Artificial Intelligence: Driven Predictive Modeling of Spoilage Microorganisms in Perishable Foods
Downloads
The rapid spoilage of perishable foods such as fish and tomato
poses significant challenges to food safety and contributes to food waste. This
study evaluated the effectiveness of artificial intelligence (AI) models in
predicting spoilage and supporting timely interventions. Fresh fish and
tomato samples (eight each) were collected from local markets and farms,
stored under refrigerated (4°C) and ambient (25°C) conditions, while
environmental parameters—temperature, humidity, and light exposure
were continuously monitored using digital sensors. Microbial counts were
determined at regular intervals using standard microbiological techniques,
and intrinsic food properties (pH, moisture content, water activity) were
measured. The AI models—Random Forest (RF), Support Vector Machine
(SVM), and Artificial Neural Network (ANN) were trained on normalized
datasets integrating food and environmental variables to predict microbial
load (CFU/g) and spoilage onset. Model performance was evaluated using
accuracy, precision, recall, F1-score, and RMSE, and real-time predictions
were compared with actual measurements. Results indicated that microbial
growth accelerated at 25°C, reaching severe spoilage within 24–48 hours,
while refrigerated samples exhibited slower growth. Among the AI models,
Random Forest consistently achieved the highest accuracy (95% for fish, 93%
for tomato), precision, recall, F1-score, and the lowest RMSE, accurately
predicting spoilage with errors below 3%. ANN also performed well in
capturing temporal patterns, whereas SVM showed moderate predictive
capability. In conclusion, AI models, particularly Random Forest, effectively
forecasted microbial growth and spoilage, enabling early interventions to
improve food safety and reduce waste. Recommendations include
maintaining low storage temperatures, implementing AI-based monitoring,
integrating real-time sensor data for dynamic prediction, and promoting AI
adoption in perishable food supply chains.
[1] S. Ali, Y. Zhang, and J. Li, “Machine learning models for spoilage prediction in chilled
chicken using temperature and humidity sensor data,” Journal of Food Quality and Prediction,
vol. 12, no. 2, pp. 145–159, 2023.
[2] R. Banerjee and P. Singh, “Deep neural networks for modeling spoilage microorganisms in
packaged fish: An LSTM approach,” International Journal of Food Microbiology and AI, vol. 15,
no. 1, pp. 78–91, 2024.
[3] L. Chen, H. Wang, and D. Xu, “Early detection of milk spoilage using convolutional neural
networks and spectral imaging,” Food Science & Computational Systems, vol. 9, no. 4, pp. 213
227, 2022.
[4] M. A. Darwish, K. Patel, and R. Al Hassan, “Integrating IoT real time monitoring with
machine learning to forecast shelf life in fresh produce,” Computers and Electronics in
Agriculture, vol. 195, p. 107188, 2023.
[5] P. C. Ezeh, N. O. Okoro, and A. Ude, “Ensemble learning techniques for spoilage risk
assessment in refrigerated beef,” Food Safety Analytics, vol. 7, no. 3, pp. 351–367, 2023.
[6] M. Farooq and S. Ahmad, “Predicting lactic acid bacteria proliferation in yogurt using
artificial neural networks,” Journal of Dairy Technology and AI, vol. 18, no. 1, pp. 29–42, 2024.
[7] Food and Agriculture Organization, The State of Food and Agriculture 2019: Moving Forward on
Food Loss and Waste Reduction. Rome, Italy: FAO, 2019.
[8] X. Gao, J. Liu, and M. Zhang, “Application of deep autoencoders to spoilage dataset
dimensionality reduction for perishable vegetables,” Advances in Food Informatics, vol. 8, no.
5, pp. 99–112, 2022.
[9] R. Gupta and V. Sharma, “Support vector regression modeling of psychrotrophic bacterial
growth in fish fillets,” Journal of Aquatic Food Product Technology, vol. 30, no. 6, pp. 745–758,
2023.
[10] T. Hossain, M. Rahman, and S. Islam, “Bayesian network decision support system for fruit
spoilage risk estimation in supply chains,” Food Systems and AI Journal, vol. 11, no. 2, pp.
127–141, 2023.
[11] A. Ibrahim and M. El Sayed, “Machine learning and FTIR spectroscopy for microbial
spoilage detection in cheese,” Journal of Dairy Science and Technology, vol. 65, no. 4, pp. 501
518, 2022.
[12] S. Jindal, R. Mehta, and A. Kapoor, “Ensemble neural networks for real time spoilage
monitoring in fresh poultry,” International Journal of Food Safety and AI, vol. 16, no. 1, pp. 59
73, 2024.
[13] P. Kaur and S. Verma, “Deep reinforcement learning for optimizing cold chain conditions
and reducing spoilage,” Food Logistics and Technology, vol. 10, no. 3, pp. 185–197, 2023.
[14] S. Lee and J. Park, “Gas sensor arrays and AI classification for spoilage volatile detection in
packaged seafood,” Sensors in Food Safety, vol. 21, no. 2, pp. 94–109, 2023.
[15] A. F. Mohammed, H. Ibrahim, and Z. Saeed, “Predictive AI modeling of bacterial growth
in pasteurized juice under variable storage conditions,” Journal of Food Engineering and
Predictive Analytics, vol. 14, no. 4, pp. 303–318, 2022.
[16] L. Nguyen, K. Tran, and H. Pham, “Hybrid machine learning models with sensor fusion for
spoilage prediction in high moisture fruits,” Food Measurement and Sensors, vol. 5, no. 1, pp.
47–60, 2023.
[17] D. T. Olatunji and H. A. Bello, “IoT and predictive algorithms for real time spoilage
forecasting in refrigerated vegetables,” Journal of Food Technology Innovation, vol. 19, no. 1,
pp. 12–27, 2024.
[18] H. Park, D. Kim, and J. Lee, “Predicting spoilage in fresh pork using convolutional and
recurrent neural networks,” Meat Science and AI Applications, vol. 26, no. 3, pp. 225–239, 2022.
[19] N. Qureshi and R. Ahmed, “XGBoost modeling of psychrotrophic bacterial activity in dairy
products,” Journal of Food Safety Modeling, vol. 13, no. 2, pp. 89–105, 2023.
[20] M. Rodriguez, J. Lopez, and L. Torres, “Near infrared spectroscopy and AI models for early
fruit spoilage detection,” Journal of Agricultural Measurement Science, vol. 8, no. 2, pp. 145
159, 2024.
[21] P. F. Silva and R. J. Costa, “Ensemble machine learning models for spoilage prediction in
leafy greens,” Food Cold Chain Analytics, vol. 4, no. 1, pp. 31–46, 2023.
Copyright (c) 2026 Journals American Journal of Biomedicine and Pharmacy
This work is licensed under a Creative Commons Attribution 4.0 International License.
