Browsing by Author "Akinola, O. A."

Now showing 1 - 3 of 3
  • Item
    Development and Scaled-up Simulation Of An Automated Electrical Energy Management System For Passageway Illumination
    (Walter de Gruyter GmbH, 2020) Odetoye, O. A.; Afolabi, A. S.; Akinola, O. A.
    Buildings account for much of the world’s energy consumption; thus, it is important to develop ways, not just to harness more of the energy in the universe, but also to make system of devices in buildings more energyefficient. Occupancy-based illumination is an emerging trend in energy management, but research in this field has mostly been focused on illumination of rooms and workspaces in building interiors. To the best of the authors’ knowledge, there is virtually no literature on the energy optimisation of depersonalised spaces such as passageways. This paper explores the development and evaluation of a controller-based model for illumination of passageways in buildings, where relatively-large number of depersonalized luminaires are usually found and automation might prove especially beneficial. After development, testing and scaled-up simulations, results show that occupancy-based illumination of exterior corridors and semi-covered passages in buildings is feasible, economical, has significant energy savings, and is worthy of consideration for modern buildings.
  • Item
    Development of mobile and desktop applications for a fingerprint-based attendance management system.
    (Institute of Advanced Engineering and Science (IAES), 2021) Akinola, O. A.; Olopade, S. O.; Afolabi, A. S.
    Mobile application technology has been at the forefront of technological advancement in recent years. This has made life easier, and tasks that were considered herculean have been made easier and executable in a much shorter time than ever. One of such tasks is the process of taking attendance during events (such as lectures and conferences) by scribbling one’s signature and other personal details on a central register. This manual process is cumbersome and inconvenient, especially when a large number of participants are involved. To address this problem, this paper presents an automated solution in which a Java-based mobile application was developed and connected wirelessly to a central database that was created using My structured query language (MySQL) application whose task, among others, was to record attendance information. The database was connected to the backend of the web-based software program which was coded in hypertext pre-processor (PHP) programming language. Authentication was achieved through username, password, and fingerprint information. The system was deployed in a university to log students’ details, time absent, time present and cumulative attendances per month and it was realised that the system was highly effective, efficient and 5 times faster than the conventional paper-based attendance logging technique.
  • Item
    A Reinforcement Learning Approach for Interference Management in Heterogeneous Wireless Networks
    (Kassel University Press GmbH, 2021) Afolabi, A. S.; Ahmed, S.; Akinola, O. A.
    Due to the increased demand for scarce wireless bandwidth, it has become insufficient to serve the network user equipment using microcell base stations only. Network densification through the addition of low power nodes (picocell) to conventional high-power nodes addresses the bandwidth dearth issue, but unfortunately introduces unwanted interference into the network which causes a reduction in throughput. The purpose of this paper is to develop a model for controlling the interference between picocell and microcell users of a cellular network so as to increase the overall network throughput. In order to achieve this, a reinforcement learning model was developed which was used in coordinating interference in a heterogeneous network comprising microcell and picocell base stations. The learning mechanism was derived based on Q-learning, which consisted of agent, state, action, and reward. The base station was modeled as the agent, while the state represented the condition of the user equipment in terms of Signal to Interference Plus Noise Ratio. The action was represented by the transmission power level and the reward was given in terms of throughput. Simulation results showed that the trend of values of the learning rate (e.g., high to low, low to high, etc.) plays a major role in throughput performance. It was particularly shown that a multi-agent system with a normal learning rate could increase the throughput of associated user equipment by a whopping 212.5% compared to a macrocell-only scheme.