School of Engineering Sciences

Permanent URI for this communityhttp://197.255.125.131:4000/handle/123456789/28140

Browse

Search Results

Now showing 1 - 8 of 8
  • Item
    Intelligent Instrument Reader Using Computer Vision and Machine Learning
    (2018 IEEE Industry Applications Society Annual Meeting, IAS 2018, 2018-09) Sowah, R.A.; Ofoli, A.R.; Mensah-Ananoo, E.; Mills, G.A.; Koumadi, K.M.
    A novel algorithm using computer vision and machine learning techniques have been developed in this research and applied to automate the reading of analog meters. This approach does not rely on any prior information about the meter being read or any human intervention during the process. High-level features of the meter including the graduation values and angles are extracted using a cascade of image contour filters with a series of digit classifiers. The features are refined and used to train regression models that return the reading of the analogue meter automatically. The proposed approach was tested to read a variety of offline and live-feed images of analog pointer meters automatically without any prior information about the meters. © 2018 IEEE
  • Item
    Integrating geo-spatial information infrastructure into conservation and management of wetlands in Ghana
    (Proceedings - 2011 2nd International Conference on Intelligent Systems, Modelling and Simulation, ISMS 2011, 2011-02) Owusu-Banahene, W.; Nti, I.K.; Sallis, P.J.
    Most data infrastructure tend to focus on data access and not particularly spatial aspects of data and services especially data relating to natural resource management. This project will conceptualise and implement a geospatial information infrastructure to facilitate conservation and management of wetlands in Ghana, where a scalable, accessible and robust solution is urgently needed. Critically, rather than relying on governmental agency as a sole means of continued and current data provision, the approach will link technical advances in mobile telephone services, global positioning systems and concepts of citizen science with advanced developments in semantics and interoperability to formalise a spatial infrastructure system capable of weighing assertion and achieving authority. This paper attempts to propose the use of the following technology in developing a Ghana Wetland Information System: remote sensed imagery plus scripting and database, e-Governance frameworks and Protégé OWL for the management of semantics. © 2011 IEEE.
  • Item
    A review on techniques applied to modelling, simulating and visualising evolution of physical landscape
    (CSSim 2009 - 1st International Conference on Computational Intelligence, Modelling, and Simulation, 2009) Nti, I.K.; Sallis, P.J.; Shanamuganathan, S.
    The paper considers contemporary physical landscape visualisation and simulation models that are used for impact analysis and decision making for geographical location studies. For this purpose a generic framework is presented that provides professionals with a tool to facilitate decision making. The main reasons for the framework construction are to provide a rigorous approach to the task of studying the evolution of physical landscapes, and to provide appropriate data for forecasting and scenario projections using computational simulations that reflect future changes. The framework is based on an in-depth analysis and assessment of a landscape monitored over time. On satisfactory completion of landscape models construction, the set of models developed are then used for the construction of visualisation images to represent the entire evolutionary process of the landscape. This framework includes functions through which users can generate visualisation models either with twodimensional maps and/or interactive immersive three dimensional images. © 2009 IEEE.