SlideShare a Scribd company logo
Virtual IMU Data Augmentation by Spring-Joint
Model for Motion Exercises Recognition without
Using Real Data
2022 ACM ISWC (note)
Chengshuo Xia, Yuta Sugiura
Keio University, Japan
2
Background: real IMU dataset for motion recognition
Participants
Wearing
sensor
Produce the
data
Real wearable IMU sensor data collection: time-costly and expensive.
Opportunity dataset [1]
[1] Daniel Roggen, Alberto Calatroni, Mirco Rossi, Thomas Holleczek, Gerhard Tröster, Paul Lukowicz, Gerald Pirkl, David Bannach, Alois Ferscha, Jakob Doppler, Clemens Holzmann, Marc Kurz, Gerald Holl, Ricardo Chavarriaga, Hesam Sagha,
Hamidreza Bayati, and José del R. Millàn. "Collecting complex activity data sets in highly rich networked sensor environments" In Seventh International Conference on Networked Sensing Systems (INSS’10), Kassel, Germany, 2010.
Dataset
Dataset
Machine
learning
model
Application
Change
Real world
A motion recognition system: machine learning (ML).
3
Background: virtual IMU sensor data in machine learning
Virtual sensor data generation help to reduce the dataset cost.
Dataset
Machine
learning
model
Application Change
Virtual sensor
data
Simulation envrionment
Virtual IMU sensor data extraction from 3D human motion:
4
Background: current problems in virtual data
• Limited 3D motion length.
• Obtaining a longer 3D motion length still is time-consuming.
• Real data distribution is needed.
5
Proposed Method: spring-joint module-based data augmentation
• Spring-joint virtual IMU sensor module.
• Used for training the classifier.
• Recognize the real IMU data.
More virtual sensor
data
Spring-Joint virtual
sensor module
3D motion
Training the ML
model
6
Related Work: virtual sensor data for human motion recognition
Virtual IMU data: IMUTube [1]
Virtual Doppler data: Vid2Doppler [2]
Virtual distance data [3]
[1] Kwon, Hyeokhyen, et al. "IMUTube: Automatic extraction of virtual on-body accelerometry from video for human activity recognition." Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 4.3 (2020): 1-29.
[2] Ahuja, Karan, et al. "Vid2Doppler: synthesizing Doppler radar data from videos for training privacy-preserving activity recognition." Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems. 2021.
[3] Xia, Chengshuo, Ayane Saito, and Yuta Sugiura. "Using the virtual data-driven measurement to support the prototyping of hand gesture recognition interface with distance sensor." Sensors and Actuators A: Physical 338 (2022): 113463.
7
Related Work: data augmentation for time-series
[1] Li, Xi'ang, Jinqi Luo, and Rabih Younes. "ActivityGAN: Generative adversarial networks for data augmentation in sensor-based human activity recognition." Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of
the 2020 ACM International Symposium on Wearable Computers. 2020.
[2] Um, Terry T., et al. "Data augmentation of wearable sensor data for parkinson’s disease monitoring using convolutional neural networks." Proceedings of the 19th ACM international conference on multimodal interaction. 2017.
GAN-based [1]: Time-series manipulation [2]:
Traditional augmentation: operate on real data
Our method: augment the virtual sensor data
8
Overview of Proposed Method
More virtual
sensor data
Spring-joint virtual
IMU sensor
module
Machine learning
model
3D human
motion
Recognize the
real motion
9
Method: how to obtain the virtual acceleration data
Posistion
Velocity
Acceleration
[1] Young, Alexander D., Martin J. Ling, and Damal K. Arvind. "IMUSim: A simulation environment for inertial sensing algorithm design and evaluation." Proceedings of the 10th ACM/IEEE International Conference on Information
Processing in Sensor Networks. IEEE, 2011.
10
Method: spatial and temporal augmentation
Spatial Augmentation:
Spring-Joint-based
Sensor Module
Temporal Augmentation:
Playback Speed
11
Method: spatial and temporal augmentation
Spatial Augmentation:
Spring-Joint-based
Sensor Module
Temporal Augmentation:
Playback Speed
12
Method: spring-joint module design
1 module  consists of 3 nodes
13
Method: adding multiple modules
(The modules follow the movement of Right Upper Leg)
14
Method: the nodes connection and parameters
Different stiffness of spring-joint: Different structure of spring-joint:
Choose four stiffness 0.2, 0.4, 0.6, 0.8 Two types of connection structure
15
Method: spatial and temporal augmentation
Spatial Augmentation:
Spring-Joint-based
Sensor Module
Temporal Augmentation:
Playback Speed
16
Method: data augmentation by motion speed shift
Speed adjustment:
access the time scale to shift the motion speed
17
Method: coordinate transformation
Virtual
acceleration
Real acceleration
Same sensor
coordinate
Coordinate
transformation
Coordinate
transformation
Fusion &
Normalization
z
y
x
Uniform coordinate
18
Experiment: validation method
Virtual
dataset
(initial):
Real
dataset
Purpose: validate of effeteness of proposed method
Virtual dataset
(with
augmentation):
Real
dataset
Real
dataset
Classifier
Result
Real
dataset
Train Test
Classifier
Result
Train Test
Classifier
Result
Train Test
Baseline 1: Baseline 2:
Proposed method:
Leave-one-subject-out
Experiment: tested exercise motions
Test motions: 3 types of aerobic exercises from YouTube online sources, 20 seconds
3D motion conversion: DeepMotion [1]
19
[1] https://www.deepmotion.com/
Reverse Lunge Warm Up High Knee Tap
21
Experiment: information
• Real sensor: Xsens Dot [1]
• Participants: 7 people
Conduct the exercises by 90 seconds
• Classifiers: SVM, Random Forest, Decision Tree
• Handcrafted features:
• Sensor Location: Right upper leg
Time & Frequency features
2-dimension features
PCA
[1] https://www.xsens.com/xsens-dot
• Virtual dataset (initial):
• 20s * 3 motions
• Virtual dataset (with augmentation):
• 20s * 8 modules * 3 nodes * 3 speeds * 3 motions
• Real dataset: for testing
• 90s * 3 motions * 7 participants
22
Experiment: Result
PCA-1
PCA-2
Virtual ReverseLunge
Real ReverseLunge
Real HighKnee
Virtual HighKnee
Real HighKnee
Virtual HighKnee
Method
(Random
Forest)
Baseline 1
(initial
virutal
data)
Baseline 2
(using
real data)
Proposed
Method
(spring-
joint
module)
Accuracy 45.5 % 78.2 % 85.3 %
23
Discussion and Limitation
Further evaluation of different physical simulation parameters
Test on more motions
Virtual-to-real data features -> domain-invariant features
24
Summary
Background
Virtual IMU data suffers from limited 3D motion length,
which leads to less virtual data samples
Related Work Virtual sensor data/Time-series data augmentation
Proposed
Scheme
Using the spring-joint module to simulate different
acceleration distribution and augment virtual acceleration
data
Details
Method
Spring-joint connection/playback speed adjust/domain
adaption
Experiment Tested on there aerobic exercises picked from YouTube
Result
Using proposed augmentation method can get 85% vs. 45%
from not augmented
Limitation More motions tested/Boundary condition test
virtual acceleration 3 virtual acceleration 1
virtual acceleration 2
real acceleration
Thank you very much!

More Related Content

Similar to Virtual IMU Data Augmentation by Spring-Joint Model for Motion Exercises Recognition without Using Real Data

Design and Evaluation Case Study: Evaluating The Kinect Device In The Task of...
Design and Evaluation Case Study: Evaluating The Kinect Device In The Task of...Design and Evaluation Case Study: Evaluating The Kinect Device In The Task of...
Design and Evaluation Case Study: Evaluating The Kinect Device In The Task of...
Waqas Tariq
 
MOTION PREDICTION USING DEPTH INFORMATION OF HUMAN ARM BASED ON ALEXNET
MOTION PREDICTION USING DEPTH INFORMATION OF HUMAN ARM BASED ON ALEXNETMOTION PREDICTION USING DEPTH INFORMATION OF HUMAN ARM BASED ON ALEXNET
MOTION PREDICTION USING DEPTH INFORMATION OF HUMAN ARM BASED ON ALEXNET
gerogepatton
 
Motion Prediction Using Depth Information of Human Arm Based on Alexnet
Motion Prediction Using Depth Information of Human Arm Based on AlexnetMotion Prediction Using Depth Information of Human Arm Based on Alexnet
Motion Prediction Using Depth Information of Human Arm Based on Alexnet
gerogepatton
 
An analysis of desktop control and information retrieval from the internet us...
An analysis of desktop control and information retrieval from the internet us...An analysis of desktop control and information retrieval from the internet us...
An analysis of desktop control and information retrieval from the internet us...
eSAT Journals
 
An analysis of desktop control and information retrieval from the internet us...
An analysis of desktop control and information retrieval from the internet us...An analysis of desktop control and information retrieval from the internet us...
An analysis of desktop control and information retrieval from the internet us...
eSAT Publishing House
 
Development of Real-World Sensor Optimal Placement Support Software(AsianCHI2...
Development of Real-World Sensor Optimal Placement Support Software(AsianCHI2...Development of Real-World Sensor Optimal Placement Support Software(AsianCHI2...
Development of Real-World Sensor Optimal Placement Support Software(AsianCHI2...
sugiuralab
 
Real-time human activity recognition from smart phone using linear support ve...
Real-time human activity recognition from smart phone using linear support ve...Real-time human activity recognition from smart phone using linear support ve...
Real-time human activity recognition from smart phone using linear support ve...
TELKOMNIKA JOURNAL
 
Human Activity Recognition Using Recurrent Neural Network
Human Activity Recognition Using Recurrent Neural NetworkHuman Activity Recognition Using Recurrent Neural Network
Human Activity Recognition Using Recurrent Neural Network
mlaij
 
GaitProjectProposal
GaitProjectProposalGaitProjectProposal
GaitProjectProposalVivek Kumar
 
IRJET- Human Activity Recognition using Flex Sensors
IRJET- Human Activity Recognition using Flex SensorsIRJET- Human Activity Recognition using Flex Sensors
IRJET- Human Activity Recognition using Flex Sensors
IRJET Journal
 
Real-time Multimodal Feedback with the CPR Tutor
Real-time Multimodal Feedback with the CPR TutorReal-time Multimodal Feedback with the CPR Tutor
Real-time Multimodal Feedback with the CPR Tutor
Daniele Di Mitri
 
Analysis of Inertial Sensor Data Using Trajectory Recognition Algorithm
Analysis of Inertial Sensor Data Using Trajectory Recognition AlgorithmAnalysis of Inertial Sensor Data Using Trajectory Recognition Algorithm
Analysis of Inertial Sensor Data Using Trajectory Recognition Algorithm
ijcisjournal
 
System for Fingerprint Image Analysis
System for Fingerprint Image AnalysisSystem for Fingerprint Image Analysis
System for Fingerprint Image Analysis
vivatechijri
 
Daily Human Activity Recognition using Adaboost Classifiers on Wisdm Dataset
Daily Human Activity Recognition using Adaboost Classifiers on Wisdm DatasetDaily Human Activity Recognition using Adaboost Classifiers on Wisdm Dataset
Daily Human Activity Recognition using Adaboost Classifiers on Wisdm Dataset
ijtsrd
 
Your Device May Know You Better Than You Know Yourself-Continuous Authenticat...
Your Device May Know You Better Than You Know Yourself-Continuous Authenticat...Your Device May Know You Better Than You Know Yourself-Continuous Authenticat...
Your Device May Know You Better Than You Know Yourself-Continuous Authenticat...
AIRCC Publishing Corporation
 
Human Movement Recognition Using Internal Sensors of a Smartphone-based HMD (...
Human Movement Recognition Using Internal Sensors of a Smartphone-based HMD (...Human Movement Recognition Using Internal Sensors of a Smartphone-based HMD (...
Human Movement Recognition Using Internal Sensors of a Smartphone-based HMD (...
sugiuralab
 
Embedded Sensing and Computational Behaviour Science
Embedded Sensing and Computational Behaviour ScienceEmbedded Sensing and Computational Behaviour Science
Embedded Sensing and Computational Behaviour Science
Daniel Roggen
 
IRJET= Air Writing: Gesture Recognition using Ultrasound Sensors and Grid-Eye...
IRJET= Air Writing: Gesture Recognition using Ultrasound Sensors and Grid-Eye...IRJET= Air Writing: Gesture Recognition using Ultrasound Sensors and Grid-Eye...
IRJET= Air Writing: Gesture Recognition using Ultrasound Sensors and Grid-Eye...
IRJET Journal
 

Similar to Virtual IMU Data Augmentation by Spring-Joint Model for Motion Exercises Recognition without Using Real Data (20)

Design and Evaluation Case Study: Evaluating The Kinect Device In The Task of...
Design and Evaluation Case Study: Evaluating The Kinect Device In The Task of...Design and Evaluation Case Study: Evaluating The Kinect Device In The Task of...
Design and Evaluation Case Study: Evaluating The Kinect Device In The Task of...
 
MOTION PREDICTION USING DEPTH INFORMATION OF HUMAN ARM BASED ON ALEXNET
MOTION PREDICTION USING DEPTH INFORMATION OF HUMAN ARM BASED ON ALEXNETMOTION PREDICTION USING DEPTH INFORMATION OF HUMAN ARM BASED ON ALEXNET
MOTION PREDICTION USING DEPTH INFORMATION OF HUMAN ARM BASED ON ALEXNET
 
Motion Prediction Using Depth Information of Human Arm Based on Alexnet
Motion Prediction Using Depth Information of Human Arm Based on AlexnetMotion Prediction Using Depth Information of Human Arm Based on Alexnet
Motion Prediction Using Depth Information of Human Arm Based on Alexnet
 
An analysis of desktop control and information retrieval from the internet us...
An analysis of desktop control and information retrieval from the internet us...An analysis of desktop control and information retrieval from the internet us...
An analysis of desktop control and information retrieval from the internet us...
 
An analysis of desktop control and information retrieval from the internet us...
An analysis of desktop control and information retrieval from the internet us...An analysis of desktop control and information retrieval from the internet us...
An analysis of desktop control and information retrieval from the internet us...
 
Development of Real-World Sensor Optimal Placement Support Software(AsianCHI2...
Development of Real-World Sensor Optimal Placement Support Software(AsianCHI2...Development of Real-World Sensor Optimal Placement Support Software(AsianCHI2...
Development of Real-World Sensor Optimal Placement Support Software(AsianCHI2...
 
final ppt
final pptfinal ppt
final ppt
 
Real-time human activity recognition from smart phone using linear support ve...
Real-time human activity recognition from smart phone using linear support ve...Real-time human activity recognition from smart phone using linear support ve...
Real-time human activity recognition from smart phone using linear support ve...
 
Human Activity Recognition Using Recurrent Neural Network
Human Activity Recognition Using Recurrent Neural NetworkHuman Activity Recognition Using Recurrent Neural Network
Human Activity Recognition Using Recurrent Neural Network
 
GaitProjectProposal
GaitProjectProposalGaitProjectProposal
GaitProjectProposal
 
IRJET- Human Activity Recognition using Flex Sensors
IRJET- Human Activity Recognition using Flex SensorsIRJET- Human Activity Recognition using Flex Sensors
IRJET- Human Activity Recognition using Flex Sensors
 
Real-time Multimodal Feedback with the CPR Tutor
Real-time Multimodal Feedback with the CPR TutorReal-time Multimodal Feedback with the CPR Tutor
Real-time Multimodal Feedback with the CPR Tutor
 
Analysis of Inertial Sensor Data Using Trajectory Recognition Algorithm
Analysis of Inertial Sensor Data Using Trajectory Recognition AlgorithmAnalysis of Inertial Sensor Data Using Trajectory Recognition Algorithm
Analysis of Inertial Sensor Data Using Trajectory Recognition Algorithm
 
System for Fingerprint Image Analysis
System for Fingerprint Image AnalysisSystem for Fingerprint Image Analysis
System for Fingerprint Image Analysis
 
Daily Human Activity Recognition using Adaboost Classifiers on Wisdm Dataset
Daily Human Activity Recognition using Adaboost Classifiers on Wisdm DatasetDaily Human Activity Recognition using Adaboost Classifiers on Wisdm Dataset
Daily Human Activity Recognition using Adaboost Classifiers on Wisdm Dataset
 
Your Device May Know You Better Than You Know Yourself-Continuous Authenticat...
Your Device May Know You Better Than You Know Yourself-Continuous Authenticat...Your Device May Know You Better Than You Know Yourself-Continuous Authenticat...
Your Device May Know You Better Than You Know Yourself-Continuous Authenticat...
 
Human Movement Recognition Using Internal Sensors of a Smartphone-based HMD (...
Human Movement Recognition Using Internal Sensors of a Smartphone-based HMD (...Human Movement Recognition Using Internal Sensors of a Smartphone-based HMD (...
Human Movement Recognition Using Internal Sensors of a Smartphone-based HMD (...
 
Embedded Sensing and Computational Behaviour Science
Embedded Sensing and Computational Behaviour ScienceEmbedded Sensing and Computational Behaviour Science
Embedded Sensing and Computational Behaviour Science
 
IRJET= Air Writing: Gesture Recognition using Ultrasound Sensors and Grid-Eye...
IRJET= Air Writing: Gesture Recognition using Ultrasound Sensors and Grid-Eye...IRJET= Air Writing: Gesture Recognition using Ultrasound Sensors and Grid-Eye...
IRJET= Air Writing: Gesture Recognition using Ultrasound Sensors and Grid-Eye...
 
micwic2013_poster
micwic2013_postermicwic2013_poster
micwic2013_poster
 

More from sugiuralab

ShadoCookies: 視点位置に依存して情報切り替え可能なクッキー製造手法
ShadoCookies: 視点位置に依存して情報切り替え可能なクッキー製造手法ShadoCookies: 視点位置に依存して情報切り替え可能なクッキー製造手法
ShadoCookies: 視点位置に依存して情報切り替え可能なクッキー製造手法
sugiuralab
 
TataPixel: 畳の異方性を利用した切り替え可能なディスプレイの提案
TataPixel: 畳の異方性を利用した切り替え可能なディスプレイの提案TataPixel: 畳の異方性を利用した切り替え可能なディスプレイの提案
TataPixel: 畳の異方性を利用した切り替え可能なディスプレイの提案
sugiuralab
 
Selfie WanD: 自撮り棒を動かすことによる撮影用入力インタフェース
Selfie WanD: 自撮り棒を動かすことによる撮影用入力インタフェースSelfie WanD: 自撮り棒を動かすことによる撮影用入力インタフェース
Selfie WanD: 自撮り棒を動かすことによる撮影用入力インタフェース
sugiuralab
 
スマートフォンを用いた新生児あやし動作の教示システム
スマートフォンを用いた新生児あやし動作の教示システムスマートフォンを用いた新生児あやし動作の教示システム
スマートフォンを用いた新生児あやし動作の教示システム
sugiuralab
 
EarAuthCam: Personal Identification and Authentication Method Using Ear Image...
EarAuthCam: Personal Identification and Authentication Method Using Ear Image...EarAuthCam: Personal Identification and Authentication Method Using Ear Image...
EarAuthCam: Personal Identification and Authentication Method Using Ear Image...
sugiuralab
 
プレイマットのパターン生成支援ツールの評価
プレイマットのパターン生成支援ツールの評価プレイマットのパターン生成支援ツールの評価
プレイマットのパターン生成支援ツールの評価
sugiuralab
 
プレイマットのパターン生成支援ツール
プレイマットのパターン生成支援ツールプレイマットのパターン生成支援ツール
プレイマットのパターン生成支援ツール
sugiuralab
 
EarHover:ヒアラブルデバイスにおける音漏れ信号を用いた空中ジェスチャ認識
EarHover:ヒアラブルデバイスにおける音漏れ信号を用いた空中ジェスチャ認識EarHover:ヒアラブルデバイスにおける音漏れ信号を用いた空中ジェスチャ認識
EarHover:ヒアラブルデバイスにおける音漏れ信号を用いた空中ジェスチャ認識
sugiuralab
 
SkinRing: 装着方向に依らない指側面でのジェスチャ入力可能なリング型デバイス
SkinRing: 装着方向に依らない指側面でのジェスチャ入力可能なリング型デバイスSkinRing: 装着方向に依らない指側面でのジェスチャ入力可能なリング型デバイス
SkinRing: 装着方向に依らない指側面でのジェスチャ入力可能なリング型デバイス
sugiuralab
 
バイオリンの運弓動作計測による初心者と経験者の差異分析
バイオリンの運弓動作計測による初心者と経験者の差異分析バイオリンの運弓動作計測による初心者と経験者の差異分析
バイオリンの運弓動作計測による初心者と経験者の差異分析
sugiuralab
 
Converting Tatamis into Touch Sensors by Measuring Capacitance
Converting Tatamis into Touch Sensors by Measuring CapacitanceConverting Tatamis into Touch Sensors by Measuring Capacitance
Converting Tatamis into Touch Sensors by Measuring Capacitance
sugiuralab
 
Pinch Force Measurement Using a Geomagnetic Sensor
Pinch Force Measurement Using a Geomagnetic SensorPinch Force Measurement Using a Geomagnetic Sensor
Pinch Force Measurement Using a Geomagnetic Sensor
sugiuralab
 
Smartphone-Based Teaching System for Neonate Soothing Motions
Smartphone-Based Teaching System for Neonate Soothing MotionsSmartphone-Based Teaching System for Neonate Soothing Motions
Smartphone-Based Teaching System for Neonate Soothing Motions
sugiuralab
 
Tactile Presentation of Orchestral Conductor's Motion Trajectory
Tactile Presentation of Orchestral Conductor's Motion TrajectoryTactile Presentation of Orchestral Conductor's Motion Trajectory
Tactile Presentation of Orchestral Conductor's Motion Trajectory
sugiuralab
 
TouchLog: Finger Micro Gesture Recognition Using Photo-Reflective Sensors
TouchLog: Finger Micro Gesture Recognition  Using Photo-Reflective SensorsTouchLog: Finger Micro Gesture Recognition  Using Photo-Reflective Sensors
TouchLog: Finger Micro Gesture Recognition Using Photo-Reflective Sensors
sugiuralab
 
Seeing the Wind: An Interactive Mist Interface for Airflow Input
Seeing the Wind: An Interactive Mist Interface for Airflow InputSeeing the Wind: An Interactive Mist Interface for Airflow Input
Seeing the Wind: An Interactive Mist Interface for Airflow Input
sugiuralab
 
Identification and Authentication Using Clavicles
Identification and Authentication Using ClaviclesIdentification and Authentication Using Clavicles
Identification and Authentication Using Clavicles
sugiuralab
 
Estimation of Violin Bow Pressure Using Photo-Reflective Sensors
Estimation of Violin Bow Pressure Using Photo-Reflective SensorsEstimation of Violin Bow Pressure Using Photo-Reflective Sensors
Estimation of Violin Bow Pressure Using Photo-Reflective Sensors
sugiuralab
 
バウンサーを動かす外付けデバイス
バウンサーを動かす外付けデバイスバウンサーを動かす外付けデバイス
バウンサーを動かす外付けデバイス
sugiuralab
 
A Virtual Window Using Curtains and Image Projection
A Virtual Window Using Curtains and Image ProjectionA Virtual Window Using Curtains and Image Projection
A Virtual Window Using Curtains and Image Projection
sugiuralab
 

More from sugiuralab (20)

ShadoCookies: 視点位置に依存して情報切り替え可能なクッキー製造手法
ShadoCookies: 視点位置に依存して情報切り替え可能なクッキー製造手法ShadoCookies: 視点位置に依存して情報切り替え可能なクッキー製造手法
ShadoCookies: 視点位置に依存して情報切り替え可能なクッキー製造手法
 
TataPixel: 畳の異方性を利用した切り替え可能なディスプレイの提案
TataPixel: 畳の異方性を利用した切り替え可能なディスプレイの提案TataPixel: 畳の異方性を利用した切り替え可能なディスプレイの提案
TataPixel: 畳の異方性を利用した切り替え可能なディスプレイの提案
 
Selfie WanD: 自撮り棒を動かすことによる撮影用入力インタフェース
Selfie WanD: 自撮り棒を動かすことによる撮影用入力インタフェースSelfie WanD: 自撮り棒を動かすことによる撮影用入力インタフェース
Selfie WanD: 自撮り棒を動かすことによる撮影用入力インタフェース
 
スマートフォンを用いた新生児あやし動作の教示システム
スマートフォンを用いた新生児あやし動作の教示システムスマートフォンを用いた新生児あやし動作の教示システム
スマートフォンを用いた新生児あやし動作の教示システム
 
EarAuthCam: Personal Identification and Authentication Method Using Ear Image...
EarAuthCam: Personal Identification and Authentication Method Using Ear Image...EarAuthCam: Personal Identification and Authentication Method Using Ear Image...
EarAuthCam: Personal Identification and Authentication Method Using Ear Image...
 
プレイマットのパターン生成支援ツールの評価
プレイマットのパターン生成支援ツールの評価プレイマットのパターン生成支援ツールの評価
プレイマットのパターン生成支援ツールの評価
 
プレイマットのパターン生成支援ツール
プレイマットのパターン生成支援ツールプレイマットのパターン生成支援ツール
プレイマットのパターン生成支援ツール
 
EarHover:ヒアラブルデバイスにおける音漏れ信号を用いた空中ジェスチャ認識
EarHover:ヒアラブルデバイスにおける音漏れ信号を用いた空中ジェスチャ認識EarHover:ヒアラブルデバイスにおける音漏れ信号を用いた空中ジェスチャ認識
EarHover:ヒアラブルデバイスにおける音漏れ信号を用いた空中ジェスチャ認識
 
SkinRing: 装着方向に依らない指側面でのジェスチャ入力可能なリング型デバイス
SkinRing: 装着方向に依らない指側面でのジェスチャ入力可能なリング型デバイスSkinRing: 装着方向に依らない指側面でのジェスチャ入力可能なリング型デバイス
SkinRing: 装着方向に依らない指側面でのジェスチャ入力可能なリング型デバイス
 
バイオリンの運弓動作計測による初心者と経験者の差異分析
バイオリンの運弓動作計測による初心者と経験者の差異分析バイオリンの運弓動作計測による初心者と経験者の差異分析
バイオリンの運弓動作計測による初心者と経験者の差異分析
 
Converting Tatamis into Touch Sensors by Measuring Capacitance
Converting Tatamis into Touch Sensors by Measuring CapacitanceConverting Tatamis into Touch Sensors by Measuring Capacitance
Converting Tatamis into Touch Sensors by Measuring Capacitance
 
Pinch Force Measurement Using a Geomagnetic Sensor
Pinch Force Measurement Using a Geomagnetic SensorPinch Force Measurement Using a Geomagnetic Sensor
Pinch Force Measurement Using a Geomagnetic Sensor
 
Smartphone-Based Teaching System for Neonate Soothing Motions
Smartphone-Based Teaching System for Neonate Soothing MotionsSmartphone-Based Teaching System for Neonate Soothing Motions
Smartphone-Based Teaching System for Neonate Soothing Motions
 
Tactile Presentation of Orchestral Conductor's Motion Trajectory
Tactile Presentation of Orchestral Conductor's Motion TrajectoryTactile Presentation of Orchestral Conductor's Motion Trajectory
Tactile Presentation of Orchestral Conductor's Motion Trajectory
 
TouchLog: Finger Micro Gesture Recognition Using Photo-Reflective Sensors
TouchLog: Finger Micro Gesture Recognition  Using Photo-Reflective SensorsTouchLog: Finger Micro Gesture Recognition  Using Photo-Reflective Sensors
TouchLog: Finger Micro Gesture Recognition Using Photo-Reflective Sensors
 
Seeing the Wind: An Interactive Mist Interface for Airflow Input
Seeing the Wind: An Interactive Mist Interface for Airflow InputSeeing the Wind: An Interactive Mist Interface for Airflow Input
Seeing the Wind: An Interactive Mist Interface for Airflow Input
 
Identification and Authentication Using Clavicles
Identification and Authentication Using ClaviclesIdentification and Authentication Using Clavicles
Identification and Authentication Using Clavicles
 
Estimation of Violin Bow Pressure Using Photo-Reflective Sensors
Estimation of Violin Bow Pressure Using Photo-Reflective SensorsEstimation of Violin Bow Pressure Using Photo-Reflective Sensors
Estimation of Violin Bow Pressure Using Photo-Reflective Sensors
 
バウンサーを動かす外付けデバイス
バウンサーを動かす外付けデバイスバウンサーを動かす外付けデバイス
バウンサーを動かす外付けデバイス
 
A Virtual Window Using Curtains and Image Projection
A Virtual Window Using Curtains and Image ProjectionA Virtual Window Using Curtains and Image Projection
A Virtual Window Using Curtains and Image Projection
 

Recently uploaded

Quantum Computing: Current Landscape and the Future Role of APIs
Quantum Computing: Current Landscape and the Future Role of APIsQuantum Computing: Current Landscape and the Future Role of APIs
Quantum Computing: Current Landscape and the Future Role of APIs
Vlad Stirbu
 
Enhancing Performance with Globus and the Science DMZ
Enhancing Performance with Globus and the Science DMZEnhancing Performance with Globus and the Science DMZ
Enhancing Performance with Globus and the Science DMZ
Globus
 
PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)
Ralf Eggert
 
The Metaverse and AI: how can decision-makers harness the Metaverse for their...
The Metaverse and AI: how can decision-makers harness the Metaverse for their...The Metaverse and AI: how can decision-makers harness the Metaverse for their...
The Metaverse and AI: how can decision-makers harness the Metaverse for their...
Jen Stirrup
 
Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?
Nexer Digital
 
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
BookNet Canada
 
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex ProofszkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
Alex Pruden
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance
 
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptxSecstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
nkrafacyberclub
 
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Albert Hoitingh
 
Essentials of Automations: The Art of Triggers and Actions in FME
Essentials of Automations: The Art of Triggers and Actions in FMEEssentials of Automations: The Art of Triggers and Actions in FME
Essentials of Automations: The Art of Triggers and Actions in FME
Safe Software
 
UiPath Community Day Dubai: AI at Work..
UiPath Community Day Dubai: AI at Work..UiPath Community Day Dubai: AI at Work..
UiPath Community Day Dubai: AI at Work..
UiPathCommunity
 
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdfFIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
KatiaHIMEUR1
 
Free Complete Python - A step towards Data Science
Free Complete Python - A step towards Data ScienceFree Complete Python - A step towards Data Science
Free Complete Python - A step towards Data Science
RinaMondal9
 
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
UiPathCommunity
 
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
James Anderson
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
UiPathCommunity
 
Climate Impact of Software Testing at Nordic Testing Days
Climate Impact of Software Testing at Nordic Testing DaysClimate Impact of Software Testing at Nordic Testing Days
Climate Impact of Software Testing at Nordic Testing Days
Kari Kakkonen
 
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdfSAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
Peter Spielvogel
 

Recently uploaded (20)

Quantum Computing: Current Landscape and the Future Role of APIs
Quantum Computing: Current Landscape and the Future Role of APIsQuantum Computing: Current Landscape and the Future Role of APIs
Quantum Computing: Current Landscape and the Future Role of APIs
 
Enhancing Performance with Globus and the Science DMZ
Enhancing Performance with Globus and the Science DMZEnhancing Performance with Globus and the Science DMZ
Enhancing Performance with Globus and the Science DMZ
 
PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)PHP Frameworks: I want to break free (IPC Berlin 2024)
PHP Frameworks: I want to break free (IPC Berlin 2024)
 
The Metaverse and AI: how can decision-makers harness the Metaverse for their...
The Metaverse and AI: how can decision-makers harness the Metaverse for their...The Metaverse and AI: how can decision-makers harness the Metaverse for their...
The Metaverse and AI: how can decision-makers harness the Metaverse for their...
 
Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?Elizabeth Buie - Older adults: Are we really designing for our future selves?
Elizabeth Buie - Older adults: Are we really designing for our future selves?
 
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...Transcript: Selling digital books in 2024: Insights from industry leaders - T...
Transcript: Selling digital books in 2024: Insights from industry leaders - T...
 
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex ProofszkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
zkStudyClub - Reef: Fast Succinct Non-Interactive Zero-Knowledge Regex Proofs
 
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdfFIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
FIDO Alliance Osaka Seminar: Passkeys at Amazon.pdf
 
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptxSecstrike : Reverse Engineering & Pwnable tools for CTF.pptx
Secstrike : Reverse Engineering & Pwnable tools for CTF.pptx
 
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
 
Essentials of Automations: The Art of Triggers and Actions in FME
Essentials of Automations: The Art of Triggers and Actions in FMEEssentials of Automations: The Art of Triggers and Actions in FME
Essentials of Automations: The Art of Triggers and Actions in FME
 
UiPath Community Day Dubai: AI at Work..
UiPath Community Day Dubai: AI at Work..UiPath Community Day Dubai: AI at Work..
UiPath Community Day Dubai: AI at Work..
 
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdfFIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
FIDO Alliance Osaka Seminar: Passkeys and the Road Ahead.pdf
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
 
Free Complete Python - A step towards Data Science
Free Complete Python - A step towards Data ScienceFree Complete Python - A step towards Data Science
Free Complete Python - A step towards Data Science
 
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
Le nuove frontiere dell'AI nell'RPA con UiPath Autopilot™
 
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
 
Climate Impact of Software Testing at Nordic Testing Days
Climate Impact of Software Testing at Nordic Testing DaysClimate Impact of Software Testing at Nordic Testing Days
Climate Impact of Software Testing at Nordic Testing Days
 
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdfSAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
SAP Sapphire 2024 - ASUG301 building better apps with SAP Fiori.pdf
 

Virtual IMU Data Augmentation by Spring-Joint Model for Motion Exercises Recognition without Using Real Data

  • 1. Virtual IMU Data Augmentation by Spring-Joint Model for Motion Exercises Recognition without Using Real Data 2022 ACM ISWC (note) Chengshuo Xia, Yuta Sugiura Keio University, Japan
  • 2. 2 Background: real IMU dataset for motion recognition Participants Wearing sensor Produce the data Real wearable IMU sensor data collection: time-costly and expensive. Opportunity dataset [1] [1] Daniel Roggen, Alberto Calatroni, Mirco Rossi, Thomas Holleczek, Gerhard Tröster, Paul Lukowicz, Gerald Pirkl, David Bannach, Alois Ferscha, Jakob Doppler, Clemens Holzmann, Marc Kurz, Gerald Holl, Ricardo Chavarriaga, Hesam Sagha, Hamidreza Bayati, and José del R. Millàn. "Collecting complex activity data sets in highly rich networked sensor environments" In Seventh International Conference on Networked Sensing Systems (INSS’10), Kassel, Germany, 2010. Dataset Dataset Machine learning model Application Change Real world A motion recognition system: machine learning (ML).
  • 3. 3 Background: virtual IMU sensor data in machine learning Virtual sensor data generation help to reduce the dataset cost. Dataset Machine learning model Application Change Virtual sensor data Simulation envrionment Virtual IMU sensor data extraction from 3D human motion:
  • 4. 4 Background: current problems in virtual data • Limited 3D motion length. • Obtaining a longer 3D motion length still is time-consuming. • Real data distribution is needed.
  • 5. 5 Proposed Method: spring-joint module-based data augmentation • Spring-joint virtual IMU sensor module. • Used for training the classifier. • Recognize the real IMU data. More virtual sensor data Spring-Joint virtual sensor module 3D motion Training the ML model
  • 6. 6 Related Work: virtual sensor data for human motion recognition Virtual IMU data: IMUTube [1] Virtual Doppler data: Vid2Doppler [2] Virtual distance data [3] [1] Kwon, Hyeokhyen, et al. "IMUTube: Automatic extraction of virtual on-body accelerometry from video for human activity recognition." Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 4.3 (2020): 1-29. [2] Ahuja, Karan, et al. "Vid2Doppler: synthesizing Doppler radar data from videos for training privacy-preserving activity recognition." Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems. 2021. [3] Xia, Chengshuo, Ayane Saito, and Yuta Sugiura. "Using the virtual data-driven measurement to support the prototyping of hand gesture recognition interface with distance sensor." Sensors and Actuators A: Physical 338 (2022): 113463.
  • 7. 7 Related Work: data augmentation for time-series [1] Li, Xi'ang, Jinqi Luo, and Rabih Younes. "ActivityGAN: Generative adversarial networks for data augmentation in sensor-based human activity recognition." Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers. 2020. [2] Um, Terry T., et al. "Data augmentation of wearable sensor data for parkinson’s disease monitoring using convolutional neural networks." Proceedings of the 19th ACM international conference on multimodal interaction. 2017. GAN-based [1]: Time-series manipulation [2]: Traditional augmentation: operate on real data Our method: augment the virtual sensor data
  • 8. 8 Overview of Proposed Method More virtual sensor data Spring-joint virtual IMU sensor module Machine learning model 3D human motion Recognize the real motion
  • 9. 9 Method: how to obtain the virtual acceleration data Posistion Velocity Acceleration [1] Young, Alexander D., Martin J. Ling, and Damal K. Arvind. "IMUSim: A simulation environment for inertial sensing algorithm design and evaluation." Proceedings of the 10th ACM/IEEE International Conference on Information Processing in Sensor Networks. IEEE, 2011.
  • 10. 10 Method: spatial and temporal augmentation Spatial Augmentation: Spring-Joint-based Sensor Module Temporal Augmentation: Playback Speed
  • 11. 11 Method: spatial and temporal augmentation Spatial Augmentation: Spring-Joint-based Sensor Module Temporal Augmentation: Playback Speed
  • 12. 12 Method: spring-joint module design 1 module  consists of 3 nodes
  • 13. 13 Method: adding multiple modules (The modules follow the movement of Right Upper Leg)
  • 14. 14 Method: the nodes connection and parameters Different stiffness of spring-joint: Different structure of spring-joint: Choose four stiffness 0.2, 0.4, 0.6, 0.8 Two types of connection structure
  • 15. 15 Method: spatial and temporal augmentation Spatial Augmentation: Spring-Joint-based Sensor Module Temporal Augmentation: Playback Speed
  • 16. 16 Method: data augmentation by motion speed shift Speed adjustment: access the time scale to shift the motion speed
  • 17. 17 Method: coordinate transformation Virtual acceleration Real acceleration Same sensor coordinate Coordinate transformation Coordinate transformation Fusion & Normalization z y x Uniform coordinate
  • 18. 18 Experiment: validation method Virtual dataset (initial): Real dataset Purpose: validate of effeteness of proposed method Virtual dataset (with augmentation): Real dataset Real dataset Classifier Result Real dataset Train Test Classifier Result Train Test Classifier Result Train Test Baseline 1: Baseline 2: Proposed method: Leave-one-subject-out
  • 19. Experiment: tested exercise motions Test motions: 3 types of aerobic exercises from YouTube online sources, 20 seconds 3D motion conversion: DeepMotion [1] 19 [1] https://www.deepmotion.com/ Reverse Lunge Warm Up High Knee Tap
  • 20. 21 Experiment: information • Real sensor: Xsens Dot [1] • Participants: 7 people Conduct the exercises by 90 seconds • Classifiers: SVM, Random Forest, Decision Tree • Handcrafted features: • Sensor Location: Right upper leg Time & Frequency features 2-dimension features PCA [1] https://www.xsens.com/xsens-dot • Virtual dataset (initial): • 20s * 3 motions • Virtual dataset (with augmentation): • 20s * 8 modules * 3 nodes * 3 speeds * 3 motions • Real dataset: for testing • 90s * 3 motions * 7 participants
  • 21. 22 Experiment: Result PCA-1 PCA-2 Virtual ReverseLunge Real ReverseLunge Real HighKnee Virtual HighKnee Real HighKnee Virtual HighKnee Method (Random Forest) Baseline 1 (initial virutal data) Baseline 2 (using real data) Proposed Method (spring- joint module) Accuracy 45.5 % 78.2 % 85.3 %
  • 22. 23 Discussion and Limitation Further evaluation of different physical simulation parameters Test on more motions Virtual-to-real data features -> domain-invariant features
  • 23. 24 Summary Background Virtual IMU data suffers from limited 3D motion length, which leads to less virtual data samples Related Work Virtual sensor data/Time-series data augmentation Proposed Scheme Using the spring-joint module to simulate different acceleration distribution and augment virtual acceleration data Details Method Spring-joint connection/playback speed adjust/domain adaption Experiment Tested on there aerobic exercises picked from YouTube Result Using proposed augmentation method can get 85% vs. 45% from not augmented Limitation More motions tested/Boundary condition test virtual acceleration 3 virtual acceleration 1 virtual acceleration 2 real acceleration
  • 24. Thank you very much!