top of page

You are here: Home  

​

/  News

Research | AfroPALM – Afrocentric palm oil adulteration learning models: An end-to-end deep learning approach for detection of palm oil adulteration

Nov 6, 2024
2 min read


Andrew Selasi Agbemenua,b,c, Andrews Tanga, Elton Modestus Gyabenga, Prince Odameb,c, Eric Tutu Tchaoa,b,c, Eliel Keelsona,c, John-Lewis Zinia Zaukuud, Jerry John Kponyob


a Distributed IoT Platforms, Privacy and Edge-Intelligence Research Lab, Kumasi, Ghana; b Responsible Artificial Intelligence Lab, Kumasi, Ghana; c Department of Computer Engineering, Kwame Nkrumah University of Science and Technology, Kumasi, Ghana; d Department of Food Science and Technology, Kwame Nkrumah University of Science and Technology, Kumasi, Ghana


Abstract: In Africa, rapid population growth and a focus on increasing food production have often overlooked the crucial aspect of food safety, leading to the highest per capita incidences of foodborne illness globally. This underscores the imperative to address the food safety challenges on the continent. A critical concern is the widespread adulteration of red palm oil across West Africa, often involving harmful red azo dyes, posing significant health risks. Current detection methods, reliant on laboratory procedures, are not only time-consuming and expensive but also impractical for broad implementation in local markets. To address these limitations, we propose an end-to-end deep learning approach that bypasses the need for manual feature extraction and laboratory-based analyses. Utilizing high-resolution imaging technology, our approach can objectively and reliably detect palm oil adulteration directly from raw image data. In our study, we developed a deep convolutional neural network dubbed AfroPALM-Custom, specifically designed for detecting palm oil adulteration in African markets. AfroPALM-Custom was pivotal in refining our deep learning approach, achieving a test accuracy of 90.63% and an F1 score of 90.98%. We later adapted mobile-efficient pretrained models, namely SqueezeNet1.1 and GhostNetV1—mobile—fine-tuned and as well dubbed AfroPALM-GhostNet and AfroPALM-SqueezeNet. In performance, AfroPALM-GhostNet and AfroPALM-SqueezeNet achieved test accuracies of 96.29% and 91.16%, respectively, and F1-scores of 96.57% and 91.95%. This proficiency in identifying adulterated palm oil demonstrates a significant advancement in food safety solutions for African markets, offering a practical and scalable approach for implementation within local marketplaces where resources are limited and laboratory methods are impractical.


Keywords: Red palm oil; Adulteration; Deep learning; Food safety


Agbemenu, A. S., Tang, A., Gyabeng, E. M., Odame, P., Tchao, E. T., Keelson, E., Zaukuu, J.-L. Z., & Kponyo, J. J. (2024). AfroPALM: Afrocentric palm oil adulteration learning models: An end-to-end deep learning approach for detection of palm oil adulteration. LWT, 213, Article 116904. https://doi.org/10.1016/j.lwt.2024.116904


Acknowledgements: This research was partly funded by the Future Africa Research Leadership Fellowship (FAR-LeaF) supported by the Carnegie Corporation of New York. The work also received technical support from the Responsible AI Lab project funded by GIZ and AI4D Africa Initiative.




Preprint publication | Gyabeng, Elton & Tang, Andrews & Agbemenu, Andrew & Odame, Prince & Tchao, E. T. & Keelson, Eliel & Zinia-Zaukuu, John-Lewis & Jerry, Kponyo. (2024). Afropalm – Afrocentric Palm Oil Adulteration Learning Models: An End-to-End Deep Learning Approach for Detection of Palm Oil Adulteration in West Africa. 10.2139/ssrn.4917970: https://rail.knust.edu.gh/2024/10/26/afropalm-afrocentric-palm-oil-adulteration-learning-models-an-end-to-end-deep-learning-approach-for-detection-of-palm-oil-adulteration-in-west-africa/

Image by Maros Misove

FUTURE AFRICA

RESEARCH LEADERSHIP FELLOWSHIP

The Future Africa Research Leadership Fellowship (FAR-LeaF) is an early career research fellowship program focused on developing transdisciplinary research and leadership skills.

pattern banner_edited.jpg

The programme seeks to build a network of emerging African scientists who have the skills to apply transdisciplinary approaches and to collaborate to address complex challenges in the human well-being and environment nexus in Africa.

bottom of page