Lameness is a condition that affects the locomotion patterns of livestock. Timely lameness detection is one of the major and costliest health problems in dairy cattle that farmers and practitioners haven’t yet solved adequately. This is due to the high initial setup costs, complex equipment and lack of multi-vendor interoperability in currently available solutions. Human observation-based solutions which rely on visual inspections are prone to late detection with possible human error, and are not scalable. This is a concern with increasing herd sizes, as prolonged or undetected lameness severely compromises cows’ health and welfare, and ultimately affects the milk productivity of the farm. . To tackle this, we have developed an end-to-end IoT application that leverages advanced machine learning and data analytics techniques to monitor the cattle in real-time and identify lameness at an early stage.
The paper presents in detail the deployment done, methodology used, and how IoT, artificial intelligence, cloud and fog computing paradigm are joined together to solve the problem of timely detection of lameness in dairy cattle.
Findings and related:
Farms are usually located in geographically remote locations facing constrained network connectivity. Most of the IoT deployments in such settings are faced with limited cellular coverage. The developed an end-to-end IoT application utilizes the emerging fog computing paradigm to handle the network connectivity constraints, and the modular-microservices based application design and development methodology proposed is the first inline to combine the approaches effectively to deliver an IoT based solution.
Our results suggest that building custom models for small groups of animals in the herd that share similar features within the herd improves the accuracy of the lameness detection as opposed to a one-size fits all approach. This approach becomes more important and practically viable with increase in size of the herd. Such approach leads to early detection of changes in animal behaviour before the visual onset of these changes. The proposed approach has been validated at a local dairy farm of 150 cows in County Waterford. As in our case, the application developed is able to detect lameness in dairy cattle 3 days before it’s visually observable with an 87% accuracy. Further, the fog-based computational assistance enables the intelligent processing of data closer to the source, thereby leading to an 84% reduction in the amount of data transfer to cloud.
Impact and Benefits to Stakeholders:
Dairy farms have all the constraints of a modern business — they have a fixed production capacity, a herd to manage, expensive farm labour and other varied farm-related processes to take care of. In this technology-driven era farmers look for assistance from smart solutions to increase profitability and to help manage their farms well. The Internet of Things (IoT) is about connecting people, processes, data and things; and is changing the way we monitor and interact with things. An active incorporation of Information and Communication Technology (ICT) coupled with sophisticated data analytics approaches has the potential to transform some of the oldest industries in the world, including dairy farming.
With increasing population, the global demands for agriculture and dairy products is only set to increase. It has been estimated that the consumer base of dairy and dairy products is set to rise from 1.8 billion people in 2009 to 4.9 billion by 2030. However, methods to improve yield from the agricultural and dairy sector have not advanced at the same rate as the increase in demand. To cope with the increased demand for food, new and effective methods are required to increase the production capacity of this sector. Data-driven decisions, methods and measures can help in increasing the production capacity of these industries.
This work is a very small contribution in that direction to help address those demands. We further believe that with such a lameness detection framework in place in dairy farms, further research can be done to address the various challenges such as ones related to greenhouse gas emissions from dairy sector.
Title: Machine Learning Based Fog Computing Assisted Data-Driven Approach For Early Lameness Detection in Dairy Cattle
Authors: Mohit Taneja ; John Byabazaire; Nikita Jalodia ; Alan Davy ; Cristian Olariu; Paul Malone
Journal: Computers and Electronics in Agriculture
Read it here –
Open-Access – Published Version: https://www.sciencedirect.com/science/article/pii/S016816991931840X