Strategically using applied machine learning for accessibility documentation in the built environment

Marvin Lange; Reuben Kirkham; Benjamin Tannert

doi:10.1007/978-3-030-85616-8_25

Strategically using applied machine learning for accessibility documentation in the built environment

Marvin Lange, Reuben Kirkham, Benjamin Tannert

Department of Human Centred Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

3 Citations (Scopus)

Abstract

There has been a considerable amount of research aimed at automating the documentation of accessibility in the built environment. Yet so far, there has been no fully automatic system that has been shown to reliably document surface quality barriers in the built environment in real-time. This is a mixed problem of HCI and applied machine learning, requiring the careful use of applied machine learning to address the real-world concern of practical documentation. To address this challenge, we offer a framework for designing applied machine learning approaches aimed at documenting the (in)accessibility of the built environment. This framework is designed to take into account the real-world picture, recognizing that the design of any accessibility documentation system has to take into account a range of factors that are not usually considered in machine learning research. We then apply this framework in a case study, illustrating an approach which can obtain a f-ratio of 0.952 in the best-case scenario.

Original language	English
Title of host publication	18th IFIP TC 13 International Conference Bari, Italy, August 30 – September 3, 2021 Proceedings, Part II
Editors	Carmelo Ardito, Rosa Lanzilotti, Alessio Malizia, Alessio Malizia, Helen Petrie, Antonio Piccinno, Giuseppe Desolda, Kori Inkpen
Place of Publication	Cham Switzerland
Publisher	Springer
Pages	426-448
Number of pages	23
ISBN (Electronic)	9783030856168
ISBN (Print)	9783030856151
DOIs	https://doi.org/10.1007/978-3-030-85616-8_25
Publication status	Published - 2021
Event	IFIP TC13 Conference on Human-Computer Interaction 2021 - Bari, Italy Duration: 30 Aug 2021 → 3 Sept 2021 Conference number: 18th https://link.springer.com/book/10.1007/978-3-030-85623-6 (Proceedings)

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	12933
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	IFIP TC13 Conference on Human-Computer Interaction 2021
Abbreviated title	INTERACT 2021
Country/Territory	Italy
City	Bari
Period	30/08/21 → 3/09/21
Internet address	https://link.springer.com/book/10.1007/978-3-030-85623-6 (Proceedings)

Keywords

Accessibility
Built-Environment
Documentation

Access to Document

10.1007/978-3-030-85616-8_25

Cite this

Lange, M., Kirkham, R., & Tannert, B. (2021). Strategically using applied machine learning for accessibility documentation in the built environment. In C. Ardito, R. Lanzilotti, A. Malizia, A. Malizia, H. Petrie, A. Piccinno, G. Desolda, & K. Inkpen (Eds.), 18th IFIP TC 13 International Conference Bari, Italy, August 30 – September 3, 2021 Proceedings, Part II (pp. 426-448). (Lecture Notes in Computer Science; Vol. 12933). Springer. https://doi.org/10.1007/978-3-030-85616-8_25

Lange, Marvin ; Kirkham, Reuben ; Tannert, Benjamin. / Strategically using applied machine learning for accessibility documentation in the built environment. 18th IFIP TC 13 International Conference Bari, Italy, August 30 – September 3, 2021 Proceedings, Part II. editor / Carmelo Ardito ; Rosa Lanzilotti ; Alessio Malizia ; Alessio Malizia ; Helen Petrie ; Antonio Piccinno ; Giuseppe Desolda ; Kori Inkpen. Cham Switzerland : Springer, 2021. pp. 426-448 (Lecture Notes in Computer Science).

@inproceedings{332d9cda747743268bc73f648b64879b,

title = "Strategically using applied machine learning for accessibility documentation in the built environment",

abstract = "There has been a considerable amount of research aimed at automating the documentation of accessibility in the built environment. Yet so far, there has been no fully automatic system that has been shown to reliably document surface quality barriers in the built environment in real-time. This is a mixed problem of HCI and applied machine learning, requiring the careful use of applied machine learning to address the real-world concern of practical documentation. To address this challenge, we offer a framework for designing applied machine learning approaches aimed at documenting the (in)accessibility of the built environment. This framework is designed to take into account the real-world picture, recognizing that the design of any accessibility documentation system has to take into account a range of factors that are not usually considered in machine learning research. We then apply this framework in a case study, illustrating an approach which can obtain a f-ratio of 0.952 in the best-case scenario.",

keywords = "Accessibility, Built-Environment, Documentation",

author = "Marvin Lange and Reuben Kirkham and Benjamin Tannert",

note = "Publisher Copyright: {\textcopyright} 2021, IFIP International Federation for Information Processing.; IFIP TC13 Conference on Human-Computer Interaction 2021, INTERACT 2021 ; Conference date: 30-08-2021 Through 03-09-2021",

year = "2021",

doi = "10.1007/978-3-030-85616-8_25",

language = "English",

isbn = "9783030856151",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "426--448",

editor = "Carmelo Ardito and Rosa Lanzilotti and Alessio Malizia and Alessio Malizia and Helen Petrie and Antonio Piccinno and Giuseppe Desolda and Kori Inkpen",

booktitle = "18th IFIP TC 13 International Conference Bari, Italy, August 30 – September 3, 2021 Proceedings, Part II",

url = "https://link.springer.com/book/10.1007/978-3-030-85623-6",

}

Lange, M, Kirkham, R & Tannert, B 2021, Strategically using applied machine learning for accessibility documentation in the built environment. in C Ardito, R Lanzilotti, A Malizia, A Malizia, H Petrie, A Piccinno, G Desolda & K Inkpen (eds), 18th IFIP TC 13 International Conference Bari, Italy, August 30 – September 3, 2021 Proceedings, Part II. Lecture Notes in Computer Science, vol. 12933, Springer, Cham Switzerland, pp. 426-448, IFIP TC13 Conference on Human-Computer Interaction 2021, Bari, Italy, 30/08/21. https://doi.org/10.1007/978-3-030-85616-8_25

Strategically using applied machine learning for accessibility documentation in the built environment. / Lange, Marvin; Kirkham, Reuben; Tannert, Benjamin.
18th IFIP TC 13 International Conference Bari, Italy, August 30 – September 3, 2021 Proceedings, Part II. ed. / Carmelo Ardito; Rosa Lanzilotti; Alessio Malizia; Alessio Malizia; Helen Petrie; Antonio Piccinno; Giuseppe Desolda; Kori Inkpen. Cham Switzerland: Springer, 2021. p. 426-448 (Lecture Notes in Computer Science; Vol. 12933).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Strategically using applied machine learning for accessibility documentation in the built environment

AU - Lange, Marvin

AU - Kirkham, Reuben

AU - Tannert, Benjamin

N1 - Conference code: 18th

PY - 2021

Y1 - 2021

N2 - There has been a considerable amount of research aimed at automating the documentation of accessibility in the built environment. Yet so far, there has been no fully automatic system that has been shown to reliably document surface quality barriers in the built environment in real-time. This is a mixed problem of HCI and applied machine learning, requiring the careful use of applied machine learning to address the real-world concern of practical documentation. To address this challenge, we offer a framework for designing applied machine learning approaches aimed at documenting the (in)accessibility of the built environment. This framework is designed to take into account the real-world picture, recognizing that the design of any accessibility documentation system has to take into account a range of factors that are not usually considered in machine learning research. We then apply this framework in a case study, illustrating an approach which can obtain a f-ratio of 0.952 in the best-case scenario.

AB - There has been a considerable amount of research aimed at automating the documentation of accessibility in the built environment. Yet so far, there has been no fully automatic system that has been shown to reliably document surface quality barriers in the built environment in real-time. This is a mixed problem of HCI and applied machine learning, requiring the careful use of applied machine learning to address the real-world concern of practical documentation. To address this challenge, we offer a framework for designing applied machine learning approaches aimed at documenting the (in)accessibility of the built environment. This framework is designed to take into account the real-world picture, recognizing that the design of any accessibility documentation system has to take into account a range of factors that are not usually considered in machine learning research. We then apply this framework in a case study, illustrating an approach which can obtain a f-ratio of 0.952 in the best-case scenario.

KW - Accessibility

KW - Built-Environment

KW - Documentation

UR - http://www.scopus.com/inward/record.url?scp=85115208088&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-85616-8_25

DO - 10.1007/978-3-030-85616-8_25

M3 - Conference Paper

SN - 9783030856151

T3 - Lecture Notes in Computer Science

SP - 426

EP - 448

BT - 18th IFIP TC 13 International Conference Bari, Italy, August 30 – September 3, 2021 Proceedings, Part II

A2 - Ardito, Carmelo

A2 - Lanzilotti, Rosa

A2 - Malizia, Alessio

A2 - Petrie, Helen

A2 - Piccinno, Antonio

A2 - Desolda, Giuseppe

A2 - Inkpen, Kori

PB - Springer

CY - Cham Switzerland

T2 - IFIP TC13 Conference on Human-Computer Interaction 2021

Y2 - 30 August 2021 through 3 September 2021

ER -

Lange M, Kirkham R, Tannert B. Strategically using applied machine learning for accessibility documentation in the built environment. In Ardito C, Lanzilotti R, Malizia A, Malizia A, Petrie H, Piccinno A, Desolda G, Inkpen K, editors, 18th IFIP TC 13 International Conference Bari, Italy, August 30 – September 3, 2021 Proceedings, Part II. Cham Switzerland: Springer. 2021. p. 426-448. (Lecture Notes in Computer Science). doi: 10.1007/978-3-030-85616-8_25

Strategically using applied machine learning for accessibility documentation in the built environment

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Cite this