Showing papers by "Aderemi A. Atayero published in 2019"

Determination of Neural Network Parameters for Path Loss Prediction in Very High Frequency Wireless Channel

Abstract: It is very important to understand the input features and the neural network parameters required for optimal path loss prediction in wireless communication channels. In this paper, an extensive investigation was conducted to determine the most appropriate neural network parameters for path loss prediction in Very High Frequency (VHF) band. Field measurements were conducted in an urban propagation environment to obtain relevant geographical and network information about the receiving mobile equipment and quantify the path losses of radio signals transmitted at 189.25 MHz and 479.25 MHz. Different neural network architectures were trained with varying kinds of input parameters, number of hidden neurons, activation functions, and learning algorithms to accurately predict corresponding path loss values. At the end of the experimentations, the performance of the developed Artificial Neural Network (ANN) models are evaluated using the following statistical metrics: Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Standard Deviation (SD) and Regression coefficient (R). Results obtained show that the ANN model that yielded the best performance employed four input variables (latitude, longitude, elevation, and distance), nine hidden neurons, hyperbolic tangent sigmoid (tansig) activation function, and the Levenberg-Marquardt (LM) learning algorithm with MAE, MSE, RMSE, SD and R values of 0.58 dB, 0.66 dB, 0.81 dB, 0.56 dB and 0.99 respectively. Finally, a comparative analysis of the developed model with Hata, COST 231, ECC-33 and Egli models showed that ANN-based path loss model has better prediction accuracy and generalization ability than the empirical models.

Path Loss Predictions in the VHF and UHF Bands Within Urban Environments: Experimental Investigation of Empirical, Heuristics and Geospatial Models

Abstract: (c) 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.

Experimental performance of a safe charge of LPG refrigerant enhanced with varying concentrations of TiO2 nano-lubricant in a domestic refrigerator

Abstract: This paper presents an experimental investigation of energy consumption and heat transfer performance characteristics of a safe mass–charge of liquefied petroleum gas refrigerant, enhanced with varying concentrations of TiO2 nano-lubricants (i.e. 0.2 gL−1, 0.4 gL−1 and 0.6 gL−1) in a domestic refrigerator. Performance parameters investigated at steady state included: instantaneous and mean power consumption, cooling capacity, coefficient of performance (COP), discharge thermal conductivity and discharge temperature. Analysis was based on temperature and pressure readings obtained from appropriate gauges attached to the test rig. Refrigerant properties were obtained from Ref-Prop NIST 9.0 software. Findings showed that reductions in mean power consumption were observed to be 14, 9 and 8% at 0.2 gL−1, 0.4 gL−1 and 0.6 gL−1 nano-lubricants respectively; the highest mean power consumption was obtained using pure compressor mineral oil while the lowest was with 0.2 gL−1 TiO2 nano-lubricant. The estimated mean cooling capacities for the various compressor lubricants were found to be higher with 0.4 gL−1 and 0.6 gL−1 nano-lubricants than pure compressor lubricant, and lower with 0.2 gL−1 nano-lubricant when compared with pure mineral oil lubricant. All the TiO2-based nano-lubricants were of higher instantaneous and mean COP values than the pure lubricant. All nano-lubricant mixtures were also found to give lower discharge temperatures than the pure lubricant. In conclusion, selected TiO2-based nano-lubricants improved the efficiency of the domestic refrigeration system considerably.

ANFIS Model for Path Loss Prediction in the GSM and WCDMA Bands in Urban Area

Abstract: Path loss propagation is a vital concern when designing and planning networks in mobile communication systems. Propagation models such as the empirical, deterministic and theoretical models, which possess complex, inconsistent, time-consuming and non-adaptable features, have proven to be inefficient in designing of wireless systems, thereby resulting in the need for a more reliable model. Artificial Intelligence methods seem to overcome the drawbacks of the propagation models for predicting path loss. In this paper, the ANFIS approach to path loss prediction in the GSM and WCDMA bands is presented for selected urban areas in Nigeria. Furthermore, the effects of the number of Membership Functions (MFs) are investigated. The prediction results indicated that the ANFIS model outperformed the Hata, Cost-231, Egli and ECC-33 models in both Kano and Abuja urban areas. In addition, an increase in the number of MFs conceded an improved RMSE result for the generalized bell-shaped MF. The general performance and outcome of this research work show the efficiency and usefulness of the ANFIS model in improving prediction accuracy over propagation models

A Web Framework for Online Peer Tutoring Application in a Smart Campus.

Abstract: Peer tutoring is a unique and efficient method of teaching that has been widely investigated. Related works in the literature ranges from cross-age peer tutoring, peer tutoring for the disabled, reciprocal peer tutoring, to peer tutoring for children. One unique method that has been scarcely documented, however, is peer tutoring with the aid of the Internet. In this paper, therefore, a web framework is proposed for online peer tutoring application in a smart campus. The peer tutoring web application identifies two key target users: the tutor and the tutee. The tutors will help in teaching other students; they are responsible for accepting requests from tutees and in turn holding tutoring sessions for the tutees. They also have the responsibility of uploading important documents to the platform which are accessible to tutees. On the other hand, the tutees search for the tutors with prowess in their course of need and make a request for a tutoring session. They also have access to the materials uploaded by the tutors. The peer tutoring web application is designed in such a way that the web browser communicates with the web server by making Hyper Text Transfer Protocol (HTTP) request to the server. The proposed framework consists of the client-side and the server-side which are connected by the web browser. In essence, web-based peer tutoring application will go a long way in improving students’ academic performance in a more efficient manner.

Characterization of Path Loss in the VHF Band using Neural Network Modeling Technique

Abstract: Artificial Neural Networks (ANNs) which are one of the main tools used in machine learning have often been utilised in developing models for path loss modelling in recent times. However, the ANN algorithm that provides the best results has not been well established neither has the models been characterized to limit their performances and applications in the various frequency bands. In this paper, we characterize the propagation loss in the Very High Frequency Band (VHF, 30-300MHz) by using different ANN learning algorithms and activation functions based on the measurement data collected at 203.25 MHz in an urban environment (Ilorin, Nigeria). Prediction results of Hata, ECC-33, Egli and COST 231 propagation models at varying distances were fed into a feed-forward neural network and mapped to each corresponding measured path loss value. Statistical analysis shows that the ANN model that was trained with hyperbolic tangent activation function (HTAF), Levenberg-Marquardt (LM) algorithm, and 80 neurons in the hidden layer produced the most satisfactory results with Mean Error (ME), Root Mean Square Error (RMSE), Standard Deviation (SD), and coefficient of determination (R^2) values of 3.75 dB, 5.10 dB, 3.46 dB, and 0.95. However, the HTAF with Scale Conjugate Gradient (SCG) is more stable even though its prediction errors were slightly higher than that of LM.

Advancing PoC Devices for Early Disease Detection using Graphene-based Sensors

Abstract: Early detection of diseases is key to better disease management and higher survival rates. It aims at discovering conditions that have already produced biochemical changes in body fluids, but have not yet reached a stage of apparent physical symptoms or medical emergency. Therefore, early disease detection relies majorly on biochemical testing of biological fluids such as serum, in the body. The laboratories for these tests require biochemical-based instrumentations that are bulky and not commonly available especially in developing countries. Moreover, the tests are expensive and require trained personnel to conduct and interpret results. On the other hand, Lab-on-a-Chip (LOC) biosensors have a potential to miniaturize the entire biochemical/laboratory methods of diagnostics into versatile, inexpensive and portable devices with great potential for low-cost Point-of-Care (POC) applications. They are capable of providing accurate and precise information on the measured health indices for sub-clinical level of diseases. Nanotechnology-inspired biosensors have further advantages of low limit of detection (required for early diagnosis), real-time analysis and lesser sample volume requirement. Of all other nanomaterials, graphene is said to be the most promising, suitable for biosensing due to its biocompatibility and consistent signal amplification even under the conditions of harsh ionic solutions found in the human body. This paper reviews the potentials, fundamental concepts and related works in using Graphene-based Field Effect Transistors (GFETs) as biosensors for early disease diagnosis. This paper also highlights a low-cost patterning mechanism for preparing SiO2/Si substrate for metal deposition (of the source and drain electrodes of FETs).

Smart City Waste Management System Using Internet of Things and Cloud Computing

Abstract: Indiscriminate disposal of solid waste is a major issue in urban centers of most developing countries and it poses a serious threat to healthy living of the citizens. Access to reliable data on the state of solid waste at different locations within the city will help both the local authorities and the citizens to effectively manage the menace. In this paper, an intelligent solid waste monitoring system is developed using Internet of Things (IoT) and cloud computing technologies. The fill level of solid waste in each of the containers, which are strategically situated across the communities, is detected using ultrasonic sensors. A Wireless Fidelity (Wi-Fi) communication link is used to transmit the sensor data to an IoT cloud platform known as ThingSpeak. Depending on the fill level, the system sends appropriate notification message (in form of tweet) to alert relevant authorities and concerned citizen(s) for necessary action. Also, the fill level is monitored on ThingSpeak in real-time. The system performance shows that the proposed solution may be found useful for efficient waste management in smart and connected communities.

Artificial Intelligence Techniques for Electrical Load Forecasting in Smart and Connected Communities

Abstract: Electricity consumption has been on a rapid increase worldwide and it is a very vital component of human life in this age. Hence, reliable supply of electricity from the utility operators is a necessity. However, the constraints that electricity supplied must be the same as electricity consumed puts the burden on the utility operators to make sure that demand is equal to supply at any point in time in smart and connected communities. Load forecasting techniques, therefore, aim to resolve these challenges for the operators by providing accurate forecasts of electrical load demand. This paper reviews current and mostly used short term forecasting techniques, drawing parallels be-tween them; and highlighting their advantages and disadvantages. This paper concludes by stating that there is no one-size-fits-all technique for load forecasting problems, as appropriate techniques depend on several factors such as data size and variability and environmental variables. Different optimization techniques can be used whether to reduce errors and its variations or to speed up computational time, hence resulting in an improved model. However, it is imperative to consider the tradeoffs between each model and its different variants in the context of smart and connected communities.

Artificial Neural Network Model for Path Loss Predictions in the VHF Band

Abstract: Artificial Neural Networks (ANNs) have been recently exploited to develop suitable models for path loss predictions . However, the ANN algorithm that provides the best results has not been well established neither has the models been characterized to limit their performances and applications in the various frequency bands. In this paper, we characterize the propagation path loss in the Very High Frequency Band (VHF) using different ANN learning algorithms and activation functions based on the measurement data collected at 203.25 MHz in an urban environment (Ilorin, Nigeria). The prediction results of Hata, COST 231, ECC-33, and Egli models at varying distances were fed into a feed-forward neural network and mapped to each corresponding measured path loss value. Statistical analysis shows that the ANN model that was trained with hyperbolic tangent activation function (HTAF), Levenberg-Marquardt (LM) algorithm, and 80 neurons in the hidden layer produced the most satisfactory results with Mean Error (ME), Root Mean Square Error (RMSE), Standard Deviation (SD), and coefficient of determination (R2) values of 3.75 dB, 5.10 dB, 3.46 dB, and 0.95. However, the HTAF with Scale Conjugate Gradient (SCG) is more stable even though its prediction errors were slightly higher than that of LM.

Performance Evaluation of Hydrocarbon based Nanorefrigerants Subjected to Periodic Door Openings

Abstract: Domestic refrigerators are required to be energy efficient and environmentally safe. In this work, a slightly modified domestic refrigeration system was infused with various concentrations (0, 0.2, 0.4 and 0.6 g/L) of TiO2 nanolubricants and R600a refrigerant with a mass charge of 40g. The average energetic characteristics of the test rig at different door openings intervals (0.5, 1, 2, 3 and 5 minutes) were evaluated. The energetic characteristics studied were coefficient of performance (COP), refrigeration capacity, power consumption and cabinet temperature recovery time. The results obtained showed that the use of nanolubricants significantly affect the energetic performance characteristics of the system. Overall, the utilization of 0.6g/L concentration of TiO2 nanolubricant gave the best performance. The COP of the system improved by 22.39 %, while the power consumption decreased by 23.5 % when compared with pure R600a refrigerant.

Experimental Performance of the Energetic Characteristics of a Domestic Refrigerator with Al 2 O 3 Nanolubricant and LPG Refrigerant

Abstract: This paper studies the experimental performance of the energetic characteristics of a slightly modified domestic refrigerator infused with nano-lubricant containing different concentrations of Al2O3 (at 0, 0.2, 0.4 and 0.6 g/L) with liquefied petroleum gas (LPG) charge of 40g. Parameters investigated were power consumption, cooling capacity, coefficient of performance (COP), discharge temperature, volumetric refrigerating capacity (VRC) and pressure ratio. The findings showed that when the nano-based lubricants were compared with pure oil, the power at 0.6g/L concentration, gave the best performance of 67.01W, at different time over 180 minutes’ periods. The discharge pressure of the system when compared to pure-oil at 0.6g/L concentrations exhibited acceptable value of 616. 33kPa. For the cabinet temperature, it was seen that the 0.6g/L had the lowest recorded temperature of -8.7oC after 180 minutes. With the coefficient of performance, the 0.2g/L concentration had the highest average performance of 2.239 at 180 minutes. The highest average performance of 174.225 kW over 180 minutes was found as the refrigerating capacity at 02.g/L concentration. The nano-lubricant can be concluded to work safely in the refrigerator but better optimization in nano-application will still be needed for better results.

Modelling Large-Scale Signal Fading in Urban Environment Based on Fuzzy Inference System

Abstract: Path loss models are veritable tools for estimation of expected large-scale signal fading in a specific propagation environment during wireless network design and optimization. In this paper, the capability of Adaptive Neuro-Fuzzy Inference System (ANFIS) to establish non-linear relationship between related variables was explored for path loss predictions at Very High Frequency (VHF) band in a typical urban propagation environment. Drive test measurements were conducted along various routes in the urban area to obtain terrain profile data and path losses of radio signals transmitted at 92.3 MHz and 189.25 MHz frequencies. ANFIS was modelled to predict the magnitude of large-scale signal fading (i.e. path loss) based on the longitude, latitude, distance and elevation of the receiver’s location. Fuzzy Inference System (FIS) was generated based on Fuzzy C-Means (FCM) and subtractive clustering methods. Model performance evaluation results showed that the ANFIS model developed based on FCM clustering method yielded the least prediction errors with a Root Mean Squared Error (RMSE) value of 0.88 dB. Whereas, the International Telecommunications Union Radiocommunication (ITU-R) had earlier set a maximum allowable RMSE value of 6 dB for urban propagation environments. Thus, ANFIS technique produced a very efficient largescale signal fading prediction model for VHF network design and optimization in urban areas.

Data Analytics: Global Contributions of World Continents to Computer Science Research

Abstract: In this paper, we present and analyze comprehensive data about scholarly contributions that were indexed in Scopus database between 2012 and 2017. The datasets are categorized (based on the country where the research was carried out) into: Africa; Asia Pacific; Europe; Middle East; North America; and South America. Scholarly contributions of each region are measured based on fifteen Scival metrics namely: grant award volume (count); grant award volume (value); international collaboration; academic-corporate collaboration; scholarly output; citations; field-weighted citation impact; outputs in top citation percentiles; publications in top journal percentiles; citations per publications; publication views; citing-patents count; patent-cited scholarly output; patent-citations count; and the number of authors. Frequency distributions and trends across the six-year study period are presented in graphs and plots. The analyses provided in this paper are made easy to facilitate further inferential studies towards a more objective and better decision making by research institutions.

Research Trends in Nigerian Universities: Analysis of Number of Publications in Scopus (2008–2017)

Abstract: Among other things, the performance of a university can be measured based on the volume and the impact of their scholarly research publications. However, the empirical evidence that are needed for objective analysis, evaluation, and ranking of universities based on this factor are often not readily and freely accessible to the public. In this paper, the trends of research publications in Nigerian Universities are analyzed. The total number of scholarly articles published by academic researchers in 67 Nigerian universities over a period of ten years (2008-2017) were sourced from Scopus abstracting/indexing database. Nigerian universities covered include 32 federal universities, 26 state universities, and nine private universities. The publication trends are presented using tables and graphs. Also, yearly percentage growth in scholarly research outputs are computed for each university. In practice, the insights provided will propel a more informed policy formulation and implementation towards improving institutional academic research productivity.

Parametric Investigation of Air Pollution Over Bafata

Abstract: Most communities in West Africa such as Bafata-Guinea Bissau do not have air quality report. Hence, the population in the area lives at the mercy of fate. Satellite measurement for aerosol optical depth (AOD) was obtained for fourteen years. The Multi-angle Imaging Spectro-Radiometer (MISR) data set was treated and subjected to computational and statistical investigation. The cumulative aerosol content i.e. aerosol loading was estimated and documented. The dataset in this research is essential to provide good basis conducting ground measurement over the region.