Da Yan, Zhou Zhao and Wilfred Ng The Hong Kong University of Science and Technology.

Slides:



Advertisements
Similar presentations
Bayesian Belief Propagation
Advertisements

CSSSIA Workshop – WWW 2008 Speeding up Web Service Composition with Volatile External Information John Harney, Prashant Doshi LSDIS Lab, Dept. of Computer.
Adaptive Accurate Indoor-Localization Using Passive RFID Xi Chen, Lei Xie, Chuyu Wang, Sanglu Lu State Key Laboratory for Novel Software Technology Nanjing.
Linear Regression.
Computer Networks Group Universität Paderborn Ad hoc and Sensor Networks Chapter 9: Localization & positioning Holger Karl.
Presented for: CPS Lab-ASU By: Ramtin Kermani
Da Yan, Zhou Zhao and Wilfred Ng The Hong Kong University of Science and Technology.
Nonlinear Regression Ecole Nationale Vétérinaire de Toulouse Didier Concordet ECVPT Workshop April 2011 Can be downloaded at
Computer vision: models, learning and inference
2008 SIAM Conference on Imaging Science July 7, 2008 Jason A. Palmer
Artificial Intelligence Lecture 2 Dr. Bo Yuan, Professor Department of Computer Science and Engineering Shanghai Jiaotong University
Visual Recognition Tutorial
1/24 Passive Interference Measurement in Wireless Sensor Networks Shucheng Liu 1,2, Guoliang Xing 3, Hongwei Zhang 4, Jianping Wang 2, Jun Huang 3, Mo.
Wireless Mesh Networks for Localization Dr. Kristofer Pister Prof. EECS, UC Berkeley Founder & CTO, Dust Networks.
Interactive Animation of Structured Deformable Objects Mathieu Desbrun Peter Schroder Alan Barr.
1 Indoor Location Sensing Using Active RFID Lionel M. Ni, HKUST Yunhao Liu, HKUST Yiu Cho Lau, IBM Abhishek P. Patil, MSU Indoor Location Sensing Using.
Robust Topology Control for Indoor Wireless Sensor Networks Greg Hackmann, Octav Chipara, and Chenyang Lu SenSys 2009 S Slides from Greg Hackmann at Washington.
EE 685 presentation Optimization Flow Control, I: Basic Algorithm and Convergence By Steven Low and David Lapsley Asynchronous Distributed Algorithm Proof.
Novel Self-Configurable Positioning Technique for Multihop Wireless Networks Authors : Hongyi Wu Chong Wang Nian-Feng Tzeng IEEE/ACM TRANSACTIONS ON NETWORKING,
Maximum Likelihood (ML), Expectation Maximization (EM)
Improved BP algorithms ( first order gradient method) 1.BP with momentum 2.Delta- bar- delta 3.Decoupled momentum 4.RProp 5.Adaptive BP 6.Trinary BP 7.BP.
RFID Object Localization Gabriel Robins and Kirti Chawla Department of Computer Science University of Virginia
ALBERT PARK EEL 6788: ADVANCED TOPICS IN COMPUTER NETWORKS Energy-Accuracy Trade-off for Continuous Mobile Device Location, In Proc. of the 8th International.
9 1 Performance Optimization. 9 2 Basic Optimization Algorithm p k - Search Direction  k - Learning Rate or.
1 Secure Cooperative MIMO Communications Under Active Compromised Nodes Liang Hong, McKenzie McNeal III, Wei Chen College of Engineering, Technology, and.
1 Location Estimation in ZigBee Network Based on Fingerprinting Department of Computer Science and Information Engineering National Cheng Kung University,
Frame by Frame Bit Allocation for Motion-Compensated Video Michael Ringenburg May 9, 2003.
Stochastic sleep scheduling (SSS) for large scale wireless sensor networks Yaxiong Zhao Jie Wu Computer and Information Sciences Temple University.
Ordinary Least-Squares Emmanuel Iarussi Inria. Many graphics problems can be seen as finding the best set of parameters for a model, given some data Surface.
Segmental Hidden Markov Models with Random Effects for Waveform Modeling Author: Seyoung Kim & Padhraic Smyth Presentor: Lu Ren.
Architectures and Applications for Wireless Sensor Networks ( ) Localization Chaiporn Jaikaeo Department of Computer Engineering.
Mapping and Localization with RFID Technology Matthai Philipose, Kenneth P Fishkin, Dieter Fox, Dirk Hahnel, Wolfram Burgard Presenter: Aniket Shah.
Localization using DOT3 Wireless Sensors Design & Implementation Motivation Wireless sensors can be used for locating objects: − Previous works used GPS,
Learning Stable Multivariate Baseline Models for Outbreak Detection Sajid M. Siddiqi, Byron Boots, Geoffrey J. Gordon, Artur W. Dubrawski The Auton Lab.
A Hybrid Method for achieving High Accuracy and Efficiency in Object Tracking using Passive RFID Lei Yang 1, Jiannong Cao 1, Weiping Zhu 1, and Shaojie.
Yafeng Yin 1, Lei Xie 1, Jie Wu 2, Athanasios V. Vasilakos 3, Sanglu Lu 1 1 State Key Laboratory for Novel Software Technology, Nanjing University, China.
Various topics Petter Mostad Overview Epidemiology Study types / data types Econometrics Time series data More about sampling –Estimation.
On Distinguishing the Multiple Radio Paths in RSS-based Ranging Dian Zhang, Yunhuai Liu, Xiaonan Guo, Min Gao and Lionel M. Ni College of Software, Shenzhen.
Prognosis of gear health using stochastic dynamical models with online parameter estimation 10th International PhD Workshop on Systems and Control a Young.
CS 782 – Machine Learning Lecture 4 Linear Models for Classification  Probabilistic generative models  Probabilistic discriminative models.
The Group Lasso for Logistic Regression Lukas Meier, Sara van de Geer and Peter Bühlmann Presenter: Lu Ren ECE Dept., Duke University Sept. 19, 2008.
WINLAB Improving RF-Based Device-Free Passive Localization In Cluttered Indoor Environments Through Probabilistic Classification Methods Rutgers University.
Computer Animation Rick Parent Computer Animation Algorithms and Techniques Optimization & Constraints Add mention of global techiques Add mention of calculus.
Maximum Likelihood Estimation Methods of Economic Investigation Lecture 17.
College of Engineering Anchor Nodes Placement for Effective Passive Localization Karthikeyan Pasupathy Major Advisor: Dr. Robert Akl Department of Computer.
A Passive Approach to Sensor Network Localization Rahul Biswas and Sebastian Thrun International Conference on Intelligent Robots and Systems 2004 Presented.
11/25/2015 Wireless Sensor Networks COE 499 Localization Tarek Sheltami KFUPM CCSE COE 1.
Performance Study of Localization Techniques in Zigbee Wireless Sensor Networks Ray Holguin Electrical Engineering Major Dr. Hong Huang Advisor.
WSP: A Network Coordinate based Web Service Positioning Framework for Response Time Prediction Jieming Zhu, Yu Kang, Zibin Zheng and Michael R. Lyu The.
Data Modeling Patrice Koehl Department of Biological Sciences National University of Singapore
ICDCS 2014 Madrid, Spain 30 June-3 July 2014
C. Savarese, J. Beutel, J. Rabaey; UC BerkeleyICASSP Locationing in Distributed Ad-hoc Wireless Sensor Networks Chris Savarese, Jan Beutel, Jan Rabaey.
An Efficient Localization Algorithm Focusing on Stop-and-Go Behavior of Mobile Nodes IEEE PerCom 2011 Takamasa Higuchi, Sae Fujii, Hirozumi Yamaguchi and.
Chapter 2-OPTIMIZATION G.Anuradha. Contents Derivative-based Optimization –Descent Methods –The Method of Steepest Descent –Classical Newton’s Method.
METHOD OF STEEPEST DESCENT ELE Adaptive Signal Processing1 Week 5.
Nonlinear differential equation model for quantification of transcriptional regulation applied to microarray data of Saccharomyces cerevisiae Vu, T. T.,
INTRO TO OPTIMIZATION MATH-415 Numerical Analysis 1.
1 Travel Times from Mobile Sensors Ram Rajagopal, Raffi Sevlian and Pravin Varaiya University of California, Berkeley Singapore Road Traffic Control TexPoint.
R. Kass/W03 P416 Lecture 5 l Suppose we are trying to measure the true value of some quantity (x T ). u We make repeated measurements of this quantity.
Teng Wei and Xinyu Zhang
Dynamic Fine-Grained Localization in Ad-Hoc Networks of Sensors
The Maximum Likelihood Method
Probabilistic Models for Linear Regression
Localization by RFID ref:
Localization by RFID ref:
Chapter 10. Numerical Solutions of Nonlinear Systems of Equations
PRAKASH CHOCKALINGAM, NALIN PRADEEP, AND STAN BIRCHFIELD
METHOD OF STEEPEST DESCENT
Lecture 15: Data Cleaning for ML
RFID Object Localization
Presentation transcript:

Da Yan, Zhou Zhao and Wilfred Ng The Hong Kong University of Science and Technology

Outline Motivation PassTrack System Overview Reader Detection Model Location Inference Model Experiments Conclusion 1

Motivation Tracking Technologies Passive RFID technologies Inventory monitoring, product flow tracking GPS technologies Outdoor location tracking Active RFID technologies Indoor location tracking 2 Our focus

Motivation Indoor Localization GPS has poor performance for indoor applications, due to its requirement of line-of-sight signal reception from the satellites Active-tag-based RFID localization systems RADAR LANDMARC... 3 Can we use passive RFID technology?

Motivation Passive RFID tags are more attractive than active ones Lower tag cost Can be used in a one-off manner Easier maintenance No maintenance overhead such as battery replacement Smaller error Active-tag-based systems usually incur meters of error 4

Outline Motivation PassTrack System Overview Reader Detection Model Location Inference Model Experiments Conclusion 5

System Overview The setting for tracking u objects n RFID readers/antennae {R 1, R 2,..., R n } m passive reference tags {T 1, T 2,..., T m } u passive tracking tags {O 1, O 2,..., O u } 6

System Overview External factors that influence the reader detection performance changes in temperature and humidity number of objects nearby Decouple the reader detection model from the location inference process Dynamically adapt the reader detection model to the changing environment 7

System Overview Decoupling Strategy For each reader/antenna R i, its detection model is “learned” from the current read rate of the reference tags dynamically Using the learned reader detection models, for each tracking tag O i, we find its most likely location based on the observed read rate of O i from each reader. 8

Outline Motivation PassTrack System Overview Reader Detection Model Location Inference Model Experiments Conclusion 9

Reader Detection Model Reader detection model estimates the distance of a tag T to an RFID antenna R Estimation is based on the readings of T received by R Metrics RSSI (received signal strength indicator) for active tags Read rate for passive tags If R detects the response from T in 3 out of a series of 10 interrogation cycles, the read rate is estimated to be

Reader Detection Model Define the Euclidean distance: Read rate is a function: Observations 11 Major Detection Range P(l) is close to 1 Minor Detection Range P(l) decreases almost linearly to 0

Reader Detection Model The curve is like an upside-down curve of the logistic function 12

Reader Detection Model Reader detection model for Reader R i l i is the distance from tag T and to R i Location of T: Location of R i : 13 Model Parameters

Reader Detection Model How to learn a i and b i ? p ij : current read rate of each reference tag T j estimated by reader R i Since the locations of reference tags and readers are fixed, is directly available At each time step, we have 14

Reader Detection Model How to learn a i and b i ? a i and b i are estimated using least square method, using 15

Reader Detection Model More interrogation cycles lead to more stable reader detection model 16

Outline Motivation PassTrack System Overview Reader Detection Model Location Inference Model Experiments Conclusion 17

Location Inference Model Maximum Likelihood Estimation O: the tracking tag of a tracking object p i (or p i (l i )): read rate of R i Pr{O responds k i times to R i in the latest N interrogation cycles} = 18

Location Inference Model Maximum Likelihood Estimation Assume that each reader R i detects O independently Likehood (to maximize): 19

Location Inference Model Maximum Likelihood Estimation Negative log-likelihood (to minimize): L is a function of the location (x, y) of O L is a function of p i p i is a function of l i l i is a function of (x, y) 20

Location Inference Model The shape of L(x, y) Almost convex 21

Location Inference Model Method for finding the location (x, y) that minimizes L(x, y) Grid search Gradient descent First-order Taylor approximation of L Newton’s method Second-order Taylor approximation of L Requires the Hessian matrix of L besides its gradient Converges faster than gradient descent 22

Location Inference Model Implementation of Newton’s method Initial location: obtained by a coarse-grained grid search Location update requires computing the Hessian matrix, which is the key to the efficiency The Hessian matrix of L at the current location (x, y) can be efficiently computed 23

Location Inference Model 24

Location Inference Model 25

Location Inference Model Alternative Method Nearest-neighbor-based heuristics 26 or

Outline Motivation PassTrack System Overview Reader Detection Model Location Inference Model Experiments Conclusion 27

Experiments Two Experimental Settings 28

Experiments Experimental Environment 29

Experiments Location Accuracy for Moving Objects 30

Experiments Location Accuracy for Moving Objects 31

Experiments Reader Detection Model Learning 32

Experiments Accuracy of different algorithms 33

Outline Motivation PassTrack System Overview Reader Detection Model Location Inference Model Experiments Conclusion 34

Conclusion Contribution of PassTrack Sigmoid-like reader detection model that dynamically adapts to the changing environment A sound probabilistic inference model 35

Conclusion Contribution of PassTrack PassTrack estimates the location of a constantly moving object (or a static object) with an average error of around 30 cm (or below 20 cm) The most accurate algorithm (Newton’s Method) is able to perform over 7500 location estimations per second on an ordinary computer 36

Thank you! 37