Ensuring Home-based Rehabilitation Exercise by Using Kinect and Fuzzified Dynamic Time Warping Algorithm Qiao Zhang.

Slides:



Advertisements
Similar presentations
Learning Trajectory Patterns by Clustering: Comparative Evaluation Group D.
Advertisements

Word Spotting DTW.
A Novel Approach of Assisting the Visually Impaired to Navigate Path and Avoiding Obstacle-Collisions.
KINECT REHABILITATION
ACCELEROMETER-BASED, GRIP-FREE CONTROLLER Tyler (You-Chi) Le ECE4220 Fall 2011 Dr. DeSouza December 5 th, 2011.
Project Proposal.
Page 1 GAME-BASED MOBILITY TRAINING AND MOTIVATION OF SENIOR CITIZENS Project Number: AAL The Usefulness of Activity Trackers in Elderly with.
Continuous Value Enhancement Process
EHealth Workshop 2003Virginia Tech e-Textiles Group An E-Textile System for Motion Analysis Mark Jones, Thurmon Lockhart, and Thomas Martin Virginia Tech.
Probability-based Dynamic Time Warping for Gesture Recognition on RGB-D data All rights reserved HuBPA© Human Pose Recovery and Behavior Analysis Group.
Energy Characterization and Optimization of Embedded Data Mining Algorithms: A Case Study of the DTW-kNN Framework Huazhong University of Science & Technology,
USign—A Security Enhanced Electronic Consent Model Yanyan Li 1 Mengjun Xie 1 Jiang Bian 2 1 University of Arkansas at Little Rock 2 University of Arkansas.
A Novel Scheme for Video Similarity Detection Chu-Hong Hoi, Steven March 5, 2003.
Introduction to Data-driven Animation Jinxiang Chai Computer Science and Engineering Texas A&M University.
1 Budgeting Dr. Varadraj Bapat Module 14.. Management Accounting Dr. Varadraj Bapat, IIT Mumbai 2 Index  Introduction  Objectives  Advantages  Components.
Learning the space of time warping functions for Activity Recognition Function-Space of an Activity Ashok Veeraraghavan Rama Chellappa Amit K. Roy-Chowdhury.
The Role of Business Research Theory Building
Hand Signals Recognition from Video Using 3D Motion Capture Archive Tai-Peng Tian Stan Sclaroff Computer Science Department B OSTON U NIVERSITY I. Introduction.
Handouts Software Testing and Quality Assurance Theory and Practice Chapter 11 System Test Design
Jan SedmidubskySeptember 23, 2014Motion Retrieval for Security Applications Jan Sedmidubsky Jakub Valcik Pavel Zezula Motion Retrieval for Security Applications.
Purpose:  Provided students with an opportunity to learn how to improve or maintain their physical fitness through novel technological based tools instead.
FUZZY LOGIC Babu Appat. OVERVIEW What is Fuzzy Logic? Where did it begin? Fuzzy Logic vs. Neural Networks Fuzzy Logic in Control Systems Fuzzy Logic in.
Business Process Performance Prediction on a Tracked Simulation Model Andrei Solomon, Marin Litoiu– York University.
Stroke Rehabilitation Engineering: Robotic Therapy By: Dana Demers.
Educational Software using Audio to Score Alignment Antoine Gomas supervised by Dr. Tim Collins & Pr. Corinne Mailhes 7 th of September, 2007.
Qualitative approximation to Dynamic Time Warping similarity between time series data Blaž Strle, Martin Možina, Ivan Bratko Faculty of Computer and Information.
Miguel Reyes 1,2, Gabriel Dominguez 2, Sergio Escalera 1,2 Computer Vision Center (CVC) 1, University of Barcelona (UB) 2
INTRODUCTION Generally, after stroke, patient usually has cerebral cortex functional barrier, for example, the impairment in the following capabilities,
Learning to Associate: HybridBoosted Multi-Target Tracker for Crowded Scene Present by 陳群元.
1 Chapter 4: Selection Structures. In this chapter, you will learn about: – Selection criteria – The if-else statement – Nested if statements – The switch.
Together.Today.Tomorrow. The BLUES Project Karen C. Fox, PhD Chief Executive Officer.
Serious Games for Physical Rehabilitation Designing Highly Configurable and Adaptable Games Department of Electronics and Informatics (ETRO),
Experimental Results ■ Observations:  Overall detection accuracy increases as the length of observation window increases.  An observation window of 100.
Online Kinect Handwritten Digit Recognition Based on Dynamic Time Warping and Support Vector Machine Journal of Information & Computational Science, 2015.
Fuzzy Reinforcement Learning Agents By Ritesh Kanetkar Systems and Industrial Engineering Lab Presentation May 23, 2003.
Pattern Discovery of Fuzzy Time Series for Financial Prediction -IEEE Transaction of Knowledge and Data Engineering Presented by Hong Yancheng For COMP630P,
Protein motif extraction with neuro-fuzzy optimization Bill C. H. Chang and Author : Bill C. H. Chang and Saman K. Halgamuge Saman K. Halgamuge Adviser.
MROrder: Flexible Job Ordering Optimization for Online MapReduce Workloads School of Computer Engineering Nanyang Technological University 30 th Aug 2013.
Stream Monitoring under the Time Warping Distance Yasushi Sakurai (NTT Cyber Space Labs) Christos Faloutsos (Carnegie Mellon Univ.) Masashi Yamamuro (NTT.
Experimentation in Computer Science (Part 2). Experimentation in Software Engineering --- Outline  Empirical Strategies  Measurement  Experiment Process.
Technology Traditional Kinect Based Therapy Exercises Patient have the option to do typical therapy exercise that would normally be performed at an in-office.
Properties Incompleteness Evaluation by Functional Verification IEEE TRANSACTIONS ON COMPUTERS, VOL. 56, NO. 4, APRIL
Using Cross-Media Correlation for Scene Detection in Travel Videos.
Error Explanation with Distance Metrics Authors: Alex Groce, Sagar Chaki, Daniel Kroening, and Ofer Strichman International Journal on Software Tools for.
Similarity Measurement and Detection of Video Sequences Chu-Hong HOI Supervisor: Prof. Michael R. LYU Marker: Prof. Yiu Sang MOON 25 April, 2003 Dept.
Data Analytics Framework for A Game-based Rehabilitation System Jiongqian (Albert) Liang*, David Fuhry*, David Maung*, Alexandra Borstad +, Roger Crawfis*,
Verification vs. Validation Verification: "Are we building the product right?" The software should conform to its specification.The software should conform.
An E-Textiles. Virginia Tech e-Textiles Group Design of an e-textile computer architecture – Networking – Fault tolerance – Power aware – Programming.
UWave: Accelerometer-based personalized gesture recognition and its applications Tae-min Hwang.
C++ for Engineers and Scientists Second Edition Chapter 4 Selection Structures.
Control of Dynamic Discrete-Event Systems Lenko Grigorov Master’s Thesis, QU supervisor: Dr. Karen Rudie.
Introduction to Machine Learning, its potential usage in network area,
Automated Evaluation of Physical Therapy Exercises by Multi-Template Dynamic Time Warping of Wearable Sensor Signals Aras Yurtman and Billur Barshan.
2 DOF Upper Limb Exoskeleton Trainer for Elderly People
Fitness and Conditioning
EXACT – Exergaming for active healthy ageing and rehabilitation
Chapter 1: Introduction to Systems Analysis and Design
Aras Yurtman and Billur Barshan
Real-time Wall Outline Extraction for Redirected Walking
Structural testing, Path Testing
Majkowska University of California. Los Angeles
NBKeyboard: An Arm-based Word-gesture keyboard
Parallelizing Dynamic Time Warping
Automated Evaluation of Physical Therapy Exercises by Multi-Template Dynamic Time Warping of Wearable Sensor Signals Aras Yurtman and Billur Barshan.
Online Graph-Based Tracking
Aras Yurtman and Billur Barshan
Chapter 1: Introduction to Systems Analysis and Design
Communication Driven Remapping of Processing Element (PE) in Fault-tolerant NoC-based MPSoCs Chia-Ling Chen, Yen-Hao Chen and TingTing Hwang Department.
Measuring the Similarity of Rhythmic Patterns
Auditory Morphing Weyni Clacken
Presentation transcript:

Ensuring Home-based Rehabilitation Exercise by Using Kinect and Fuzzified Dynamic Time Warping Algorithm Qiao Zhang

Outline Concept Introduction Background and Motivation Related Work Research Methodology Implementation Conclusion

Concept Introduction

Rehabilitation Treatments and exercises concerned with remediation of impairments and disabilities.

Fuzzy Logic In contrast with traditional logic theory, where traditional binary sets have two-valued logic: true or false, fuzzy logic variables may have a truth value that ranges between 0 and 1.

Background and Motivation

Rehabilitation In the case of rehabilitation, a traditional therapy process generally conducted in a hospital setting and requires direct supervision of a skilled caregiver. The aim of home-based rehabilitation is to provide an in-home alternative to in hospital rehabilitation. Home- based rehabilitation allows for great flexibility so that patients can tailor their program of rehabilitation and conform to individual schedules.

Kinect Preprocessing that detects human object silhouette and extracts silhouette descriptors Pose estimation that quantitatively characterizes and localizes human limbs in each frame.

Dynamic Time Warping Algorithm In time series analysis, dynamic time warping (DTW) is an algorithm for measuring similarity between two temporal sequences which may vary in time or speed. They utilize the benefit of DTW algorithm to solve comparing two sequences which have different time length in order to determine the similarity between the standard and the patient exercise.

Fuzzy Logic When physicians evaluate trajectory and speed of rehabilitation exercise mainly based on their experience and subjective evaluation without utilizing more precise and measurable computer value. Therefore, they cannot set a value of trajectory and speed to evaluate result using traditional logic theory.

Related Work

Rehabilitation with Device Help Many researches use industrial motion sensors and Nintendo Wii Remote to assist physicians and patients. (x) Uncomfortable and boring: motion sensors have some defects, such as patients need to fasten it on limbs, hold it in the hands or wear it on the body.

Kinect Applications These Kinect games can let users to do exercise in their home, but the wrong exercise leads to sports injuries. Previous work proved that patients can get more motivation and outcome of rehabilitation with Kinect. But their rehabilitation systems are too specific.

Fuzzy Logic There are a handful of existing systems that utilize fuzzy logic evaluation. The accuracy can be as high as 80-90%. Further, the application of fuzzy set theory can provide an effective way to formulate decision problems in a fuzzy environment where the information available is subjective and imprecise.

Research Methodology

Phases A tailored exercise is performed by the patient and recorded under the supervision of a physician by using the proposed KEHR system. The evaluation can then be achieved by exploring the differences derived from two factors: 1. Trajectory disparity: the motional path created by each joint over time 2. Speed variation: the time consumption in completing a designated exercise.

The KEHR Architecture

Kinect-based Rehabilitation Management Module Manage rehabilitation process Capture user performed exercise under supervision of a professional Replay the exercise for user to execute at home Evaluate the performance of the exercise.

Capture

Evaluate - Overview

Evaluate - DTW Given two time series A = (a1, a2, …, am) and B = (b1, b2, …, bn) where ai = ( xi, yi, zi ), i=1,…,m; bj = ( xj, yj, zj ), j=1,…,n; To align two sequences using DTW they construct an n-by- m matrix where the (ith, jth) element of the matrix contains the Euclidean distance between the two points ai and bj. A warping path P is a contiguous set of matrix elements that defines a mapping between A and B. The warping path has too satisfy 3 criteria: Boundary condition, Continuity, Monotonic condition

Evaluate – DTW example

But what is DTW distance?

Evaluate – DTW example {(a6,b5) (a5,b5) (a4,b4) (a3,b3) (a2,b2) (a1,b1)}

Evaluate - Fuzzy Inference The Euclidean distance Ed of the optimal path is calculated for serving as a metric of disparity between A and B.

Implementation

Conclusion

They tested the KEHR on three different shoulder rehabilitation exercises performed by four different users. The evaluation by KEHR agrees with the physician with the average of 80.01%. This result shows that KEHR is suitable for home-based rehabilitation exercise.

Using the Kinect to Encourage Older Adults to Exercise

Motivation Though older adults are willing to exercise, they fear injury, which is a hindrance. They would prefer exercising at their convenience in the safety of their homes and to use methods that are cost-effective and convenient to them. Make exercise fun, such as through a game.

Data Gathering Discussion with Field Expert The prime problem areas were identified as: (a) flexibility, (b) strengthening, (c) walking, and (d) balance. Focus Group The discussion revealed that all of the participants walked on a regular basis and enjoyed the activity and saw it as pleasurable. However, they were also intimidated to take a walk by themselves because of safety issues.

Design and Prototype

Questions? Thanks for listening!