Locating in fingerprint space: wireless indoor localization with little human intervention. Proceedings of the 18th annual international conference on.

Slides:



Advertisements
Similar presentations
Robust spectral 3D-bodypart segmentation along time Fabio Cuzzolin, Diana Mateus, Edmond Boyer, Radu Horaud Perception project meeting 24/4/2007 Submitted.
Advertisements

Clustering Categorical Data The Case of Quran Verses
Computer Science Dr. Peng NingCSC 774 Adv. Net. Security1 CSC 774 Advanced Network Security Topic 7.3 Secure and Resilient Location Discovery in Wireless.
FM-BASED INDOOR LOCALIZATION TsungYun 1.
Computer Networks Group Universität Paderborn Ad hoc and Sensor Networks Chapter 9: Localization & positioning Holger Karl.
Heterogeneous Data Warehouse Analysis and Dimensional Integration Marius Octavian Olaru XXVI Cycle Computer Engineering and Science Advisor: Prof. Maurizio.
L OCATING IN F INGERPRINT S PACE : W IRELESS I NDOOR LOCALIZATION WITH L ITTLE H UMAN I NTERVENTION Zheng Yang, Chenshu Wu, and Yunhao Liu MobiCom 2012.
LYRIC-BASED ARTIST NETWORK METHODOLOGY Derek Gossi CS 765 Fall 2014.
Assessment. Schedule graph may be of help for selecting the best solution Best solution corresponds to a plateau before a high jump Solutions with very.
Clustering approaches for high- throughput data Sushmita Roy BMI/CS 576 Nov 12 th, 2013.
66: Priyanka J. Sawant 67: Ayesha A. Upadhyay 75: Sumeet Sukthankar.
Error Estimation for Indoor Location Fingerprinting.
Using Structure Indices for Efficient Approximation of Network Properties Matthew J. Rattigan, Marc Maier, and David Jensen University of Massachusetts.
A shot at Netflix Challenge Hybrid Recommendation System Priyank Chodisetti.
Localization from Mere Connectivity Yi Shang (University of Missouri - Columbia); Wheeler Ruml (Palo Alto Research Center ); Ying Zhang; Markus Fromherz.
1 University of Freiburg Computer Networks and Telematics Prof. Christian Schindelhauer Wireless Sensor Networks 16th Lecture Christian Schindelhauer.
1 Localization Technologies for Sensor Networks Craig Gotsman, Technion/Harvard Collaboration with: Yehuda Koren, AT&T Labs.
Novel Self-Configurable Positioning Technique for Multihop Wireless Networks Authors : Hongyi Wu Chong Wang Nian-Feng Tzeng IEEE/ACM TRANSACTIONS ON NETWORKING,
1 Spatial Localization Light-Seminar Spring 2005.
Automatic Camera Calibration for Image Sequences of a Football Match Flávio Szenberg (PUC-Rio) Paulo Cezar P. Carvalho (IMPA) Marcelo Gattass (PUC-Rio)
The Calibration Process
05/06/2005CSIS © M. Gibbons On Evaluating Open Biometric Identification Systems Spring 2005 Michael Gibbons School of Computer Science & Information Systems.
NonLinear Dimensionality Reduction or Unfolding Manifolds Tennenbaum|Silva|Langford [Isomap] Roweis|Saul [Locally Linear Embedding] Presented by Vikas.
An automated image prescreening tool for a printer qualification process by † Du-Yong Ng and ‡ Jan P. Allebach † Lexmark International Inc. ‡ School of.
Sensor Positioning in Wireless Ad-hoc Sensor Networks Using Multidimensional Scaling Xiang Ji and Hongyuan Zha Dept. of Computer Science and Engineering,
1 Location Estimation in ZigBee Network Based on Fingerprinting Department of Computer Science and Information Engineering National Cheng Kung University,
Krishna Chintalapudi Anand Padmanabha Iyer Venkata N. Padmanabhan ——presented by Xu Jia-xing.
Minimum Phoneme Error Based Heteroscedastic Linear Discriminant Analysis for Speech Recognition Bing Zhang and Spyros Matsoukas BBN Technologies Present.
Jong Y. Choi, Joshua Rosen, Siddharth Maini, Marlon E. Pierce, and Geoffrey C. Fox Community Grids Laboratory Indiana University.
Mobile Navigation With SVG Christian Schmitt SVG Open 2005.
1 SUPPORT VECTOR MACHINES İsmail GÜNEŞ. 2 What is SVM? A new generation learning system. A new generation learning system. Based on recent advances in.
WORD SENSE DISAMBIGUATION STUDY ON WORD NET ONTOLOGY Akilan Velmurugan Computer Networks – CS 790G.
Data Mining Knowledge on rough set theory SUSHIL KUMAR SAHU.
CLIPS: Infrastructure-free Collaborative Indoor Positioning for Time-critical Team Operations Youngtae Noh (Cisco Systems) Hirozumi Yamaguchi (Osaka University,
Datasets on the GRID David Adams PPDG All Hands Meeting Catalogs and Datasets session June 11, 2003 BNL.
A New Hybrid Wireless Sensor Network Localization System Ahmed A. Ahmed, Hongchi Shi, and Yi Shang Department of Computer Science University of Missouri-Columbia.
Andreas Papadopoulos - [DEXA 2015] Clustering Attributed Multi-graphs with Information Ranking 26th International.
A Passive Approach to Sensor Network Localization Rahul Biswas and Sebastian Thrun International Conference on Intelligent Robots and Systems 2004 Presented.
RADAR: an In-building RF-based user location and tracking system
Central China Normal University A Cluster-based and Range Free Multidimensional Scaling-MAP Localization Scheme in WSN 1 Ke Xu, Yuhua Liu ( ), Cui Xu School.
University “Ss. Cyril and Methodus” SKOPJE Cluster-based MDS Algorithm for Nodes Localization in Wireless Sensor Networks Ass. Biljana Stojkoska.
2015/12/251 Hierarchical Document Clustering Using Frequent Itemsets Benjamin C.M. Fung, Ke Wangy and Martin Ester Proceeding of International Conference.
Cooperative Location- Sensing for Wireless Networks Authors : Haris Fretzagias Maria Papadopouli Presented by cychen IEEE International Conference on Pervasive.
© 2007 Sean A. Williams 1 Ecolocation: A Sequence Based Technique for RF Localization in Wireless Sensor Networks Authors: Kiran Yedavalli, Bhaskar Krishnamachari,
Jin Yan Embedded and Pervasive Computing Center
Data Mining Course 2007 Eric Postma Clustering. Overview Three approaches to clustering 1.Minimization of reconstruction error PCA, nlPCA, k-means clustering.
Math 285 Project Diffusion Maps Xiaoyan Chong Department of Mathematics and Statistics San Jose State University.
Indexing OLAP Data Sunita Sarawagi Monowar Hossain York University.
System To Generate Test Data: The Analysis Program Syed Nabeel.
Collaborative Filtering via Euclidean Embedding M. Khoshneshin and W. Street Proc. of ACM RecSys, pp , 2010.
The Utilization of Artificial Intelligence in a Hybrid Intrusion Detection System Authors : Martin Botha, Rossouw von Solms, Kent Perry, Edwin Loubser.
Hybrid Indoor Positioning with Wi-Fi and Bluetooth: Architecture and Performance IEEE Mobile Data Management 2013 Artur Baniukevic†, Christian S. Jensen‡,
Smartphone-based Wi-Fi Pedestrian-Tracking System Tolerating the RSS Variance Problem Yungeun Kim, Hyojeong Shin, and Hojung Cha Yonsei University Bing.
Out of sample extension of PCA, Kernel PCA, and MDS WILSON A. FLORERO-SALINAS DAN LI MATH 285, FALL
Cluster Analysis What is Cluster Analysis? Types of Data in Cluster Analysis A Categorization of Major Clustering Methods Partitioning Methods.
Avoiding Multipath to Revive Inbuilding WiFi Localization
A Self-organizing Semantic Map for Information Retrieval Xia Lin, Dagobert Soergel, Gary Marchionini presented by Yi-Ting.
SZRZ6014 Research Methodology Prepared by: Aminat Adebola Adeyemo Study of high-dimensional data for data integration.
Geographic Routing without Location Information. Assumption by Geographic Routing Each node knows its own location.  outdoor positioning device: GPS:
Presented by Edith Ngai MPhil Term 3 Presentation
Ananya Das Christman CS311 Fall 2016
The Calibration Process
Understanding and Organizing User Generated Data
Dejavu:An accurate Energy-Efficient Outdoor Localization System
Subway Station Real-time Indoor Positioning System for Cell Phones
Fast Localization for Emergency Monitoring and Rescue in Disaster Scenarios Based on WSN SPEAKER:Jyun-Ying Yu ADVISOR:DR. Kai-Wei Ke DATE:2018/05/04.
The BIRCH Algorithm Davitkov Miroslav, 2011/3116
Wireless Mesh Networks
Multidimensional Scaling
Unsupervised Indoor Localization
Presentation transcript:

Locating in fingerprint space: wireless indoor localization with little human intervention. Proceedings of the 18th annual international conference on Mobile computing and networking. ACM, RSSI Fingerprint Automatic Radio Map Generation Presenter: Jongtack Jung

 Localization technique where each location is associated with the RSSI Fingerprint of the location  Arbitrary fingerprint from an unknown location is matched with the radio map, and best fitting option is selected 2 RSSI Fingerprint Method?

 Site survey process  Training phase a.k.a. calibration  Fingerprint  A set of RSS values obtained at a location  Radio map  The map of RSS fingerprints associated with the location  MDS (Multi-Dimensional Scaling)  A method to map points into given dimensional space where only the dissimilarities among the points are known  Stress (MDS term)  How well the mapping expresses the dissimilarity matrix 3 Terminology

PROS  All APs can be exploited  Including password protected APs  Fast execution  Best accuracy of all 4 Pros and Cons of RSSI Fingerprint CONS  Necessary training period  Necessary maintenance  EXPENSIVE  Training and maintenance require human labor

 The cost of RSSI Fingerprint method can be reduced using automated status update mechanism  The concept of automation is adopted  Many methods have been attempted to automate the process of site surveying 5 RSSI Fingerprint

 Main Idea  Since the geographic distance does not really represent the actual walking distance of two positions, use walking distance to create a map  Concept  Two position close together in walking distance means similar fingerprint  The number of footsteps obtained from accelerometer provides the distance between locations  Hybrid of fingerprint and dead reckoning 6 Locating in Fingerprint Space – Innovation!

7 Overview

 Stress  The accuracy of MDS  If a distance map can be perfectly resolved in given dimensions, the stress is 0  Given dataset, higher dimension means less stress  Draw 3D floor plan  Disparity between two locations is given with the number of footsteps  The distance between two nodes in the graph is the actual walking distance  Footstep recognition  The number of footsteps is obtained from accelerometer – only the #steps, not the distance 8 Stress-free Floor Plan

 The distance between fingerprints can also be expressed with disparity map  MDS algorithm is tolerant to measurement errors on its own  If no user actually passes through a particular pair of fingerprints, the value is calculated with shortest path 9 Fingerprint Space High dimension floor plan (top) and fingerprint space map(bottom)

 With above equation as dissimilarity, two points having the value less than threshold are considered as the same point and merged together. 10 Pre Processing

 Fingerprint space needs to be mapped on stress-free floor plan  Floor-level transformation  Use simplest linear transformation and shift between the two graphs  Room-level transformation  Detect rooms with K-cluster method and apply MDS to each room, and then match them 11 Space Transformations MST of fingerprint space map

 The virtual high dimensional data needs to be mapped on actual floor plan  Corridor recognition  MST betweenness  Room Recognition  Clustering of nodes  Reference Point Mapping  Point where values change largely are considered as doors 12 Mapping

 Betweenness Centrality Distribution of all points  K-Means Clustering of all points 13 Evaluation Results

14 Evaluation Results

15 Fingerprints clusters vs. Floor plan rooms

 The result is not so much impressive, but the values indicate the Fingerprint generation without site survey is possible  Fingerprint generation needs to be conveyed with human hands, but the required labor for the system is reduced a lot 16 Notes on High Dimension Fingerprint

 RSSI Fingerprint method’s credibility has been widely accepted to be the best method  It shows slightly less accuracy than traditional fingerprint method, but the cost is reduced by much 17 Conclusion