EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Development and validation of the Alcoholic Beverage Identification Deep Learning Algorithm version 2 for quantifying alcohol exposure in electronic images

Abraham Albert Bonela iD, Zhen He, Thomas Norman iD, Emmanuel Kuntsche iD

Alcoholism: Clinical and Experimental Research · 2022-10 · 46 (10) · 1837-1845

DOI: 10.1111/acer.14925 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Alcoholism: Clinical and Experimental Research, online erschienen am 15.10.2022. Verfasst von Abraham Albert Bonela und 3 weiteren Autor:innen. Beteiligte Einrichtung: Centre for Alcohol Policy Research, La Trobe University, Melbourne, Victoria, Australia. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 18 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Seeing alcohol in media has been demonstrated to increase alcohol craving, impulsive decision‐making, and hazardous drinking. Due to the exponential growth of (social) media use it is important to develop algorithms to quantify alcohol exposure efficiently in electronic images. In this article, we describe the development of an improved version of the Alcoholic Beverage Identification Deep Learning Algorithm (ABIDLA), called ABIDLA2.

Methods

ABIDLA2 was trained on 191,286 images downloaded from Google Image Search results (based on search terms) and Bing Image Search results. In Task‐1, ABIDLA2 identified images as containing one of eight beverage categories (beer/cider cup, beer/cider bottle, beer/cider can, wine, champagne, cocktails, whiskey/cognac/brandy, other images). In Task‐2, ABIDLA2 made a binary classification between images containing an “alcoholic beverage” or “other”. An ablation study was performed to determine which techniques improved algorithm performance.

Results

ABIDLA2 was most accurate in identifying Whiskey/Cognac/Brandy (88.1%) followed by Beer/Cider Can (80.5%), Beer/Cider Bottle (78.3%), and Wine (77.8%). Its overall accuracy was 77.0% (Task‐1) and 87.7% (Task‐2). Even the identification of the least accurate beverage category (Champagne, 64.5%) was more than five times higher than random chance (12.5% = 1/8 categories). The implementation of balanced data sampler to address class skewness and the use of self‐training to make use of a large, secondary, weakly labeled dataset particularly improved overall algorithm performance.

Conclusion

With extended capabilities and a higher accuracy, ABIDLA2 outperforms its predecessor and enables the screening of any kind of electronic media rapidly to estimate the quantity of alcohol exposure. Quantifying alcohol exposure automatically through algorithms like ABIDLA2 is important because viewing images of alcoholic beverages in media tends to increase alcohol consumption and related harms.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningAlcoholic BeveragesBeerEthanolBeveragesElectronics

Stichwörter der Autor:innen

alcohol exposurealcoholic beverage recognitionartificial intelligencedeep learningimagesmedia

Substanzen

Ethanol

Autor:innen und Institutionen

  • Centre for Alcohol Policy Research, La Trobe University, Melbourne, Victoria, Australia.
  • Department of Computer Science and Information Technology, La Trobe University, Melbourne, Victoria, Australia.
  • Australian Research Centre in Sex, Health and Society, La Trobe University, Melbourne, Victoria, Australia.

ORCID-Profile: Abraham Albert Bonela, Thomas Norman, Emmanuel Kuntsche

Zitieren

APA

Bonela, A. A., He, Z., Norman, T., & Kuntsche, E. (2022). Development and validation of the Alcoholic Beverage Identification Deep Learning Algorithm version 2 for quantifying alcohol exposure in electronic images. Alcoholism: Clinical and Experimental Research, 46(10), 1837-1845. https://doi.org/10.1111/acer.14925

Vancouver

Bonela AA, He Z, Norman T, Kuntsche E. Development and validation of the Alcoholic Beverage Identification Deep Learning Algorithm version 2 for quantifying alcohol exposure in electronic images. Alcoholism: Clinical and Experimental Research. 2022;46(10):1837-1845. doi:10.1111/acer.14925

BibTeX
@article{Bonela2022,
  author = {Bonela, Abraham Albert and He, Zhen and Norman, Thomas and Kuntsche, Emmanuel},
  title = {Development and validation of the Alcoholic Beverage Identification Deep Learning Algorithm version 2 for quantifying alcohol exposure in electronic images},
  journal = {Alcoholism: Clinical and Experimental Research},
  year = {2022},
  volume = {46},
  number = {10},
  pages = {1837--1845},
  doi = {10.1111/acer.14925}
}
Kostenlos starten →