AI based Digital record keeping system for COE dairy

This paper presented an AI-based digital record-keeping system developed for COE Dairy to overcome the limitations of traditional manual dairy management practices. By integrating a Flutter-based multi-platform client application with a secure, cloud-native Firebase backend, the system enables reliable data capture, real-time synchronization, and intelligent analytics. The incorporation of AI-driven modules such as hybrid ARIMA-LSTM milk yield prediction, feed optimization, health alert generation, and automated PDF report generation transforms raw operational data into actionable insights, thereby improving productivity, decision-making accuracy, and operational transparency. The role-based access control model ensures secure multi-user operations across admin and staff roles. The successful implementation and evaluation at COE Dairy demonstrate that the proposed system is scalable, cost-effective, and well-suited for real-world dairy environments, particularly in rural settings. The system provides a strong foundation for future advancements in smart and sustainable dairy management, including integration with IoT-based sensors, advanced deep learning forecasting models, and veterinary advisory modules.

[1] Y.-C. Jin, Q. Cao, Q. Sun, Y. Lin, D.-M. Liu, S. Yu, C.-X. Wang, X.-L. Wang, and X.-Y. Wang, "Models for COVID-19 Data Prediction Based on Improved LSTM-ARIMA Algorithms," IEEE Access, vol. 12, pp. 3981–3995, 2024, doi: 10.1109/ACCESS.2023.3347403. [2] S. Hochreiter and J. Schmidhuber, "Long Short-Term Memory," Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997. [3] G. Box, G. Jenkins, G. Reinsel, and G. Ljung, Time Series Analysis: Forecasting and Control, 5th ed., Wiley, 2015. [4] A. Dairi, F. Harrou, Y. Sun, and M. Senouci, "Short-term forecasting of COVID-19 spread using CNN-LSTM networks," IEEE Access, vol. 9, pp. 100092–100102, 2021. [5] S. Singh, "Application of ARIMA model for forecasting COVID-19 cases in Malaysia," Journal of Applied Statistics, vol. 48, no. 5, pp. 879–892, 2021. [6] M. Yuan, X. Wang, and J. Li, "Bayesian optimization of LSTM networks for time-series prediction," Applied Soft Computing, vol. 96, 2020. [7] J. Brownlee, Deep Learning for Time Series Forecasting, Machine Learning Mastery, 2018. [8] Cardona, J., and Paredes, M., "Hybrid MLP-LSTM Model for Dairy Production Prediction," Journal of Agricultural Informatics, 2025. [9] Badr, M. et al., "ARIMA-Based Forecasting of Milk Production Trends in Dairy Farms," Applied Agricultural Sciences, 2022. [10] Buyuksahin, U., and Ertekin, S., "A Hybrid ARIMA-ANN Model for Improved Forecasting Accuracy," Expert Systems with Applications, 2018.