检索结果-内蒙古大学图书馆

SAR Image Segmentation with Structure Tensor Based Hierarchical Student's t-Mixture Model

JOURNAL OF INTERNET TECHNOLOGY 2020年第3期21卷 615-628页

作者： Ge, Huilin Sung, Yahui Huang, Yueh-Min Lim, Se-Jung Jiangsu Univ Sci & Technol Sch Elect & Informat Zhenjiang Jiangsu Peoples R China Nanjing Univ Informat Sci & Technol Sch Comp & Software Nanjing Peoples R China Natl Cheng Kung Univ Dept Engn Sci Tainan Taiwan Natl Cheng Kung Univ Inst Educ Tainan Taiwan Honam Univ Liberal Arts & Convergence Studies Gwangju South Korea

Synthetic aperture radar (SAR) plays an important role in Satellite IoT, due to its remarkable capability of all-weather monitoring and information acquisition under complicated conditions. It is well-known that SAR image interpretation usually requires accurate segmentation. However, SAR image segmentation inevitably encounters speckle noise because of the unique imaging mechanism of SAR. In order to address the problem, we proposed SAR images segmentation method by combined a hierarchical Student's t-mixture model (HSMM) with an anisotropic mean template, which can divide the global SAR image segmentation into several sub-clustering-issues efficiently resolved using classical algorithm. With the aid of a non-linear structure tensor for image contents analysis, the adaptive template can explore more spatial correlations between pixels for the purpose of improving HSMM robustness and segmentation accuracy. Experiments results both synthetic and real SAR images demonstrate that our proposed HSMM is more robust to speckle noise and obtains more accurate segmented images.

关键词： sensor data processing Machine learning SAR image segmentation Satellite IoT

来源：评论

学校读者我要写书评

暂无评论

How much information is lost when sampling driving behavior data?Indicators to quantify the extent of information loss

引用

Journal of Intelligent and Connected Vehicles 2020年第1期3卷 17-29页

作者： Jun Liu Asad Khattak Lee Han Quan Yuan Department of Civil Construction and Environmental EngineeringThe University of AlabamaTuscaloosaAlabamaUSA Department of Civil and Environmental Engineering The University of TennesseeKnoxvilleTennesseeUSA State Key Laboratory of Automotive Safety and Energy School of Vehicle and MobilityTsinghua UniversityBeijingChina

Purpose–Individuals’driving behavior data are becoming available widely through Global Positioning System devices and on-board diagnostic *** incoming data can be sampled at rates ranging from one Hertz(or even lower)to hundreds of *** to capture substantial changes in vehicle movements over time by“undersampling”can cause loss of information and misinterpretations of the data,but“oversampling”can waste storage and processing *** purpose of this study is to empirically explore how micro-driving decisions to maintain speed,accelerate or decelerate,can be best captured,without substantial loss of ***/methodology/approach–This study creates a set of indicators to quantify the magnitude of information loss(MIL).Each indicator is calculated as a percentage to index the extent of information loss(EIL)in different *** overall information loss index named EIL is created to combine the MIL *** from a driving simulator study collected at 20 Hertz are analyzed(N=718,481 data points from 35,924 s of driving tests).The study quantiﬁes the relationship between information loss indicators and sampling ***–The results show that marginally more information is lost as data are sampled down from 20 to 0.5 Hz,but the relationship is not *** four indicators of MILs,the overall EIL is 3.85 per cent for 1-Hz sampling rate driving behavior *** sampling rates are higher than 2 Hz,all MILs are under 5 per cent for importation ***/value–This study contributes by developing a framework for quantifying the relationship between sampling rates,and information loss and depending on the objective of their study,researchers can choose the appropriate sampling rate necessary to get the right amount of accuracy.

关键词： Driver behaviours and assistance sensor data processing Information loss Instantaneous driving decisions Sampling rate Undersampling

来源：评论

学校读者我要写书评

暂无评论

ICCF: An Information-Centric Collaborative Fog Platform for Building Energy Management Systems

引用

IEEE ACCESS 2019年 7卷 40402-40415页

作者： Shen, Zhishu Zhang, Tiehua Jin, Jiong Yokota, Kenji Tagami, Atsushi Higashino, Teruo KDDI Res Inc Fujimino 3568502 Japan Swinburne Univ Technol Sch Software & Elect Engn Melbourne Vic 3122 Australia Osaka Univ Grad Sch Informat Sci & Technol Suita Osaka 5650871 Japan

In order to construct future large-scale Internet of Things (IoT) networks, Fog computing is a promising paradigm that brings big data processing capability, storage, and control from a remote cloud closer to the end users/things. However, the majority of prior studies have focused on the data connection to realize a vertical Cloud-Fog-devices' continuum. In this paper, we propose an information-centric collaborative Fog (ICCF) platform, empowered by a novel horizontal Fog-to-Fog layer. Specifically, the ICCF enhances sensor data processing performance by enabling horizontal data transfer in the Fog layer through connectionless name-based Fog-to-Fog data transmission. It utilizes the Fog node's distributed data processing power to achieve a satisfactory data processing performance, while communication with the Cloud is only required to report detected anomalies. Moreover, because the connectionless name-based scheme significantly reduces data connection overhead, this guarantees real-time communication and the ability of processing large-scale IoT data. Building energy management system (BEMS) for detecting abnormal sensor data is adopted as a case study to illustrate our design philosophy and, more importantly, to validate the advantages of the proposed ICCF by conducting a variety of experiments based on the sensor data collected from a real-world indoor environment.

关键词： Building energy management system fog computing information-centric networking Internet of Things machine learning sensor data processing

来源：评论

学校读者我要写书评

暂无评论

A Statistical View on Synthetic Aperture Imaging for Occlusion Removal

引用

IEEE sensorS JOURNAL 2019年第20期19卷 9374-9383页

作者： Kurmi, Indrajit Schedl, David C. Bimber, Oliver Johannes Kepler Univ Linz Inst Comp Graph A-4040 Linz Austria

Synthetic apertures find applications in many fields, such as radar, radio telescopes, microscopy, sonar, ultrasound, LiDAR, and optical imaging. They approximate the signal of a single hypothetical wide aperture sensor with either an array of static small aperture sensors or a single moving small aperture sensor. Common sense in synthetic aperture sampling is that a dense sampling pattern within a wide aperture is required to reconstruct a clear signal. In this paper, we show that there exist practical limits to both, the synthetic aperture size and the number of samples for the application of occlusion removal. This leads to an understanding on how to design synthetic aperture sampling patterns and sensors in a most optimal and practically efficient way. We apply our findings to airborne optical sectioning, which uses camera drones and synthetic aperture imaging to computationally remove occluding vegetation or trees for inspecting ground surfaces.

关键词： sensor data processing synthetic aperture imaging airborne optical sectioning light fields

来源：评论

学校读者我要写书评

暂无评论

Assessment of Occupancy Estimators for Smart Buildings 10

Assessment of Occupancy Estimators for Smart Buildings

引用

10th IEEE International Conference on Intelligent data Acquisition and Advanced Computing Systems - Technology and Applications (IDAACS)

作者： Chitu, Claudia Stamatescu, Grigore Stamatescu, Iulia Sgarciu, Valentin Univ Politehn Bucuresti Dept Automat Control & Ind Informat Bucharest Romania Graz Univ Technol Inst Tech Informat Graz Austria

ISBN: (纸本)9781728140698

Dense distributed sensor systems deployed to monitor and control the built environment open up wide application areas for improving the quality of life through smart spaces. By implementing these systems in residential or commercial buildings, more efficient, pervasive, real-time and finally more robust decision support is achieved. As one of the key tasks, high accuracy occupancy detection and estimation within buildings offers the potential to improve HVAC utilization while reducing maintenance needs, enhancing energy savings for building operators as well as a more suitable thermal comfort for occupants. In this context the main contribution of the paper consists of an assessment of supervised machine learning techniques namely random forests and extreme machine learning neural networks for indirect occupancy profile estimation. The methods are applied on a benchmarking dataset of indoor carbon dioxide measurements and ventilation damper positions as collected from the building information system. The impact of data preprocessing through filtering and smoothing as well as hardware constraints and cloud distributed processing for algorithm deployment are also discussed. We highlight key challenges and discuss how the learned models can be integrated for online operation to improve energy efficiency.

关键词： statistical learning occupancy estimation sensor data processing smart buildings

来源：评论

学校读者我要写书评

暂无评论

Energy-efficient Activation/Inactivation Strategy for Long-term IoT Network Operation

Energy-efficient Activation/Inactivation Strategy for Long-t...

引用

IEEE Conference on SmartWorld, Ubiquitous Intelligence and Computing, Advanced and Trusted Computing, Scalable Computing and Communications, Cloud and Big data Computing, Internet of People and Smart City Innovation

作者： Shen, Zhishu Yokota, Kenji Tagami, Atsushi Higashino, Teruo KDDI Res Inc Fujimino Japan Osaka Univ Grad Sch Informat Sci & Technol Suita Osaka Japan

ISBN: (纸本)9781728140346

A critical concern for IoT (Internet of Things) networks is how to operate a large number of sensors in an energy-efficient manner. Energy consumption caused by operating these sensors cannot be overlooked, especially for long-term IoT network operation. Inactivating some of the unneeded sensors during the operation is one of the feasible solutions. Recent studies have mainly focused on selecting the unneeded sensors in a duty-cycled manner based on the sensor's geographic location or the sensor's communication status. These studies involve obtaining some of the user's private information, moreover, anomaly detection performance, a significant criterion regarding IoT network operation performance has not been considered. In this paper, we develop a novel activation/inactivation strategy for long-term IoT network operation. In this strategy, a machine learning model is adopted to adaptively select the unneeded sensors to be inactivated during network operation. Moreover, to maintain high sensor data processing performance during long-term operation, by only using the basic sensor data (e.g., temperature and humidity), our proposal selects the unneeded sensor candidates which are periodically updated. Numerical experiments conducted in two IoT network environments over seven-month operation verify the effectiveness of our proposal.

关键词： IoT network sensor data processing anomaly detection machine learning

来源：评论

学校读者我要写书评

暂无评论

Where to begin climbing? Computing start-of-stair position for robotic platforms 11

Where to begin climbing? Computing start-of-stair position f...

引用

11th International Conference on Computational Intelligence and Communication Networks (CICN)

作者： Sharma, Bishwajit Syed, Imran A. Ctr Artificial Intelligence & Robot Bangalore 560093 Karnataka India

ISBN: (纸本)9781538684399

Multi-floor autonomous robot navigation involves climbing staircases and exploring all the floors in a building using the onboard sensors. While some works investigate the method of exploring indoor floors, other works address the issues in staircase navigation. The proposed work bridges these tasks by allowing a tracked ground robot exploring a floor to find the position where it should begin its climb on the identified staircase. Ideally, such a position is before the first step on the mid line of a staircase, with sufficient space on the floor for the robot to fit in. Various geometric considerations, statistical measurements and randomized algorithms are combined to compute the start-of-stair position from point cloud data obtained from an RGBD camera. An efficient slope finding method is developed to detect the slope containing the staircase. The stair-center on the plane is then computed. The stair bottom, and eventually the start-of-stair position is computed based on the intersection of stair and ground planes. Results are presented on single RGBD frames as well as accumulated point cloud obtained from a mapping algorithm. The scope of error in the initial detection is also analyzed and sample results indicate that the point cloud processing can overcome spatial errors in the initial detection over a considerable margin.

关键词： computational intelligence point-cloud RGBD camera sensor data processing plane-fitting real-time stair detection stair climbing robotics machine vision intelligence autonomous navigation

来源：评论

学校读者我要写书评

暂无评论

A framework for learning and embedding multi-sensor forecasting models into a decision support system: A case study of methane concentration in coal mines

引用

INFORMATION SCIENCES 2018年 451卷 112-133页

作者： Slezak, Dominik Grzegorowski, Marek Janusz, Andrzej Kozielski, Michal Sinh Hoa Nguyen Sikora, Marek Stawicki, Sebastian Wrobel, Lukasz Univ Warsaw Inst Informat Ul Banacha 2 PL-02097 Warsaw Poland Silesian Tech Univ Inst Informat Ul Akad 16 PL-44100 Gliwice Poland Polish Japanese Acad Informat Technol Ul Koszykowa 86 PL-02008 Warsaw Poland Inst Innovat Technol EMAG Ul Leopolda 31 PL-40189 Katowice Poland

We introduce a new approach for learning forecasting models over large multi-sensor data sets, including the steps of sliding-window-based feature extraction and rough-set-inspired feature subset ensemble selection. We show how to integrate this approach with the major data-processing-related components of DISESOR - a decision support system which is a coherent and complete framework for exploring streams of sensor readings registered in underground coal mines. As a case study, we report our experiments related to the task of methane concentration forecasting. The contributions in this paper refer to both the analysis how the nature of sensor readings influenced the architecture of the developed system and the empirical proof that the designed methods for data processing and analytics turned out to be efficient in practice. 2018 Elsevier Inc. All rights reserved.

关键词： sensor data processing Methane concentration forecasting Sliding-window feature engineering Feature subset ensemble selection

来源：评论

学校读者我要写书评

暂无评论

Multitarget Localization With Inaccurate sensor Locations via Variational EM Algorithm

IEEE SENSORS LETTERS

引用

IEEE sensorS LETTERS 2019年第2期3卷

作者： Qian, Peng Guo, Yan Li, Ning Army Engn Univ Coll Commun Engn Nanjing 210007 Peoples R China

In wireless sensor networks, target localization has been the focus of considerable research effort, and the compressive sensing (CS) based localization method is of particular interest. However, most existing works usually assume that the positions of sensors are known exactly, while in practice, they may not be accurate. When the assumption is violated, the localization performance will deteriorate dramatically. In this article, we propose a novel CS-based multiple target localization method using the superimposed received signal strength, measured by sensors with inaccurate positions. In order to address such issues, we regard the known but inaccurate sensor locations as adjustable parameters. Accordingly, the sensor positions can be refined through the adjustment of parameters. As a result, the problem is reformulated as a joint sparse signal estimation and parameter optimization task. Then, the variational expectation-maximization (EM) algorithm and the subspace trust-region method are applied to iteratively estimate the unknown target locations and refine inaccurate sensor locations. Simulation results are included to confirm the superior localization performance of the proposed algorithm by comparing with the state-of-the-art methods.

关键词： sensor signals processing compressive sensing (CS) multitarget localization received signal strength (RSS) sensor data processing the subspace trust-region method variational expectation-maximization (EM) algorithm

来源：评论

学校读者我要写书评

暂无评论

Investigations of rotor shaft position sensor signal processing in electric drive train systems

Investigations of rotor shaft position sensor signal process...

引用

IEEE Transportation Electrification Conference and Expo Asia-Pacific (ITEC Asia-Pacific)

作者： Datlinger, Christoph Hirz, Mario Graz Univ Technol FTG Inst Automot Engn Graz Austria

ISBN: (纸本)9781538657829

This paper deals with the evaluation of rotor shaft position sensor systems used in automotive electric powertrain applications. Those sensor systems comprise of an angular rotor position sensor as well as the powertrain's electronic control unit (ECU), processing the sensor data in terms of digitalization, filtering, position- and speed computation. The work introduces an evaluation method of influencing factors on the accuracy of rotor position measurement, e.g. quantization errors, filter settings and time latency of data processing chain. In this way, performance evaluation and investigation of electric powertrain sensor systems is enabled by combination of specific simulation and measurement procedures.

关键词： electric powertrain system rotor shaft position sensor system sensor data processing resolver electronic control unit ECU resolver-to-digital-conversion latency

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：