experimental results show that the proposed algorithm can track people under various environment in real-time. The proposed system has potential uses in the area of surveillance, shape analysis, and model-based coding.

关键词： Shape Training Laplace equations Real time systems Computer vision Target tracking

来源：评论

学校读者我要写书评

暂无评论

An AI-Based Deep Learning with K-Mean Approach for Enhancing Altitude Estimation Accuracy in Unmanned Aerial Vehicles

引用

DRONES 2024年第12期8卷 718-718页

作者： Piyakawanich, Prot Phasukkit, Pattarapong King Mongkuts Inst Technol Ladkrabang Sch Engn Bangkok 10520 Thailand King Mongkut Chaokhun Thahan Hosp King Mongkuts Inst Technol Ladkrabang Bangkok 10520 Thailand

In the rapidly evolving domain of Unmanned Aerial Vehicles (UAVs), precise altitude estimation remains a significant challenge, particularly for lightweight UAVs. This research presents an innovative approach to enhance altitude estimation accuracy for UAVs weighing under 2 kg without cameras, utilizing advanced AI Deep Learning algorithms. The primary novelty of this study lies in its unique integration of unsupervised and supervised learning techniques. By synergistically combining K-Means Clustering with a multiple-input deep learning regression-based model (DL-KMA), we have achieved substantial improvements in altitude estimation accuracy. This methodology represents a significant advancement over conventional approaches in UAV technology. Our experimental design involved comprehensive field data collection across two distinct altitude environments, employing a high-precision Digital Laser Distance Meter as the reference standard (Class ii). This rigorous approach facilitated a thorough evaluation of our model's performance across varied terrains, ensuring robust and reliable results. The outcomes of our study are particularly noteworthy, with the model demonstrating remarkably low Mean Squared Error (MSE) values across all data clusters, ranging from 0.011 to 0.072. These results not only indicate significant improvements over traditional methods, but also establish a new benchmark in UAVs altitude estimation accuracy. A key innovation in our approach is the elimination of costly additional hardware such as Light Detection and Ranging (LiDAR), offering a cost-effective, software-based solution. This advancement has broad implications, enhancing the accessibility of advanced UAVs technology and expanding its potential applications across diverse sectors including precision agriculture, urban planning, and emergency response. This research represents a significant contribution to the integration of AI and UAVs technology, potentially unlocking new possibilities i

关键词： Unmanned Aerial Vehicles (UAVs) drones altitude estimation deep learning sensor fusion K-means clustering lightweight UAVs lightweight drones

来源：评论

学校读者我要写书评

暂无评论

Distributed multi-speaker voice activity detection for wireless acoustic sensor networks

arXiv

引用

arXiv 2017年

作者： Bahari, Mohamad Hasan Hamaidi, L. Khadidja Muma, Michael Plata-Chaves, Jorge Moonen, Marc Zoubir, Abdelhak M. Bertrand, Alexander Stadius Center for Dynamical Systems Signal Processing and Data Analytics KU Leuven Belgium Signal Processing Group Technische Universitat Darmstadt Darmstadt Germany

A distributed multi-speaker voice activity detection (DM-VAD) method for wireless acoustic sensor networks (WASNs) is proposed. DM-VAD is required in many signal processing applications, e.g. distributed speech enhancement based on multi-channel Wiener filtering, but is non-existent up to date. The proposed method neither requires a fusion center nor prior knowledge about the node positions, microphone array orientations or the number of observed sources. It consists of two steps: (i) distributed source-specific energy signal unmixing (ii) energy signal based voice ac-tivity detection. Existing computationally efficient methods to extract source-specific energy signals from the mixed observations, e.g., multi-plicative non-negative independent component analysis (MNICA) quickly loose performance with an increasing number of sources, and require a fusion center. To overcome these limitations, we introduce a distributed energy signal unmixing method based on a source-specific node cluster-ing method to locate the nodes around each source. To determine the number of sources that are observed in the WASN, a source enumeration method that uses a Lasso penalized Poisson generalized linear model is developed. Each identified cluster estimates the energy signal of a sin-gle (dominant) source by applying a two-component MNICA. The VAD problem is transformed into a clustering task, by extracting features from the energy signals and applying K-means type clustering algorithms. All steps of the proposed method are evaluated using numerical experiments. A VAD accuracy of > 85% is achieved for a challenging scenario where 20 nodes observe 7 sources in a simulated reverberant rectangular room. Copyright © 2017, The Authors. All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Streamlining River Flood Prevention with an Integrated AIoT Framework

Streamlining River Flood Prevention with an Integrated AIoT ...

引用

ACS/IEEE International Conference on Computer Systems and applications

作者： Zakaria Boulouard Mariya Ouaissa Mariyam Ouaissa Moez Krichen Mutiq Almutiq Mohammad Algarni LIM Hassan II University Casablanca Morocco Computer Systems Engineering Laboratory Cadi Ayyad University Marrakech Morocco Laboratory of Information Technologies Chouaib Doukkali University El Jadida Morocco Department of Information Technology Al-Baha University Al-Baha Saudi Arabia Department of Management Information Systems and Production Management College of Business and Economics Qassim University Buraidah Saudi Arabia Computer Science Department Al-Baha University Al-Baha Saudi Arabia

River floods stand among the natural disasters with far-reaching impacts, affecting human lives, the economy, infrastructure, agriculture, and more. Substantial investments by organizations are directed toward innovative strategies for flood prevention. The concept of Artificial Intelligence of Things (AIoT), a fusion of Artificial Intelligence and Internet of Things technologies, has showcased its prowess across various domains. In this paper, we introduce an AIoT framework where river flood sensors, located in every region, transmit their data using LoRaWAN technology to local broadcast centers in proximity. These broadcast centers subsequently forward the data via 4G/5G networks to a centralized cloud server. The server employs efficient AI algorithms to analyze the data and predict river conditions nationwide, contributing to proactive flood prevention. This approach has demonstrated effectiveness on multiple fronts. LoRaWAN-based communication between sensor nodes and broadcast centers offers reduced energy consumption and expanded coverage, while AI-driven data analysis enhances the accuracy of river flood predictions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Survey of Autonomous Driving from a Deep Learning Perspective

引用

ACM Computing Surveys 1000年

作者： Jingyuan Zhao Yuyan Wu Rui Deng Susu Xu Jinpeng Gao Andrew Burke University of California Davis Davis United States Stanford University Stanford United States Johns Hopkins University Baltimore United States

Autonomous driving represents a significant advancement in the transportation industry, enhancing vehicle intelligence, optimizing traffic management, and improving user experiences. Central to these innovations is deep learning, which enables systems to handle complex data and make informed decisions. Our survey explores critical applications of deep learning in autonomous driving, such as perception and detection, localization and mapping, and decision-making and control. We investigate specialized deep learning techniques, including convolutional neural networks, recurrent neural networks, self-attention transformers, and their variants, among others. These methods are applied within various learning paradigms—supervised, unsupervised and reinforcement learning—to suit the specific needs of autonomous driving. Our analysis evaluates the effectiveness, benefits, and limitations of these technologies, focusing on their integration with other intelligent algorithms to enhance system performance. Furthermore, we examine the architectures of autonomous systems, analyzing how knowledge and information are organized from modular, pipeline-based frameworks to comprehensive end-to-end models. By presenting an exhaustive overview of the progressing domain of autonomous driving and bridging various research areas, our survey aims to synthesize diverse research threads into a unified narrative. This effort not only aims to enhance our understanding but also pushes the boundaries of what is achievable in this interdisciplinary field.

关键词： autonomous driving deep learning perception trajectory planning decision-making reinforcement learning simulation sensor fusion end-to-end real-world algorithms Design Experimentation Performance Reliability

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：