adenike folaponmile | Kaduna Polytechnic (original) (raw)
Uploads
Papers by adenike folaponmile
FUOYE Journal of Engineering and Technology
Fuzzy Time Series (FTS) is able to eliminate the problem of overfitting that is fundamental to Ar... more Fuzzy Time Series (FTS) is able to eliminate the problem of overfitting that is fundamental to Artificial Neural Network (ANN), hence this study used air pollution data acquired from three different sampling stations in Kaduna metropolis, Nigeria, to implement FTS using the Adaptive Neuro Fuzzy Inference System (ANFIS). The fuzzy inference system (FIS) was generated by the ANFIS model using grid partitioning and subtractive clustering optimization types with backpropagation and hybrid training algorithms. The models were implemented using MATLAB 2018b software, and a total of thirteen models were developed. The resulting models were used to forecast the daily mean for the next ten days for each sampling station and for each pollutant. Carbon monoxide (CO), Nitrogen dioxide (NO2), Sulfur dioxide (SO2), Particulate matter, (PM2.5 and PM10) air pollutants were considered. Determination of the accuracies of the developed models in forecasting the next ten days was achieved using the err...
FUOYE Journal of Engineering and Technology, 2023
Fuzzy Time Series (FTS) is able to eliminate the problem of overfitting that is fundamental to Ar... more Fuzzy Time Series (FTS) is able to eliminate the problem of overfitting that is fundamental to Artificial Neural Network (ANN), hence this study used air pollution data acquired from three different sampling stations in Kaduna metropolis, Nigeria, to implement FTS using the Adaptive Neuro Fuzzy Inference System (ANFIS). The fuzzy inference system (FIS) was generated by the ANFIS model using grid partitioning and subtractive clustering optimization types with backpropagation and hybrid training algorithms. The models were implemented using MATLAB 2018b software, and a total of thirteen models were developed. The resulting models were used to forecast the daily mean for the next ten days for each sampling station and for each pollutant. Carbon monoxide (CO), Nitrogen dioxide (NO2), Sulfur dioxide (SO2), Particulate matter, (PM2.5 and PM10) air pollutants were considered. Determination of the accuracies of the developed models in forecasting the next ten days was achieved using the error performance metrics of Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE). The results of the performance metrics from the models in the same category are correlated and indicated similar trends. Comparison and analysis of the models revealed the one with the most accurate prediction for each sampling station and pollutant.
TIMBOU-AFRICA ACADEMIC PUBLICATIONS, 2023
Particulate matter is a prominent indicator of air pollution in any particular place. More people... more Particulate matter is a prominent indicator of air pollution in any particular place. More people are impacted by it than by any other pollutant. PM2.5 offers the greatest health concerns, hence the need to accurately estimate future values and give early warning. In this study, air pollution data was acquired from an Internet of Things-based air pollution monitor. The data was used to train the artificial neural network and fuzzy time series models for PM2.5 pollutant. The results of the models were evaluated and compared using error performance evaluation metrics of Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE). The best-performing model was used to forecast PM2.5 for five days and validated with the results from an online air quality app termed airvisual. The average AQI for the five days is 69.2 for the actual AQI, 66.6 for airvisual AQI, and 73.6 for the forecasted AQI. All of these values fall into the moderate AQI category. The comparative results of the validation indicated that the values correlate.
Keywords: Artificial Neural Network, Forecasting, Fuzzy Time Series, Particulate Matter 2.5, Air Quality Index, and Kaduna
Journal of research in national development (JORIND), 2018
This work uses a capacitive fingerprint sensor, Arduino Uno board, a Bluetooth device and a mobil... more This work uses a capacitive fingerprint sensor, Arduino Uno board, a Bluetooth device and a mobile phone to design a prototype that can be used for students' authentication for examination purposes thereby preventing impersonation in exams. It is subdivided into two main sections, the first is the process of enrolling each student whereby the fingerprint sensor captures the student's finger pattern when the thumb is place on it and sends the information to the microcontroller on the Arduino Uno board which in turn is saved on a mobile device which is interfaced with the microcontroller by a Bluetooth. For the purpose of this work, an android mobile phone on which an application has been developed and installed is used. The second section is the process of authentication whereby each student places his/her thumb on the fingerprint sensor and the pre-stored information about the student pops up if the student had been previously registered otherwise, an error message is displayed signifying the presence of an impersonator.
Journal of research in national development (JORIND), 2018
The lack of efficient operation of most state water corporations forces most landlords and proper... more The lack of efficient operation of most state water corporations forces most landlords and property owners to produce their own water from borehole or well. With a well or borehole as the source of water to buildings which could either be residential, commercial or government, a water pump is required to draw up water to an overhead tank from where it serves the building but with this arrangement in place, residents unintentionally allow the water pump to work continuously even when the overhead tank has reached full capacity thereby, leading to wastage of water, electricity and reduction in the lifespan of the machine. In other to prevent this, an automated water supply system that is able to sense water levels at the overhead tank as well as in the water source (borehole or well) and act accordingly is developed. The water system consist of water level sensors, alarm, relays, Arduino Uno, display unit and water pump. The automated domestic water control system was designed, constructed and tested to be working as desired. This proposed system is easy to implement and operates without human intervention however it would stop operating once there is no electricity supply to the control unit to power the water pump. It is therefore recommended that the design be improved upon by connecting it to a continuous source of power supply such as solar power. This will ensure that the system does not stop working once the power supply is cut off.
This paper presents a brief study of proportional integral sliding mode control (PISMC) technique... more This paper presents a brief study of proportional integral sliding mode control (PISMC) techniques for controlling the rotor position of PMDC motor drive system. In particular, since SMC is robust in the presence of the matched uncertainties and external disturbances, the desired position is perfectly tracked. In addition, the advantages and disadvantages of both proportional-integral (PI) and sliding mode control (SMC) control methods are studied. Since the major drawback of SMC is a phenomenon, known as chattering, resulting from discontinuous controllers, the PISMC method presented reduced the chattering very well. The performance of this method, PISMC is compared with the responses of the system with PID and conventional SMC controllers, and the PISMC is found to be better with higher precision and better robustness to plant imprecision and external disturbances than PID controllers.
FUOYE Journal of Engineering and Technology
Fuzzy Time Series (FTS) is able to eliminate the problem of overfitting that is fundamental to Ar... more Fuzzy Time Series (FTS) is able to eliminate the problem of overfitting that is fundamental to Artificial Neural Network (ANN), hence this study used air pollution data acquired from three different sampling stations in Kaduna metropolis, Nigeria, to implement FTS using the Adaptive Neuro Fuzzy Inference System (ANFIS). The fuzzy inference system (FIS) was generated by the ANFIS model using grid partitioning and subtractive clustering optimization types with backpropagation and hybrid training algorithms. The models were implemented using MATLAB 2018b software, and a total of thirteen models were developed. The resulting models were used to forecast the daily mean for the next ten days for each sampling station and for each pollutant. Carbon monoxide (CO), Nitrogen dioxide (NO2), Sulfur dioxide (SO2), Particulate matter, (PM2.5 and PM10) air pollutants were considered. Determination of the accuracies of the developed models in forecasting the next ten days was achieved using the err...
FUOYE Journal of Engineering and Technology, 2023
Fuzzy Time Series (FTS) is able to eliminate the problem of overfitting that is fundamental to Ar... more Fuzzy Time Series (FTS) is able to eliminate the problem of overfitting that is fundamental to Artificial Neural Network (ANN), hence this study used air pollution data acquired from three different sampling stations in Kaduna metropolis, Nigeria, to implement FTS using the Adaptive Neuro Fuzzy Inference System (ANFIS). The fuzzy inference system (FIS) was generated by the ANFIS model using grid partitioning and subtractive clustering optimization types with backpropagation and hybrid training algorithms. The models were implemented using MATLAB 2018b software, and a total of thirteen models were developed. The resulting models were used to forecast the daily mean for the next ten days for each sampling station and for each pollutant. Carbon monoxide (CO), Nitrogen dioxide (NO2), Sulfur dioxide (SO2), Particulate matter, (PM2.5 and PM10) air pollutants were considered. Determination of the accuracies of the developed models in forecasting the next ten days was achieved using the error performance metrics of Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE). The results of the performance metrics from the models in the same category are correlated and indicated similar trends. Comparison and analysis of the models revealed the one with the most accurate prediction for each sampling station and pollutant.
TIMBOU-AFRICA ACADEMIC PUBLICATIONS, 2023
Particulate matter is a prominent indicator of air pollution in any particular place. More people... more Particulate matter is a prominent indicator of air pollution in any particular place. More people are impacted by it than by any other pollutant. PM2.5 offers the greatest health concerns, hence the need to accurately estimate future values and give early warning. In this study, air pollution data was acquired from an Internet of Things-based air pollution monitor. The data was used to train the artificial neural network and fuzzy time series models for PM2.5 pollutant. The results of the models were evaluated and compared using error performance evaluation metrics of Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE). The best-performing model was used to forecast PM2.5 for five days and validated with the results from an online air quality app termed airvisual. The average AQI for the five days is 69.2 for the actual AQI, 66.6 for airvisual AQI, and 73.6 for the forecasted AQI. All of these values fall into the moderate AQI category. The comparative results of the validation indicated that the values correlate.
Keywords: Artificial Neural Network, Forecasting, Fuzzy Time Series, Particulate Matter 2.5, Air Quality Index, and Kaduna
Journal of research in national development (JORIND), 2018
This work uses a capacitive fingerprint sensor, Arduino Uno board, a Bluetooth device and a mobil... more This work uses a capacitive fingerprint sensor, Arduino Uno board, a Bluetooth device and a mobile phone to design a prototype that can be used for students' authentication for examination purposes thereby preventing impersonation in exams. It is subdivided into two main sections, the first is the process of enrolling each student whereby the fingerprint sensor captures the student's finger pattern when the thumb is place on it and sends the information to the microcontroller on the Arduino Uno board which in turn is saved on a mobile device which is interfaced with the microcontroller by a Bluetooth. For the purpose of this work, an android mobile phone on which an application has been developed and installed is used. The second section is the process of authentication whereby each student places his/her thumb on the fingerprint sensor and the pre-stored information about the student pops up if the student had been previously registered otherwise, an error message is displayed signifying the presence of an impersonator.
Journal of research in national development (JORIND), 2018
The lack of efficient operation of most state water corporations forces most landlords and proper... more The lack of efficient operation of most state water corporations forces most landlords and property owners to produce their own water from borehole or well. With a well or borehole as the source of water to buildings which could either be residential, commercial or government, a water pump is required to draw up water to an overhead tank from where it serves the building but with this arrangement in place, residents unintentionally allow the water pump to work continuously even when the overhead tank has reached full capacity thereby, leading to wastage of water, electricity and reduction in the lifespan of the machine. In other to prevent this, an automated water supply system that is able to sense water levels at the overhead tank as well as in the water source (borehole or well) and act accordingly is developed. The water system consist of water level sensors, alarm, relays, Arduino Uno, display unit and water pump. The automated domestic water control system was designed, constructed and tested to be working as desired. This proposed system is easy to implement and operates without human intervention however it would stop operating once there is no electricity supply to the control unit to power the water pump. It is therefore recommended that the design be improved upon by connecting it to a continuous source of power supply such as solar power. This will ensure that the system does not stop working once the power supply is cut off.
This paper presents a brief study of proportional integral sliding mode control (PISMC) technique... more This paper presents a brief study of proportional integral sliding mode control (PISMC) techniques for controlling the rotor position of PMDC motor drive system. In particular, since SMC is robust in the presence of the matched uncertainties and external disturbances, the desired position is perfectly tracked. In addition, the advantages and disadvantages of both proportional-integral (PI) and sliding mode control (SMC) control methods are studied. Since the major drawback of SMC is a phenomenon, known as chattering, resulting from discontinuous controllers, the PISMC method presented reduced the chattering very well. The performance of this method, PISMC is compared with the responses of the system with PID and conventional SMC controllers, and the PISMC is found to be better with higher precision and better robustness to plant imprecision and external disturbances than PID controllers.