Who is winning? A comparison of humans versus computers for calibration model building

Research output: Contribution to journalJournal articlepeer-review

Standard

Who is winning? A comparison of humans versus computers for calibration model building. / Rasmussen, Morten Arendt; Rinnan, Åsmund; Risum, Anne Bech; Bro, Rasmus.

In: Journal of Chemometrics, Vol. 35, No. 12, 3378, 2021.

Research output: Contribution to journalJournal articlepeer-review

Harvard

Rasmussen, MA, Rinnan, Å, Risum, AB & Bro, R 2021, 'Who is winning? A comparison of humans versus computers for calibration model building', Journal of Chemometrics, vol. 35, no. 12, 3378. https://doi.org/10.1002/cem.3378

APA

Rasmussen, M. A., Rinnan, Å., Risum, A. B., & Bro, R. (2021). Who is winning? A comparison of humans versus computers for calibration model building. Journal of Chemometrics, 35(12), [3378]. https://doi.org/10.1002/cem.3378

Vancouver

Rasmussen MA, Rinnan Å, Risum AB, Bro R. Who is winning? A comparison of humans versus computers for calibration model building. Journal of Chemometrics. 2021;35(12). 3378. https://doi.org/10.1002/cem.3378

Author

Rasmussen, Morten Arendt ; Rinnan, Åsmund ; Risum, Anne Bech ; Bro, Rasmus. / Who is winning? A comparison of humans versus computers for calibration model building. In: Journal of Chemometrics. 2021 ; Vol. 35, No. 12.

Bibtex

@article{82c3a57e311a4bee9582ac4416eb4731,
title = "Who is winning? A comparison of humans versus computers for calibration model building",
abstract = "Increasing awareness of the ability to transform data into knowledge has steered more focus on data science within the educational system as well as the development of machine learning methods capable of handling complex problems with minimal or no human interaction. In principle, this raises the question on where human-computer interaction is superior in building good models in contrast to fully automated algorithms. In this study, we investigated modeling performance by using bachelor students, master students, and a fully automated procedure on three near-infrared (NIR) calibration tasks of increasing complexity. From a total of 107 student and +5000 automated models, it is evident that simple calibration tasks can be automated to achieve similar or better performance, whereas for the more complicated tasks, the human-computer interaction is superior. Indeed, teaching data science and chemometrics should focus on tools for fundamental data understanding and emphasize the use of domain knowledge and critical thinking in the analysis of data.",
keywords = "human-computer interaction, machine learning, teaching data science",
author = "Rasmussen, {Morten Arendt} and {\AA}smund Rinnan and Risum, {Anne Bech} and Rasmus Bro",
year = "2021",
doi = "10.1002/cem.3378",
language = "English",
volume = "35",
journal = "Journal of Chemometrics",
issn = "0886-9383",
publisher = "Wiley",
number = "12",

}

RIS

TY - JOUR

T1 - Who is winning? A comparison of humans versus computers for calibration model building

AU - Rasmussen, Morten Arendt

AU - Rinnan, Åsmund

AU - Risum, Anne Bech

AU - Bro, Rasmus

PY - 2021

Y1 - 2021

N2 - Increasing awareness of the ability to transform data into knowledge has steered more focus on data science within the educational system as well as the development of machine learning methods capable of handling complex problems with minimal or no human interaction. In principle, this raises the question on where human-computer interaction is superior in building good models in contrast to fully automated algorithms. In this study, we investigated modeling performance by using bachelor students, master students, and a fully automated procedure on three near-infrared (NIR) calibration tasks of increasing complexity. From a total of 107 student and +5000 automated models, it is evident that simple calibration tasks can be automated to achieve similar or better performance, whereas for the more complicated tasks, the human-computer interaction is superior. Indeed, teaching data science and chemometrics should focus on tools for fundamental data understanding and emphasize the use of domain knowledge and critical thinking in the analysis of data.

AB - Increasing awareness of the ability to transform data into knowledge has steered more focus on data science within the educational system as well as the development of machine learning methods capable of handling complex problems with minimal or no human interaction. In principle, this raises the question on where human-computer interaction is superior in building good models in contrast to fully automated algorithms. In this study, we investigated modeling performance by using bachelor students, master students, and a fully automated procedure on three near-infrared (NIR) calibration tasks of increasing complexity. From a total of 107 student and +5000 automated models, it is evident that simple calibration tasks can be automated to achieve similar or better performance, whereas for the more complicated tasks, the human-computer interaction is superior. Indeed, teaching data science and chemometrics should focus on tools for fundamental data understanding and emphasize the use of domain knowledge and critical thinking in the analysis of data.

KW - human-computer interaction

KW - machine learning

KW - teaching data science

U2 - 10.1002/cem.3378

DO - 10.1002/cem.3378

M3 - Journal article

VL - 35

JO - Journal of Chemometrics

JF - Journal of Chemometrics

SN - 0886-9383

IS - 12

M1 - 3378

ER -

ID: 285870223