[PPT] - Quantitative hierarchical representation and comparison of hand PowerPoint Presentation

SLIDE 1

Page 1/19

Quantitative hierarchical representation and comparison of hand grasps from electromyography and kinematic data

Francesca Stival1,2, Stefano Michieletto1, Enrico Pagello1, Henning Mü̈ller2, and Manfredo Atzori2

1Intelligent Autonomous Systems Lab (IAS-Lab) Department of Information

Engineering (DEI), University of Padova, Italy

2Information Systems Institute, University of Applied Sciences Western

Switzerland (HES-SO Valais), Sierre, Switzerland

SLIDE 2

Page 2/19

What is a taxonomy

f hand grasps?

SLIDE 3

Page 3/19

What is a taxonomy

Taxonomy is the practice and science of classification.
A taxonomy is a particular classification scheme (hierarchical
r not).

SLIDE 4

Page 4/19

Hand grasp taxonomies

Several hand grasp taxonomies have been developed, based

n qualitative parameters:
Grasp force
Opposition (palm, pad, side)
Thumb adduction / abduction
Virtual finger opposition

SLIDE 5

Page 5/19

Usefulness of grasp taxonomies and current limits

Usefulness:

Robotics: to compare the functionality of robotic hands with real

human ones in different tasks

Prosthetics: to better define the requirements of prostheses and

control methods

Physiology: to create a link between hand synergies and real life

needs

Rehabilitation: to prioritize the hand functionalities to restore with

higher priority

Limits:

Lack of quantitative foundation
Subjectivity and interpretability
Quantitative evaluations and comparisons are not directly possible

SLIDE 6

Page 6/19

Methods: what is the Ninapro database for hand movements?

SLIDE 7

Page 7/19

Ninapro database

Publicly available (url: http://ninapro.hevs.ch)
7 datasets
More than 120 subjects
13 trans radial amputated subjects
~50 different movements
5 different acquisition setups

SLIDE 8

Page 8/19

Ninapro data acquisition

Kinematic data Cyberglove II sEMG Delsys Trigno Wireless System

SLIDE 9

Page 9/19

Database: Movements

Hato, 2004 Sebelius, 2005 Farrel, 2008 Crawford, 2005 Feix, 2008 DASH Score

! ! ! ! ! ! ! ! ! ! ! !

Exercise 1

12 movements

! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! !

Exercise 2

17 movements

! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! ! !

!

! !

Exercise 3

23 movements

Exercise 4

9 force patterns

SLIDE 10

Page 10/19

Double Myo ~ 300 € 8 Otto Bock ~ 6000 € 12 Cometa ~ 15’000 € 12 Delsys Trigno ~ 18’000 €

Recent results:

Effect of clinical parameters on accuracy

Body mass index
Remaining forearm percentage
Phantom limb sensation intensity
Years Since Amputation

Standardized comparison of different acquisition setups

Similar performance for pattern recognition tasks.

Atzori et al., Journal of Rehabilitation Research and Development, 2016

1 2 3 4 5 10 20 30 40 50 60

Phantom Limb Sensation Intensity (a.u) F (x) = 2.8 + 24.37x0.36 R 2 = 0.63 ± 0.06 p = 0.005 ± 0.004 Classification Accuracy (%) Classification Accuracy vs Phantom Limb Sensation

Pizzolato et al., PLOS One 2017

SLIDE 11

Page 11/19

Ongoing work

Reproducing eye-hand coordination in hand prosthetics using gaze, computer vision and sEMG.

Giordaniello et al., ICORR 2017, Cognolato et al., ICVS 2017

SLIDE 12

Page 12/19

Methods: subject specific quantitative taxonomies

SLIDE 13

Page 13/19

Movement hierarchical representation and comparison:

Subjects: 40 intact subject (Ninapro DB2)
Windowing: 200 ms (10 ms overlap)
Signal feature extraction: Root Mean Square, Mean & Integrated

Absolute Value, Waveform Length, Time Domain Statistics.

Movement hierarchical representation: one hierarchical tree for each

modality-feature combination (5 sEMG and 5 kinematic trees / subj.)

Comparison of trees: edit distance (minimal-cost sequence of node

edit operations required to obtain one tree from another)

SLIDE 14

Page 14/19

Results: differences between taxonomies

SLIDE 15

Page 15/19

Same subject, different signal features

IAV & MAV trees are almost identical (sEMG & kinematic)
RMS, IAV and MAV trees are very similar
Several characteristics are shared among different trees
TD trees are in general the most different

SLIDE 16

Page 16/19

Inter-subject differences

Most subjects have a similar behavior (similar to Subj. 2).
Some subjects have different results (e.g. Subject 9)

SLIDE 17

Page 17/19

Conclusions

SLIDE 18

Page 18/19

Conclusions

Quantitative hierarchical representations of hand movements

can be performed systematically with the proposed approach

The results can be compared and are usually similar

considering different subjects and features

We are currently creating a quantitative taxonomy of hand

movements that solves the limits of qualitative approaches.

SLIDE 19

Page 19/19

Thanks a lot to:

Francesca Stival

Dr. Stefano Michieletto
Prof. Henning Müller
Prof. Enrico Pagello