Detecting human activities using smartphones and maps Leon Stenneth Adviser: Professor Ouri Wolfson Co-Adviser: Professor Philip Yu University of Illinois,

Slides:



Advertisements
Similar presentations
Pseudo-Relevance Feedback For Multimedia Retrieval By Rong Yan, Alexander G. and Rong Jin Mwangi S. Kariuki
Advertisements

Real time street parking availability estimation Dr. Xu, Prof. Wolfson, Prof. Yang, Stenneth, Prof. Yu University of Illinois, Chicago.
CS 4100 Artificial Intelligence Prof. C. Hafner Class Notes March 27, 2012.
Xiaolong Zheng, Zhichao Cao, Jiliang Wang, Yuan He, and Yunhao Liu SenSys 2014 ZiSense Towards Interference Resilient Duty Cycling in Wireless Sensor Networks.
GPS and Multi-Week Data Collection of Activity-Travel Patterns Harry Timmermans Eindhoven University of Technology 4/19/2015.
Supervised Learning Techniques over Twitter Data Kleisarchaki Sofia.
VTrack: Accurate, Energy-Aware Road Traffic Delay Estimation Using Mobile Phones Arvind Thiagarajan, Lenin Ravindranath, Katrina LaCurts, Sivan Toledo,
Using Mobile Phones to Determine Transportation Modes Hyeong-il Ko Sasank Reddy et al., ACM Transactions on Sensor Networks, Vol. 6, No. 2,
Using Mobile Phones to Determine Transportation Modes Sasank Reddy, Min Mun, Jeff Burke, D. Estrin, M. Hansen, M. Srivastava TOSN 2010.
Mining Motion Sensor Data from Smartphones for Estimating Vehicle Motion Tamer Nadeem, PhD Department of Computer Science NSF Workshop on Large-Scale Traffic.
Accelerometer-based Transportation Mode Detection on Smartphones
Tracking Fine-grain Vehicular Speed Variations by Warping Mobile Phone Signal Strengths Presented by Tam Vu Gayathri Chandrasekaran*, Tam Vu*, Alexander.
Multiple Criteria for Evaluating Land Cover Classification Algorithms Summary of a paper by R.S. DeFries and Jonathan Cheung-Wai Chan April, 2000 Remote.
T-Drive : Driving Directions Based on Taxi Trajectories Microsoft Research Asia University of North Texas Jing Yuan, Yu Zheng, Chengyang Zhang, Xing Xie,
Transportation mode detection using mobile phones and GIS information Leon Stenneth, Ouri Wolfson, Philip Yu, Bo Xu 1University of Illinois, Chicago.
Report on Intrusion Detection and Data Fusion By Ganesh Godavari.
1 Learning to Detect Objects in Images via a Sparse, Part-Based Representation S. Agarwal, A. Awan and D. Roth IEEE Transactions on Pattern Analysis and.
Generic Object Detection using Feature Maps Oscar Danielsson Stefan Carlsson
1 The Expected Performance Curve Samy Bengio, Johnny Mariéthoz, Mikaela Keller MI – 25. oktober 2007 Kresten Toftgaard Andersen.
Student: Hsu-Yung Cheng Advisor: Jenq-Neng Hwang, Professor
Learning Transportation Mode from Raw GPS Data for Geographic Applications on the Web Yu Zheng, Like Liu, Xing Xie Microsoft Research.
Business Statistics: Communicating with Numbers
Rutgers: Gayathri Chandrasekaran, Tam Vu, Marco Gruteser, Rich Martin,
Sensys 2009 Speaker:Lawrence.  Introduction  Overview & Challenges  Algorithm  Travel Time Estimation  Evaluation  Conclusion.
GPS Trajectories Analysis in MOPSI Project Minjie Chen SIPU group Univ. of Eastern Finland.
Extracting Places and Activities from GPS Traces Using Hierarchical Conditional Random Fields Yong-Joong Kim Dept. of Computer Science Yonsei.
Processing of large document collections Part 3 (Evaluation of text classifiers, applications of text categorization) Helena Ahonen-Myka Spring 2005.
Detecting Movement Type by Route Segmentation and Classification Karol Waga, Andrei Tabarcea, Minjie Chen and Pasi Fränti.
by B. Zadrozny and C. Elkan
Digital Camera and Computer Vision Laboratory Department of Computer Science and Information Engineering National Taiwan University, Taipei, Taiwan, R.O.C.
Automatically Identifying Localizable Queries Center for E-Business Technology Seoul National University Seoul, Korea Nam, Kwang-hyun Intelligent Database.
Report on Intrusion Detection and Data Fusion By Ganesh Godavari.
Machine Learning Approach to Report Prioritization with an Application to Travel Time Dissemination Piotr Szczurek Bo Xu Jie Lin Ouri Wolfson.
Partially Supervised Classification of Text Documents by Bing Liu, Philip Yu, and Xiaoli Li Presented by: Rick Knowles 7 April 2005.
Predicting Earthquakes By Lois Desplat. Why Predict Earthquakes?  To minimize the loss of life and property.  Unfortunately, current techniques do not.
Ensemble Learning Spring 2009 Ben-Gurion University of the Negev.
BAGGING ALGORITHM, ONLINE BOOSTING AND VISION Se – Hoon Park.
University of Colorado Boulder ASEN 5070: Statistical Orbit Determination I Fall 2014 Professor Brandon A. Jones Lecture 26: Singular Value Decomposition.
CSSE463: Image Recognition Day 11 Lab 4 (shape) tomorrow: feel free to start in advance Lab 4 (shape) tomorrow: feel free to start in advance Test Monday.
Stable Multi-Target Tracking in Real-Time Surveillance Video
CVPR2013 Poster Detecting and Naming Actors in Movies using Generative Appearance Models.
1 Value of information – SITEX Data analysis Shubha Kadambe (310) Information Sciences Laboratory HRL Labs 3011 Malibu Canyon.
The famous “sprinkler” example (J. Pearl, Probabilistic Reasoning in Intelligent Systems, 1988)
Indoor Location Detection By Arezou Pourmir ECE 539 project Instructor: Professor Yu Hen Hu.
1Ellen L. Walker Category Recognition Associating information extracted from images with categories (classes) of objects Requires prior knowledge about.
Machine Learning Tutorial-2. Recall, Precision, F-measure, Accuracy Ch. 5.
CSSE463: Image Recognition Day 11 Due: Due: Written assignment 1 tomorrow, 4:00 pm Written assignment 1 tomorrow, 4:00 pm Start thinking about term project.
Presented by: Idan Aharoni
Identifying “Best Bet” Web Search Results by Mining Past User Behavior Author: Eugene Agichtein, Zijian Zheng (Microsoft Research) Source: KDD2006 Reporter:
1 Travel Times from Mobile Sensors Ram Rajagopal, Raffi Sevlian and Pravin Varaiya University of California, Berkeley Singapore Road Traffic Control TexPoint.
Learning and Inferring Transportation Routines Lin Liao, Don Patterson, Dieter Fox, Henry Kautz Department of Computer Science and Engineering University.
Shadow Detection in Remotely Sensed Images Based on Self-Adaptive Feature Selection Jiahang Liu, Tao Fang, and Deren Li IEEE TRANSACTIONS ON GEOSCIENCE.
Introduction to Information Retrieval Introduction to Information Retrieval Lecture 15: Text Classification & Naive Bayes 1.
ParkNet: Drive-by Sensing of Road-Side Parking Statistics Irfan Ullah Department of Information and Communication Engineering Myongji university, Yongin,
Privacy Vulnerability of Published Anonymous Mobility Traces Chris Y. T. Ma, David K. Y. Yau, Nung Kwan Yip (Purdue University) Nageswara S. V. Rao (Oak.
Trajectory Data Mining Dr. Yu Zheng Lead Researcher, Microsoft Research Chair Professor at Shanghai Jiao Tong University Editor-in-Chief of ACM Trans.
Machine Learning – Classification David Fenyő
T-Share: A Large-Scale Dynamic Taxi Ridesharing Service
Traffic Sign Recognition Using Discriminative Local Features Andrzej Ruta, Yongmin Li, Xiaohui Liu School of Information Systems, Computing and Mathematics.
Session 7: Face Detection (cont.)
CSSE463: Image Recognition Day 11
Transport mode detection in the city of Lyon using mobile phone sensors Jorge Chong Internship for MLDM M1 Jean Monnet University
Automatic Picking of First Arrivals
Vijay Srinivasan Thomas Phan
Transportation Mode Recognition using Smartphone Sensor Data
REMOTE SENSING Multispectral Image Classification
iSRD Spam Review Detection with Imbalanced Data Distributions
CSSE463: Image Recognition Day 11
Roc curves By Vittoria Cozza, matr
CSSE463: Image Recognition Day 11
Presentation transcript:

Detecting human activities using smartphones and maps Leon Stenneth Adviser: Professor Ouri Wolfson Co-Adviser: Professor Philip Yu University of Illinois, Chicago1

Road map Outdoor transportation mode detection Indoor and outdoor transportation mode detection Parking status detection Parking availability estimation University of Illinois, Chicago2

Sensors University of Illinois, Chicago3 Image source:

Maps Bus stop locations, real time bus locations, road network, rail line trajectory, location of parking pay boxes, etc. University of Illinois, Chicago4

Transportation mode detection using mobile phones and GIS information Patent filed Paper published at ACM SIGSPATIAL GIS external citations 5University of Illinois, Chicago

Problem Detecting a mobile user’s current mode of transportation based on GPS and GIS. Possible transportation modes considered are: 6University of Illinois, Chicago

Motivations Value added services (e.g. in Google Maps) More customized advertisements can be sent Providing more accurate travel demand surveys instead of people manually recording trips and transfers Determining a traveler’s carbon footprint. 7University of Illinois, Chicago

Contributions Improve accuracy of detection by 17% for GPS only models Improve accuracy of detection for 9% compared to GPS/GIS models Introduce new classification features that can distinguish between motorized and non- motorized modes. University of Illinois, Chicago8

Technique A supervised machine learning model New classification features derived by combining GPS with GIS Trained multiple models with these extracted features and labeled data. 9University of Illinois, Chicago

Data model GPS sensor report: pi = GPS trace: T = p0 → p1 → · · · → pk University of Illinois, Chicago10

Approach In addition to traditional features on speed, acceleration, and heading change. We build classification features using GPS and GIS data 11University of Illinois, Chicago

Features Traditional – Speed, acceleration, and heading change Combining GPS and GIS – Rail line closeness – Average bus closeness – Candidate bus closeness – Bus stop closeness rate 12University of Illinois, Chicago

Rail line closeness ARLC - average rail line closeness Let {p 1, p 2, p 3, p 4 …p n } be a finite the set of GPS reports submitted within a time window. ARLC = ∑ i=1 to n d i rail / n 13University of Illinois, Chicago

Average bus closeness (ABC) Let {p 1, p 2, p 3, p 4 …p n } be a finite the set of GPS reports submitted within a time window. ABC = (∑ i=1 to n d i bus ) / n 14University of Illinois, Chicago

Candidate Bus closeness (CBC) d j.t bus 1≤j≤m - Euclidian distance to each bus bus j D j - total Euclidian distance to bus j over all reports submitted in the time window D j = ∑ t=1 to n d j.t bus 1≤j≤m Given D j for all the m buses, we compute CBC as follows. CBC = min (D j ) 1≤j≤m 15University of Illinois, Chicago

Bus stop closeness rate (BSCR) | PS | is the number of GPS reports who's Euclidian distance to the closest bus stop is less than the threshold BSCR = | PS | / window size 16University of Illinois, Chicago

Machine learning models We compared five different models then choose the most effective – Random Forest (RF) – Decision trees (DT) – Neural networks (MLP) – Naïve Bayes (NB) – Bayesian Network (BN) WEKA machine learning toolkit 17University of Illinois, Chicago

Evaluation matrices Precision(M)=(number of correctly classified instances of mode M) / (number of instances classified as mode M) Recall (M) = (number of correctly classified instances of mode M) / (number of instances of mode M) University of Illinois, Chicago18

Data set 6 individuals 3 weeks University of Illinois, Chicago19

Results Random Forest was the most effective model 20University of Illinois, Chicago

Feature Ranking Below we rank the features to determine the most effective. 21University of Illinois, Chicago

Results Using the top ranked features only Precision and recall is shown below 22University of Illinois, Chicago

Deployed System We can provide further information (i.e. route, bus id) on the particular bus one is riding. 23University of Illinois, Chicago

Related work with GPS Liao et. al (2004) – consider the user’s history such as where one parked or bus stop boarded. Zheng et. al (2008) – Robust set of GPS only features and a change point segmentation method. Reddy et. al (2010) – Combined accelerometer and GPS to achieve high accuracy. University of Illinois, Chicago24

Conclusion Using GIS data improves transportation mode detection accuracy. This improvement is more noticeable for motorized transportation modes. Only a subset of our initial set of features are needed. Random forest is the most effective model We can provide further information about the bus that a user is riding 25University of Illinois, Chicago

Limitationsand solutions Using GPS consumes battery power aggressively [explore low power sensors such as BT or accelerometer] Misclassification of car as rail [map matching using both road and rail artifacts] The effects of window size on classification feature effectiveness [more experiments] University of Illinois, Chicago26

Adding Accelerometer sensor to the model Acceleration in all three axes Consumes less energy than GPS Common on today’s mobile phone (e.g. iPhone) University of Illinois, Chicago27

Adding accelerometer to the model University of Illinois, Chicago

Contribution of accelerometer 4 % increase in outdoor detection accuracy Effective for indoor transportation mode detection (stairs, elevator, escalator) Finer granularity on mode detection (e.g. calorie trackers) University of Illinois, Chicago29

Accelerometer readings University of Illinois, Chicago30

Accelerometer and body position University of Illinois, Chicago31

Results Random Forest is most effective Increase in 5.5% for outdoor transportation mode Detects each indoor (i.e. stairs, elevator, escalator) mode by over 80% accuracy GPS and GIS model by itself is not effective for indoor transportation mode detection University of Illinois, Chicago32

Limitations of accelerometer study Small data set Constrained mobile phone position University of Illinois, Chicago33

Real time street parking availability estimation Motivation – Vehicles searching for parking in LA business district CO2 emission (730 tons in 1yr) Waste gasoline (burnt 47K gals 1yr) Waste time (38 trips around the world) University of Illinois, Chicago34

Real-time street parking availability estimation The traffic product – sparse probes, map matching, map, travel speed, tta, color maps indicating current travel speed. University of Illinois, Chicago35

Parking status detection (PSD) Determines spatial-temporal property of parking event (maybe parking probes) Image sources:

Parking status detectors (PSD) Contribution to PSD: Three less expensive techniques to detect spatial and temporal property parking events using mobile phones [patent pending] University of Illinois, Chicago37

Our schemes for PSD 38

Our schemes for PSD University of Illinois, Chicago39

Street parking estimation model University of Illinois, Chicago40 location errors false + false - false – false + Estimate the number of available parking spaces on a street block. PSD – Parking status detector HAP – Historical availability profile PAE – Parking availability estimator

HAP construction scheme estimates the historic mean (i.e. ) and variance (i.e. ) of parking relevant terms – prohibited period, permitted period (PP i ), fp, fn, b, N 41

Historical availability profile (HAP) Algorithm Start with a time at which the street block is fully available, e.g., end of a prohibited time interval (start permitted period) When a parking report is received, availability is reduced by: Deparking causes increase of availability by same factor b: penetration ratio (uniform distribution) fn: false negative probability fp: false positive probability Justification: 1. Each report (statistically) corresponds to 1/b actual parking 2. 1/(1  fn) reports should have been received if there were no false negatives 3. The report is correct with 1  fp probability

HAP algorithm Permitted period 1 43 Permitted period 2 Permitted period 3 Permitted period m

HAP algorithm termination condition HAP terminates when the difference between q(t) and is less than x parking spaces with k% confidence. Automatically determines m. 44

Computing confidence Assumptions – PSD vehicles are uniformly distributed among all vehicles – Parking activities are detected independently of each other. – are identically and independently distributed See upcoming lemmas: University of Illinois, Chicago45

Computing confidence Lemma 1: Proof – p i (t)|P i (t)  Binomial(P i (t), b  (1  fn)) 1. – d i (t)|D i (t)  Binomial(D i (t), b  (1  fn)) 2. – – From 1. – Thus, University of Illinois, Chicago46

Computing confidence Also showed that for i=1,2,…, m. University of Illinois, Chicago47.

More specifically: Example: – If we want error < 2 with 90% confidence, standard deviation of the estimation is 10 (i.e., the average fluctuation of estimated availability at the 8:00am is 10). – then we need 68 permitted periods. i.e. about two months of data. Estimation average Estimation variance True average Number of samples, or permitted periods Cumulative distribution function of normal distr.

Evaluation of HAP Real parking signals from SF Park Simulated errors (i.e. fp and fn) University of Illinois, Chicago49

HAP Results Polk St. block 12 spaces available 50

HAP Results Chestnut St. block 4 spaces available 51

Parking availability estimation (PAE) algorithms 52

Parking Availability Estimation (PAE) Combining history (i.e. HAP) with real time – Weighted average with pre-fitted weights 53

Parking Availability Estimation (PAE) combining history (i.e. HAP) with real time – Kalman Filter estimation (KF) 54

PAE results 55

PAE results Boolean availability i.e. at least one slot available b =1 % 56

Conclusion We can provide reasonable parking availability estimation that does not deviate from the true availability by too much. Works under low penetration ratio (e.g. b=1%) Robust to false+ and false- errors University of Illinois, Chicago57

Limitations and solutions PSD penetration ratio can be low. [Can we use signals from neighboring blocks?] PAE algorithms did not consider the previous known parking availability at time t-1 for a street block [try to combine history & previous & current parking observations] University of Illinois, Chicago58

Current work Increasing parking signals by using signals from neighboring blocks University of Illinois, Chicago59

Current work University of Illinois, Chicago60

Future work Temporal correlations Incorporating neighboring signals in Kalman Filter Incorporating parking availability at previous epoch in the model New parking status detectors(e.g. acoustic sensors) University of Illinois, Chicago61

The end Thanks you for your time Questions………. University of Illinois, Chicago62