Department of Electrical and Computer Engieering

Permanent URI for this community

https://kwasuspace.kwasu.edu.ng/handle/123456789/96

Browse

Now showing 1 - 20 of 91

A chi-square-SVM based pedagogical rule extraction method for microarray data analysis
(Institute of Advanced Engineering and Science (IAES), 2020) Salawu, Mukhtar Damola; Arowolo, Micheal Olaolu; Abdulsalam, Sulaiman Olaniyi; Isiaka, Rafiu Mope; Jimada-Ojuolape, Bilkisu; Olumide, Mudashiru Lateef; Gbolagade, Kazeem A.
Support Vector Machine (SVM) is currently an efficient classification technique due to its ability to capture nonlinearities in diagnostic systems, but it does not reveal the knowledge learnt during training. It is important to understand of how a decision is reached in the machine learning technology, such as bioinformatics. On the other hand, a decision tree has good comprehensibility; the process of converting such incomprehensible models into an understandable model is often regarded as rule extraction. In this paper we proposed an approach for extracting rules from SVM for microarray dataset by combining the merits of both the SVM and decision tree. The proposed approach consists of three steps; the SVM-CHI-SQUARE is employed to reduce the feature set. Dataset with reduced features is used to obtain SVM model and synthetic data is generated. Classification and Regression Tree (CART) is used to generate Rules as the Last phase. We use breast masses dataset from UCI repository where comprehensibility is a key requirement. From the result of the experiment as the reduced feature dataset is used, the proposed approach extracts smaller length rules, thereby improving the comprehensibility of the system. We obtained accuracy of 93.53%, sensitivity of 89.58%, specificity of 96.70%, and training time of 3.195 seconds. A comparative analysis is carried out done with other algorithms.
A Comparative Analysis of Complexity of C++ and Python Programming Languages Using Multi- Paradigm Complexity Metric (MCM)
(International Journal of Science and Research (IJSR), 2018-10-26) Balogun M. O.; Sotonwa K. A.
Software complexity metrics have used to quantifydifferent types of software properties such as cost, effort, time, maintainability, understanding and reliability. The existing metrics considered limited factors that affect software complexity, but do not consider the characteristics that affect complexity of multi-paradigm languages. In this work, a Multi-paradigm Complexity Metric (MCM) for measuring software complexity was developed for multi-paradigm codes. Multi-paradigm languages that were considered in thiswork are C++ and Python, these two languages combine the features of procedural and object oriented paradigms, therefore this research began with investigation of factors that affect the complexity of procedural code and object oriented code, so that the developed metric could be used not only for procedural code, but also either object oriented codes or in more general for multi-paradigm codes. The developed metric was then applied on sample programs written in most popular programming languages such as Python and C++, and the result of the developed metric was further evaluated with other existing complexity metrics like effective line of code (eLOC), cyclomatic complexity metric and Halstead complexity measures. The study showed that the developed complexity metric have significant comparison with the existing complexity metrics and can be used to rank numerous programs and difficulties of various modules.
A Complexity Metric for Multi-Paradigm Programming Languages
(International Journal of Emerging Technology and Advanced Engineering, 2014-04-22) Olabiyisi S. O.; Omidiora E. O.; Balogun M. O.
Software complexity metrics are used to measure variety of software properties such as cost, effort, time, maintenance, understanding and reliability. Most of the existing metrics considered limited factors that affect software complexity, but do not consider the characteristics of multi-paradigm languages. In this work, a Multi-paradigm Complexity Metric (MCM) for measuring software complexity was developed for multi-paradigm codes. Multi-paradigm languages that were used in this work combine the features of procedural and object oriented paradigms, therefore this research began with investigation of factors that affect the complexity of procedural code, thereafter with a more modern approach, the research was further extended by adding object oriented features, so that the developed metric could be used not only for procedural code, but also either object oriented codes or in more general meaning for multi-paradigm codes. The developed metric was then applied on sample programs written in most popular programming languages such as Python, Java and C++, and was further evaluated with other existing complexity metrics like effective line of code (eLOC), cyclomatic complexity metric and Halstead complexity measures. The study showed that the developed complexity metric have significant comparison with the existing complexity metrics and can be used to rank competitive programs and difficulties of various modules.
A Control Model of the Operating Head Dynamics of Jebba Hydropower System.
(Nigerian Journal of Technological Research (NJTR), 2019) Ogunbiyi O., Thomas C., Omeiza I. O. A. , Akanni J., Olufeagba B. J.
Electricity availability in Nigeria has been very poor over the years, underscoring the need for a better approach for managing generating resources. This paper presents the development of a dynamical model of the operating head of Jebba hydroelectric power plants for system studies and control system design. The mathematical model of the plant was developed from flow continuity conditions, some model parameters were obtained from the source while others were estimated from observations and analysis of the measured data. The developed dynamical equation was validated by comparing the response produced with values obtained by measurement. Upon integrating the model equation in the Microsoft EXCEL VBA® environment, a deviation of 2% from measured values was observed. Operators can therefore use the model as a decision support system, while control engineers can find the model directly applicable for optimal and robust control system design for the station.
A Direct Optimal Control of the Jebba Hydropower Station
(2nd International Conference of the IEEE Nigeria Computer Chapter, NigeriaComputConf, 2019) Ogunbiyi, O., Thomas, C. T., Olufeagba, B. J., Madugu, I. S., Adebiyi, B. H., & Adesina, L. M.
The optimal power generation from the Jebba hydroelectric power station is subject to the reservoir operating head, weather-related factors, units’ availability and system dynamics. In this paper, a computer control system is designed to ensure safe operation and maximize power generation. The controller is an optimal controller, which determines the amount of inflow required to regulate the reservoir operating head. The control law is an optimal control procedure developed around the steepest descent and conjugate gradient algorithm. The algorithms determine the control signal and state trajectories for the minimization of a performance index defined for the regulation of the reservoir operating head. The results show that the two techniques are feasible in estimating an optimal inflow needed to move the reservoir operating head from any level to the nominal head. The two techniques were compared under different operating conditions of the hydropower system, the conjugate gradient algorithm performs better in terms of computational time. The control algorithm is recommended for use in the realization of a computer control system for the station.
A Method of Colour-Histogram Matching for Nigerian Paper Currency Notes Classification
(Jordan Journal of Electrical Engineering (JJEE), 2023) Omeiza, I. O. A., Ogunbiyi, O., Ogundepo, O. Y., Otuoze, A. O., Egbune, D. O., & Osunsanya, K.
In this paper a new algorithm for the classification of three Nigerian paper currency notes, namely 200, 500, and 1000 Naira (N) denominations is presented. The work examines the effectiveness of using only colour histograms to differentiate between the classes or denominations of the three Nigerian paper currency notes. The bin-heights of the histograms of the HSI component images for the paper currencies are used as features while a rule-based classifier designed to take advantage of the changes or variations in the histogram patterns is used to classify the paper currencies into the right denomination class. The algorithm involves the utilization of a simple and effective comparison strategy as opposed to the existing, too-rigid metrics for histogram-comparison used by other authors for color indexing in content-based image retrieval systems. Over a testing data-set of 300 samples, the algorithm achieved an average classification accuracy of 98.66%, and classification accuracies of 100%, 99% and 97% for the N=200, N=500 and N=1000 denominations, respectively. The proposed algorithm does not require extensive preprocessing of the paper-currency images and as such is fast in implementation.
A Modified COST-231-Hata Path Loss Model for Typical Semi-Urban Environments in Nigeria
(KIU Journal of Science, Engineering and Technology, 2024) AKANNI, Jimoh, ISA Abdurrhaman Ademola, OGUNBIYI Olalekan, OLUFEAGBA Benjamin Jimmy
Outdoor path loss propagation modeling is critical in the planning and design of the coverage area by the Global System for Mobile Communication (GSM). For the best prediction of GSM signal at any location within its coverage region, an accurate forecast based on critical characteristics and a mathematical model is necessary. Multiple studies on path loss propagation model prediction for GSM networks conducted at various semi-urban environments in Nigeria proclaimed that propagation path loss models may provide different results when utilized in environments other than those in which they were initially designed, that car drive-test methodology was used during the data collection, and that COST-231-Hata model provides closet prediction to the practical measure values. This paper created an appropriate path loss model based on the COST-23-Hata model and outdoor measurement at 1800 MHz frequency range for the semi-urban area of Kwara State, Nigeria. The created model was used and validated with the measured data and COST-231-Hata model at other different semi-urban environments in Nigeria. The results analysis shows that the created model performed satisfactorily given the closet path loss prediction to the practical measure path loss values at all the study locations. It also gives the lowest Square Root Means Error (SRME) and Standard Deviation (SD) in all the base stations that were tested in semi-urban environments. The newly created model would therefore be more appropriate for GSM 1800 network design and installation in semi-urban environments in Kwara State, Nigeria, as well as any other semi-urban locations in Nigeria.
A Nonlinear Control Model and Operational Support System for the Kainji Hydroelectric Power System
(2019) Ogunbiyi, O., Thomas, C. T., Omeiza, I. O. A., Akanni, J., & Olufeagba, B. J.
Over the past years, the hydropower model and control were largely based on classical and linear transfer functions, this was motivated by the available control system design techniques that were available and the desire to simplify the design procedure. Such a model is inadequate for dynamic study and design of hydropower stations in the presence of uncertainties in the water head, discharge rate, elastic water effect, travelling wave effect, large variation power output and frequency. This research, therefore, focuses on developing a nonlinear model for the Kainji hydroelectric power station. The model relies on the energy conversion principles, inflows, discharge, evaporation rate and number of units on the busbar. The parameters of the model were also estimated, and the model was validated with an error within +1.4% to -3.6%. The model is expected to be used to determine the optimal control policies for the operation of the station and the release of water to downstream.
A Nonlinear Control Model and Operational Support System for the Kainji Hydroelectric Power System.
(Nigerian Journal of Technology (NIJOTECH), 2019) Ogunbiyi, O., Thomas, C. T., Omeiza, I. O. A., Akanni, J., & Olufeagba, B. J.
Over the past years, the hydropower model and control were largely based on classical and linear transfer functions, this was motivated by the available control system design techniques that were available and the desire to simplify the design procedure. Such a model is inadequate for dynamic study and design of hydropower station in the presence of uncertainties in the water head, discharge rate, elastic water effect, traveling wave effect, large variation power output and frequency. This research, therefore, focuses on developing a nonlinear model for the Kainji hydroelectric power station. The model relies on the energy conversion principles, inflows, discharge, evaporation rate and number of units on busbar. The parameters of the model were also estimated, and the model validated with an error within +1.4% to -3.6%. The model is expected to be used to determine the optimal control policies for the operation of the station and the release of water to the downstream.
A Progressive Domain Expansion Method for Solving Optimal Control Problem.
(TELKOMNIKA (Telecommunication, Computing, Electronics and Control), 2020) Ogunbiyi, O., Ogundepo, O. Y., & Sani, M. I.
Electricity generation at the hydropower stations in Nigeria has been below the expected value. While the hydro stations have a capacity to generate up to 2,380 MW, the daily average energy generated in 2017 was estimated at around 846 MW. A factor responsible for this is the lack of a proper control system to manage the transfer of resources between the cascaded Kainji-Jebba Hydropower stations operating in tandem. This paper addressed the optimal regulation of the operating head of the Jebba hydropower reservoir in the presence of system constraints, flow requirements and environmental factors that are weather-related. The resulting two-point boundary value problem was solved using the progressive expansion of domain technique as against the shooting or multiple shooting techniques. The results provide the optimal inflow required to keep the operating head of the Jebba reservoir at a nominal level, hence ensuring that the maximum number of turbo-alternator units are operated.
A Steepest Descent Algorithm for the Optimal Control of a Cascaded Hydropower System
(International Journal of Electrical and Computer Engineering (IJECE), 2020) Ogunbiyi, O., Thomas, C. T., Ogundepo, O. Y., Omeiza, I. O. A., Akanni, J., & Olufeagba, B. J.
Optimal power generation along the cascaded Kainji-Jebba hydroelectric power system had been very difficult to achieve. The reservoir's operating heads are being affected by possible variations in impoundments upstream, stochastic factors that are weather-related, availability of the turbo-alternators and power generated at any time. Proposed in this paper, is an algorithm for solving the optimal release of water on the cascaded hydropower system based on the steepest descent method. The uniqueness of this work is the conversion of the infinite-dimensional control problem to a finite one, the introduction of clever techniques for choosing the steepest descent step size in each iteration and the nonlinear penalty embedded in the procedure. The control algorithm was implemented in an Excel VBA® environment to solve the formulated Lagrange problem within an accuracy of 0.03%. It is recommended for use in system studies and control design for optimal power generation in the cascaded hydropower system.
A Study of Energy Conversion at the Jebba Hydroelectric Power Station
(IEEE 3rd International Conference on Electro-Technology for National Development (NIGERCON), 2017) Thomas C. T., Akorede M. F., Ogunbiyi O., Olufeagba B. J., & Samuel S. J.
Hydroelectric power significantly contributes to the national power grid of Nigeria. This paper examined the extent of utilization of the energy supplied into each of the turboalternators at the Jebba Hydroelectric Power Station (JHEPS), Nigeria and suggests a corrective culture to be employed for improved efficiency. The basic principle of a hydropower scheme and its conversion considerations were highlighted. The daily discharge, Q, in cumecs and the power generated, P, in MW at JHEPS over a decade period (2005 – 2014) were analyzed using codes and scripts of Microsoft EXCEL-VBA. Jebba hydroelectric power station is one of the three major hydropower stations in Nigeria and the potential is just beginning to be exploited. The stochastic distribution pattern of the station is also presented for further analysis of failure and repair of the station. The conversion behavior of each unit was found to be linear and all have a value greater than 0.5 on a scale of 0.00 to 1.00. Turbo-alternator (TA) unit 1 was found to have the highest conversion characteristic of 0.9951, while unit 4 was the least at 0.6884. However unit 6 was exempted in this analysis as it was not in use during this period. The paper also gave an insight into the effective operating head of each TA, the paper also suggests the corrective measure to employ for each turbine.
AJ-Olu-1: An Innovative Path Loss Model for Typical Nigerian Urban Environments
(KIU Journal of Science, Engineering and Technology, 2023) Akanni, J., Isa, A. A., Ogunbiyi, O., Olufeagba, B. J., & Sanni, T. A.
The modelling of outdoor path loss propagation is critical in the planning and construction of the Global System for Mobile Communication (GSM) coverage area. For GSM signal prediction at any location inside its service region, a precise forecast based on critical characteristics and a mathematical model is required. Numerous research findings on path loss propagation model forecast for GSM mobile networks conducted in various cities in Nigeria revealed that the COST-231-Hata model gives closer prediction to most of the practical measure path loss values. Based on the existing COST-23-Hata path loss model and outdoor measurements at 1800 MHz frequency range within the Ilorin metropolis, this paper proposed a suitable path loss model. The developed model was used and validated in various locations throughout Ilorin City with the measured and COST-231 Hata models. The analysis of the results revealed that the developed model performed satisfactorily in terms of the closest path loss prediction to the practical measure path loss values at all study locations. It also has the lowest Square Root Means Error and Standard Deviation (SD) of any Base Station (BTS) tested in Ilorin, Nigeria. As a result, it is concluded that the newly developed AJ-Olu-1 model is more suitable for GSM 1800 network design and installation in Ilorin City, Nigeria, as well as other cities in Nigeria and other cities outside Nigeria with similar environments.
ARMA MODEL FOR PREDICTION OF SOLAR RADIATION IN KANO-NIGERIA
(Zaria Journal of Electrical Engineering Technology, Department of Electrical Engineering, Ahmadu Bello University, Zaria – Nigeria., 2019) Ibrahim S. Madugu, B. J. Olufeagba, Yinusa A. Adediran, A. Abdulkarim F. Abdulkadir, James. U. Inaku, Olalekan Ogunbiyi, O. Ibrahim, A. U. Lawan and Mubarak A. Afolayan
Statistical approach is one of the most prominent ways of forecasting a trend of a time series data such as solar radiation. This paper explore the autoregressive integrated moving average (ARMA) model using Box and Jenkins methodology to determine the most parsimonious model of Kano, Nigeria solar radiation time series. The result obtained showed that ARMA(3,0) has the least value of Root Mean Square Error (RMSE), Sum Of Square (SSE), Mean Absolute Percentage Error (MAPE) and Theil’s U-Statistics with 0.0004, 0.0422, 0.0388 and 0.0061 respectively. Therefore ARMA(3,0) is the best model that fits the solar radiation data and hence the most parsimonious.
ARTIFICIAL NEURAL NETWORK ALGORITHM BASED SHORT-TERM LOAD FORECASTING FOR MEDIUM VOLTAGE NETWORKS
(ARPN Journal of Engineering and Applied Sciences, 2021) Lambe Mutalub Adesina, Busayo Hadir Adebiyi and Olalekan Ogunbiyi
Electrical energy is generally known that it cannot be stored. Therefore, it is generated whenever there is need or demand for it. Thus, it is imperative for the power utility companies that the load on their systems should be estimated in advance while such estimation of load in advance is referred to as load forecasting. The forecasting could be Short term, Medium term and Long term depending on the certain parameters in consideration. Short term load forecasting method usually has period ranging from one hour to one week. It often assists in approximating load flow and to make decisions that can intercept overloading. Also, Short term forecasting provides obligatory information for the system management of daily operations and unit commitment. This paper presents an Artificial Neural Network-based model for Short-Term Electricity Load Forecasting. The performance of the model is evaluated by applying the hourly load data of a leading power utility company in Nigeria to predict the required load of the next day in advance. These hourly load data were obtained from two number 33KV feeders; namely the Government house and Sabo-Oke. Also, the data were normalized and then loaded into the model. The model was trained in MATLAB R2020a neural network Simulink environment. The simulation results show a good prediction accuracy for the two domains.
Assessment of Failure and Repair Behaviors of the Jebba Hydroelectric Power Station
(ELEKTRIKA Journal of Electrical Engineering, 2018) Cornelius Temitope Thomas, Olalekan Ogunbiyi , Mudathir Funsho Akorede and Benjamin Jimi Olufeagba
Nigeria power generation is circa 4000 MW as at October 2016, this is far less than the national required value. Jebba Hydroelectric Power Station (JHEPS) is one of the three major hydropower stations in the country which its maximum average generation value is still less than the rated value of 578.4 MW. This paper presented some basic concepts of analysis of failure and repair. An algorithm was set up to extract the contiguous set of up-times and down-times to determine time-tofail (TTF) and time-to-repair (TTR) events, these events were analyzed for stochastic study. It was observed that the longest up time was 262 days and seen in turbo-alternator unit five, while the shortest was zero day and seen in the entire units except that of unit two. The longest downtime was 133 days and seen in the turbo-alternator of unit one, the least time-to-repair is a day and common to all the units. The frequency distributions for both TTF and TTR showed that 79% of TTF events and 57% of TTR events are distributed in the first 2 classes
Assessment of Failure and Repair Behaviours of the Jebba Hydroelectric Power Station
(ELEKTRIKA- Journal of Electrical Engineering, 2018) Thomas, C. T., Ogunbiyi, O., Akorede, M. F., & Olufeagba, J. B.
Nigeria power generation is circa 4000 MW as at October 2016, this is far less than the national required value. Jebba Hydroelectric Power Station (JHEPS) is one of the three major hydropower stations in the country which its maximum average generation value is still less than the rated value of 578.4 MW. This paper presented some basic concepts of analysis of failure and repair. An algorithm was set up to extract the contiguous set of up-times and down-times to determine time-tofail (TTF) and time-to-repair (TTR) events, these events were analyzed for stochastic study. It was observed that the longest up time was 262 days and seen in turbo-alternator unit five, while the shortest was zero day and seen in the entire units except that of unit two. The longest downtime was 133 days and seen in the turbo-alternator of unit one, the least time-to-repair is a day and common to all the units. The frequency distributions for both TTF and TTR showed that 79% of TTF events and 57% of TTR events are distributed in the first 2 classes
Automatic Generation of Root Locus Plots for Linear Time Invariant Systems
(Nigerian Journal of Technology (NIJOTECH), 2017) Durutoye, N., & Ogunbiyi, O.
Design and analysis of control systems often become difficult due to the complexity of the system model and the design techniques involved. This paper presents the development of a Tools Box in Microsoft Excel for control engineers that uses root locus as a time domain technique for system design and analysis. The Tool Box can also serve as a computer-aided graphical analytical tool for trainers. The work was done in two phases: the first phase is the development of programmable algorithms for root locus using the angle condition and bisection method while the second phase is the implementation of the developed algorithms. The implementation was done using Microsoft Excel (R) Visual Basic Application (VBA). Results of simulations for different systems show the potential of the Tool Box as an alternative for other software package and the ease of using it on the readily available Microsoft Excel environment.
Code Quality Metric of Searching Algorithms for Multi-Paradigm Languages
(International Journal of Scientific Research and Management (IJSRM), 2019-05-20) Sotonwa K. A.; Balogun M. O.; Olusi Titilayo
This study investigated the comprehensibility of a software code from a developer‟s point of view and proposed new metric accordingly. The factors that affect the complexity of procedural, object-oriented, and multi-paradigm codes were analyzed for this purpose. Addition to the investigated factors, various metrics and several aspects were combined in the proposed metric. The proposed metric were empirically validated in different paradigms.
Comparative Analysis of Complexity of C++ and Python Programming Languages
(Asian J. Soc. Sci. Manag. Technol, 2022-05-20) 11. Balogun, M. O.
Software complexity is one of the natural systems complexity which measure the rate at which a particular software is difficult to comprehend, edit, understand, manipulate and maintain. With various system interfaces and complex requirements, the complexity of software systems sometimes grows beyond control, making applications and portfolios too costly to maintain and difficult to improve. A complex software if left uncorrected can run rambling in the developed code, leaving behind bloated, cumbersome, incomprehensible and difficult to maintain applications. In this paper, complexity of two object oriented programming languages (C++ and Python) were compared using some existing complexity measures such as lines of code (LOC) and Halstead complexity measures. The results of the comparison showed that Python programming language is less complex than C++ programming language.

Browse

Browsing Department of Electrical and Computer Engieering by Title

Results Per Page

Sort Options