A multimodal deep learning architecture for smoking detection with a small data approach

Róbert Lakatos; Péter Pollner; András Hajdu; Tamás Joó

doi:10.3389/frai.2024.1326050

A multimodal deep learning architecture for smoking detection with a small data approach

Front Artif Intell. 2024 Feb 28:7:1326050. doi: 10.3389/frai.2024.1326050. eCollection 2024.

Authors

Róbert Lakatos^{1

2

3}, Péter Pollner⁴, András Hajdu², Tamás Joó^{3

4}

Affiliations

¹ Doctoral School of Informatics, University of Debrecen, Debrecen, Hungary.
² Department of Data Science and Visualization, Faculty of Informatics, University of Debrecen, Debrecen, Hungary.
³ Neumann Technology Platform, Neumann Nonprofit Ltd., Budapest, Hungary.
⁴ Data-Driven Health Division of National Laboratory for Health Security, Health Services Management Training Centre, Semmelweis University, Budapest, Hungary.

Abstract

Covert tobacco advertisements often raise regulatory measures. This paper presents that artificial intelligence, particularly deep learning, has great potential for detecting hidden advertising and allows unbiased, reproducible, and fair quantification of tobacco-related media content. We propose an integrated text and image processing model based on deep learning, generative methods, and human reinforcement, which can detect smoking cases in both textual and visual formats, even with little available training data. Our model can achieve 74% accuracy for images and 98% for text. Furthermore, our system integrates the possibility of expert intervention in the form of human reinforcement. Using the pre-trained multimodal, image, and text processing models available through deep learning makes it possible to detect smoking in different media even with few training data.

Keywords: AI supported preventive healthcare; automated assessment of covert advertisement; few-shot learning; multimodal deep learning; pre-training with generative AI; smoking detections.

Grants and funding

The author(s) declare financial support was received for the research, authorship, and/or publication of this article. The project no. KDP-2021 has been implemented with the support provided by the Ministry of Culture and Innovation of Hungary from the National Research, Development, and Innovation Fund, financed under the C1774095 funding scheme. Also, this work was partly funded by the project GINOP-2.3.2-15-2016-00005 supported by the European Union, co-financed by the European Social Fund, and by the project TKP2021-NKTA-34, implemented with the support provided by the National Research, Development, and Innovation Fund of Hungary under the TKP2021-NKTA funding scheme. In addition, the study received further funding from the National Research, Development and Innovation Office of Hungary grant (RRF-2.3.1-21-2022-00006, Data-Driven Health Division of National Laboratory for Health Security).