Deep Learning-Enabled Real Time In-Site Quality Inspection Based On Gesture Classification

Ioan-Matei Sarivan; Stefan Andreas Baumann; Daniel Díez Alvarez; Felix Euteneuer; Matthias Reichenbach; Ulrich Berger; Ole Madsen; Simon Bøgh

Deep Learning-Enabled Real Time In-Site Quality Inspection Based On Gesture Classification

Ioan-Matei Sarivan, Stefan Andreas Baumann, Daniel Díez Alvarez, Felix Euteneuer, Matthias Reichenbach, Ulrich Berger, Ole Madsen, Simon Bøgh

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

Abstract

In this paper we present a novel method for performing in site real time quality inspection (QI) and consequently, digitalization of manual processes performed by human workers. It complements and improves our previous work in this area, which makes use of telemetry gathered from a smartwatch to classify manual actions as successful or unsuccessful. This new methodology provides the worker with a real time capable, robust and more accurate quality inspector. This work enhances the existing system through the elimination of input from the user by making use of a BIOX bracelet that detects gestures. The signal pro- cessing and classification methods are simplified and optimised by using assembled neural networks thus merging together the data gathered from multiple signal sources. Consequently, the overall QI system is improved with around 70% thus furthering the necessary development needed to have a system ready to be used on a production environment.

Original language	English
Title of host publication	Advances in Automotive Production Technology - Theory and Application : Stuttgart Conference on Automotive Production (SCAP2020)
Editors	Philipp Weißgraeber, Frieder Heieck, Clemens Ackermann
Number of pages	9
Place of Publication	ARENA2036, Stuttgart
Publisher	Springer Nature
Publication date	2021
Pages	221-229
Article number	10
Chapter	C
ISBN (Print)	978-3-662-62961-1
ISBN (Electronic)	978-3-662-62962-8
Publication status	Published - 2021
Event	Stuttgart Conference on Automotive Production 2020 - Stuttgart, Germany Duration: 2 Nov 2020 → 10 Nov 2020 https://conference.arena2036.de/event/1/overview

Conference

Conference	Stuttgart Conference on Automotive Production 2020
Country/Territory	Germany
City	Stuttgart
Period	02/11/2020 → 10/11/2020
Internet address	https://conference.arena2036.de/event/1/overview

Series	ARENA2036
ISSN	2524-7247

Keywords

Deep Learning
Signal Processing
Smart Wearable Devices
MFCC
Convolutional Neural Network
Accelerometer data
Smart Manufacturing

Access to Document

https://link.springer.com/content/pdf/10.1007%2F978-3-662-62962-8_26.pdf

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

Sarivan, I.-M., Baumann, S. A., Díez Alvarez, D., Euteneuer, F., Reichenbach, M., Berger, U., Madsen, O., & Bøgh, S. (2021). Deep Learning-Enabled Real Time In-Site Quality Inspection Based On Gesture Classification. In P. Weißgraeber, F. Heieck, & C. A. (Eds.), Advances in Automotive Production Technology - Theory and Application: Stuttgart Conference on Automotive Production (SCAP2020) (pp. 221-229). Article 10 Springer Nature. https://link.springer.com/content/pdf/10.1007%2F978-3-662-62962-8_26.pdf

Sarivan, Ioan-Matei ; Baumann, Stefan Andreas ; Díez Alvarez, Daniel et al. / Deep Learning-Enabled Real Time In-Site Quality Inspection Based On Gesture Classification. Advances in Automotive Production Technology - Theory and Application: Stuttgart Conference on Automotive Production (SCAP2020). editor / Philipp Weißgraeber ; Frieder Heieck ; Clemens Ackermann. ARENA2036, Stuttgart : Springer Nature, 2021. pp. 221-229 (ARENA2036).

@inproceedings{ea38f321b4e9405886872578a45b06c4,

title = "Deep Learning-Enabled Real Time In-Site Quality Inspection Based On Gesture Classification",

abstract = "In this paper we present a novel method for performing in site real time quality inspection (QI) and consequently, digitalization of manual processes performed by human workers. It complements and improves our previous work in this area, which makes use of telemetry gathered from a smartwatch to classify manual actions as successful or unsuccessful. This new methodology provides the worker with a real time capable, robust and more accurate quality inspector. This work enhances the existing system through the elimination of input from the user by making use of a BIOX bracelet that detects gestures. The signal pro- cessing and classification methods are simplified and optimised by using assembled neural networks thus merging together the data gathered from multiple signal sources. Consequently, the overall QI system is improved with around 70% thus furthering the necessary development needed to have a system ready to be used on a production environment.",

keywords = "Deep Learning, Signal Processing, Smart Wearable Devices, MFCC, Convolutional Neural Network, Accelerometer data, Smart Manufacturing",

author = "Ioan-Matei Sarivan and Baumann, {Stefan Andreas} and {D{\'i}ez Alvarez}, Daniel and Felix Euteneuer and Matthias Reichenbach and Ulrich Berger and Ole Madsen and Simon B{\o}gh",

year = "2021",

language = "English",

isbn = "978-3-662-62961-1",

series = "ARENA2036",

publisher = "Springer Nature",

pages = "221--229",

editor = "Philipp Wei{\ss}graeber and Frieder Heieck and {Clemens Ackermann}",

booktitle = "Advances in Automotive Production Technology - Theory and Application",

address = "United States",

note = "Stuttgart Conference on Automotive Production 2020, SCAP2020 ; Conference date: 02-11-2020 Through 10-11-2020",

url = "https://conference.arena2036.de/event/1/overview",

}

Sarivan, I-M, Baumann, SA, Díez Alvarez, D, Euteneuer, F, Reichenbach, M, Berger, U, Madsen, O & Bøgh, S 2021, Deep Learning-Enabled Real Time In-Site Quality Inspection Based On Gesture Classification. in P Weißgraeber, F Heieck & CA (eds), Advances in Automotive Production Technology - Theory and Application: Stuttgart Conference on Automotive Production (SCAP2020)., 10, Springer Nature, ARENA2036, Stuttgart, ARENA2036, pp. 221-229, Stuttgart Conference on Automotive Production 2020, Stuttgart, Germany, 02/11/2020. <https://link.springer.com/content/pdf/10.1007%2F978-3-662-62962-8_26.pdf>

Deep Learning-Enabled Real Time In-Site Quality Inspection Based On Gesture Classification. / Sarivan, Ioan-Matei; Baumann, Stefan Andreas; Díez Alvarez, Daniel et al.
Advances in Automotive Production Technology - Theory and Application: Stuttgart Conference on Automotive Production (SCAP2020). ed. / Philipp Weißgraeber; Frieder Heieck; Clemens Ackermann. ARENA2036, Stuttgart: Springer Nature, 2021. p. 221-229 10 (ARENA2036).

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - Deep Learning-Enabled Real Time In-Site Quality Inspection Based On Gesture Classification

AU - Sarivan, Ioan-Matei

AU - Baumann, Stefan Andreas

AU - Díez Alvarez, Daniel

AU - Euteneuer, Felix

AU - Reichenbach, Matthias

AU - Berger, Ulrich

AU - Madsen, Ole

AU - Bøgh, Simon

PY - 2021

Y1 - 2021

N2 - In this paper we present a novel method for performing in site real time quality inspection (QI) and consequently, digitalization of manual processes performed by human workers. It complements and improves our previous work in this area, which makes use of telemetry gathered from a smartwatch to classify manual actions as successful or unsuccessful. This new methodology provides the worker with a real time capable, robust and more accurate quality inspector. This work enhances the existing system through the elimination of input from the user by making use of a BIOX bracelet that detects gestures. The signal pro- cessing and classification methods are simplified and optimised by using assembled neural networks thus merging together the data gathered from multiple signal sources. Consequently, the overall QI system is improved with around 70% thus furthering the necessary development needed to have a system ready to be used on a production environment.

AB - In this paper we present a novel method for performing in site real time quality inspection (QI) and consequently, digitalization of manual processes performed by human workers. It complements and improves our previous work in this area, which makes use of telemetry gathered from a smartwatch to classify manual actions as successful or unsuccessful. This new methodology provides the worker with a real time capable, robust and more accurate quality inspector. This work enhances the existing system through the elimination of input from the user by making use of a BIOX bracelet that detects gestures. The signal pro- cessing and classification methods are simplified and optimised by using assembled neural networks thus merging together the data gathered from multiple signal sources. Consequently, the overall QI system is improved with around 70% thus furthering the necessary development needed to have a system ready to be used on a production environment.

KW - Deep Learning

KW - Signal Processing

KW - Smart Wearable Devices

KW - MFCC

KW - Convolutional Neural Network

KW - Accelerometer data

KW - Smart Manufacturing

UR - https://link.springer.com/book/10.1007/978-3-662-62962-8

M3 - Article in proceeding

SN - 978-3-662-62961-1

T3 - ARENA2036

SP - 221

EP - 229

BT - Advances in Automotive Production Technology - Theory and Application

A2 - Weißgraeber, Philipp

A2 - Heieck, Frieder

A2 - , Clemens Ackermann

PB - Springer Nature

CY - ARENA2036, Stuttgart

T2 - Stuttgart Conference on Automotive Production 2020

Y2 - 2 November 2020 through 10 November 2020

ER -

Sarivan IM, Baumann SA, Díez Alvarez D, Euteneuer F, Reichenbach M, Berger U et al. Deep Learning-Enabled Real Time In-Site Quality Inspection Based On Gesture Classification. In Weißgraeber P, Heieck F, CA, editors, Advances in Automotive Production Technology - Theory and Application: Stuttgart Conference on Automotive Production (SCAP2020). ARENA2036, Stuttgart: Springer Nature. 2021. p. 221-229. 10. (ARENA2036).

Deep Learning-Enabled Real Time In-Site Quality Inspection Based On Gesture Classification

Abstract

Conference

Keywords

Access to Document

AUB Link

Other files and links

Fingerprint

SCAP2020 Best Presentation Award

Verfahren zur Überprüfung mindestens eines durch eine Person durchgeführten manuellen Arbeitsschritts

Cite this

Deep Learning-Enabled Real Time In-Site Quality Inspection Based On Gesture Classification

Abstract

Conference

Keywords

Access to Document

AUB Link

Other files and links

Fingerprint

Prizes

SCAP2020 Best Presentation Award

Research output

Verfahren zur Überprüfung mindestens eines durch eine Person durchgeführten manuellen Arbeitsschritts

Cite this