Abstract-In order to introduce modern warehousing, improve upon the storage of grain and grain marketing business processes for the Food Reserve Agency in Zambia, a prototype of a remote sensor network was developed and built as a proof of concept for a much wider deployment using cloud computing and the internet of things concept. It was determined that a wireless sensor network would aid the Food Reserve Agency in analytics, timely action and real-time reporting from all its food depots spread-out throughout Zambia. Google's Android Things Platform was used in order to achieve the objectives. Advantages of Android Things over traditional platforms that have been used to develop wireless sensor networks were looked into and presented in this paper.

The use of Artificial Intelligence in agriculture is a novel approach that promises many benefits. Notable is the emphasis by nations of the world to end hunger by 2030 as enshrined in Sustainable Development Goal number 2[1]. To end world hunger, the fundamental ways of doing things in and around the agricultural space will have to change by adopting much more sustainable models and relooking at the supply chain system with the space. For example, it is noted that more food goes to waste through spoilage than is required to feed all the hungry on earth. While in other parts of the globe, the food supply would be sufficient were it not for the stock that spoils due to pests and diseases. It the goal of this paper to provide a possible solution for the second scenario on spoilage due to pests and diseases by adopting Artificial Intelligence approaches such as Machine Learning and tweaking existing methods by improving the overall prediction score. We provide areas of interest that may be considered and show that further research in the subject may yield positive results in the field of Predictive Analysis as concerns the field of agriculture. A Systematic Review is done on over 20 pieces of literature around the field of Predictive analysis and notable gaps are highlighted while areas of possible improvement are also indicated. It is then against this backdrop that the highlighted areas of improvement may later be tested in subsequent work.

E-government has been an essential part of the targets set forth by all governments that are signatory to the United Nations 2030 sustainable development goals which am to create effective, accountable and inclusive governments. In order to achieve e-government in the most efficient manner, more and more governments around the world are embracing cloud storage and cloud applications as the de facto standard for data storage, archiving, analysis and manipulation. The amounts of money that governments will spend are huge and the infrastructure requirements far exceed the capabilities of most government institutions. Models such as centralized management of cloud infrastructure have been adopted but this defeats the purpose of cloud computing where resources and even management of those resources are decentralized. In this paper we present a proposal for a standard model for governments to utilize their existing or planned cloud infrastructure and leverage private and public cloud infrastructure in order to achieve true cloud decentralization. We propose that Blockchain technologies provide the most optimal and quickest methods towards e-government. We look into the problem of analyzing big data in national data centres and methods of optimization based on already available technology.