Journal Press India^®

Author Details ( * ) denotes Corresponding author

Drug abuse has become a widespread global issue, affecting individuals, families, and communities. Machine learning techniques have shown promise in combating drug addiction prevalence through early prediction and immediate intervention. This study proposes an improved facial analysis-based drug addiction prediction system using a random forest classification algorithm, trained on facial images. Feature extraction and selection were performed using a histogram of oriented gradients and recursive feature elimination, respectively. The random forest classification model was tuned with grid search cross-validation, and evaluated using accuracy, precision, recall, and F1-score. Tuning the system significantly improved its performance, with accuracy increasing from 84.62% to 87.18%, precision from 82.61% to 83.33%, recall from 90.48% to 95.24%, and F1-score from 86.37% to 88.89%. This increase demonstrates the importance of hyperparameter tuning and the robustness of the random forest algorithm. Future studies can improve upon this work by incorporating a larger facial dataset for better practical results.

Keywords

Drug addiction; Random forest; Grid search cross-validation; Recursive feature elimination; Histogram of oriented gradient

1. Almahmood, M., Najadat, H., Alzu’bi, D., Abualigah, L., Zitar, R. A., Abualigah, S., & Al-Saqqar, F. (2023). Predictive model of psychoactive drugs consumption using classification machine learning algorithms. Applied and Computational Engineering, 8(1), 738-743.
2. Amato, G., Falchi, F., Gennaro, C., & Vairo, C. (2018). A comparison of face verification with facial landmarks and deep features. In International Conference on Advances in Multimedia (MMEDIA) pp. 1–6.
3. Arif, M., Alghamdi, K. K., Sahel, S. A., Alosaimi, S. O., Alsahafi, M. E., Alharthi, M. A.  & Arif, M. (2021). Role of machine learning algorithms in forest fire management: A literature review. Journal of Robotics & Automation, 5(1), 212-226.
4. Basuni, N. & Siregar, A. M. (2023). Comparison of the accuracy of drug user classification models using machine learning methods. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), 7(6), 1348-1353.
5. Chavan, M., Yawalkar, Y. & Suryawanshi, K. (2024). Innovation in healthcare by implementing IoT application to achieve sustainability: A study from Indian perspective.  Computology: Journal of Applied Computer Science and Intelligent Technologies, 4 (1), 55-73. Retrieved From:  https://www.journalpressindia.com/computology-journal-of-applied-computer-science-and-intelligent-technologies/doi/10.17492/computology.v4i1.2404
6. Choi, J., Chung, J. & Choi, J. (2021). Exploring impact of Marijuana (Cannabis) abuse on adults using machine learning. International Journal of Environmental Research and Public Health, 18(19), 1-12.
7. Choi, J., Jung, H. T., Ferrell, A., Woo, S. & Haddad, L. (2021b). Machine learning-based nicotine addiction prediction models for youth e-cigarette and waterpipe (Hookah) users. Journal of Clinical Medicine, 10(5), 1-13.
8. Deedee, B., Onate, T., & Emmah, V. (2024). Fake profile detection and stalking prediction on X using random forest and deep convolutional neural networks. Computology: Journal of Applied Computer Science and Intelligent Technologies, 4 (1), 1-19. Retrieved From:  https://www.journalpressindia.com/computology-journal-of-applied-computer-science-and-intelligent-technologies/doi/10.17492/computology.v4i1.2401
9. Gong, H., Xie, C., Yu, C., Sun, N., Lu, H., & Xie, Y. (2021). Psychosocial factors predict the level of substance craving of people with drug addiction: A machine learning approach. International Journal of Environmental Research and Public Health, 18(22), 1-12.
10. Gu, X., Yang, B., Gao, S., Yan, L. F., Xu, D., & Wang, W. (2021). Application of bi-modal signal in the classification and recognition of drug addiction degree based on machine learning. Mathematical Biosciences and Engineering, 18(5), 6926-6940.
11. Haque, U. M., Kabir, E. & Khanam, R. (2021). Detection of child depression using machine learning methods. PLoS one, 16(12), 1-13.
12. Jeon, H. & Oh, S. (2020). Hybrid-recursive feature elimination for efficient feature selection. Applied Sciences, 10(9), 1-8.
13. Lakshmi, J. V. N. & Das, A. (2023). Forecasting the risk of coronary heart diseases using machine learning algorithms. Computology: Journal of Applied Computer Science and Intelligent Technologies, 3(2), 133-152. Retrieved From https://www.journalpressindia.com /computology-journal-of-applied-computer-science-and-intelligent-technologies/doi/10.174 92/computology.v3i2.2307
14. Li, Y., Yan, X., Zhang, B., Wang, Z., Su, H. & Jia, Z. (2021). A method for detecting and analyzing facial features of people with drug use disorders. Diagnostics, 11(9), 1-18.
15. Mahmoud, B. S. & Garko, A. B. (2022). A machine learning model for malware detection using recursive feature elimination (RFE) for feature selection and ensemble technique. IOS Journals, 24(1), 23-30.
16. Misra, P. & Yadav, A. S. (2020). Improving the classification accuracy using recursive feature elimination with cross-validation. International Journal of Emerging Technologies, 11(3), 659-665.
17. Oliva, V., De Prisco, M., Pons-Cabrera, M. T., Guzmán, P., Anmella, G., Hidalgo-Mazzei, D., Grande, I., Fanelli, G., Fabbri, C., Serretti, A., Fornaro, M., Lasevoli, F., de Bartolomeis, A., Murru, A., Vieta, E. & Fico, G. (2022). Machine learning prediction of comorbid substance use disorders among people with bipolar disorder. Journal of Clinical Medicine, 11(14), 1-13.
18. Parekh, T. & Fahim, F. (2021). Building risk prediction models for daily use of marijuana using machine learning techniques. Drug and Alcohol Dependence, 225, 1-6.
19. Ramezan, C. A. (2022). Transferability of recursive feature elimination (RFE)-derived feature sets for support vector machine land cover classification. Remote Sensing, 14(24),  1-25.
20. Sharma, A., Sharma, H., Varshney, S. & Gusain, N. (2023). Heart disease prediction: A comparative analysis of machine learning algorithms. Computology: Journal of Applied Computer Science and Intelligent Technologies, 3(2), 171-192. Retrieved From https://www.journalpressindia.com/computology-journal-of-applied-computer-science-and-intelligent-technologies/doi/10.17492/computology.v3i2.2309
21. Uddin, M. N., Hafiz, M. F. B., Hossain, S. & Islam, S. M. M. (2022). Drug sentiment analysis using machine learning classifiers. International Journal of Advanced Computer Science and Applications, 13(1), 92-100.
22. UNODC (2022). World drug report 2018. Executive summary conclusions and policy implications. Retrieved from https://www.unodoc.org.wdr