Service-oriented Data Mining Architecture for Climate-Smart Agriculture
Issue:
Volume 5, Issue 1, June 2020
Pages:
1-10
Received:
16 January 2020
Accepted:
10 February 2020
Published:
19 February 2020
Abstract: The increasing volume of agricultural data and the availability of advanced technologies such as mobile platforms and connected devices have revolutionized the way data is captured, processed, stored and mined. The technologies have been applied in everyday life including agriculture, to enable creation of seamless systems that are intuitive and capable of providing real-time, affordable and accessible data to aid decision making. However, due to the inherent challenges of mobile platforms such as low-bandwidth networks, reduced storage space, limited battery power, slower processors and small screens to visualize the results, have hindered onboard data mining. Also, mobile devices have different platforms, which makes integration with server applications problematic. This paper, therefore, sought to solve these problems by proposing application of service-oriented architecture (SOA) based on web services, and artificial neural network (ANN) to facilitate mobile data mining of large agronomic and climate data, and prediction of yield and weather patterns. The architecture was proposed after a critical review of the available mobile data mining architecture. SOA was an ideal choice since it uses web services to improve inter-operability between clients and server applications independently from the different platforms they execute on hence providing data mining capabilities to mobile devices. The paper proposes a 7-layer architectural design premised on the concept advanced in the SO-M-Miner model. The components of the architecture included an SMS gateway, data client, mobile networks, web service, database and ODBC connector.
Abstract: The increasing volume of agricultural data and the availability of advanced technologies such as mobile platforms and connected devices have revolutionized the way data is captured, processed, stored and mined. The technologies have been applied in everyday life including agriculture, to enable creation of seamless systems that are intuitive and ca...
Show More
Prediction of Agro Products Sales Using Regression Algorithm
Terungwa Simon Yange,
Charity Ojochogwu Egbunu,
Oluoha Onyekwere,
Kater Amos Foga
Issue:
Volume 5, Issue 1, June 2020
Pages:
11-19
Received:
3 June 2020
Accepted:
17 June 2020
Published:
6 July 2020
Abstract: This study aimed at developing a system using support vector machine (SVM) that will forecast sales of farm products for an agricultural farm so that managers can take strategic decisions timely to better market the excess farm products which some by nature are perishable. The sales prediction model used SVMs and Fuzzy Theory. The implementation was done using Python Programming Language. The system comprised of three (3) modules: web interface, flask and the SVM Framework. To evaluate the result of the SVM model, the RBF neural network was used as a benchmark. Data of previous sales records from University of Agriculture Makurdi (UAM) farm was used to train and test the system. After training the network with data which covered the time period from 21st January, 2017 to 30th June, 2019, the remaining data which covered from 1st July 2019 up to the 31st December, 2019 was used to test and validate the forecasting performance of the system. The Forecasting Precision (FP) value for the SVM was 96.75% and that of the RBF neural network forecasting value was 90.55%. Analysis from the results shows that the forecasting system with SVM had a greater precision in the sales of agricultural products.
Abstract: This study aimed at developing a system using support vector machine (SVM) that will forecast sales of farm products for an agricultural farm so that managers can take strategic decisions timely to better market the excess farm products which some by nature are perishable. The sales prediction model used SVMs and Fuzzy Theory. The implementation wa...
Show More
