Who is winning? A comparison of humans versus computers for calibration model building
Research output: Contribution to journal › Journal article › Research › peer-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 journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
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