SlideShare a Scribd company logo
Exercise repetition detection
for resistance training based
on smartphones,
+ Pers. Ubiquit. Comput.
(2013),
- Igor Pernek et al,
/ 맹욱재
x 2015 Rainy Fall
UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 2
Contents
1. Intro
2. Related Works
3. System & Algorithm
4. Evaluation
UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 3
Intro - Why this paper?
WookFit : Wearable Device for Breast Cancer Survivors doing Resistance ExcersiceElastic-band stretching Counter
UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 4
Intro - Why this paper?(Cont.)
Key word for searching paper
Breast Cancer Rehabilitations
Resistance Excersise(traning)
Home-based Excersise(traning)
Lymphedema
Theraband(Resistance band)
Wearable
IoT
Quality of Life
Smartphone Application
Accelerometer
UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 5
Key word for searching paper
Breast Cancer Rehabilitations
Resistance Excersise(traning)
Home-based Excersise(traning)
Lymphedema
Theraband(Resistance band)
Wearable
IoT
Quality of Life
Smartphone Application
Accelerometer
Intro - Why this paper?(Cont.)
UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 6
Intro - Take away
1. Dynamic Time Warping algorithm can accurately count
the number of repetition, duration.
2. Giving real time feedback on Quality of Performance 

can be done using duration, start, end time of repetition
UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 7
Intro - Abstract
Problem
Solution
Most of systems focus only on cardio exercises such as running and cycling
Exploit smartphones to support leisure activities with a focus on resistance training.
Off-the-shelf smartphones without additional external sensors can be leveraged 

to capture resistance training data and to give reliable training feedback
Algorithm
Dynamic Time Warping based algorithm to detect individual resistance training
repetitions from the smartphone’s acceleration stream
UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 8
Intro - Abstract
Feedback in detail
Providing feedback about the quality of repetitions, use the duration of an
individual repetition and analyze how accurately start and end times of repetitions
can be detected by our algorithm
In terms of the number of correctly recognized repetitions. 

3,598 repetitions performed by 10 volunteers exercising in 2 distinct scenarios 

a gym and a natural environment.
The results show an overall repetition miscount rate of about 1 % overall
temporal detection error of about 11 % of individual repetition duration.
Evalution
UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 9
Related Works
Manual input problem
manual input is cumbersome, taking notes about resistance training is often avoided,
negatively affect people’s activity levels and decrease their motivation for regular training
https://www.jefit.com/products/androidpro/index.php
https://play.google.com/store/apps/details?id=com.namuan.health&hl=ko
UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 10
Related Works - Fitlinxx
https://www.youtube.com/watch?time_continue=303&v=BfnPogUokKs
1. very expensive, as the gym has to be equipped with specific exercise machines and
infrastructure, and has therefore not gained broader popularity
2. have to log in to the system prior to performing any exercise,
UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 11
Related Works - Recognizing Upper Body Postures using Textile Strain Sensors
UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 12
Related Works- The Virtual Trainer: Supervising Movements Through a Wearable Wireless Sensor Network
the algorithm relies on exercise specific
features, such as the position of the elbow
during the biceps curl exercise, and can
therefore not be easily applied to a general
resistance training exercise.
UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 13
Related Works- Implementation and evaluation of the personal wellness coach
The acceleration stream-laptop computer
threshold-based low-pass filtering algorithm:
each transition from resting to exercise state to
count the number of repetitions. the number of
time units in each state is analyzed to detect
struggling during exercise execution. all the
repetitions have a similar single peak acceleration
footprint, which is not true for exercises
performed in different environments
UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 14
Related Works -Tracking Free-Weight Exercises
feature phone + 2 external accelerometer sensors.
data from a glove & chest belt, only derive info
for a limited set of free-weight exercises.
simple peak detection algorithms that are 

no detect a repetition’s start and end time 

->lack capabilities for providing qualitative
feedback based on the duration of repetitions.
UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 15
Related Works - myHealthAssistant: A Phone-based Body Sensor
Network that Captures the Wearer’s Exercises throughout the Day
advance ‘Tracking Free-Weight Exercises' by
making the repetition detection algorithm robust
to different exercising speeds
UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 16
Related Works- What can an arm holster worn smart phone do for activity recognition?
arm worn smartphones to
recognize a number of upper
body resistance training
exercises from a continuous
acceleration stream. Main
focus lies on spotting series
of exercises, repetitions-
peak detection. start & end
times of individual
repetitions cannot be
detected.
UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 17
Related Works
Missing information
1) not ubiquitous -> mobile(smartphone)
2) targeted to a set of specific exercises 

-> broader set of exercises, performed using different types of equipment
3) not support fine-grained tracking of individual repetitions. 

important to give feedback about the correctness and quality of exercising

-> by detection of duration of individual repetitions.
WookFit
1) mobile(smartphone) + Wearable device
2) targeted to a set of specific exercises
3) not support fine-grained tracking of individual repetitions.
UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 18
System - Requirement
1) Should not add high extra cost nor demand the cumbersome installation of
additional sensors and tools

=> off-the-shelf smartphones
2) Easy to use interface, be encouraging by suggesting particular exercises, and give
feedback on the exercising performance as well as the training progress

=> Quality of Performance Feedback
3) Usable in different environments including gyms and natural environments and
cover a wide range of exercises

=> Constrained(gym, fitness center) + Unconstrained(free-weight, resistance band,
body weight)
UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 19
System - Resistance Training Assistant
UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 20
System - Resistance Training Assistant
1) Download different training plans and exercises from an online training database.
2) The application proposes exercises to perform along with some additional information -
the number of repetitions required or the intensity(weight)

3) Realtime feedback about the desired exercise effect by evaluating the duration of the
repetitions.
4) Permanently stores the number and the intensity of repetitions for each exercise and
allows users to upload it to an online profile to track progress and observe exercising
trends (information may be shared within an online community).
UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 21
Unconstrained Exercise Constrained Exercise
System - Device Position
UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 22
System - Selected Exercise
UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 23
Algorithm - Overview
UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 24
Algorithm - Dynamic Time Warping
Definition
In time series analysis, algorithm for measuring similarity between two temporal
sequences which may vary in time or speed
UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 25
Evaluation - Precision, Recall, F score
UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 26
Evaluation - Box plot for Temporal error of s,e
Fig. 5 Temporal error of detecting individual repetition start and end times normalized by the total duration of
the repetition for externally generated repetition patterns (median, quartiles, and extreme values)
감사합니다
맹욱재
wjmaeng@gmail.com

More Related Content

What's hot

The video tracking analysis
The video tracking analysisThe video tracking analysis
The video tracking analysis
Mauro Testa
 
Special Gadget Report: Video Camera
Special Gadget Report: Video CameraSpecial Gadget Report: Video Camera
Special Gadget Report: Video Camera
kleigh113
 
Kompass Motion Lab - the art & science of motion analysis - Final
Kompass Motion Lab - the art & science of motion analysis - FinalKompass Motion Lab - the art & science of motion analysis - Final
Kompass Motion Lab - the art & science of motion analysis - Final
Kenneth Craig
 
Morin emg 2015_slideshare.pptx
Morin emg 2015_slideshare.pptxMorin emg 2015_slideshare.pptx
Morin emg 2015_slideshare.pptx
JB Morin
 
Injuries prevention 2
Injuries prevention 2Injuries prevention 2
Injuries prevention 2
Mauro Testa
 
Robotics in neurosurgery
Robotics in neurosurgeryRobotics in neurosurgery
Robotics in neurosurgery
SHAMEEJ MUHAMED KV
 
Robotics and simulation in neurosurgery
Robotics and simulation in neurosurgeryRobotics and simulation in neurosurgery
Robotics and simulation in neurosurgery
Dr Kaushal Deep Singh Mathuria
 

What's hot (7)

The video tracking analysis
The video tracking analysisThe video tracking analysis
The video tracking analysis
 
Special Gadget Report: Video Camera
Special Gadget Report: Video CameraSpecial Gadget Report: Video Camera
Special Gadget Report: Video Camera
 
Kompass Motion Lab - the art & science of motion analysis - Final
Kompass Motion Lab - the art & science of motion analysis - FinalKompass Motion Lab - the art & science of motion analysis - Final
Kompass Motion Lab - the art & science of motion analysis - Final
 
Morin emg 2015_slideshare.pptx
Morin emg 2015_slideshare.pptxMorin emg 2015_slideshare.pptx
Morin emg 2015_slideshare.pptx
 
Injuries prevention 2
Injuries prevention 2Injuries prevention 2
Injuries prevention 2
 
Robotics in neurosurgery
Robotics in neurosurgeryRobotics in neurosurgery
Robotics in neurosurgery
 
Robotics and simulation in neurosurgery
Robotics and simulation in neurosurgeryRobotics and simulation in neurosurgery
Robotics and simulation in neurosurgery
 

Viewers also liked

SNU UX Lab 패턴랭귀지 (The origin of Pattern Language)
SNU UX Lab 패턴랭귀지 (The origin of Pattern Language)SNU UX Lab 패턴랭귀지 (The origin of Pattern Language)
SNU UX Lab 패턴랭귀지 (The origin of Pattern Language)
Hyun-Soo Ji
 
SNU UX Lab) Exploring Memory in Email Refinding
SNU UX Lab) Exploring Memory in Email RefindingSNU UX Lab) Exploring Memory in Email Refinding
SNU UX Lab) Exploring Memory in Email Refinding
Hyun-Soo Ji
 
MuscleMemory
MuscleMemoryMuscleMemory
MuscleMemory
Hyunjin Yoo
 
SNU UX Lab Meeting - 포털 서비스의 하위 메뉴 카테고리에 관한 
사용자 인식 연구 (141128)
SNU UX Lab Meeting - 포털 서비스의 하위 메뉴 카테고리에 관한 
사용자 인식 연구 (141128)SNU UX Lab Meeting - 포털 서비스의 하위 메뉴 카테고리에 관한 
사용자 인식 연구 (141128)
SNU UX Lab Meeting - 포털 서비스의 하위 메뉴 카테고리에 관한 
사용자 인식 연구 (141128)
Hyun-Soo Ji
 
From Care Plans to Care Coordination: Opportunities for Computer Support of T...
From Care Plans to Care Coordination: Opportunities for Computer Support of T...From Care Plans to Care Coordination: Opportunities for Computer Support of T...
From Care Plans to Care Coordination: Opportunities for Computer Support of T...
Hyun-Soo Ji
 
A large scale study of daily information needs captured in situ
A large scale study of daily information needs captured in situA large scale study of daily information needs captured in situ
A large scale study of daily information needs captured in situ
Wookjae Maeng
 
Effects of Simultaneous and Sequential Work Structures
Effects of Simultaneous and Sequential Work StructuresEffects of Simultaneous and Sequential Work Structures
Effects of Simultaneous and Sequential Work Structures
Hyunjeong Lee
 
0126 패턴 랭귀지 ios 가이드라인
0126 패턴 랭귀지  ios 가이드라인0126 패턴 랭귀지  ios 가이드라인
0126 패턴 랭귀지 ios 가이드라인
Hyunjeong Lee
 
160602
160602160602
160602
Hyesoo Yoo
 
KnowMe and ShareMe: Understanding Automatically Discovered Personality Trai...
 KnowMe and ShareMe:  Understanding Automatically Discovered Personality Trai... KnowMe and ShareMe:  Understanding Automatically Discovered Personality Trai...
KnowMe and ShareMe: Understanding Automatically Discovered Personality Trai...
Wookjae Maeng
 
SNU UX Lab Meeting - Facebook의 사용자경험연구: 사용자의 시선경로와 광고콘텐츠를 중심으로 (141107)
SNU UX Lab Meeting - Facebook의 사용자경험연구: 사용자의 시선경로와 광고콘텐츠를 중심으로 (141107)SNU UX Lab Meeting - Facebook의 사용자경험연구: 사용자의 시선경로와 광고콘텐츠를 중심으로 (141107)
SNU UX Lab Meeting - Facebook의 사용자경험연구: 사용자의 시선경로와 광고콘텐츠를 중심으로 (141107)
Hyun-Soo Ji
 
SNU UX Lab Meeting - MIT Technology Review
SNU UX Lab Meeting - MIT Technology ReviewSNU UX Lab Meeting - MIT Technology Review
SNU UX Lab Meeting - MIT Technology Review
Hyun-Soo Ji
 
SNU UX Lab Meeting - Panopticon as an eLearning Support Search Tool (141031)
SNU UX Lab Meeting - Panopticon as an eLearning Support Search Tool (141031)SNU UX Lab Meeting - Panopticon as an eLearning Support Search Tool (141031)
SNU UX Lab Meeting - Panopticon as an eLearning Support Search Tool (141031)
Hyun-Soo Ji
 
Understanding My Data Myself [Ubicomp 2011]
Understanding My Data Myself [Ubicomp 2011]Understanding My Data Myself [Ubicomp 2011]
Understanding My Data Myself [Ubicomp 2011]
Hyunjeong Lee
 
Ambient influence
Ambient influenceAmbient influence
Ambient influence
Hyunjin Yoo
 
Smart Handbag as a Wearable Public Display -Exploring Concepts and User perc...
 Smart Handbag as a Wearable Public Display -Exploring Concepts and User perc... Smart Handbag as a Wearable Public Display -Exploring Concepts and User perc...
Smart Handbag as a Wearable Public Display -Exploring Concepts and User perc...
Slava Han
 
Future Command and Control Systems Should Combine Decision Support and Person...
Future Command and Control Systems Should Combine Decision Support and Person...Future Command and Control Systems Should Combine Decision Support and Person...
Future Command and Control Systems Should Combine Decision Support and Person...
Slava Han
 
160428 Do Users' Perceptions of Password Security Match Reality?
160428 Do Users' Perceptions of Password Security Match Reality?160428 Do Users' Perceptions of Password Security Match Reality?
160428 Do Users' Perceptions of Password Security Match Reality?
Hyesoo Yoo
 
Swivrchair- a motorized swivel chair to nudge users’ orientation for 360 degr...
Swivrchair- a motorized swivel chair to nudge users’ orientation for 360 degr...Swivrchair- a motorized swivel chair to nudge users’ orientation for 360 degr...
Swivrchair- a motorized swivel chair to nudge users’ orientation for 360 degr...
Slava Han
 
Eye-Wearable Technology for Machine Maintenance: Effects of Display Position ...
Eye-Wearable Technology for Machine Maintenance: Effects of Display Position ...Eye-Wearable Technology for Machine Maintenance: Effects of Display Position ...
Eye-Wearable Technology for Machine Maintenance: Effects of Display Position ...
Slava Han
 

Viewers also liked (20)

SNU UX Lab 패턴랭귀지 (The origin of Pattern Language)
SNU UX Lab 패턴랭귀지 (The origin of Pattern Language)SNU UX Lab 패턴랭귀지 (The origin of Pattern Language)
SNU UX Lab 패턴랭귀지 (The origin of Pattern Language)
 
SNU UX Lab) Exploring Memory in Email Refinding
SNU UX Lab) Exploring Memory in Email RefindingSNU UX Lab) Exploring Memory in Email Refinding
SNU UX Lab) Exploring Memory in Email Refinding
 
MuscleMemory
MuscleMemoryMuscleMemory
MuscleMemory
 
SNU UX Lab Meeting - 포털 서비스의 하위 메뉴 카테고리에 관한 
사용자 인식 연구 (141128)
SNU UX Lab Meeting - 포털 서비스의 하위 메뉴 카테고리에 관한 
사용자 인식 연구 (141128)SNU UX Lab Meeting - 포털 서비스의 하위 메뉴 카테고리에 관한 
사용자 인식 연구 (141128)
SNU UX Lab Meeting - 포털 서비스의 하위 메뉴 카테고리에 관한 
사용자 인식 연구 (141128)
 
From Care Plans to Care Coordination: Opportunities for Computer Support of T...
From Care Plans to Care Coordination: Opportunities for Computer Support of T...From Care Plans to Care Coordination: Opportunities for Computer Support of T...
From Care Plans to Care Coordination: Opportunities for Computer Support of T...
 
A large scale study of daily information needs captured in situ
A large scale study of daily information needs captured in situA large scale study of daily information needs captured in situ
A large scale study of daily information needs captured in situ
 
Effects of Simultaneous and Sequential Work Structures
Effects of Simultaneous and Sequential Work StructuresEffects of Simultaneous and Sequential Work Structures
Effects of Simultaneous and Sequential Work Structures
 
0126 패턴 랭귀지 ios 가이드라인
0126 패턴 랭귀지  ios 가이드라인0126 패턴 랭귀지  ios 가이드라인
0126 패턴 랭귀지 ios 가이드라인
 
160602
160602160602
160602
 
KnowMe and ShareMe: Understanding Automatically Discovered Personality Trai...
 KnowMe and ShareMe:  Understanding Automatically Discovered Personality Trai... KnowMe and ShareMe:  Understanding Automatically Discovered Personality Trai...
KnowMe and ShareMe: Understanding Automatically Discovered Personality Trai...
 
SNU UX Lab Meeting - Facebook의 사용자경험연구: 사용자의 시선경로와 광고콘텐츠를 중심으로 (141107)
SNU UX Lab Meeting - Facebook의 사용자경험연구: 사용자의 시선경로와 광고콘텐츠를 중심으로 (141107)SNU UX Lab Meeting - Facebook의 사용자경험연구: 사용자의 시선경로와 광고콘텐츠를 중심으로 (141107)
SNU UX Lab Meeting - Facebook의 사용자경험연구: 사용자의 시선경로와 광고콘텐츠를 중심으로 (141107)
 
SNU UX Lab Meeting - MIT Technology Review
SNU UX Lab Meeting - MIT Technology ReviewSNU UX Lab Meeting - MIT Technology Review
SNU UX Lab Meeting - MIT Technology Review
 
SNU UX Lab Meeting - Panopticon as an eLearning Support Search Tool (141031)
SNU UX Lab Meeting - Panopticon as an eLearning Support Search Tool (141031)SNU UX Lab Meeting - Panopticon as an eLearning Support Search Tool (141031)
SNU UX Lab Meeting - Panopticon as an eLearning Support Search Tool (141031)
 
Understanding My Data Myself [Ubicomp 2011]
Understanding My Data Myself [Ubicomp 2011]Understanding My Data Myself [Ubicomp 2011]
Understanding My Data Myself [Ubicomp 2011]
 
Ambient influence
Ambient influenceAmbient influence
Ambient influence
 
Smart Handbag as a Wearable Public Display -Exploring Concepts and User perc...
 Smart Handbag as a Wearable Public Display -Exploring Concepts and User perc... Smart Handbag as a Wearable Public Display -Exploring Concepts and User perc...
Smart Handbag as a Wearable Public Display -Exploring Concepts and User perc...
 
Future Command and Control Systems Should Combine Decision Support and Person...
Future Command and Control Systems Should Combine Decision Support and Person...Future Command and Control Systems Should Combine Decision Support and Person...
Future Command and Control Systems Should Combine Decision Support and Person...
 
160428 Do Users' Perceptions of Password Security Match Reality?
160428 Do Users' Perceptions of Password Security Match Reality?160428 Do Users' Perceptions of Password Security Match Reality?
160428 Do Users' Perceptions of Password Security Match Reality?
 
Swivrchair- a motorized swivel chair to nudge users’ orientation for 360 degr...
Swivrchair- a motorized swivel chair to nudge users’ orientation for 360 degr...Swivrchair- a motorized swivel chair to nudge users’ orientation for 360 degr...
Swivrchair- a motorized swivel chair to nudge users’ orientation for 360 degr...
 
Eye-Wearable Technology for Machine Maintenance: Effects of Display Position ...
Eye-Wearable Technology for Machine Maintenance: Effects of Display Position ...Eye-Wearable Technology for Machine Maintenance: Effects of Display Position ...
Eye-Wearable Technology for Machine Maintenance: Effects of Display Position ...
 

Similar to Exercise repetition detection for resistance training based on smartphones

Pose Trainer: “An Exercise Guide and Assessment in Physiotherapy”
Pose Trainer: “An Exercise Guide and Assessment in Physiotherapy”Pose Trainer: “An Exercise Guide and Assessment in Physiotherapy”
Pose Trainer: “An Exercise Guide and Assessment in Physiotherapy”
IRJET Journal
 
WIRELESS BODY AREA SENSOR NETWORK FOR SOLDIER SYSTEM.
WIRELESS BODY AREA SENSOR NETWORK FOR SOLDIER SYSTEM.WIRELESS BODY AREA SENSOR NETWORK FOR SOLDIER SYSTEM.
WIRELESS BODY AREA SENSOR NETWORK FOR SOLDIER SYSTEM.
ijiert bestjournal
 
Estimation of Walking rate in Complex activity recognition
Estimation of Walking rate in Complex activity recognitionEstimation of Walking rate in Complex activity recognition
Estimation of Walking rate in Complex activity recognition
Editor IJCATR
 
Balance trainer for smartphone
Balance trainer for smartphoneBalance trainer for smartphone
Balance trainer for smartphone
Sciencehit.by
 
Study of AI Fitness Model Using Deep Learning
Study of AI Fitness Model Using Deep LearningStudy of AI Fitness Model Using Deep Learning
Study of AI Fitness Model Using Deep Learning
IRJET Journal
 
Artificial Neural Networks Project report
Artificial Neural Networks Project reportArtificial Neural Networks Project report
Artificial Neural Networks Project report
Rengarajan Sankaranarayanan
 
VoLearn: A Cross-Modal Operable Motion-Learning System Combined with Virtual ...
VoLearn: A Cross-Modal Operable Motion-Learning System Combined with Virtual ...VoLearn: A Cross-Modal Operable Motion-Learning System Combined with Virtual ...
VoLearn: A Cross-Modal Operable Motion-Learning System Combined with Virtual ...
sugiuralab
 
AI Personal Trainer Using Open CV and Media Pipe
AI Personal Trainer Using Open CV and Media PipeAI Personal Trainer Using Open CV and Media Pipe
AI Personal Trainer Using Open CV and Media Pipe
IRJET Journal
 
IoT Based Human Activity Recognition and Classification Using Machine Learning
IoT Based Human Activity Recognition and Classification Using Machine LearningIoT Based Human Activity Recognition and Classification Using Machine Learning
IoT Based Human Activity Recognition and Classification Using Machine Learning
IRJET Journal
 
Campus_Abnormal_Behavior_Recognition_With_Temporal_Segment_Transformers.docx
Campus_Abnormal_Behavior_Recognition_With_Temporal_Segment_Transformers.docxCampus_Abnormal_Behavior_Recognition_With_Temporal_Segment_Transformers.docx
Campus_Abnormal_Behavior_Recognition_With_Temporal_Segment_Transformers.docx
Shakas Technologies
 
Towards Whole Body Fatigue Assessment of Human Movement: A Fatigue-Tracking S...
Towards Whole Body Fatigue Assessment of Human Movement: A Fatigue-Tracking S...Towards Whole Body Fatigue Assessment of Human Movement: A Fatigue-Tracking S...
Towards Whole Body Fatigue Assessment of Human Movement: A Fatigue-Tracking S...
toukaigi
 
Recognition of anaerobic based on machine learning using smart watch sensor data
Recognition of anaerobic based on machine learning using smart watch sensor dataRecognition of anaerobic based on machine learning using smart watch sensor data
Recognition of anaerobic based on machine learning using smart watch sensor data
Suhyun Cho
 
Observer based dynamic control model for bilaterally controlled MU-LapaRobot:...
Observer based dynamic control model for bilaterally controlled MU-LapaRobot:...Observer based dynamic control model for bilaterally controlled MU-LapaRobot:...
Observer based dynamic control model for bilaterally controlled MU-LapaRobot:...
IJECEIAES
 
R4101112115
R4101112115R4101112115
R4101112115
IJERA Editor
 
[Skolkovo Robotics 2015 Day 1] Терашима К. Modeling and Taylormade Training M...
[Skolkovo Robotics 2015 Day 1] Терашима К. Modeling and Taylormade Training M...[Skolkovo Robotics 2015 Day 1] Терашима К. Modeling and Taylormade Training M...
[Skolkovo Robotics 2015 Day 1] Терашима К. Modeling and Taylormade Training M...
Skolkovo Robotics Center
 
Hamza, others
Hamza, othersHamza, others
Hamza, others
William Kritsonis
 
Ieeepro techno solutions 2013 ieee embedded project - child activity recog...
Ieeepro techno solutions   2013 ieee embedded project  - child activity recog...Ieeepro techno solutions   2013 ieee embedded project  - child activity recog...
Ieeepro techno solutions 2013 ieee embedded project - child activity recog...
srinivasanece7
 
Active model
Active modelActive model
Active model
MohsenAbadi1
 
IOT POWERED WEARABLE HEALTH BAND
IOT POWERED WEARABLE HEALTH BANDIOT POWERED WEARABLE HEALTH BAND
IOT POWERED WEARABLE HEALTH BAND
SIDDHARTHHATKAR
 
Real-time Estimation of Human’s Intended Walking Speed for Treadmill-style Lo...
Real-time Estimation of Human’s Intended Walking Speed for Treadmill-style Lo...Real-time Estimation of Human’s Intended Walking Speed for Treadmill-style Lo...
Real-time Estimation of Human’s Intended Walking Speed for Treadmill-style Lo...
toukaigi
 

Similar to Exercise repetition detection for resistance training based on smartphones (20)

Pose Trainer: “An Exercise Guide and Assessment in Physiotherapy”
Pose Trainer: “An Exercise Guide and Assessment in Physiotherapy”Pose Trainer: “An Exercise Guide and Assessment in Physiotherapy”
Pose Trainer: “An Exercise Guide and Assessment in Physiotherapy”
 
WIRELESS BODY AREA SENSOR NETWORK FOR SOLDIER SYSTEM.
WIRELESS BODY AREA SENSOR NETWORK FOR SOLDIER SYSTEM.WIRELESS BODY AREA SENSOR NETWORK FOR SOLDIER SYSTEM.
WIRELESS BODY AREA SENSOR NETWORK FOR SOLDIER SYSTEM.
 
Estimation of Walking rate in Complex activity recognition
Estimation of Walking rate in Complex activity recognitionEstimation of Walking rate in Complex activity recognition
Estimation of Walking rate in Complex activity recognition
 
Balance trainer for smartphone
Balance trainer for smartphoneBalance trainer for smartphone
Balance trainer for smartphone
 
Study of AI Fitness Model Using Deep Learning
Study of AI Fitness Model Using Deep LearningStudy of AI Fitness Model Using Deep Learning
Study of AI Fitness Model Using Deep Learning
 
Artificial Neural Networks Project report
Artificial Neural Networks Project reportArtificial Neural Networks Project report
Artificial Neural Networks Project report
 
VoLearn: A Cross-Modal Operable Motion-Learning System Combined with Virtual ...
VoLearn: A Cross-Modal Operable Motion-Learning System Combined with Virtual ...VoLearn: A Cross-Modal Operable Motion-Learning System Combined with Virtual ...
VoLearn: A Cross-Modal Operable Motion-Learning System Combined with Virtual ...
 
AI Personal Trainer Using Open CV and Media Pipe
AI Personal Trainer Using Open CV and Media PipeAI Personal Trainer Using Open CV and Media Pipe
AI Personal Trainer Using Open CV and Media Pipe
 
IoT Based Human Activity Recognition and Classification Using Machine Learning
IoT Based Human Activity Recognition and Classification Using Machine LearningIoT Based Human Activity Recognition and Classification Using Machine Learning
IoT Based Human Activity Recognition and Classification Using Machine Learning
 
Campus_Abnormal_Behavior_Recognition_With_Temporal_Segment_Transformers.docx
Campus_Abnormal_Behavior_Recognition_With_Temporal_Segment_Transformers.docxCampus_Abnormal_Behavior_Recognition_With_Temporal_Segment_Transformers.docx
Campus_Abnormal_Behavior_Recognition_With_Temporal_Segment_Transformers.docx
 
Towards Whole Body Fatigue Assessment of Human Movement: A Fatigue-Tracking S...
Towards Whole Body Fatigue Assessment of Human Movement: A Fatigue-Tracking S...Towards Whole Body Fatigue Assessment of Human Movement: A Fatigue-Tracking S...
Towards Whole Body Fatigue Assessment of Human Movement: A Fatigue-Tracking S...
 
Recognition of anaerobic based on machine learning using smart watch sensor data
Recognition of anaerobic based on machine learning using smart watch sensor dataRecognition of anaerobic based on machine learning using smart watch sensor data
Recognition of anaerobic based on machine learning using smart watch sensor data
 
Observer based dynamic control model for bilaterally controlled MU-LapaRobot:...
Observer based dynamic control model for bilaterally controlled MU-LapaRobot:...Observer based dynamic control model for bilaterally controlled MU-LapaRobot:...
Observer based dynamic control model for bilaterally controlled MU-LapaRobot:...
 
R4101112115
R4101112115R4101112115
R4101112115
 
[Skolkovo Robotics 2015 Day 1] Терашима К. Modeling and Taylormade Training M...
[Skolkovo Robotics 2015 Day 1] Терашима К. Modeling and Taylormade Training M...[Skolkovo Robotics 2015 Day 1] Терашима К. Modeling and Taylormade Training M...
[Skolkovo Robotics 2015 Day 1] Терашима К. Modeling and Taylormade Training M...
 
Hamza, others
Hamza, othersHamza, others
Hamza, others
 
Ieeepro techno solutions 2013 ieee embedded project - child activity recog...
Ieeepro techno solutions   2013 ieee embedded project  - child activity recog...Ieeepro techno solutions   2013 ieee embedded project  - child activity recog...
Ieeepro techno solutions 2013 ieee embedded project - child activity recog...
 
Active model
Active modelActive model
Active model
 
IOT POWERED WEARABLE HEALTH BAND
IOT POWERED WEARABLE HEALTH BANDIOT POWERED WEARABLE HEALTH BAND
IOT POWERED WEARABLE HEALTH BAND
 
Real-time Estimation of Human’s Intended Walking Speed for Treadmill-style Lo...
Real-time Estimation of Human’s Intended Walking Speed for Treadmill-style Lo...Real-time Estimation of Human’s Intended Walking Speed for Treadmill-style Lo...
Real-time Estimation of Human’s Intended Walking Speed for Treadmill-style Lo...
 

Recently uploaded

1比1复刻澳洲皇家墨尔本理工大学毕业证本科学位原版一模一样
1比1复刻澳洲皇家墨尔本理工大学毕业证本科学位原版一模一样1比1复刻澳洲皇家墨尔本理工大学毕业证本科学位原版一模一样
1比1复刻澳洲皇家墨尔本理工大学毕业证本科学位原版一模一样
2g3om49r
 
按照学校原版(Columbia文凭证书)哥伦比亚大学毕业证快速办理
按照学校原版(Columbia文凭证书)哥伦比亚大学毕业证快速办理按照学校原版(Columbia文凭证书)哥伦比亚大学毕业证快速办理
按照学校原版(Columbia文凭证书)哥伦比亚大学毕业证快速办理
uyesp1a
 
一比一原版(KCL文凭证书)伦敦国王学院毕业证如何办理
一比一原版(KCL文凭证书)伦敦国王学院毕业证如何办理一比一原版(KCL文凭证书)伦敦国王学院毕业证如何办理
一比一原版(KCL文凭证书)伦敦国王学院毕业证如何办理
kuehcub
 
按照学校原版(Westminster文凭证书)威斯敏斯特大学毕业证快速办理
按照学校原版(Westminster文凭证书)威斯敏斯特大学毕业证快速办理按照学校原版(Westminster文凭证书)威斯敏斯特大学毕业证快速办理
按照学校原版(Westminster文凭证书)威斯敏斯特大学毕业证快速办理
yizxn4sx
 
按照学校原版(SUT文凭证书)斯威本科技大学毕业证快速办理
按照学校原版(SUT文凭证书)斯威本科技大学毕业证快速办理按照学校原版(SUT文凭证书)斯威本科技大学毕业证快速办理
按照学校原版(SUT文凭证书)斯威本科技大学毕业证快速办理
1jtj7yul
 
一比一原版(Monash文凭证书)莫纳什大学毕业证如何办理
一比一原版(Monash文凭证书)莫纳什大学毕业证如何办理一比一原版(Monash文凭证书)莫纳什大学毕业证如何办理
一比一原版(Monash文凭证书)莫纳什大学毕业证如何办理
xuqdabu
 
一比一原版(UOL文凭证书)利物浦大学毕业证如何办理
一比一原版(UOL文凭证书)利物浦大学毕业证如何办理一比一原版(UOL文凭证书)利物浦大学毕业证如何办理
一比一原版(UOL文凭证书)利物浦大学毕业证如何办理
eydeofo
 
一比一原版(UCSB毕业证)圣塔芭芭拉社区大学毕业证如何办理
一比一原版(UCSB毕业证)圣塔芭芭拉社区大学毕业证如何办理一比一原版(UCSB毕业证)圣塔芭芭拉社区大学毕业证如何办理
一比一原版(UCSB毕业证)圣塔芭芭拉社区大学毕业证如何办理
aozcue
 
按照学校原版(UST文凭证书)圣托马斯大学毕业证快速办理
按照学校原版(UST文凭证书)圣托马斯大学毕业证快速办理按照学校原版(UST文凭证书)圣托马斯大学毕业证快速办理
按照学校原版(UST文凭证书)圣托马斯大学毕业证快速办理
zpc0z12
 
一比一原版(Adelaide文凭证书)阿德莱德大学毕业证如何办理
一比一原版(Adelaide文凭证书)阿德莱德大学毕业证如何办理一比一原版(Adelaide文凭证书)阿德莱德大学毕业证如何办理
一比一原版(Adelaide文凭证书)阿德莱德大学毕业证如何办理
xuqdabu
 
按照学校原版(Adelaide文凭证书)阿德莱德大学毕业证快速办理
按照学校原版(Adelaide文凭证书)阿德莱德大学毕业证快速办理按照学校原版(Adelaide文凭证书)阿德莱德大学毕业证快速办理
按照学校原版(Adelaide文凭证书)阿德莱德大学毕业证快速办理
terpt4iu
 
Why is the AIS 140 standard Mandatory in India?
Why is the AIS 140 standard Mandatory in India?Why is the AIS 140 standard Mandatory in India?
Why is the AIS 140 standard Mandatory in India?
Watsoo Telematics
 
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证如何办理
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证如何办理一比一原版(IIT毕业证)伊利诺伊理工大学毕业证如何办理
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证如何办理
aozcue
 
Building a Raspberry Pi Robot with Dot NET 8, Blazor and SignalR
Building a Raspberry Pi Robot with Dot NET 8, Blazor and SignalRBuilding a Raspberry Pi Robot with Dot NET 8, Blazor and SignalR
Building a Raspberry Pi Robot with Dot NET 8, Blazor and SignalR
Peter Gallagher
 
加急办理美国南加州大学毕业证文凭毕业证原版一模一样
加急办理美国南加州大学毕业证文凭毕业证原版一模一样加急办理美国南加州大学毕业证文凭毕业证原版一模一样
加急办理美国南加州大学毕业证文凭毕业证原版一模一样
u0g33km
 
一比一原版(Greenwich文凭证书)格林威治大学毕业证如何办理
一比一原版(Greenwich文凭证书)格林威治大学毕业证如何办理一比一原版(Greenwich文凭证书)格林威治大学毕业证如何办理
一比一原版(Greenwich文凭证书)格林威治大学毕业证如何办理
byfazef
 
按照学校原版(KCL文凭证书)伦敦国王学院毕业证快速办理
按照学校原版(KCL文凭证书)伦敦国王学院毕业证快速办理按照学校原版(KCL文凭证书)伦敦国王学院毕业证快速办理
按照学校原版(KCL文凭证书)伦敦国王学院毕业证快速办理
terpt4iu
 
按照学校原版(QU文凭证书)皇后大学毕业证快速办理
按照学校原版(QU文凭证书)皇后大学毕业证快速办理按照学校原版(QU文凭证书)皇后大学毕业证快速办理
按照学校原版(QU文凭证书)皇后大学毕业证快速办理
8db3cz8x
 
一比一原版(UQ文凭证书)昆士兰大学毕业证如何办理
一比一原版(UQ文凭证书)昆士兰大学毕业证如何办理一比一原版(UQ文凭证书)昆士兰大学毕业证如何办理
一比一原版(UQ文凭证书)昆士兰大学毕业证如何办理
xuqdabu
 
按照学校原版(Greenwich文凭证书)格林威治大学毕业证快速办理
按照学校原版(Greenwich文凭证书)格林威治大学毕业证快速办理按照学校原版(Greenwich文凭证书)格林威治大学毕业证快速办理
按照学校原版(Greenwich文凭证书)格林威治大学毕业证快速办理
yizxn4sx
 

Recently uploaded (20)

1比1复刻澳洲皇家墨尔本理工大学毕业证本科学位原版一模一样
1比1复刻澳洲皇家墨尔本理工大学毕业证本科学位原版一模一样1比1复刻澳洲皇家墨尔本理工大学毕业证本科学位原版一模一样
1比1复刻澳洲皇家墨尔本理工大学毕业证本科学位原版一模一样
 
按照学校原版(Columbia文凭证书)哥伦比亚大学毕业证快速办理
按照学校原版(Columbia文凭证书)哥伦比亚大学毕业证快速办理按照学校原版(Columbia文凭证书)哥伦比亚大学毕业证快速办理
按照学校原版(Columbia文凭证书)哥伦比亚大学毕业证快速办理
 
一比一原版(KCL文凭证书)伦敦国王学院毕业证如何办理
一比一原版(KCL文凭证书)伦敦国王学院毕业证如何办理一比一原版(KCL文凭证书)伦敦国王学院毕业证如何办理
一比一原版(KCL文凭证书)伦敦国王学院毕业证如何办理
 
按照学校原版(Westminster文凭证书)威斯敏斯特大学毕业证快速办理
按照学校原版(Westminster文凭证书)威斯敏斯特大学毕业证快速办理按照学校原版(Westminster文凭证书)威斯敏斯特大学毕业证快速办理
按照学校原版(Westminster文凭证书)威斯敏斯特大学毕业证快速办理
 
按照学校原版(SUT文凭证书)斯威本科技大学毕业证快速办理
按照学校原版(SUT文凭证书)斯威本科技大学毕业证快速办理按照学校原版(SUT文凭证书)斯威本科技大学毕业证快速办理
按照学校原版(SUT文凭证书)斯威本科技大学毕业证快速办理
 
一比一原版(Monash文凭证书)莫纳什大学毕业证如何办理
一比一原版(Monash文凭证书)莫纳什大学毕业证如何办理一比一原版(Monash文凭证书)莫纳什大学毕业证如何办理
一比一原版(Monash文凭证书)莫纳什大学毕业证如何办理
 
一比一原版(UOL文凭证书)利物浦大学毕业证如何办理
一比一原版(UOL文凭证书)利物浦大学毕业证如何办理一比一原版(UOL文凭证书)利物浦大学毕业证如何办理
一比一原版(UOL文凭证书)利物浦大学毕业证如何办理
 
一比一原版(UCSB毕业证)圣塔芭芭拉社区大学毕业证如何办理
一比一原版(UCSB毕业证)圣塔芭芭拉社区大学毕业证如何办理一比一原版(UCSB毕业证)圣塔芭芭拉社区大学毕业证如何办理
一比一原版(UCSB毕业证)圣塔芭芭拉社区大学毕业证如何办理
 
按照学校原版(UST文凭证书)圣托马斯大学毕业证快速办理
按照学校原版(UST文凭证书)圣托马斯大学毕业证快速办理按照学校原版(UST文凭证书)圣托马斯大学毕业证快速办理
按照学校原版(UST文凭证书)圣托马斯大学毕业证快速办理
 
一比一原版(Adelaide文凭证书)阿德莱德大学毕业证如何办理
一比一原版(Adelaide文凭证书)阿德莱德大学毕业证如何办理一比一原版(Adelaide文凭证书)阿德莱德大学毕业证如何办理
一比一原版(Adelaide文凭证书)阿德莱德大学毕业证如何办理
 
按照学校原版(Adelaide文凭证书)阿德莱德大学毕业证快速办理
按照学校原版(Adelaide文凭证书)阿德莱德大学毕业证快速办理按照学校原版(Adelaide文凭证书)阿德莱德大学毕业证快速办理
按照学校原版(Adelaide文凭证书)阿德莱德大学毕业证快速办理
 
Why is the AIS 140 standard Mandatory in India?
Why is the AIS 140 standard Mandatory in India?Why is the AIS 140 standard Mandatory in India?
Why is the AIS 140 standard Mandatory in India?
 
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证如何办理
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证如何办理一比一原版(IIT毕业证)伊利诺伊理工大学毕业证如何办理
一比一原版(IIT毕业证)伊利诺伊理工大学毕业证如何办理
 
Building a Raspberry Pi Robot with Dot NET 8, Blazor and SignalR
Building a Raspberry Pi Robot with Dot NET 8, Blazor and SignalRBuilding a Raspberry Pi Robot with Dot NET 8, Blazor and SignalR
Building a Raspberry Pi Robot with Dot NET 8, Blazor and SignalR
 
加急办理美国南加州大学毕业证文凭毕业证原版一模一样
加急办理美国南加州大学毕业证文凭毕业证原版一模一样加急办理美国南加州大学毕业证文凭毕业证原版一模一样
加急办理美国南加州大学毕业证文凭毕业证原版一模一样
 
一比一原版(Greenwich文凭证书)格林威治大学毕业证如何办理
一比一原版(Greenwich文凭证书)格林威治大学毕业证如何办理一比一原版(Greenwich文凭证书)格林威治大学毕业证如何办理
一比一原版(Greenwich文凭证书)格林威治大学毕业证如何办理
 
按照学校原版(KCL文凭证书)伦敦国王学院毕业证快速办理
按照学校原版(KCL文凭证书)伦敦国王学院毕业证快速办理按照学校原版(KCL文凭证书)伦敦国王学院毕业证快速办理
按照学校原版(KCL文凭证书)伦敦国王学院毕业证快速办理
 
按照学校原版(QU文凭证书)皇后大学毕业证快速办理
按照学校原版(QU文凭证书)皇后大学毕业证快速办理按照学校原版(QU文凭证书)皇后大学毕业证快速办理
按照学校原版(QU文凭证书)皇后大学毕业证快速办理
 
一比一原版(UQ文凭证书)昆士兰大学毕业证如何办理
一比一原版(UQ文凭证书)昆士兰大学毕业证如何办理一比一原版(UQ文凭证书)昆士兰大学毕业证如何办理
一比一原版(UQ文凭证书)昆士兰大学毕业证如何办理
 
按照学校原版(Greenwich文凭证书)格林威治大学毕业证快速办理
按照学校原版(Greenwich文凭证书)格林威治大学毕业证快速办理按照学校原版(Greenwich文凭证书)格林威治大学毕业证快速办理
按照学校原版(Greenwich文凭证书)格林威治大学毕业证快速办理
 

Exercise repetition detection for resistance training based on smartphones

  • 1. Exercise repetition detection for resistance training based on smartphones, + Pers. Ubiquit. Comput. (2013), - Igor Pernek et al, / 맹욱재 x 2015 Rainy Fall
  • 2. UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 2 Contents 1. Intro 2. Related Works 3. System & Algorithm 4. Evaluation
  • 3. UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 3 Intro - Why this paper? WookFit : Wearable Device for Breast Cancer Survivors doing Resistance ExcersiceElastic-band stretching Counter
  • 4. UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 4 Intro - Why this paper?(Cont.) Key word for searching paper Breast Cancer Rehabilitations Resistance Excersise(traning) Home-based Excersise(traning) Lymphedema Theraband(Resistance band) Wearable IoT Quality of Life Smartphone Application Accelerometer
  • 5. UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 5 Key word for searching paper Breast Cancer Rehabilitations Resistance Excersise(traning) Home-based Excersise(traning) Lymphedema Theraband(Resistance band) Wearable IoT Quality of Life Smartphone Application Accelerometer Intro - Why this paper?(Cont.)
  • 6. UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 6 Intro - Take away 1. Dynamic Time Warping algorithm can accurately count the number of repetition, duration. 2. Giving real time feedback on Quality of Performance 
 can be done using duration, start, end time of repetition
  • 7. UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 7 Intro - Abstract Problem Solution Most of systems focus only on cardio exercises such as running and cycling Exploit smartphones to support leisure activities with a focus on resistance training. Off-the-shelf smartphones without additional external sensors can be leveraged 
 to capture resistance training data and to give reliable training feedback Algorithm Dynamic Time Warping based algorithm to detect individual resistance training repetitions from the smartphone’s acceleration stream
  • 8. UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 8 Intro - Abstract Feedback in detail Providing feedback about the quality of repetitions, use the duration of an individual repetition and analyze how accurately start and end times of repetitions can be detected by our algorithm In terms of the number of correctly recognized repetitions. 
 3,598 repetitions performed by 10 volunteers exercising in 2 distinct scenarios 
 a gym and a natural environment. The results show an overall repetition miscount rate of about 1 % overall temporal detection error of about 11 % of individual repetition duration. Evalution
  • 9. UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 9 Related Works Manual input problem manual input is cumbersome, taking notes about resistance training is often avoided, negatively affect people’s activity levels and decrease their motivation for regular training https://www.jefit.com/products/androidpro/index.php https://play.google.com/store/apps/details?id=com.namuan.health&hl=ko
  • 10. UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 10 Related Works - Fitlinxx https://www.youtube.com/watch?time_continue=303&v=BfnPogUokKs 1. very expensive, as the gym has to be equipped with specific exercise machines and infrastructure, and has therefore not gained broader popularity 2. have to log in to the system prior to performing any exercise,
  • 11. UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 11 Related Works - Recognizing Upper Body Postures using Textile Strain Sensors
  • 12. UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 12 Related Works- The Virtual Trainer: Supervising Movements Through a Wearable Wireless Sensor Network the algorithm relies on exercise specific features, such as the position of the elbow during the biceps curl exercise, and can therefore not be easily applied to a general resistance training exercise.
  • 13. UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 13 Related Works- Implementation and evaluation of the personal wellness coach The acceleration stream-laptop computer threshold-based low-pass filtering algorithm: each transition from resting to exercise state to count the number of repetitions. the number of time units in each state is analyzed to detect struggling during exercise execution. all the repetitions have a similar single peak acceleration footprint, which is not true for exercises performed in different environments
  • 14. UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 14 Related Works -Tracking Free-Weight Exercises feature phone + 2 external accelerometer sensors. data from a glove & chest belt, only derive info for a limited set of free-weight exercises. simple peak detection algorithms that are 
 no detect a repetition’s start and end time 
 ->lack capabilities for providing qualitative feedback based on the duration of repetitions.
  • 15. UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 15 Related Works - myHealthAssistant: A Phone-based Body Sensor Network that Captures the Wearer’s Exercises throughout the Day advance ‘Tracking Free-Weight Exercises' by making the repetition detection algorithm robust to different exercising speeds
  • 16. UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 16 Related Works- What can an arm holster worn smart phone do for activity recognition? arm worn smartphones to recognize a number of upper body resistance training exercises from a continuous acceleration stream. Main focus lies on spotting series of exercises, repetitions- peak detection. start & end times of individual repetitions cannot be detected.
  • 17. UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 17 Related Works Missing information 1) not ubiquitous -> mobile(smartphone) 2) targeted to a set of specific exercises 
 -> broader set of exercises, performed using different types of equipment 3) not support fine-grained tracking of individual repetitions. 
 important to give feedback about the correctness and quality of exercising
 -> by detection of duration of individual repetitions. WookFit 1) mobile(smartphone) + Wearable device 2) targeted to a set of specific exercises 3) not support fine-grained tracking of individual repetitions.
  • 18. UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 18 System - Requirement 1) Should not add high extra cost nor demand the cumbersome installation of additional sensors and tools
 => off-the-shelf smartphones 2) Easy to use interface, be encouraging by suggesting particular exercises, and give feedback on the exercising performance as well as the training progress
 => Quality of Performance Feedback 3) Usable in different environments including gyms and natural environments and cover a wide range of exercises
 => Constrained(gym, fitness center) + Unconstrained(free-weight, resistance band, body weight)
  • 19. UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 19 System - Resistance Training Assistant
  • 20. UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 20 System - Resistance Training Assistant 1) Download different training plans and exercises from an online training database. 2) The application proposes exercises to perform along with some additional information - the number of repetitions required or the intensity(weight)
 3) Realtime feedback about the desired exercise effect by evaluating the duration of the repetitions. 4) Permanently stores the number and the intensity of repetitions for each exercise and allows users to upload it to an online profile to track progress and observe exercising trends (information may be shared within an online community).
  • 21. UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 21 Unconstrained Exercise Constrained Exercise System - Device Position
  • 22. UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 22 System - Selected Exercise
  • 23. UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 23 Algorithm - Overview
  • 24. UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 24 Algorithm - Dynamic Time Warping Definition In time series analysis, algorithm for measuring similarity between two temporal sequences which may vary in time or speed
  • 25. UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 25 Evaluation - Precision, Recall, F score
  • 26. UX Lab, Graduate School of Convergence Science and Technology, Seoul National Univ. 26 Evaluation - Box plot for Temporal error of s,e Fig. 5 Temporal error of detecting individual repetition start and end times normalized by the total duration of the repetition for externally generated repetition patterns (median, quartiles, and extreme values)