检索结果-内蒙古大学图书馆

arXiv 2025年

作者： San-Segundo, Rubén Angulo, Lucía Gil-Martín, Manuel Carramiñana, David Bernardos, Ana M. Speech Technology and Machine Learning Group Information Processing and Telecommunications Center Universidad Politécnica de Madrid ETSI Telecomunicación Av. Complutense 30 Madrid28040 Spain Simulation and Data Processing Group Information Processing and Telecommunications Center Universidad Politécnica de Madrid ETSI Telecomunicación Av. Complutense 30 Madrid28040 Spain

Objective: This paper describes the development of hybrid artificial intelligence strategies for drone navigation. Methods: The navigation module combines a deep learning model with a rule-based engine depending on the agent state. The deep learning model has been trained using reinforcement learning. The rule-based engine uses expert knowledge to deal with specific situations. The navigation module incorporates several strategies to explain the drone decision based on its observation space, and different mechanisms for including human decisions in the navigation process. Finally, this paper proposes an evaluation methodology based on defining several scenarios and analyzing the performance of the different strategies according to metrics adapted to each scenario. Results: Two main navigation problems have been studied. For the first scenario (reaching known targets), it has been possible to obtain a 90% task completion rate, reducing significantly the number of collisions thanks to the rule-based engine. For the second scenario, it has been possible to reduce 20% of the time required to locate all the targets using the reinforcement learning model. Conclusions: Reinforcement learning is a very good strategy to learn policies for drone navigation, but in critical situations, it is necessary to complement it with a rule-based module to increase task success rate. © 2025, CC BY-NC-ND.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Methods to Characterize the Change of the Respiratory Sinus Arrhythmia with Age in Sleep Apnea Patients

Evaluation of Methods to Characterize the Change of the Resp...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： John F Morales Margot Deviaene Javier Milagro Dries Testelmans Bertien Buyse Rik Willems Michele Orini Sabine Van Huffel Raquel Bailόn Carolina Varon ESAT - STADIUS Stadius Centre for Dynamical Systems Signal Processing and Data Analytics and with IMEC KU Leuven Leuven Belgium Biomedical Signal Interpretation and Computational Simulation (BSICoS) group University of Zaragoza Zaragoza Spain Department of Pneumology UZ Leuven Leuven Belgium Department of Cardiology UZ Leuven Leuven Belgium Barts Heart Centre St Bartholomews Hospital University College London London U.K

The High Frequency (HF) band of the power spectrum of the Heart Rate Variability (HRV) is widely accepted to contain information related to the respiration. However, it is known that this often results in misleading estimations of the strength of the Respiratory Sinus Arrhythmia (RSA). In this paper, different approaches to characterize the change of the RSA with age, combining HRV and respiratory signals, are studied. These approaches are the bandwidths in the power spectral density estimations, bivariate phase rectified signal averaging, information dynamics, a time-frequency representation, and a heart rate decomposition based on subspace projections. They were applied to a dataset of sleep apnea patients, specifically to periods without apneas and during NREM sleep. Each estimate reflected a different relationship between RSA and age, suggesting that they all capture the cardiorespiratory information in a different way. The comparison of the estimates indicates that the approaches based on the extraction of respiratory information from HRV provide a better characterization of the age-dependent degradation of the RSA.

关键词： Heart rate variability Sleep apnea Estimation Time-frequency analysis Entropy Bandwidth

来源：评论

学校读者我要写书评

暂无评论

A System to Enable Level-of-Detail Mobile Interaction with Augmented Media Objects

A System to Enable Level-of-Detail Mobile Interaction with A...

引用

International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing (IMIS)

作者： David Gómez Ana M. Bernardos José R. Casar Data Processing and Simulation Group Telecommunications School of the Technical University of Madrid Madrid Spain Telecommun. Sch. Tech. Univ. of Madrid Madrid Spain

This paper presents a service concept that enables the virtual augmentation of physical objects through a mobile device. Each object is linked to a tree of virtual resources (e.g. digital contents). Resources are organized in levels-of-detail that depend on the user's distance and orientation towards the object itself (i.e. user's attitude). The root node of the content tree hosts a set of items that can be retrieved from the most distant position to the object, each depth level in the tree is associated to the observer's attitude towards the object, thus the structure facilitates 'spatial browsing' of information. On this concept, we have implemented an indoor sensor-based Augmented Reality system that relies on a RFID positioning mat for positioning. To complete the attitude calculation and to adjust the service interface, we have handled typical indoor problems such as compass calibration and its bias management. The service has been instantiated to augment a TV set to spatially browse geography contents, the content tree is organized in continent, country and city levels and delivers synchronized resources to the mobile interface and to the TV, depending on the user's attitude and its previous interactions. Results of a limited user test show that the service concept is acceptable to the users and underline the need to get better control of resources representation. Although the chosen object for demonstration is a media one, the concept is applicable to any kind of object.

关键词： TV Mobile communication Media Calibration Mobile handsets Compass Visualization

来源：评论

学校读者我要写书评

暂无评论

A review on mobile applications for citizen emergency management

A review on mobile applications for citizen emergency manage...

引用

作者： Gómez, David Bernardos, Ana M. Portillo, Javier I. Tarrío, Paula Casar, José R. Data Processing and Simulation Group Dpt. Signals Systems and Radiocommunications School of Telecommunications Engineering Technical University of Madrid Av. Complutense 30 Madrid Spain

ISBN: (纸本)9783642380600

Mobile devices may be a powerful tool to help in case of emergency, not only for the person or people in danger but also for those ones giving assistance to them, professionally or not. In order to determine how mobile applications are currently being used in this area and the possibilities for innovation, this paper gathers the result of a review of about more than 250 applications commercially available. These applications have been featured to analyze their value proposition (e.g. main service goal, target user or pricing approach) and their operational features, with respect to their level of context-awareness and the discovery and notification of emergencies. Additionally, the paper proposes the functional design of a mobile application for Citizen Emergency Management, which takes advantage of the gap of the available offer. © Springer-Verlag Berlin Heidelberg 2013.

关键词： Mobile computing

来源：评论

学校读者我要写书评

暂无评论

Indoor augmented reality based on ultrasound localization systems

Indoor augmented reality based on ultrasound localization sy...

引用

作者： Gómez, David Tarrío, Paula Li, Juan Bernardos, Ana M. Casar, José R. Data Processing and Simulation Group Dpt. Signals Systems and Radiocommunications School of Telecommunications Engineering Technical University of Madrid Av. Complutense 30 Madrid Spain

ISBN: (纸本)9783642380600

Augmented reality applications are beginning to reach the general public due to the widespread use of smartphones and tablet devices. Most AR systems require the use of image processing techniques to superimpose the virtual information over the image of the real world. However, this may quickly consume the battery of the user's device. In this paper, we design and implement an AR system for indoor environments that relies on an external ultrasound localization system and on the inertial sensors embedded in the device to estimate the position and orientation of the user. The system was implemented on a tablet device, offers several functionalities, such as visualization of virtual objects and interaction with the virtual view, and aims at providing appropriate accuracy for a satisfactory user experience without the need of using costly vision-based techniques. © Springer-Verlag Berlin Heidelberg 2013.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Fusion of RSS and inertial measurements for calibration-free indoor pedestrian tracking

Fusion of RSS and inertial measurements for calibration-free...

引用

International Conference on Information Fusion

作者： Paula Tarrío Juan A. Besada José R. Casar Data Processing and Simulation Group ETSI Telecomunicación Universidad Politécnica de Madrid Madrid Spain

ISBN: (纸本)9781479902842

RSS-based localization techniques are widely used in indoor environments to estimate the position of people or objects. Recent work proposes to combine this localization technique with a dead reckoning strategy (using inertial sensors on the person or object to be tracked) to improve the accuracy of the localization results and, at the same time, track the position of the user continuously. The RSS-based subsystem of most of the proposed hybrid systems rely on a time consuming calibration phase to build a radio map of the environment, which is used to find a correspondence between the RSS measurements and the position. However, due to the changing environmental dynamics, the behavior of the channel may change after some time, thus, recalibration processes are necessary to maintain the positioning accuracy. In order to avoid these calibration and re-calibration needs, this paper proposes to use a nearly calibration-free RSS channel modeling localization approach and fuse it with the inertial measurements through a Kalman filter. The proposed strategy is tested through numerical simulation and experimental tests, showing accuracy gains with respect to other strategies. Furthermore, the proposed method has a low deployment cost, as very little calibration is needed prior to the operation.

关键词： Sensors Kalman filters Mobile nodes Acceleration Accuracy Calibration

来源：评论

学校读者我要写书评

暂无评论

26th Annual Computational Neuroscience Meeting (CNS*2017): Part 3 Antwerp, Belgium. 15-20 July 2017 Abstracts

引用

BMC NEUROSCIENCE 2017年第SUPPL 1期18卷 95-176页

作者： [Anonymous] Department of Neuroscience Yale University New Haven CT 06520 USA Department Physiology & Pharmacology SUNY Downstate Brooklyn NY 11203 USA NYU School of Engineering 6 MetroTech Center Brooklyn NY 11201 USA Departament de Matemàtica Aplicada Universitat Politècnica de Catalunya Barcelona 08028 Spain Institut de Neurobiologie de la Méditerrannée (INMED) INSERM UMR901 Aix-Marseille Univ Marseille France Center of Neural Science New York University New York NY USA Aix-Marseille Univ INSERM INS Inst Neurosci Syst Marseille France Laboratoire de Physique Théorique et Modélisation CNRS UMR 8089 Université de Cergy-Pontoise 95300 Cergy-Pontoise Cedex France Department of Mathematics and Computer Science ENSAT Abdelmalek Essaadi’s University Tangier Morocco Laboratory of Natural Computation Department of Information and Electrical Engineering and Applied Mathematics University of Salerno 84084 Fisciano SA Italy Department of Medicine University of Salerno 84083 Lancusi SA Italy Dipartimento di Fisica Università degli Studi Aldo Moro Bari and INFN Sezione Di Bari Italy Data Analysis Department Ghent University Ghent Belgium Coma Science Group University of Liège Liège Belgium Cruces Hospital and Ikerbasque Research Center Bilbao Spain BIOtech Department of Industrial Engineering University of Trento and IRCS-PAT FBK 38010 Trento Italy Department of Data Analysis Ghent University Ghent 9000 Belgium The Wellcome Trust Centre for Neuroimaging University College London London WC1N 3BG UK Department of Electronic Engineering NED University of Engineering and Technology Karachi Pakistan Blue Brain Project École Polytechnique Fédérale de Lausanne Lausanne Switzerland Departement of Mathematics Swansea University Swansea Wales UK Laboratory for Topology and Neuroscience at the Brain Mind Institute École polytechnique fédérale de Lausanne Lausanne Switzerland Institute of Mathematics University of Aberdeen Aberdeen Scotland UK Department of Integrativ

来源：评论

学校读者我要写书评

暂无评论

Impact of data-link on ground-based trajectory prediction accuracy for continuous descent arrivals

Impact of data-link on ground-based trajectory prediction ac...

引用

AIAA Modeling and simulation Technologies (MST) Conference

作者： Bronsvoort, Jesper McDonald, Greg Boucquey, Jean Avello, Carlos Garcia Vilaplana, Miguel Besada, Juan Alberto Airservices Australia Future Service Delivery GPO Box 1093 Melbourne VIC 3043 Australia EUROCONTROL Rue de la Fusée 96 Brussels 1130 Belgium EUROCONTROL Brussels 1130 Belgium Air Traffic Management Technologies Boeing Research and Technology Europe Avenida Sur Aeropuerto de Barajas 38 Edif. 4 Piso 4 Madrid 28042 Spain Universidad Politécnica de Madrid Data Processing and Simulation Group Despacho C-321 ETSI Telecomunicación Avenida Complutense 30 Madrid 28040 Spain

The purpose of this paper is to assess the improvements in trajectory prediction accuracy that result from enhancing the quality of the input data and supporting models of a groundbased Trajectory Predictor (TP). Focus is on the prediction of continuous descent trajectories where improvements to the quality of TP input data and models have been applied in a step by step manner in order to analyse the sensitivity of the prediction accuracy to each of the enhancements. As a first static enhancement aircraft intent within the Terminal Area is accurately modelled with use of the Aircraft Intent Description Language (AIDL) based on standard arrival and airline procedures. The dynamic enhancements are related to information likely to become available to ground-based systems through future flight planning and data-link standards like the Flight Information eXchange Model (FIXM) and Automatic Dependent Surveillance Contract (ADS-C) Extended Predicted Profile (EPP) respectively. This information includes descent speed schedule, aircraft mass, and geometric descent profile. The study used data from actual continuous descents performed by Future Air Navigation Systems (FANS) 1/A data-link equipped aircraft into Melbourne, Australia. While the current FANS-1/A standard does not directly provide information as descent speed schedule and mass as part of the down-linked trajectory information from the Flight Management System (FMS), these parameters were successfully inferred. Results indicated that descent speed schedule is most significant for temporal accuracy;the additional use of the aircraft mass mainly improved the prediction of the Top of Descent position. A technique was demonstrated to fully synchronise the geometric descent profile between air and ground predicted trajectories, while also improving on the prediction of the time dimension with respect to the original down-linked data from the FMS. While future data-link standards as EPP will provide key information as de

关键词： Air navigation

来源：评论

学校读者我要写书评

暂无评论

Advances in Intelligent and Soft Computing: Preface

Advances in Intelligent and Soft Computing

引用

Advances in Intelligent and Soft Computing 2012年 151 AISC卷 V-VI页

作者： Omatu, Sigeru De Paz Santana, Juan F. González, Sara Rodríguez Molina, Jose M. Bernardos, Ana M. Rodríguez, Juan M. Corchado Graduate School of Engineering Osaka Prefecture University Sakai Osaka Japan Department of Computer Science Faculty of Science University of Salamanca Salamanca Spain Applied Artificial Intelligence Group Universidad Carlos III de Madrid Colmenarejo Madrid Spain Data Processing and Simulation Group ETSI. Telecomunicación Universidad Politécnica de Madrid Madrid Spain

来源：评论

学校读者我要写书评

暂无评论

A low power routing algorithm for localization in IEEE 802.15.4 networks

A low power routing algorithm for localization in IEEE 802.1...

引用

作者： Bergesio, Luca Tarrío, Paula Bernardos, Ana M. Casar, José R. Data Processing and Simulation Group ETSI. Telecomunicación Universidad Politécnica de Madrid Madrid Spain

ISBN: (纸本)9783642199073

Many context-aware applications rely on the knowledge of the position of the user and the surrounding objects to provide advanced, personalized and real-time services. In wide-area deployments, a routing protocol is needed to collect the location information from distant nodes. In this paper, we propose a new source-initiated (on demand) routing protocol for location-aware applications in IEEE 802.15.4 wireless sensor networks. This protocol uses a low power MAC layer to maximize the lifetime of the network while maintaining the communication delay to a low value. Its performance is assessed through experimental tests that show a good trade-off between power consumption and time delay in the localization of a mobile device. © 2011 Springer-Verlag Berlin Heidelberg.

关键词： Wireless sensor networks

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：