Scholarly record
CLOUD DATAFLOW FOR MACHINE LEARNING MODELING ON IOT DATA IN SMART LIVESTOCK FARMING
Abstract
The development of modern dairy farming is aimed at creating larger farms with more intensive production in accordance with the market needs. New larger livestock facilities need new approaches to management and logistics. The Internet of Things (IoT), machine learning (ML) and cloud computing are forming the basis of digital animal husbandry as they are increasingly being introduced into dairy farming. The collection of IoT sensor data and their storage in the information cloud allows the use of machine learning methods for predicting events in livestock farms. ML is characterized by its hunger for computing resources in all its phases, which can be resolved using cloud computing. Collected data by IoT devices require cleaning and scaling. Building a model requires training, testing, and validation. All these activities should be carried out in a timely sequence. The purpose of this article is to build models trained to predict the future amount of milk with the greatest accuracy for each individual animal. To achieve this goal, a pure Azure Cloud DataFlow (ADF) has been created, which monitors the processes from collecting and storing Io- data, to data processing, modelling, and model evaluation to visualization of results. Following this data flow, the experimental studies described in this article are performed. Three regression machine learning models were trained on the data collected from a Smart Livestock farm. Testing of the developed models has proven the applicability of the developed Cloud DataFlow, as the Boosted Decision Tree Regression Model shows the highest accuracy in predicting the amount of milk produced by each individual animal.
Publication Impact Profile
- Citations
- Scopus - Citation Indexes: 3
- Captures
- Mendeley - Readers: 9
Publication details
References10
Neethirajan S., Kemp B., Digital Livestock Farming, Sensing and Bio-Sensing Research, vol. 32, 100408, 2021. DOI: 10.1016/j.sbsr.2021.100408
Dineva K., Atanasova T., Expandable IoT Architecture for Livestock in Agriculture 5.0. Proc. 21st Int. Multidisciplinary Sci. Geoconf. SGEM 2021, pp. 147-154, 2021. DOI: 10.5593/sgem2021/6.1/s25.19
Park J. K. and Park E. Y., Animal Monitoring Scheme in Smart Farm using CloudBased System, ECTI-CIT Transactions, vol. 15, no. 1, pp. 24�33, Nov. 2020. DOI: 10.37936/ecti-cit.2021151.240087
Vigneswari T., Kalaiselvi N., Mathumitha K., Niveditha A., Sowmian A. Smart IOT Cloud Based Livestock Monitoring System: A Survey, TURCOMAT, vol. 12, 2021.
Eastwood, C., Ayre, M., Nettle, R., Dela Rue, B., Making sense in the cloud: Farm advisory services in a smart farming future, Wageningen J. Life Sci., vol.12, no.1, 2019. DOI: 10.1016/j.njas.2019.04.004
Durai S.K.S., Shamili M. D., Smart farming using Machine Learning and Deep Learning techniques, Decision Analytics Journal, vol. 3, 100041, 2022. DOI: 10.1016/j.dajour.2022.100041
Venkatesan, S., Lim, J., Ko, H., Cho, Y., A Machine Learning Based Model for Energy Usage Peak Prediction in Smart Farms. Electronics, vol. 11, 218, 2022. DOI: 10.3390/electronics11020218
Gurrapu, S., Sikder, N., Wang, P., Gorentala, N., Williams, M., Batarseh, F. A., Applications of Machine Learning for Precision Agriculture and Smart Farming. The Int.l FLAIRS Conf. Proc., 34. 2021. DOI: 10.32473/flairs.v34i1.128497
Sharma A., Jain A., Gupta P., Chowdary V., Machine Learning Applications for Precision Agriculture: A Comprehensive Review, IEEE Access, vol. 9, 2021. DOI: 10.1109/access.2020.3048415
Kalyani, Y.; Collier, R. A Systematic Survey on the Role of Cloud, Fog, and Edge Computing Combination in Smart Agriculture. Sensors, vol. 21, 5922, 2021. DOI: 10.3390/s21175922
View or Download full articleAccess options
SWS access login
Login as SWS Scientific CommitteeLogin as SWS Scientific PartnerLogin as SWS AuthorAuthors and approved SWS contributors will read and export their own linked papers after identity matching by SWS profile, email and SGEM GlobalID.
For librarian assistance: [email protected]
Purchase Instant Access
- Article can be downloaded after successful payment.
- Article may be used according to SWS library access terms.
- Article cannot be redistributed.