Development of a Mobile App for Real-Time Dairy Cow Health Monitoring and Management

Thesis Abstract

The effective management and health monitoring of dairy cattle remain critical challenges for contemporary livestock producers due to their significant impact on productivity, animal welfare, and farm profitability, compounded by the limited real-time data available to farmers for timely decision-making. This study aims to develop a comprehensive mobile application designed to facilitate real-time health monitoring and management of dairy cows through integrating sensor data, machine learning algorithms, and user-friendly interfaces. The primary objectives are to identify key health indicators for dairy cattle, design an architecture for the mobile app incorporating these indicators, and evaluate the app’s usability, accuracy, and impact on management practices. Employing a mixed-methods research design, the study combines quantitative hardware testing and data analysis with qualitative usability assessments. The target population comprises dairy farmers, veterinarians, and animal health technicians operating within a medium-scale dairy farm setting with approximately 200 dairy cattle. A purposive sampling technique was employed, with a sample size of 50 dairy farmers participating in usability testing, complemented by focus group discussions with 10 veterinarians for contextual insights. Data collection utilized sensor devices installed on a subset of 50 dairy cows to capture physiological parameters such as body temperature, activity level, rumination patterns, and milk yield, transmitted wirelessly to the mobile app. The app’s performance was further evaluated through surveys, user interviews, and task completion assessments. Instrument validity was ensured via expert validation of the app prototype and sensor calibration, while reliability was established through repeated measurement trials and test-retest procedures. Quantitative data analysis involved descriptive statistics to summarize sensor readings, regression analysis to identify significant predictors of health anomalies, and analysis of variance (ANOVA) to evaluate differences across user groups in system usability scores. Qualitative data from interviews and focus groups were subjected to thematic analysis, allowing for identification of recurrent themes regarding user experience, perceived benefits, and areas for system improvement. The study further employed the Technology Acceptance Model (TAM) to assess factors influencing user acceptance and intended sustained use of the mobile app. Expected findings suggest that the developed mobile app will accurately detect early signs of illness such as mastitis, metabolic disorders, and heat stress by analyzing real-time physiological data, leading to prompt intervention and improved health outcomes. The app’s usability is expected to be rated high, with positive feedback emphasizing ease of use, usefulness, and integration into existing management workflows. Additionally, the system is anticipated to increase farm efficiency by reducing disease incidence and minimizing manual record-keeping errors. The study will also identify critical technical and usability challenges faced by users and propose strategies to mitigate them. This research contributes novel insights into the application of mHealth and precision livestock farming technologies in dairy management, providing a scalable framework for real-time health monitoring systems in similar settings. It expands current literature by integrating sensor-based monitoring with user-centered design principles, grounded in the Diffusion of Innovations Theory and the Health Belief Model, to address behavioral and technological adoption barriers. The findings will inform policymakers, technology developers, and livestock managers about best practices for implementing ICT-driven health management solutions and fostering sustainable dairy farming practices. The study concludes that the mobile app has the potential to revolutionize dairy herd health management by enabling proactive interventions, enhancing animal welfare, and increasing productivity. Recommendations include further validation of sensor accuracy across varied environmental conditions, expansion of the app’s functionalities to include disease prediction models, and training programs to facilitate widespread adoption among dairy farmers. Future research should explore long-term impacts on herd health outcomes and economic benefits at regional and national levels.