Research Articles

Permanent URI for this collectionhttps://atuspace.atu.edu.gh/handle/123456789/31

Browse

Now showing 1 - 20 of 29

Pedagogically-Improved blended learning of a chemistry course through a computerized virtual laboratory.
(2022) Asabere, N. Y.,; Gbagbe, G. E.; Tawia, E. A.; Amegashie, J. E.; Ayin, D. A.
In the last decades, ICT has been promoting the creation and adoption of new learning and teaching styles. Virtual (computerized) laboratories play vital roles in learning and teaching by overcoming some limitations of conventional hands-on experiments. The number of chemistry (physical) laboratories in the Science Laboratory Technology (SLT) Department in Accra Technical University (ATU), Ghana is inadequate for the current population of students. Consequently, laboratory practice by students is very low. In this paper, we propose a virtual chemistry laboratory with simulated experiments for SLT students in ATU to support their education. To corroborate the research problem, we utilized a quantitative (questionnaire) research method, which involved a sample size of 271 SLT students (n = 271). Evaluation results of the study showed that the majority of students in the SLT Department are willing to use the virtual chemistry lab, and most of the students consider the virtual labs as an educative platform that would help them attain practical knowledge in their chemistry studies.
Collaborative and social-personality aware recommendation of programmes.
(Mobile Information Systems, 2022) Asabere, N. Y.
Globally, the selection of tertiary programmes for higher education in a university by prospective applicants is a daunting task. Different universities offer a wide range of programmes using different education delivery modes for teaching and learning. This creates information overload in the context of tertiary programmes. To tackle the information overload problem of tertiary programmes in the context of higher education institutions (HEIs), this paper, therefore, proposes a novel recommendation model called Collaborative and Social-Personality Aware Recommendation of Programmes (CoSPARP) for tertiary programme selection. CoSPARP utilizes a hybrid filtering system that incorporates the computation of similarities relating to the CF, personality traits, and the tie strength of users (prospective applicants) to generate effective programme recommendations for a tertiary programme applicant (TPA). The proposed CoSPARP recommendation method employs the above recommendation entities to create profiles of the TPAs as a basis of profile similarity for tertiary programme recommendations. Results of benchmarking experiments showed that CoSPARP overcomes cold-start due to the proposed (innovative) hybridization process. Additionally, using a relevant real-world dataset and suitable evaluation metrics such as precision, recall, and F-measure, CoSPARP produces more favourable outcomes in comparison to other state-of-the-art methods.
Exploiting cyber-attack prediction through socially-aware recommendation.
(International Journal of Decision Support System Technology, 2022) Asabere, N. Y.; Fiamavle, E.; Agyiri, J.; Torgby, W. K.; Dzata, J. E.; Doe, N. P.
In the domain of cyber security, the defence mechanisms of networks has traditionally been placed in a reactionary role. Cyber security professionals are therefore disadvantaged in a cyber-attack situation due to the fact that it is vital that they maneuver such attacks before the network is totally compromised. In this paper, we utilize the Betweenness Centrality network measure (social property) to discover possible cyber-attack paths and then employ computation of similar personality of nodes/users to generate predictions about possible attacks within the network. Our method proposes a social recommender algorithm called socially-aware recommendation of cyber-attack paths (SARCP), as an attack predictor in the cyber security defence domain. In a social network, SARCP exploits and delivers all possible paths which can result in cyber-attacks. Using a real-world dataset and relevant evaluation metrics, experimental results in the paper show that our proposed method is favorable and effective.
Automatic fault detection and location in power transmission lines using GSM technology.
(International Journal of Advance Research in Science and Engineering, 2016) Agbesi, K.; Okai, F. A.
Many electricity transmission companies across the world and Ghana in particular are continuously looking for ways to utilise modern technologies, in order to improve reliability of power supply to consumers. These transmission companies manly relies on circuit indicators (FCIs) to assist in locating specific spots within their transmission lines where power fault had occured. In this paper, a smart GSM based fault detection and location system was used to adequatly and accurately indicate and locate the exact spot where fault had occured. This will ensure a shorter response time for technical crew to rectify these faults and thus help save transformers from damage and disasters. The system uses a current transformer, a voltage transformer, PIC 16F877 Microcontroller, RS-232 connector, and a GSM modem. The system automatically detects faults, analyses and classifies these faults and then, calculates the fault distance from the control room using an impedance-based algorithm method. Finally the fault information is transmitted to the control room. In conclusion, the time required to locate a fault is drastically reduced, as the system automatically and accurately provides accurate fault location information.
A configuration-based approach to mitigating man-in-the-middle attacks in enterprise cloud IaaS Networks running BGP.
(International Journal of Computer Applications, 2016) Oti, S. B.; Bansah, I.; Adegboyega, T. M.
Cloud IaaS service providers offer virtualized computing resources to enterprises over the internet. As with most internet based services, cloud service providers may need to establish BGP peering relationships with upstream/neighbor ISPs for the purposes of exchanging routing information between their respective Autonomous systems thereby making it possible for a rogue AS to carry out a Man-In-The-Middle (MITM) attack. Available literature supports the fact that BGP as an infrastructure protocol is vulnerable to MITM attacks yet a good number of proposals aimed at counteracting these attacks have not been fully implemented. Secure BGP, Secure Origin BGP and Pretty Secure BGP are all proposals which have not been fully implemented due to high overhead and invariable router load. We believe however that an existing cloud IaaS service provider could mitigate the risk of a MITM attack by optimizing their configurations and ensuring that upstream providers do a proper job filtering prefixes using a prefix-list. This paper presents a GNS-3 simulation of a MITM attack by mimicking a section of the internet and goes on to show how the application of a prefix-list can help mitigate the attack.
Resilient campus network to support research and educational network in Ghana (case study of Accra Technical University).
(International Journal of Computer Applications, 2017) Okai, F. A.; Agbesi, K.; Gbedawo, V.
This paper describes how to setup a fully resilient design in a campus network to support Research and Educational Network in Ghana. The main idea of resilient topology for tertiary institutional campuses is to minimize downtime to the barest possible minimum. These down times usually happen during crashes and device upgrades. This paper describes how all critical devices are used twice to avoid having a single point of failure. Therefore, any single device can be turned off without significant disruption for the connected applications and users. Finally an appropriate resilient network that will support both students and staff research and collaborative works, with adequate bandwidth requirement to render the system scalable within the next seven years has been determined and recommended.
Intrusion detection on campus network, the open-source approach: Accra Technical University case study
(International Journal of Computer Applications, 2017) Gbedawo, V.; Agbesi, K.; Adukpo, T.
The computer network security landscape in recent times has become a crucial area in computer networking for both network administrators and network users such that, a compromise of this network security makes the services it provides and more importantly the data it holds, highly susceptible to exploits by malicious people for different purposes and reasons. This is particularly so for campus networks in view of the fact that, they do not only provide services to promote academic work directly but in many ways are integrated into the administrative setup of the institutions they serve. This research therefore seeks to investigate the security threats and vulnerabilities of campus networks and systems to a great extent, so as to propose interventions to resolving these threats, vulnerabilities and exploits, so as to improve the security of these networks by conducting a penetration test that simulates Intrusion Detection employing free and open source software (FOSS) tools. The research adopted “Cloppert‟s kill chain” Approach to Penetration Testing. The elements of the simulation included the following FOSS tools VMware Fusion (Operating System simulator), Zentyal Server (unified network server), Snort (Intrusion Detection System), Suricata (Intrusion Prevention System), Nmap (Network scanning), OpenVAS (Vulnerability Assessment Software) and Metasploit Framework (Exploitation tool). Results of the simulation revealed injection flaws to be the prevalent security vulnerability that was exploited and hence, discussed to improve computer network and application security in a rather cost effective fashion
An ICT model for integrating teaching, learning and research in Technical University Education in Ghana.
(International Journal of Education and Development using ICT, 2017) Asabere, N. Y.; Togo, G.; Acakpovi, A.; Torgby, W.; Ampadu, K
Information and Communication Technologies (ICT) has changed the way we communicate and carry out certain daily activities. Globally, ICT has become an essential means for disseminating information. Using Accra Technical University in Ghana as a case study, this paper proposes an ICT model called Awareness Incentives Demand and Support (AIDS). Our proposed AIDS model depicts how different ICTs can be integrated in tertiary education for effective teaching, learning and research. Currently, Accra Technical University does not have a resilient means of providing ICT in education. In this study, relevant data was obtained through a quantitative research method involving questionnaires. The questionnaire was developed using the main components of the proposed AIDS model. In all, ninety (90) students and twelve (12) lecturers were considered from a maximum of three (3) schools in Accra Technical University. Samples of lecturers and students from all the three (3) schools were surveyed. Based on the responses received from the participants, the AIDS model was proposed. Successful implementation of the AIDS model practically increased the use of ICT for education by both teachers and students in Accra Technical University.
Improving education delivery in a technical university in Ghana through mobile learning technology.
(International Journal of ICT Research in Africa and the Middle East (IJICTRAME), 2020) Asabere, N. Y.; Agyiri, J.; Acakpovi, A.; Nachanja, A.; Awuku, P.
Although in Accra Technical University (ATU), Ghana there exists a traditional face-to-face (F2F) mode of education already in place, the implementation of mobile learning (m-learning) through ICT in education will solve problems such as small classroom size, inappropriate time schedule for lectures, and provision technological resources needed to run successful classroom education. In order to validate successful implementation of m-learning in ATU, this paper employed a questionnaire research instrument with reference to the technology acceptance model (TAM-2) as a theoretical framework. Closed-ended questionnaires were administered to a sample size of 160 students and 15 lecturers in the Faculty of Applied Sciences (FAS) in ATU. Based on the responses received, the authors established positive technological acceptance of respondents, which paved the way to propose and develop a suitable m-learning system for ATU. It is envisaged that successful implementation of the m-learning system proposed in this paper will practically increase the use of ICT in education by both lecturers and students in ATU.
TruCom: Exploiting domain-specific trust networks for multicategory item recommendation.
(IEEE Systems Journal, 2017)
Recommender systems (RSs) have become important tools for solving the problem of information overload. With the advent and popularity of online social networks, some studies on network-based recommendation have emerged, raising the concern of many researchers. Trust is one kind of important information available in social networks and is often used for performance improvement in social-network-based RSs. However, most trust-aware RSs ignore the fact that people trust different subsets of friends pertaining to different domains, such as music and movies, because people behave differently in diverse domains according to different interests. This paper proposes a novel recommendation method called TruCom. In a multicategory item recommendation domain, TruCom first generates a domain-specific trust network pertaining to each domain and then builds a unified objective function for improving recommendation accuracy by incorporating the hybrid information of direct and indirect trust into a matrix factorization recommendation model. Through relevant benchmark experiments on two real-world data sets, we show that TruCom achieves better performance than other existing recommendation methods, which demonstrates the effectiveness and reliability of TruCom.
Socially aware conference participant recommendation with personality traits.
(IEEE Systems Journal, 2017) Xia, F.; Asabere, N. Y.; Liu, H.; Chen, Z.; Wang, W.
As a result of the importance of academic collaboration at smart conferences, various researchers have utilized recommender systems to generate effective recommendations for participants. Recent research has shown that the personality traits of users can be used as innovative entities for effective recommendations. Nevertheless, subjective perceptions involving the personality of participants at smart conferences are quite rare and have not gained much attention. Inspired by the personality and social characteristics of users, we present an algorithm called Socially and Personality Aware Recommendation of Participants (SPARP). Our recommendation methodology hybridizes the computations of similar interpersonal relationships and personality traits among participants. SPARP models the personality and social characteristic profiles of participants at a smart conference. By combining the aforementioned recommendation entities, SPARP then recommends participants to each other for effective collaborations. We evaluate SPARP using a relevant data set. Experimental results confirm that SPARP is reliable and outperforms other state-of-the-art methods.
ROVETS: Search based socially-aware recommendation of smart conference sessions.
(Support System Technology, 2019) Asabere, N. Y.; Acakpovi, A.
As a result of the tremendous proliferation of sessions at academic conferences, recommending appropriate venues for researchers has become a considerable problem. In this article, the authors propose an innovative recommender algorithm called Recommendation of Venues and Environments Through Social-Awareness (ROVETS). ROVETS seeks to enhance the social awareness of attendees at a smart conference. ROVETS initially employs closeness centrality and Breadth First Search (BFS) to detect potential presenters for a target attendee. Then, the accurate tie strength between the attendees and presenters as well as the degree centrality of the presenters are computed based on similarity of their research interests. Using the computations above, ROVETS generates effective recommendations pertaining to venues for attendees who have high tie strength with presenters. Through a relevant real-world dataset, this article evaluates the proposed recommender algorithm. These experimental results validate that ROVETS exhibits favorable enhancements over other existing state-of-the-art methods.
SARVE-2: Exploiting Social Venue Recommendation in the Context of Smart Conferences
(IEEE Computer Society, 2021) Asabere, N. Y.; Xu, B.; Acakpovi, A.; Deonauth, N.
Globally, the superfluity of scholarly research conferences in varying disciplines has introduced the issue of scholarly big data and information overload related to both research papers and conference proceedings/sessions. This evident scholarly expansion in different disciplines has increased the collaborative importance of conferences. Consequently, the problem regarding attendees selecting the right conference session(s) to attend in academic conferences requires further and urgent attention. Using a smart conference scenario, this paper aims to address the problem above by proposing an improved venue recommender algorithm called Socially-Aware Recommendation of Venues and Environments-2 (SARVE-2). Using a closeness centrality approach, SARVE-2 initially employs Breadth First Search (BFS) and Depth First Search (DFS) strategies to search for relevant presenters for a target attendee. Then, the tie strength of the (searched) presenter and target attendee is computed to generate reliable social research papers and conference proceedings/sessions. This evident scholarly expansion in different disciplines has increased the collaborative importance of conferences. Consequently, the problem regarding attendees selecting the right conference session(s) to attend in academic conferences requires further and urgent attention. Using a smart conference scenario, this paper aims to address the problem above by proposing an improved venue recommender algorithm called Socially-Aware Recommendation of Venues and Environments-2 (SARVE-2). Using a closeness centrality approach, SARVE-2 initially employs Breadth First Search (BFS) and Depth First Search (DFS) strategies to search for relevant presenters for a target attendee. Then, the tie strength of the (searched) presenter and target attendee is computed to generate reliable social (conference session) recommendations for the target attendee. Through the utilization of a relevant (real-world) dataset, our benchmark experiments reveal that, in comparison with other contemporary methods, SARVE-2 exhibits better performance in terms of effective social recommendation search, as well as social recommendation quality, coverage and accuracy.
Mapping and auditing internet addiction in technical education
(IGI Global, 2021) Asabere, N. Y.; Torgby, W.; Acakpovi, A.; Enguah, S. E.; Asare, I. O.
The current proliferation of social networking sites (e.g., Facebook), electronic devices (e.g., smartphones and tablets), and the internet has paved the way for a charge in promoting the phenomenon of internet addiction (IA). This paper analyzed and examined the validity and appropriateness of a well-established instrument for measuring IA among technical education students in Ghana, specifically students of Accra Technical University (ATU). Using a quantitative research method involving questionnaires, data collected from 260 (n=260) students in ATU was used to validate the research objectives and also measure the levels of IA among the students. The principal component tool in statistical package for social sciences (SPSS) was employed to analyze the received data. Analytical results of the study showed that a sizeable majority of students in ATU, especially male students, suffer frequent addiction problems due to the use of the internet. Additionally, results of the study showed that IA psychometric constructs in the Western world differ from those in the African context.
Measuring the constructs that influence student and lecturer acceptance of an E-library in accra technical university, Ghana
(IGI Global, 2021) Asabere, N. Y.; Acakpovi, A.; Agyiri, J.; Awuku, M. C.; Sakyi, M. A.; Teyewayo, D. A.
Even though many universities across the world have incorporated internet-based educational and academic systems, the success of their implementation requires an extensive understanding of the end user acceptance process. Access to academic resources for teaching and learning using technology (electronic library) has become a popular approach within higher education institutions due to the continuous growth of internet innovations and technologies. This case study research, conducted at Accra Technical University uses the technology acceptance model (TAM) as a theoretical framework. The study investigates the effects of the system characteristics such as appropriate user interface (UI), software design, and relevance towards the perceived ease of use and perceived usefulness on intention to use the proposed e-library system. Two hundred (200) students and sixteen (16) lecturers participated in this quantitative study. Results show that improvement of the existing e-library system in ATU will enable students to utilize digital learning resources for effective teaching and learning, especially during the current global COVID-19 pandemic.
Application of machine learning in predicting construction project profit in Ghana using Support Vector Regression Algorithm (SVRA)
(Emerald Group Holdings Ltd., 2021) Adinyira, E.; Adjei, E. A. G.; Agyekum, K.; Fugar, F. D. K.
Purpose: Knowledge of the effect of various cash-flow factors on expected project profit is important to effectively manage productivity on construction pwas conducted to develop and test the sensitivity of a Machine Learning Support Vector Regression Algorithm (SVRA) to predict construction project profit in Ghana. Design/methodology/approach: The study relied on data from 150 institutional projects executed within the past five years (2014–2018) in developing the model. Eighty percent (80%) of the data from the 150 projects was used at hyperparameter selection and final training phases of the model development and the remaining 20% for model testing. Using MATLAB for Support Vector Regression, the parameters available for tuning were the epsilon values, the kernel scale, the box constraint and standardisations. The sensitivity index was computed to determine the degree to which the independent variables impact the dependent variable. Findings: The developed model's predictions perfectly fitted the data and explained all the variability of the response data around its mean. Average predictive accuracy of 73.66% was achieved with all the variables on the different projects in validation. The developed SVR model was sensitive to labour and loan. Originality/value: The developed SVRA combines variation, defective works and labour with other financial constraints, which have been the variables used in previous studies. It will aid contractors in predicting profit on completion at commencement and also provide information on the effect of changes to cash-flow factors on profit.
Classification of Public Health Centres in Accra through a Web-Based Portal Integrated with Geographical Information System (GIS)
(Hindawi Limited, 2021) Asabere, N. Y.; Lawson, G.; Badu-Marfo, G.; Kwofie, L.; Mensah, D. O.; Lartey, R.
A health system is described as a logically organized collection of resources, agents, and institutions that offer healthcare to a specific population based on the finance, regulation, and delivery of health services. Many health centres have been established in Accra, the capital city of Ghana, due to the importance of good health. People in other developed nations can seek adequate healthcare, since information about relevant health centres is readily available. However, there is a paucity of information about the services provided by existing health institutions in Ghana, particularly in Accra. The majority of patients commute to either Korle-Bu Teaching Hospital or Greater Accra Regional Hospital, putting a considerable medical strain on these facilities. In this study, we use a Geographic Information System (GIS) to establish a database for all of Accra's health centres and categorize them according to the services they provide. This research tackled the previously mentioned problem by proposing and developing a web-based map called Geohealth for the classification of public health centres in Accra using GIS to assist users in accessing information and locating health centres. We utilized a mixed-method approach consisting of quantitative as well as Build Computer Science Research Methods. Results of our study show that the majority of the participants and stakeholders in our research are eager to embrace Geohealth. Furthermore, in comparison with existing techniques such as Google Maps, our proposed approach, Geohealth, takes less time to obtain information and locate public health centres in Accra, Ghana.
Assessment of High Network Latency on Broadband Powerline Communication
(Institute of Electrical and Electronics Engineers Inc., 2019) Antwi, O. A.; Mohammed, H.; Acakpovi, A.; Donkor, L. M.
This paper focuses on the evaluation of broadband power line communication taking in terms of data transmission and the delayed measured and compared to theoretical values. The utilization of communication systems has expanded rapidly. However, there is a need to deploy new telecommunication systems and transmission technologies that can carry more data and allows faster transmission at a minimal cost. Due to this, the effect of high latency, noise and interference in communication networks is one major challenge that pose great danger to faster and successful data transmission. We use data obtained from the software tool (ICMP) which recorded the ping statistics and (SPSS) in data coding and analysis. Broadband power line communication may be seen as complementary or alternative solutions to traditional fixed line networks and wireless networks according to existing network architectures with PLC bandwidths set to increase
Design of power distribution network fault data collector for fault detection, location and classification using machine learning
(IEEE Computer Society, 2018) Sowah, R.; Dzabeng, N. A.; Ofoli, A. R.; Acakpovi, A.; Koumadi, K. M.; Ocrah, J.; Martin, D.
The protection and maintenance of a power transmission system during fault condition is indispensable to ensure efficient and reliable power supply to consumers. Most methods of fault detection and location rely on measurements of electrical quantities provided by current and voltage transformers. In this paper, a prototype data collecting device was built for collecting data during different faulted conditions in a single-phase distribution network. Machine learning algorithms were developed for fault detection, location and classification on single-phase distribution lines. The transmission line was modelled using resistor network in the device; the current and voltage sensors were used in the prototype model with the data collection device for current and voltage readings under open-circuit and short-circuit faulted conditions. Training data was collected by varying the load on the line during the simulation of the fault type, sensor location on the node and analyzed. The test data was assessed using three (3) machine learning algorithms namely: K-Nearest Neighbor (KNN), Decision Trees and Support Vector Machines (SVM) for prediction of fault, location and classification within the single-phase distribution network. Test results showed that a higher accuracy rate of 99.42 % was obtained by using the Decision Trees algorithm compared to the others investigated.
SARPPIC: Exploiting COVID-19 Contact Tracing Recommendation through Social Awareness
(Hindawi Limited, 2020) Asabere, N. Y.; Acakpovi, A.; Ofori, E. K.; Torgby, W.; Kuuboore, M.; Lawson, G.; Adjaloko, E.
Globally, the current coronavirus disease 2019 (COVID-19) pandemic is resulting in high fatality rates. Consequently, the prevention of further transmission is very vital. Until vaccines are widely available, the only available infection prevention methods include the following: contact tracing, case isolation and quarantine, social (physical) distancing, and hygiene measures (washing of hands with soap and water and using alcohol-based hand sanitizers). Contact tracing, which is key in preventing the spread of COVID-19, refers to the process of finding unreported people who maybe infected by using a verified case to trace back possible infections of contacts. Consequently, the wide and fast spread of COVID-19 requires computational approaches which utilize innovative algorithms that build a memory of proximity contacts of cases that are positive. In this paper, a recommender algorithm called socially aware recommendation of people probably infected with COVID-19 (SARPPIC) is proposed. SARPPIC initially utilizes betweenness centrality in a social network to measure the number of target contact points (nodes/users) who have come into contact with an infected contact point (COVID-19 patient). Then, using contact durations and contact frequencies, tie strengths of the same contact points above are also computed. Finally, the above algorithmic computations are hybridized through profile integration to generate results for effective contact tracing recommendations of possible COVID-19-infected patients who will require testing in a healthcare facility. Benchmarking experimental results in the paper demonstrate that, using two interconnected relevant real-world datasets, SARPPIC outperforms other relevant methods in terms of suitable evaluation metrics such as precision, recall, and F-measure.

Browse

Recent Submissions