top of page

IM502 Big Data in Agriculture

DESCRIPTION

This unit provides advanced knowledge regarding the broad nature and scope of big data in agriculture through an understanding of sensors, drones, precision agriculture, Blockchain technology, Hadoop, MapReduce and Hadoop distributed file systems (HDFS), consumer sentiment analysis, smart social media usage for farm and product development and their incorporation into big data analytics using R programming and other open source tools.


RELEVANT COURSES

Master of Agricultural Information Management*

Master of Business Administration (Agribusiness)

Graduate Diploma in Agribusiness


*Core unit

Elective unit

Master of Agriculture specialisation in Agriculture Information Systems


CREDIT POINTS

10


DELIVERY MODE

On campus

Mixed mode

Online

Intensive

Extensive


PREREQUISITE OR CO-REQUISITE

IM501 Agriculture Data and Information Management


UNIT LEARNING OUTCOMES

LO1 Critically evaluate and explain the use of big data tools and techniques in the context of agriculture

LO2 Apply various data mining techniques to discover patterns in large data sets

LO3 Critically examine the application of big data tools and techniques in scenarios involving various combinations of physical and economic factors

LO4 Apply R programming to produce real-time analysis of emerging issues in agricultural products.

LO5 Critically evaluate the advanced algorithms of social media analytics to leverage insights into customer sentiment


CONTENT

  • An introduction to big data in agriculture with importance of big data science in agriculture

  • Getting acquainted with important software and programs of big data analytics including social media analytics and its use in agribusiness

  • Blockchain and cryptocurrency

  • Business drivers of blockchain; integration of blockchain technology in agriculture

  • Hadoop architecture and HDFS

  • Hadoop clusters and the Hadoop ecosystem

  • Incorporation of agriculture data from precision agriculture and drones into Hadoop MapReduce Framework

  • R programming basics for application of big data analytics in agriculture

  • Basic statistical analysis of agribusiness data in R Studio- data preparation and missing value treatment, univariate statistics, ANOVA, Chi-Square Test

  • Basics of correlation test and developing the correlation matrix, logistic regression, and discriminant analysis, -Use of regression techniques in agribusiness

  • Nonlinear regression, factor analysis, segmentation and clustering, decision tree analysis, agri-consumer behaviour analytics-neural network, text analytics, sentiment analysis, perceptual mapping

  • Special lecture on the big analytics and incorporation of its technique in agriculture at commercial level – a new advanced technology being developed commercially and offered to farmers in Australia


ASSESSMENT METHODS

1. Quizzes - 20%

2. Practical and goup project - 20% group / 20% individual contribution

3. Project - 40% 


PRESCRIBED READINGS

Nil


Check with the lecturer each semester before purchasing any textbooks.

bottom of page