Dr Collins N. Udanor had his Ph.D in Electronic Engineering, and M.Sc in Computer Science in 2013 and 2004, respectively, from the University of Nigeria, Nsukka. He is a Senior Lecturer in the Department of Computer Science, University of Nigeria Nsukka (UNN).
His research interests include Design and development of Intelligent Systems using multi-agents. This was his Doctoral research work in which he developed a multi-agent system using the Java Agent Development (JADE) framework to implement Intelligent Mobile Learning System. The agents improved the response times of the application eight times compared to the non-agent version. This work has four journal publications and one conference presentation.
His current research activities include Machine Learning, Distributed and High Performance Computing (HPC), in which he leads the High Performance and Intelligence Computing (HiPIC) group in UNN. He has deployed Grid infrastructure in UNN and is currently deploying Cloud Computing infrastructures, Designing Clusters for Research and Education Networks. Over the last five years he has been deeply involved in the development, deployment and training of scientists, and actively involved in workshop and conference presentations on e-Infrastructures under the UNESCO-HP Brain Gain Initiative, eI4Africa project, WACREN, EU Grid Community Forum, Sci-GaIA, etc.
PLANTISC-2: Development of a SGW-based Plant Tissue Culture Micropropagation Yield Forecasting Application
Plant tissue culture is a collection of techniques used to maintain or grow plant cells, tissues or organs under sterile conditions on a nutrient culture medium of known composition. Plant tissue
culture is widely used to produce clones of a plant in a method known as micropropagation. During the UNESCO-HP Brain Gain Initiative (BGI) project (2009-2013), the University of Nigeria team conducted series of plant tissue culture experiments and developed a stand-alone application, Plantisc. A Plant Tissue Culture micro propagation simulation software, which achieved over 67% predication accuracy whose result was published in a peer-reviewed journal.
PLANTISC-2 is a simulation application that predicts the desired hormonal combinations using provided input data. A two variable multi-Regression is used for the prediction.
For storing and retrieving medical images, PLANTISC-2 adopted the Sci-GaIA Open Access Repository (OAR), in which specific sub-categories have been created for the use case. A DataCite-issued Digital Object Identifier (DOI) is automatically assigned by the OAR to each image to improve its findability, discoverability and reusability.
For processing medical images, the PLANTISC-2 Science Gateway is connected to a FutureGateway API Server – developed in the context of the INDIGO-DataCloud project – which seamlessly executes jobs on local, Grid and Cloud resources belonging to the Africa & Arabia Regional Operation Centre.
The PLANTISC-2 Science Gateway is a Service Provider of the GrIDP “catch-all” Identity Federation.