Tap Position Inference on Smart Phones
|
|
- Everett Marshall
- 5 years ago
- Views:
Transcription
1 Tap Position Inference on Smart Phones Ankush Chauhan Outline Introduction Application Architecture Sensor Event Data Sensor Data Collection App Demonstration Scalable Data Collection Pipeline Feature Extraction Pipeline Feature Engineering Screen Partitioning Data Visualizations Model Selection Comparing Accuracies Conclusion Links Related Works 1
2 Introduction Immersive Full Screen Data collection application for Tap Event Detection Scalable Data Collection Pipeline Sensor Fusion algorithm for extracting rotations Clustering of similar regions based on screen partitioning Ensemble Machine Learning Approach to combine multiple ML models. Interactive Notebooks for data analytics Application Architecture Recording Sensors No explicit manifest declaration required. CallBack Event Listener onsensorchanged() Service Records sensor data event in background Log data to a CSV file File name contains Experiment Epoch Each record contains lastsensorvalues() with Timestamp as event time delta from Epoch. Recording screen taps Full Immersive Layout Highest granularity of 20px X 20px region Tabular Arrangement 16 Rows 9 Columns Lowest granularity of 1920px X 1080px region Store valid taps in a defined JSON schema to NOSQL database. 2
3 Sensor Event Data Motion Sensors used for capturing sequences on 3- coordinate axis Accelerometer acceleration force measurements Magnetometer magnetic field measurements Gyroscope angular velocity measurements Delay SENSOR_DELAY_FASTEST (no delay) SENSOR_DELAY_GAME (20,000 microsecond delay) Sensor Data Collection 01 For complete duration of one experimental run, we log raw updates for selected sensors to a temporary cache file on device. 02 On leaving the app activity the cached file is uploaded to Firebase storage for staging the data. 3
4 TapLogger App Demo Record Sensor Event Log Training Ends Upload Log Cloud Storage TapLogger Launched Initialize Data Capturing Modules Tap Event Insert Event Realtime Database On-Exit Event Handler On-Click Event Handler 4
5 Load Sensor Recording CSV Parser Sensor Data Frame Transform Features Feature Set Sensor Data Staging Extracted Sensors Features + Target Labels Load Tap Recordings JSON Parser Tap Data Frame Transform Labels Label Set Tap Data Staging Rotations in 3D Roll Pitch Yaw 5
6 Feature Engineering Sensor data filtered using Madgwick AHRS algorithm for extracting rotations in phone s frame of reference. Decomposing Rotations from MAG; filter and update technique to extract Euler Angles (Roll, Pitch, Yaw) 3 rotations Cons Ambiguity, Gimbal Lock Quaternions 1 rotation, as Sin and Cos captured. (q0,q1,q2,q3) Cons - Human Interpretability For each such field, we calculate it s first four statistical moments as a feature set in the tap interval sequence. F [start end] = F Mean F Variance F Skewness F Kurtosis Corresponding to each tap event we divide the feature sequence to two monotonic sections. F Down and F Up 2 Target Regions 4 Target Regions 8 Target Regions 16 Target Regions 6
7 3 Target Regions 9 Target Regions 7
8 8
9 Horizontal Partitions 1200 Vertical Partitions Class wise Sampling Distribution
10 Feature Correlation Quaternions Euler Angles Model Selection OneVsRestClassifier LR - Logistic Regression CART Decision Tree NB Gaussian Naïve Bayes LDA Linear Discriminant Analysis KNN K Nearest Neighbors SVM Support Vector Machine Ensemble technique known as majority voting, which combines the predicted class for a particular class label that represents the majority (mode) of the class labels predicted by each individual classifier. 10
11 2 Class Classification Accuracy on Euler Angles 11
12 2 Class Classification Accuracy on Quaternions 12
13 3 Class Classification Accuracy on Euler Angles 13
14 3 Class Classification Accuracy on Quaternions 14
15 4 Class Classification Accuracy on Euler Angles 15
16 4 Class Classification Accuracy on Quaternions 16
17 Our learning system has been able to predict better than a random guess which screen area has been tapped. Validation on lower granularity will require combining correlated features. Conclusion Attack strategies can be evaluated for confirming model robustness. Suggested mitigation efforts include additive noise strategies to mask those micro-level changes in sensor reading. Data Science Stack Scientific Computation Machine Learning Data Structures Data Visualization Numerical Computation Interactive Kernel Notebooks 17
18 Project Repositories Xu, Zhi, Kun Bai, and Sencun Zhu. "Taplogger: Inferring user inputs on smartphone touchscreens using on-board motion sensors." Proceedings of the fifth ACM conference on Security and Privacy in Wireless and Mobile Networks. ACM, Zheng, Nan, et al. "You are how you touch: User verification on smartphones via tapping behaviors." Network Protocols (ICNP), 2014 IEEE 22nd International Conference on. IEEE, Related Works Madgwick, Sebastian OH, Andrew JL Harrison, and Ravi Vaidyanathan. "Estimation of IMU and MARG orientation using a gradient descent algorithm." Rehabilitation Robotics (ICORR), 2011 IEEE International Conference on. IEEE,
19 Questions? Thank You 19
Windows Phone Week5 Tuesday -
Windows Phone 8.1 - Week5 Tuesday - Smart Embedded System Lab Kookmin University 1 Objectives and what to study Training 1: To Get Accelerometer Sensor Value Training 2: To Get Compass Sensor Value To
More informationLow Cost solution for Pose Estimation of Quadrotor
Low Cost solution for Pose Estimation of Quadrotor mangal@iitk.ac.in https://www.iitk.ac.in/aero/mangal/ Intelligent Guidance and Control Laboratory Indian Institute of Technology, Kanpur Mangal Kothari
More informationImperfections of Sensors Make Smartphone Users Trackable. Srihari Nelakuditi
Imperfections of Sensors Make Smartphone Users Trackable Srihari Nelakuditi Privacy is hot in the press Privacy is not a new concern Source: 3M privacy filter for laptops promotional campaign Privacy is
More informationReal Time Motion Authoring of a 3D Avatar
Vol.46 (Games and Graphics and 2014), pp.170-174 http://dx.doi.org/10.14257/astl.2014.46.38 Real Time Motion Authoring of a 3D Avatar Harinadha Reddy Chintalapalli and Young-Ho Chai Graduate School of
More informationSelection and Integration of Sensors Alex Spitzer 11/23/14
Selection and Integration of Sensors Alex Spitzer aes368@cornell.edu 11/23/14 Sensors Perception of the outside world Cameras, DVL, Sonar, Pressure Accelerometers, Gyroscopes, Magnetometers Position vs
More informationAccelerometer Gesture Recognition
Accelerometer Gesture Recognition Michael Xie xie@cs.stanford.edu David Pan napdivad@stanford.edu December 12, 2014 Abstract Our goal is to make gesture-based input for smartphones and smartwatches accurate
More informationProceedings 3D Visualisation of Wearable Inertial/Magnetic Sensors
Proceedings 3D Visualisation of Wearable Inertial/Magnetic Sensors Tomohito Wada 1,2, *, Mirai Mizutani 1, James Lee 2,3, David Rowlands 2 and Daniel James 2 1 National Institute of Fitness and Sports,
More informationExploring unconstrained mobile sensor based human activity recognition
Exploring unconstrained mobile sensor based human activity recognition ABSTRACT Luis Gerardo Mojica de la Vega luis.mojica@utdallas.edu Arvind Balasubramanian arvind@utdallas.edu Human activity recognition
More informationUse of ISP1880 Accelero-Magnetometer, Temperature and Barometer Sensor
Use of Accelero-Magnetometer, Temperature and Barometer Sensor Application Note AN181105 Introduction Scope This application note describes how to set up a Sensor demonstration with Sensors Board that
More informationCamera and Inertial Sensor Fusion
January 6, 2018 For First Robotics 2018 Camera and Inertial Sensor Fusion David Zhang david.chao.zhang@gmail.com Version 4.1 1 My Background Ph.D. of Physics - Penn State Univ. Research scientist at SRI
More informationSpecialist ICT Learning
Specialist ICT Learning APPLIED DATA SCIENCE AND BIG DATA ANALYTICS GTBD7 Course Description This intensive training course provides theoretical and technical aspects of Data Science and Business Analytics.
More informationInertial Measurement Units II!
! Inertial Measurement Units II! Gordon Wetzstein! Stanford University! EE 267 Virtual Reality! Lecture 10! stanford.edu/class/ee267/!! wikipedia! Polynesian Migration! Lecture Overview! short review of
More informationEstimation of Altitude and Vertical Velocity for Multirotor Aerial Vehicle using Kalman Filter
Estimation of Altitude and Vertical Velocity for Multirotor Aerial Vehicle using Kalman Filter Przemys law G asior, Stanis law Gardecki, Jaros law Gośliński and Wojciech Giernacki Poznan University of
More informationSH-2 Reference Manual
SH-2 Reference Manual Document Number: 1000-3625 Document Revision: 1.2 Date: 05/19/2017 Hillcrest Laboratories, Inc. 15245 Shady Grove Road, Suite 400 Rockville, MD 20850 Copyright 2017 Hillcrest Labs,
More informationQuaternion Kalman Filter Design Based on MEMS Sensors
, pp.93-97 http://dx.doi.org/10.14257/astl.2014.76.20 Quaternion Kalman Filter Design Based on MEMS Sensors Su zhongbin,yanglei, Kong Qingming School of Electrical and Information. Northeast Agricultural
More informationMachine Learning for the Quantified Self. Lecture 2 Basic of Sensory Data
Machine Learning for the Quantified Self Lecture 2 Basic of Sensory Data Dataset (1) During the course we will use a running example provided by CrowdSignals.io People share their mobile sensors data (smart
More informationReal-time Gesture Pattern Classification with IMU Data
Real-time Gesture Pattern Classification with IMU Data Alex Fu Stanford University Computer Science Department alexfu@stanford.edu Yangyang Yu Stanford University Electrical Engineering Department yyu10@stanford.edu
More informationOptimization of Control Parameter for Filter Algorithms for Attitude and Heading Reference Systems
Optimization of Control Parameter for Filter Algorithms for Attitude and Heading Reference Systems Simone A. Ludwig North Dakota State University Fargo, ND, USA simone.ludwig@ndsu.edu Abstract An Attitude
More informationAn Intro to Gyros. FTC Team #6832. Science and Engineering Magnet - Dallas ISD
An Intro to Gyros FTC Team #6832 Science and Engineering Magnet - Dallas ISD Gyro Types - Mechanical Hubble Gyro Unit Gyro Types - Sensors Low cost MEMS Gyros High End Gyros Ring laser, fiber optic, hemispherical
More informationInertial Measurement Units I!
! Inertial Measurement Units I! Gordon Wetzstein! Stanford University! EE 267 Virtual Reality! Lecture 9! stanford.edu/class/ee267/!! Lecture Overview! coordinate systems (world, body/sensor, inertial,
More informationComputationally Efficient Visual-inertial Sensor Fusion for GPS-denied Navigation on a Small Quadrotor
Computationally Efficient Visual-inertial Sensor Fusion for GPS-denied Navigation on a Small Quadrotor Chang Liu & Stephen D. Prior Faculty of Engineering and the Environment, University of Southampton,
More informationOn Classification: An Empirical Study of Existing Algorithms Based on Two Kaggle Competitions
On Classification: An Empirical Study of Existing Algorithms Based on Two Kaggle Competitions CAMCOS Report Day December 9th, 2015 San Jose State University Project Theme: Classification The Kaggle Competition
More informationMio- x AHRS. Attitude and Heading Reference System. Engineering Specifications
General Description Mio- x AHRS Attitude and Heading Reference System Engineering Specifications Rev. G 2012-05-29 Mio-x AHRS is a tiny sensormodule consists of 9 degree of freedom motion sensors (3 accelerometers,
More informationGPS denied Navigation Solutions
GPS denied Navigation Solutions Krishnraj Singh Gaur and Mangal Kothari ksgaur@iitk.ac.in, mangal@iitk.ac.in https://www.iitk.ac.in/aero/mangal/ Intelligent Guidance and Control Laboratory Indian Institute
More informationSUPERVISED LEARNING METHODS. Stanley Liang, PhD Candidate, Lassonde School of Engineering, York University Helix Science Engagement Programs 2018
SUPERVISED LEARNING METHODS Stanley Liang, PhD Candidate, Lassonde School of Engineering, York University Helix Science Engagement Programs 2018 2 CHOICE OF ML You cannot know which algorithm will work
More information3D Transformations. CS 4620 Lecture Kavita Bala w/ prior instructor Steve Marschner. Cornell CS4620 Fall 2015 Lecture 11
3D Transformations CS 4620 Lecture 11 1 Announcements A2 due tomorrow Demos on Monday Please sign up for a slot Post on piazza 2 Translation 3 Scaling 4 Rotation about z axis 5 Rotation about x axis 6
More informationInertial Navigation Systems
Inertial Navigation Systems Kiril Alexiev University of Pavia March 2017 1 /89 Navigation Estimate the position and orientation. Inertial navigation one of possible instruments. Newton law is used: F =
More informationSphero Lightning Lab Cheat Sheet
Actions Tool Description Variables Ranges Roll Combines heading, speed and time variables to make the robot roll. Duration Speed Heading (0 to 999999 seconds) (degrees 0-359) Set Speed Sets the speed of
More informationSensor-fusion Demo Documentation
Sensor-fusion Demo Documentation Release 1.2 Alexander Pacha Aug 13, 2018 Contents: 1 Euler Angles 3 2 Installation 5 3 Contribute 7 4 License 9 i ii Sensor-fusion Demo Documentation, Release 1.2 This
More informationCMMotionManager Overview
MSDOSX Core Motion CMMotionManager Overview A CMMotionManager object is the gateway Accelerometer data Rotation-rate data Magnetometer data Other device-motion data such as attitude Create one instance
More informationCOSC160: Detection and Classification. Jeremy Bolton, PhD Assistant Teaching Professor
COSC160: Detection and Classification Jeremy Bolton, PhD Assistant Teaching Professor Outline I. Problem I. Strategies II. Features for training III. Using spatial information? IV. Reducing dimensionality
More informationTesting the Possibilities of Using IMUs with Different Types of Movements
137 Testing the Possibilities of Using IMUs with Different Types of Movements Kajánek, P. and Kopáčik A. Slovak University of Technology, Faculty of Civil Engineering, Radlinského 11, 81368 Bratislava,
More informationApplied Statistics for Neuroscientists Part IIa: Machine Learning
Applied Statistics for Neuroscientists Part IIa: Machine Learning Dr. Seyed-Ahmad Ahmadi 04.04.2017 16.11.2017 Outline Machine Learning Difference between statistics and machine learning Modeling the problem
More informationNetwork Traffic Measurements and Analysis
DEIB - Politecnico di Milano Fall, 2017 Sources Hastie, Tibshirani, Friedman: The Elements of Statistical Learning James, Witten, Hastie, Tibshirani: An Introduction to Statistical Learning Andrew Ng:
More informationE80. Experimental Engineering. Lecture 9 Inertial Measurement
Lecture 9 Inertial Measurement http://www.volker-doormann.org/physics.htm Feb. 19, 2013 Christopher M. Clark Where is the rocket? Outline Sensors People Accelerometers Gyroscopes Representations State
More informationDevelopment of a Ground Based Cooperating Spacecraft Testbed for Research and Education
DIPARTIMENTO DI INGEGNERIA INDUSTRIALE Development of a Ground Based Cooperating Spacecraft Testbed for Research and Education Mattia Mazzucato, Sergio Tronco, Andrea Valmorbida, Fabio Scibona and Enrico
More informationMachine Learning. Chao Lan
Machine Learning Chao Lan Machine Learning Prediction Models Regression Model - linear regression (least square, ridge regression, Lasso) Classification Model - naive Bayes, logistic regression, Gaussian
More informationMe 3-Axis Accelerometer and Gyro Sensor
Me 3-Axis Accelerometer and Gyro Sensor SKU: 11012 Weight: 20.00 Gram Description: Me 3-Axis Accelerometer and Gyro Sensor is a motion processing module. It can use to measure the angular rate and the
More informationLarge-Scale Lasso and Elastic-Net Regularized Generalized Linear Models
Large-Scale Lasso and Elastic-Net Regularized Generalized Linear Models DB Tsai Steven Hillion Outline Introduction Linear / Nonlinear Classification Feature Engineering - Polynomial Expansion Big-data
More informationThorsten Joachims Then: Universität Dortmund, Germany Now: Cornell University, USA
Retrospective ICML99 Transductive Inference for Text Classification using Support Vector Machines Thorsten Joachims Then: Universität Dortmund, Germany Now: Cornell University, USA Outline The paper in
More informationnavigation Isaac Skog
Foot-mounted zerovelocity aided inertial navigation Isaac Skog skog@kth.se Course Outline 1. Foot-mounted inertial navigation a. Basic idea b. Pros and cons 2. Inertial navigation a. The inertial sensors
More informationIntroduction to Data Science. Introduction to Data Science with Python. Python Basics: Basic Syntax, Data Structures. Python Concepts (Core)
Introduction to Data Science What is Analytics and Data Science? Overview of Data Science and Analytics Why Analytics is is becoming popular now? Application of Analytics in business Analytics Vs Data
More informationLPMS-B Reference Manual
INTRODUCTION LPMS-B Reference Manual Version 1.1.0 2013 LP-RESEARCH www.lp-research.com 1 INTRODUCTION I. INTRODUCTION Welcome to the LP-RESEARCH Motion Sensor Bluetooth version (LPMS-B) User s Manual!
More informationPackage RAHRS. July 18, 2015
Package RAHRS July 18, 2015 Type Package Title Data Fusion Filters for Attitude Heading Reference System (AHRS) with Several Variants of the Kalman Filter and the Mahoney and Madgwick Filters Version 1.0.2
More informationLPMS-B Reference Manual
INTRODUCTION LPMS-B Reference Manual Version 1.0.12 2012 LP-RESEARCH 1 INTRODUCTION I. INTRODUCTION Welcome to the LP-RESEARCH Motion Sensor Bluetooth version (LPMS-B) User s Manual! In this manual we
More informationOverview. Non-Parametrics Models Definitions KNN. Ensemble Methods Definitions, Examples Random Forests. Clustering. k-means Clustering 2 / 8
Tutorial 3 1 / 8 Overview Non-Parametrics Models Definitions KNN Ensemble Methods Definitions, Examples Random Forests Clustering Definitions, Examples k-means Clustering 2 / 8 Non-Parametrics Models Definitions
More informationHuman Activity Recognition via Cellphone Sensor Data
Human Activity Recognition via Cellphone Sensor Data Wei Ji, Heguang Liu, Jonathan Fisher Abstract The purpose of this project is to identify human activities while using cell phones via mobile sensor
More informationUsing Machine Learning to Identify Security Issues in Open-Source Libraries. Asankhaya Sharma Yaqin Zhou SourceClear
Using Machine Learning to Identify Security Issues in Open-Source Libraries Asankhaya Sharma Yaqin Zhou SourceClear Outline - Overview of problem space Unidentified security issues How Machine Learning
More informationOverview. Background. Intelligence at the Edge. Learning at the Edge: Challenges and Brainstorming. Amazon Alexa Smart Home!
Overview Background Intelligence at the Edge Samsung Research Learning at the Edge: Challenges and Brainstorming Amazon Alexa Smart Home! Background Ph.D. at UW CSE RFID, Mobile, Sensors, Data Nokia Research
More informationCS5670: Computer Vision
CS5670: Computer Vision Noah Snavely Lecture 33: Recognition Basics Slides from Andrej Karpathy and Fei-Fei Li http://vision.stanford.edu/teaching/cs231n/ Announcements Quiz moved to Tuesday Project 4
More informationQuaternions & Rotation in 3D Space
Quaternions & Rotation in 3D Space 1 Overview Quaternions: definition Quaternion properties Quaternions and rotation matrices Quaternion-rotation matrices relationship Spherical linear interpolation Concluding
More information9 Degrees of Freedom Inertial Measurement Unit with AHRS [RKI-1430]
9 Degrees of Freedom Inertial Measurement Unit with AHRS [RKI-1430] Users Manual Robokits India info@robokits.co.in http://www.robokitsworld.com Page 1 This 9 Degrees of Freedom (DOF) Inertial Measurement
More informationSpring Lecture 9 Lecturer: Omid Jafarinezhad
Mobile Programming Sharif University of Technology Spring 2016 - Lecture 9 Lecturer: Omid Jafarinezhad Sensors Overview Most Android-powered devices have built-in sensors that measure motion, orientation,
More informationPython With Data Science
Course Overview This course covers theoretical and technical aspects of using Python in Applied Data Science projects and Data Logistics use cases. Who Should Attend Data Scientists, Software Developers,
More informationKeeping a Good Attitude: A Quaternion-Based Orientation Filter for IMUs and MARGs
City University of New York (CUNY) CUNY Academic Works Publications and Research City College of New York August 2015 Keeping a Good Attitude: A Quaternion-Based Orientation Filter for IMUs and MARGs Roberto
More informationUser Manual for TeraRanger Hub Evo
User Manual for TeraRanger Hub Evo Hardware revision 10 Firmware revision 100 1/24 Table of contents: 1 Introduction 3 2 Mechanical Integration 3 21 Mechanical Design 3 21 Compatibility with TeraRanger
More informationSupport Vector Machines + Classification for IR
Support Vector Machines + Classification for IR Pierre Lison University of Oslo, Dep. of Informatics INF3800: Søketeknologi April 30, 2014 Outline of the lecture Recap of last week Support Vector Machines
More informationMovit System G1 WIRELESS MOTION DEVICE SYSTEM
Movit System G1 WIRELESS MOTION DEVICE SYSTEM 1 INTRODUCTION The Movit System G1 incorporates multiple wireless motion devices (Movit G1) with the Dongle G1 station, dedicated software and a set of full
More informationUsing SensorTag as a Low-Cost Sensor Array for AutoCAD
Using SensorTag as a Low-Cost Sensor Array for AutoCAD Kean Walmsley Autodesk SD5013 In 2012 Texas Instruments Inc. launched the SensorTag, a $25 sensor array that communicates via Bluetooth Smart (also
More informationLecture 9: Support Vector Machines
Lecture 9: Support Vector Machines William Webber (william@williamwebber.com) COMP90042, 2014, Semester 1, Lecture 8 What we ll learn in this lecture Support Vector Machines (SVMs) a highly robust and
More informationPreface to the Second Edition. Preface to the First Edition. 1 Introduction 1
Preface to the Second Edition Preface to the First Edition vii xi 1 Introduction 1 2 Overview of Supervised Learning 9 2.1 Introduction... 9 2.2 Variable Types and Terminology... 9 2.3 Two Simple Approaches
More informationSelf Lane Assignment Using Smart Mobile Camera For Intelligent GPS Navigation and Traffic Interpretation
For Intelligent GPS Navigation and Traffic Interpretation Tianshi Gao Stanford University tianshig@stanford.edu 1. Introduction Imagine that you are driving on the highway at 70 mph and trying to figure
More informationPerformance Evaluation of Various Classification Algorithms
Performance Evaluation of Various Classification Algorithms Shafali Deora Amritsar College of Engineering & Technology, Punjab Technical University -----------------------------------------------------------***----------------------------------------------------------
More informationCollective classification in network data
1 / 50 Collective classification in network data Seminar on graphs, UCSB 2009 Outline 2 / 50 1 Problem 2 Methods Local methods Global methods 3 Experiments Outline 3 / 50 1 Problem 2 Methods Local methods
More informationTizen Sensors (Tizen Ver. 2.3)
Tizen Sensors (Tizen Ver. 2.3) Spring 2015 Soo Dong Kim, Ph.D. Professor, Department of Computer Science Software Engineering Laboratory Soongsil University Office 02-820-0909 Mobile 010-7392-2220 sdkim777@gmail.com
More informationApplying Supervised Learning
Applying Supervised Learning When to Consider Supervised Learning A supervised learning algorithm takes a known set of input data (the training set) and known responses to the data (output), and trains
More informationKeyword Extraction by KNN considering Similarity among Features
64 Int'l Conf. on Advances in Big Data Analytics ABDA'15 Keyword Extraction by KNN considering Similarity among Features Taeho Jo Department of Computer and Information Engineering, Inha University, Incheon,
More information3D Object Recognition using Multiclass SVM-KNN
3D Object Recognition using Multiclass SVM-KNN R. Muralidharan, C. Chandradekar April 29, 2014 Presented by: Tasadduk Chowdhury Problem We address the problem of recognizing 3D objects based on various
More informationOnline Pose Classification and Walking Speed Estimation using Handheld Devices
Online Pose Classification and Walking Speed Estimation using Handheld Devices Jun-geun Park MIT CSAIL Joint work with: Ami Patel (MIT EECS), Jonathan Ledlie (Nokia Research), Dorothy Curtis (MIT CSAIL),
More informationConvolution Neural Networks for Chinese Handwriting Recognition
Convolution Neural Networks for Chinese Handwriting Recognition Xu Chen Stanford University 450 Serra Mall, Stanford, CA 94305 xchen91@stanford.edu Abstract Convolutional neural networks have been proven
More informationTutorial on Machine Learning Tools
Tutorial on Machine Learning Tools Yanbing Xue Milos Hauskrecht Why do we need these tools? Widely deployed classical models No need to code from scratch Easy-to-use GUI Outline Matlab Apps Weka 3 UI TensorFlow
More informationVCIT Visually Corrected Inertial Tracking
Maximilian Eibl, Martin Gaedke. (Hrsg.): INFORMATIK 2017, Lecture Lecture Notes Notes in Informatics in Informatics (LNI), (LNI), Gesellschaft Gesellschaft für für Informatik, Informatik, Bonn Bonn 2017
More informationPredictive Analytics using Teradata Aster Scoring SDK
Predictive Analytics using Teradata Aster Scoring SDK Faraz Ahmad Software Engineer, Teradata #TDPARTNERS16 GEORGIA WORLD CONGRESS CENTER At Teradata, we believe. Analytics and data unleash the potential
More informationHeeyoul (Henry) Choi. Dept. of Computer Science Texas A&M University
Heeyoul (Henry) Choi Dept. of Computer Science Texas A&M University hchoi@cs.tamu.edu Facial Action Coding System Overview Optic Flow Analysis Local Velocity Extraction Local Smoothing Holistic Analysis
More informationHCOMM Reference Manual
HCOMM Reference Manual Document Number: 1000-2984 Document Revision: 0.3.2 Date: December 23, 2013 November 21, 2013 1000-2984 Revision 0.3.1 1 / 49 Copyright 2012, Hillcrest Laboratories, Inc. All rights
More informationRandom Forest A. Fornaser
Random Forest A. Fornaser alberto.fornaser@unitn.it Sources Lecture 15: decision trees, information theory and random forests, Dr. Richard E. Turner Trees and Random Forests, Adele Cutler, Utah State University
More informationSupervised vs unsupervised clustering
Classification Supervised vs unsupervised clustering Cluster analysis: Classes are not known a- priori. Classification: Classes are defined a-priori Sometimes called supervised clustering Extract useful
More informationR (2) Data analysis case study using R for readily available data set using any one machine learning algorithm.
Assignment No. 4 Title: SD Module- Data Science with R Program R (2) C (4) V (2) T (2) Total (10) Dated Sign Data analysis case study using R for readily available data set using any one machine learning
More informationMachine Learning. Classification
10-701 Machine Learning Classification Inputs Inputs Inputs Where we are Density Estimator Probability Classifier Predict category Today Regressor Predict real no. Later Classification Assume we want to
More informationActivity recognition and energy expenditure estimation
Activity recognition and energy expenditure estimation A practical approach with Python WebValley 2015 Bojan Milosevic Scope Goal: Use wearable sensors to estimate energy expenditure during everyday activities
More informationAdaptive Dropout Training for SVMs
Department of Computer Science and Technology Adaptive Dropout Training for SVMs Jun Zhu Joint with Ning Chen, Jingwei Zhuo, Jianfei Chen, Bo Zhang Tsinghua University ShanghaiTech Symposium on Data Science,
More informationSupervised Learning Classification Algorithms Comparison
Supervised Learning Classification Algorithms Comparison Aditya Singh Rathore B.Tech, J.K. Lakshmipat University -------------------------------------------------------------***---------------------------------------------------------
More informationRESEARCH ON THE APPLICATION OF STABLE ATTITUDE ALGORITHM BASED ON DATA FUSION OF MULTI- DIMENSIONAL MEMS INERTIAL SENSORS
U.P.B. Sci. Bull., Series C, Vol. 79, Iss. 2, 2017 ISSN 2286-3540 RESEARCH ON THE APPLICATION OF STABLE ATTITUDE ALGORITHM BASED ON DATA FUSION OF MULTI- DIMENSIONAL MEMS INERTIAL SENSORS Liu XIA 1, Qiao
More informationMargarita Grinvald. Gesture recognition for Smartphones/Wearables
Margarita Grinvald Gesture recognition for Smartphones/Wearables Gestures hands, face, body movements non-verbal communication human interaction 2 Gesture recognition interface with computers increase
More informationCollaboration is encouraged among small groups (e.g., 2-3 students).
Assignments Policies You must typeset, choices: Word (very easy to type math expressions) Latex (very easy to type math expressions) Google doc Plain text + math formula Your favorite text/doc editor Submit
More informationBatch-Incremental vs. Instance-Incremental Learning in Dynamic and Evolving Data
Batch-Incremental vs. Instance-Incremental Learning in Dynamic and Evolving Data Jesse Read 1, Albert Bifet 2, Bernhard Pfahringer 2, Geoff Holmes 2 1 Department of Signal Theory and Communications Universidad
More informationClassification and Detection in Images. D.A. Forsyth
Classification and Detection in Images D.A. Forsyth Classifying Images Motivating problems detecting explicit images classifying materials classifying scenes Strategy build appropriate image features train
More informationMEAM 620: HW 1. Sachin Chitta Assigned: January 10, 2007 Due: January 22, January 10, 2007
MEAM 620: HW 1 Sachin Chitta (sachinc@grasp.upenn.edu) Assigned: January 10, 2007 Due: January 22, 2006 January 10, 2007 1: MATLAB Programming assignment Using MATLAB, write the following functions: 1.
More informationLecture 13 Visual Inertial Fusion
Lecture 13 Visual Inertial Fusion Davide Scaramuzza Course Evaluation Please fill the evaluation form you received by email! Provide feedback on Exercises: good and bad Course: good and bad How to improve
More informationAutonomous Navigation for Flying Robots
Computer Vision Group Prof. Daniel Cremers Autonomous Navigation for Flying Robots Lecture 3.1: 3D Geometry Jürgen Sturm Technische Universität München Points in 3D 3D point Augmented vector Homogeneous
More informationA novel approach to motion tracking with wearable sensors based on Probabilistic Graphical Models
A novel approach to motion tracking with wearable sensors based on Probabilistic Graphical Models Emanuele Ruffaldi Lorenzo Peppoloni Alessandro Filippeschi Carlo Alberto Avizzano 2014 IEEE International
More informationLouis Fourrier Fabien Gaie Thomas Rolf
CS 229 Stay Alert! The Ford Challenge Louis Fourrier Fabien Gaie Thomas Rolf Louis Fourrier Fabien Gaie Thomas Rolf 1. Problem description a. Goal Our final project is a recent Kaggle competition submitted
More informationContents. Preface to the Second Edition
Preface to the Second Edition v 1 Introduction 1 1.1 What Is Data Mining?....................... 4 1.2 Motivating Challenges....................... 5 1.3 The Origins of Data Mining....................
More informationClassification Algorithms in Data Mining
August 9th, 2016 Suhas Mallesh Yash Thakkar Ashok Choudhary CIS660 Data Mining and Big Data Processing -Dr. Sunnie S. Chung Classification Algorithms in Data Mining Deciding on the classification algorithms
More informationA problem - too many features. TDA 231 Dimension Reduction: PCA. Features. Making new features
A problem - too many features TDA 1 Dimension Reduction: Aim: To build a classifier that can diagnose leukaemia using Gene expression data. Data: 7 healthy samples,11 leukaemia samples (N = 8). Each sample
More informationCAMCOS Report Day. December 9 th, 2015 San Jose State University Project Theme: Classification
CAMCOS Report Day December 9 th, 2015 San Jose State University Project Theme: Classification On Classification: An Empirical Study of Existing Algorithms based on two Kaggle Competitions Team 1 Team 2
More informationEEG Imaginary Body Kinematics Regression. Justin Kilmarx, David Saffo, and Lucien Ng
EEG Imaginary Body Kinematics Regression Justin Kilmarx, David Saffo, and Lucien Ng Introduction Brain-Computer Interface (BCI) Applications: Manipulation of external devices (e.g. wheelchairs) For communication
More informationInertial Measurement Units in Gait Analysis Applications Questions, Suggestions and Answers
Inertial Measurement Units in Gait Analysis Applications Questions, Suggestions and Answers Harald Loose 1, Katja Orlowski 1 and Robert Amann 2 1 Fachhochschule Brandenburg, Magdeburger Str. 50, 14770
More informationGood Cell, Bad Cell: Classification of Segmented Images for Suitable Quantification and Analysis
Cell, Cell: Classification of Segmented Images for Suitable Quantification and Analysis Derek Macklin, Haisam Islam, Jonathan Lu December 4, 22 Abstract While open-source tools exist to automatically segment
More informationPrognosis of Lung Cancer Using Data Mining Techniques
Prognosis of Lung Cancer Using Data Mining Techniques 1 C. Saranya, M.Phil, Research Scholar, Dr.M.G.R.Chockalingam Arts College, Arni 2 K. R. Dillirani, Associate Professor, Department of Computer Science,
More information