Master of Science degree in Agricultural Informatics and Data Analytics (MAIDA)
Programme Overview
To address the demand of Information Technologies, Data processing and Analytical techniques in Agriculture for sustainable food and fiber production, natural resources management and overall economic growth.
Entry Requirements
To be eligible in the programme, a candidate must normally be a holder of at least a lower second class (2.2) first degree in Agriculture, Agricultural Economics; Economics; Mathematics; Statistics; Information Technology or any other related programme from a recognized University.
PROGRAMME STRUCTURE
- The degree programme shall have at least 32 taught modules spread over the six teaching semesters.
Level 1 Semester 1
*MAIDA 701 Emerging Issues in e-Agriculture 18
*MAIDA 702 Data Science: Analytics and Visualizations 18
*MAIDA 703 Qualitative and Quantitative Techniques in Agriculture Analysis 18
*MAIDA 704 Geographical Information Systems 18
Level 1 Semester 2
*MAIDA 705 Research Methods 18
*MAIDA 706 Socio-economic Data Base Systems Design 18
*MAIDA 707 Big Data Analytics in Agriculture 18
*MAIDA 708 Agricultural Value Chains Development and Financing 18
OPTIONS (CHOOSE TWO)
MAIDA 709 Agricultural Policy Informatics 18
MAIDA 710 Agricultural Trade and Policy 18
MAIDA 711 Information Security, Ethics and Legal Aspects 18
MAIDA 712 Sustainable development and Smart Agriculture 18
MAIDA 713 Cyber Analytics 18
Level 2 Semester 1 & 2
*MAIDA 715 Dissertation 90
MODULE SYNOPSIS
MAIDA701 Emerging Issues in e-Agriculture
The module discusses contemporary issues in e-Agriculture. More emphasis will be placed on; Technology for changing times, Mobile telephony, from mobile phones to smartphones, Mobile financial services, Use of ICTs in agriculture, e-Agriculture strategies in ICT policies, Online learning, Growing use of big/open/real-time data collection and analysis, Digital dilemma and Appropriate technologies.
MAIDA702 Data Science: Analytics and Visualizations
The module covers; Supervised learning and applications. Multicol9linearity, ridge regression, the LASSO and the elastic net. Parametric and nonparametric logistic regression and nonlinear regression. Survival regression. Regression extensions: Random forests MARS and Conjoint analysis. Neural networks.
MAIDA703 Qualitative and Quantitative Techniques in Agriculture Analysis
A wide range of quantitative and qualitative techniques are applied to the analysis of management problems. This module will provide students with the skills to apply a wide range of quantitative and qualitative techniques to a variety of management problems in the various areas of agriculture. A critical feature of the module is the use of managerial oriented cases to focus students on the application of quantitative and qualitative techniques to management problems. Particular emphasis will be placed on computer-based applications of quantitative and qualitative techniques.
MAIDA704 Geographical Information Systems
This module seeks to equip students with the theoretical understanding and practical skills in geo-informatics that underpin natural resources and environmental management. The module comprises basic theoretical and practical concepts in Geographic Information Systems (GIS) and remote sensing (RS). The GIS component presents the concepts and techniques for collecting or creating, processing, storing and analyzing spatial data; while the RS component addresses the theory and techniques requisite for handling optical satellite images. Topics covered include the nature of GIS, spatial data capture and storage, spatial data models, spatial analysis, satellite remote sensing and image analysis.
MAIDA705 Research Methods
This module introduces postgraduate students to the basic ideas about conduction research. Students will learn methods for reading technical papers, selecting research topics, devising research questions, planning research, project management and ethics. The evaluation is based on the assignments throughout the course and a final project report and presentation.
MAIDA706 Socio-economic Data Base Systems Design
The module covers the following topics; Information in Social Context, Socio-economic data, Aggregate and disaggregate data, Cross-sectional and longitudinal data, Sources of socio-economic data, Database design, determining data to be stored, Principle of orthogonal design, determining data relationships, Concept mapping, logically structuring data, Entity-Relationship model, Database normalization, Conceptual schema and Physical design of the database.
MAIDA707 Big Data Analytics in Agriculture
This module examines the theoretical and practical techniques used in the analysis of large data sets. It covers data collection, data pre-processing, predictive, prescriptive and descriptive analytics as well as social network analytics. The module will facilitate discussion of case studies that involve big data analytics including fraud detection, web analytics and recommender systems. Due to the data and technology-intensive nature of the material, this module will be delivered primarily through face-to-face instruction and hands-on lab sessions.
MAIDA708 Agricultural Value Chains Development and Financing
The module will cover the following topics; value chain finance in agriculture, understanding agricultural value chain finance, Value chain business models, Agricultural value chain finance instruments, Innovations, strategy and design recommendations for programmes dealing with agricultural value chains and agricultural value chain finance.
MAIDA709 Agricultural Policy Informatics
The module addresses the following topics pertaining to agriculture; Public policy theory, domestic and international policy, introduction to policy and practice, international policies and organizations, urban politics, Information and Communication Technology policy, legal and regulatory policy frameworks.
MAIDA710 Agricultural Trade and Policy
The module covers the following issues; an understanding of why nations trade and the role of supply and demand factors in determining trade; a basis for evaluating international competitiveness and comparative advantage; an appreciation for how agricultural trade is related to growth and development; an ability to evaluate the welfare implications of policies affecting production, consumption, and trade; an understanding of the implications of protectionism, free trade, managed trade, regional trade blocs, and multilateral trade liberalization, and the role for international trade institutions.
MAIDA711 Information Security, Ethics and Legal Aspects
This module introduces students to theoretical and practical aspects of information security, ethics and legal aspects as it relates to data and information in organizations. The module aims to provide students with the skills and knowledge necessary for the planning and implementation of policies and procedures for the security of an organization’s information assets.
MAIDA712 Sustainable Development and Smart Agriculture
The module gives an overview of climate-smart agriculture as an approach to address the interlinked challenges of achieving sustainability, increasing food security and responding to climate change. The module describes an overall framework for building resilience and increasing efficiency in various agricultural production systems. Issues to be addressed to implement climate-smart agriculture and make progress towards efficient and resilient agriculture production systems and food systems.
MAIDA713 Cyber Analytics
The module will address the following aspects; Reviewing, from a statistical perspective, the cyber-infrastructure ecosystem including distributed computing, and multi node and distributed file eco systems, such as Amazon Web Services. Structured and unstructured data sources, including social media data and image data. Setting up of large data structures for analysis. Algorithms and techniques for computing statistics and statistical models on distributed data. Software to be used include, Hadoop, Map reduce, SAS, SAS Data loader for Hadoop.
MAIDA715 Dissertation
This is a scientific report of between 15 000 and 20 000 words, based on supervised research by the student. The dissertation should be presented to a panel of the Departmental Board.