Browsing by Author "Sowah, R.A."

Now showing 1 - 14 of 14

Automatic Satellite Dish Positioning for Line of Sight Communication using Bluetooth Technology
(Science and Development (A Journal of the College of Basic and Applied Sciences (CBAS), University of Ghana), 2017-12) Sowah, R.A.; Mills, G.A.; Nortey, J.Y.; Armoo, S.K.; Fiawoo, S.Y.
Satellite dishes are used to receive beams of signals from satellites and other broadcasting sources which are then focused onto an antenna. The dish needs to be adjusted to get the desired azimuth and elevation for maximum signal reception. To overcome the difficulty of adjusting it manually, it would be beneficial to have a system that aligns the satellite receiver by mechanical means while allowing the user to interact with the system remotely to achieve a line of sight communication with the satellite source of interest. This paper proposes the design and development of a system which receives user specifications from an Android application via Bluetooth by either specifying the direction of orientation of the dish or selecting a satellite of interest. A control system interacting with the developed user interface achieves this. It employs a microcontroller, a GPS device, a compass and two servo motors to manage the orientation of the dish on its horizontal and vertical axes. The Smartphone utilizes its Bluetooth socket to communicate with the Bluetooth module interfaced to the microcontroller. A database containing information on available satellites is included in the Android application which is transferred to the microcontroller for computation of azimuth and elevation angles when the GPS coordinates and compass headings are obtained from their respective devices. Tests carried out showed positive results for control of the orientation of the satellite dish in various directions over a 50m radius. The automatic adjustment functionality provided precise direction for line of sight communication when users chose their satellite of focus.
Decision Support System (DSS) for Fraud Detection in Health Insurance Claims Using Genetic Support Vector Machines (GSVMs)
(Journal of Engineering, 2019-09-02) Sowah, R.A.; Kuuboore, M.; Ofoli, A.; Kwofie, S.; Asiedu, L.; Koumadi, K.M.; Apeadu, K.O.
Fraud in health insurance claims has become a significant problem whose rampant growth has deeply affected the global delivery of health services. In addition to financial losses incurred, patients who genuinely need medical care suffer because service providers are not paid on time as a result of delays in the manual vetting of their claims and are therefore unwilling to continue offering their services. Health insurance claims fraud is committed through service providers, insurance subscribers, and insurance companies. (e need for the development of a decision support system (DSS) for accurate, automated claim processing to offset the attendant challenges faced by the National Health Insurance Scheme cannot be overstated. (is paper utilized the National Health Insurance Scheme claims dataset obtained from hospitals in Ghana for detecting health insurance fraud and other anomalies. Genetic support vector machines (GSVMs), a novel hybridized data mining and statistical machine learning tool, which provide a set of sophisticated algorithms for the automatic detection of fraudulent claims in these health insurance databases are used.(eexperimental results have proven that the GSVM possessed better detection and classification performance when applied using SVM kernel classifiers. (ree GSVM classifiers were evaluated and their results compared. Experimental results show a significant reduction in computational time on claims processing while increasing classification accuracy via the various SVM classifiers (linear (80.67%), polynomial (81.22%), and radial basis function (RBF) kernel (87.91%).
Design and development of a microcontroller based traffic light control system using image processing techniques: - A case study prototype for Legon-Okponglo Junction, University of Ghana
(Proceedings of the 2012 IEEE 4th International Conference on Adaptive Science and Technology, ICAST 2012, 2012-10) Asare, S.K.; Sowah, R.A.
Traffic congestion on our roads especially in the urban cities is becoming overwhelming. Safety and comfort of road users is gradually becoming a matter of grave concern. Present Traffic Light Controllers (TLC) are based on microcontroller and microprocessor. The limitation with the TLC is that it uses the pre-defined hardware, which is functioning according to the program that does not have the flexibility of modification on real time basis. This proposed system makes use of embedded technology along with image processing analysis to control traffic at a local intersection that consists of a main road and two side roads and it is an improvement upon the efficiency of the current Traffic Light Controllers. Intervals between the green, amber and red states are based on current traffic density, which optimizes traffic light switching and avoids traffic congestion. A prototype for controlling traffic at the intersection is designed and simulated using the Proteus Design Suite. Using image processing technique via OpenCV, background differencing of an empty-lane road and a traffic congested road is performed. The resulting output is fed as input to the microcontroller system for traffic light control system on real-time data. © 2012 IEEE.
Design and development of an Android application to process and display summarised corporate data
(Proceedings of the 2012 IEEE 4th International Conference on Adaptive Science and Technology, ICAST 2012, 2012-12) Fiawoo, S.Y.; Sowah, R.A.
In the corporate world today, managers are always faced with a lot of decisions to make based on data generated at their various offices. The decision-making process is very vital as decisions taken by management could make a company either overtake or stay within reach of its competitors. This paper presents the design and development of an Android application that would retrieve summarised data from a central database process and display that information on an android device so as to aid managers in their decision-making process. The components of designed and developed system include (1) a web application through which workers would input data at their various workplaces (2) a database hosted on a central server that would store information entered by workers (3) an application programming interface (API) that would take requests from the Android application, query the database and serve the results back to the Android application and (4) an android application that processes and displays results to users. The android application is developed using Eclipse in conjunction with android SDK tools. The application retrieves data from a database per user request and displays the retrieved information on an android device. Users of this application would be able to analyse data quicker hence make quick decisions as they would not be drowned in a flood of detailed information. There is also an added benefit of having access to company data on the go. © 2012 IEEE.
Design and development of GPS/GSM based vehicle tracking and alert system for commercial inter-city buses
(Proceedings of the 2012 IEEE 4th International Conference on Adaptive Science and Technology, ICAST 2012, 2012-10) Fleischer, P.B.; Nelson, A.Y.; Sowah, R.A.; Bremang, A.
In this paper we proposed the design, development and deployment of GPS (Global Positioning System)/GSM (Global System for Mobile Communications) based Vehicle Tracking and Alert System which allows inter-city transport companies to track their vehicles in real-time and provides an alert system for reporting armed robbery and accident occurrences. © 2012 IEEE.
Detection and Prevention of Man-in-the-Middle Spoofing Attacks in MANETs Using Predictive Techniques in Artificial Neural Networks (ANN)
(Journal of Computer Networks and Communications, 2019-01) Sowah, R.A.; Ofori-Amanfo, K.B.; Mills, G.A.; Koumadi, K.M.
A Mobile Ad-Hoc Network (MANET) is a convenient wireless infrastructure which presents many advantages in network settings. With Mobile Ad-Hoc Network, there are many challenges. These networks are more susceptible to attacks such as black hole and man-in-the-middle (MITM) than their corresponding wired networks. This is due to the decentralized nature of their overall architecture. In this paper, ANN classification methods in intrusion detection for MANETs were developed and used with NS2 simulation platform for attack detection, identification, blacklisting, and node reconfiguration for control of nodes attacked. The ANN classification algorithm for intrusion detection was evaluated using several metrics. The performance of the ANN as a predictive technique for attack detection, isolation, and reconfiguration was measured on a dataset with network-varied traffic conditions and mobility patterns for multiple attacks. With a final detection rate of 88.235%, this work not only offered a productive and less expensive way to perform MITM attacks on simulation platforms but also identified time as a crucial factor in determining such attacks as well as isolating nodes and reconfiguring the network under attack. This work is intended to be an opening for future malicious software time signature creation, identification, isolation, and reconfiguration to supplement existing Intrusion Detection Systems (IDSs).
Hardware Module Design and Software Implementation of Multisensor Fire Detection and Notification System Using Fuzzy Logic and Convolutional Neural Networks (CNNs)
(Hindawi Journal of Engineering, 2020-02-01) Sowah, R.A.; Apeadu, K.; Gatsi, F.; Ampadu, K.O.; Mensah, B.S.
)is paper presents the design and development of a fuzzy logic-based multisensor fire detection and a web-based notification system with trained convolutional neural networks for both proximity and wide-area fire detection. Until recently, most consumer-grade fire detection systems relied solely on smoke detectors. )ese offer limited protection due to the type of fire present and the detection technology at use. To solve this problem, we present a multisensor data fusion with convolutional neural network (CNN) fire detection and notification technology. Convolutional Neural Networks are mainstream methods of deep learning due to their ability to perform feature extraction and classification in the same architecture. )e system is designed to enable early detection of fire in residential, commercial, and industrial environments by using multiple fire signatures such as flames, smoke, and heat. )e incorporation of the convolutional neural networks enables broader coverage of the area of interest, using visuals from surveillance cameras. With access granted to the web-based system, the fire and rescue crew gets notified in real-time with location information. )e efficiency of the fire detection and notification system employed by standard fire detectors and the multisensor remote-based notification approach adopted in this paper showed significant improvements with timely fire detection, alerting, and response time for firefighting. )e final experimental and performance evaluation results showed that the accuracy rate of CNN was 94% and that of the fuzzy logic unit is 90%.
Integrating MATLAB/simulink technical computing environment into engineering education pedagogy in Ghanaian Universities: - A case study for university of Ghana, computer engineering department
(Proceedings of the 2012 IEEE 4th International Conference on Adaptive Science and Technology, ICAST 2012, 2012-10) Sowah, R.A.; Mills, G.A.; Bremang, A.; Armoo, S.K.
In this paper we proposed a joint model of simultaneous instruction with laboratory sessions to reinforce and enrich the learning experience so as to train better engineers able to compete globally. In accomplishing this, we integrated MATLAB/Simulink, the de facto standard for technical computing into the university curriculum for teaching four Computer Engineering courses namely Numerical Methods, Signals and Systems, Digital Control Systems and Digital Signal Processing during the 2010/2011 academic year at the University of Ghana. The course modules were developed in consultation with others and taught over the period of 13 weeks. The semester examinations consisted of laboratory and written exams sessions of three hours duration. After grading and collating of examinations results, it was clearly demonstrated by students that they have learnt the key requirements in engineering education. The statistics was staggering and interesting; for example 90 students registered the Numerical Methods, one withdrew due to ill-health and 89 students passed the seemingly difficult course with good grades. © 2012 IEEE.
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
Joint bandwidth and power allocation at mobile stations for QoS-constrained multimedia applications
(Proceedings of the 2012 IEEE 4th International Conference on Adaptive Science and Technology, ICAST 2012, 2012-10) Koumadi, K.M.; Sowah, R.A.; Acakpovi, A.
Various multimedia applications will be supported by beyond third generation (B3G) mobile communication systems. Mobile users may choose to simultaneously launch various applications with quality of service (QoS) constraints. Subject to the chosen applications' respective QoS constraints, the user may have to allocate her/his available resources for satisfaction maximization. In this paper, a utility-based algorithm is proposed to jointly allocate available power and uplink bandwidth, at mobile station (MS) level. Using Karush-Kuhn-Tucker (KKT) conditions and simulation, the algorithm is proved to be optimal. Under certain conditions, the algorithm (which may be applied in both downlink and uplink) is iterative and its convergence is shown by simulation. © 2012 IEEE.
Maximum Power Point Tracking in Power System Control Using Reservoir Computing
(Frontiers in Energy Research, 2022) Seddoh, M.A.; Sowah, R.A.; Sackey, D.M.; et al.
This article deals with an innovative approach to maximum power point tracking (MPPT) in power systems using the reservoir computing (RC) technique. Even though extensive studies have been conducted on MPPT to improve solar PV systems efficiency, there is still considerable room for improvement. The methodology consisted in modeling and programming with MATLAB software, the reservoir computing paradigm, which is a form of recurrent neural network. The performances of the RC algorithm was compared to two well-known methods of maximum power point tracking: perturbed and observed (P&O) and artificial neural networks (ANN). Power, voltage, current, and temperature characteristics were assessed, plotted, and compared. It was established that the RC-MPPT provided better performances than P&O-MPPT and ANN-MPPT from the perspective of training and testing MSE, rapid convergence, and accuracy of tracking. These findings suggest the need for rapid implementation of the proposed RC-MPPT algorithm on microcontroller chips for their widespread use and adoption globally
Rotational Energy Harvesting To Prolong Flight Duration of Quadcopters
(IEEE Transactions on Industry Applications, 2017-10) Sowah, R.A.; Acquah, M.A.; Ofoli, A.R.; Mills, G.A.; Koumadi, K.M.
This paper presents a rotational energy harvester using a brushless dc (BLdc) generator to harvest ambient energy for quadcopter in order to prolong it flight duration. For a quadcopter, its endurance is essential in order to achieve operational goals such as scientific research, security, surveillance, and reconnaissance. Because quadcopters have a limitation on size and mass, they cannot carry a large mass of on-board energy thereby having short flight time. In this paper, BLdc generators are coupled with the propellers of the quadcopter to transfer kinetic energy from the propellers to the generator. Taking into consideration the power requirement of quadcopter, the output of the generator is amplified using dc-dc boost, and is regulated to power and charge the on-board battery. The BLdc generator is simulated in MATLAB/Simulink. A final prototype of the rotational energy harvesting system is built, and this comprises a quadcopter, power management system, and a battery charging system. © 1972-2012 IEEE.
Transmission power minimization for a multi-application user in OFDMA systems
(Proceedings of the 2012 IEEE 4th International Conference on Adaptive Science and Technology, ICAST 2012, 2012-10) Koumadi, K.M.; Acakpovi, A.; Sowah, R.A.
When a user in Beyong third generation (B3G) mobile communication systems launches multiple applications simultaneously, the user's radio resources (subcarriers, symbols, power,⋯) need to be efficiently allocated to these applications while maintaining their quality of service (QoS) requirements and user utility. In this paper, a power minimization subcarrier, symbol, and power allocation problem is formulated, solved, and algorithms are derived. The problem formulation differs from those in existing works in that all the applications are from the same user. This relaxes some subcarrier allocation constraints that exist in multiuser single-application-per-user cases, leading to different solution techniques. Furthermore, the multiuser diversity which is the basis for many existing algorithms does not exist in the context of this paper. © 2012 IEEE.
Vulnerability Analysis of Online Banking Sites to Cross-Site Scripting and Request Forgery Attacks: A Case Study in East Africa
(IEEE 8th International Conference on Adaptive Science and Technology, 2021) Buah, G.; Memusi, S.; Sowah, R.A.; et al.
Web applications are prone to several attacks. Two common threats are cross-site scripting attacks and cross site request forgery. With internet banking becoming more popular in East Africa, the level of security that online banking services offer has become an increasing concern. This paper presents an analysis of the safety of these applications used by many unsuspecting customers seeking convenience and determines ways to detect and prevent these attacks from taking place. We assumed that if people with a technical background in IT and information security are vulnerable to CSRF and XSS attacks, the public would be even more vulnerable. Out of 96 users, 35 answered our survey, 53.1% of the respondents said they do not check the URLs of online banking websites they visit to ensure they are not on a phishing site. Secondly, only 36.4% of users considered the security implications of clicking on links in emails or even on banking websites all the time. Based on the interviews done, testing and analysis conducted, there is a clear indication that Internet banking users are vulnerable to XSS and CSRF. Notably, close to 50 % of the Internet banking users we interviewed reported that they do not receive ample tips from the banks regarding security issues to look out for when transacting online. The findings from this research help make recommendations to banks and users to ensure that future online banking transactions are done more securely.