Department of Computer Science

Permanent URI for this collection

http://197.255.125.131:4000/handle/123456789/23129

Browse

Now showing 1 - 20 of 67

Robust facial expression recognition system in higher poses
(Visual Computing for Industry, Biomedicine, and Art, 2022) Owusu, E.; Appati, J.K.; Okae, P.
Facial expression recognition (FER) has numerous applications in computer security, neuroscience, psychology, and engineering. Owing to its non-intrusiveness, it is considered a useful technology for combating crime. However, FER is plagued with several challenges, the most serious of which is its poor prediction accuracy in severe head poses. The aim of this study, therefore, is to improve recognition accuracy in severe head poses by proposing a robust 3D head-tracking algorithm based on an ellipsoidal model, advanced ensemble of AdaBoost, and saturated vector machine (SVM). The FER features are tracked from one frame to the next using the ellipsoidal tracking model, and the Visible, expressive facial key points are extracted using Gabor filters. The ensemble algorithm (Ada-AdaSVM) is then used for feature selection and classification. The proposed technique is evaluated using the Bosphorus, BU-3DFE, MMI, CK+ and BP4D-Spontaneous facial expression databases. The overall performance is outstanding.
Assessing the impact of persuasive features on user’s intention to continuous use: the case of academic social networking sites
(Behaviour & Information Technology, 2020) Wiafe, I.; Kastriku, F.A.; Koranteng, F.N.; Gyamera, G.O.
Social networking sites enable people to connect, communicate and share ideas. These sites have therefore become key for information sharing. Particularly, academics and researchers have adopted them for networking and collaboration. This study seeks to investigate how embedded persuasive features on social networking sites designed for academics and researchers affect continuous use intention. The study adopted an existing model for assessing the effectiveness of persuasive features on systems and sampled 416 participants who are engaged in academic research and analyzed their responses. The results indicate that Social Support, Computer-Human Dialogue Support and Primary Task Support significantly impact how users perceive social networking sites designed for effective academic work. Contrary to existing knowledge that Perceived Credibility, Perceived Effectiveness, Perceived Effort and Perceived Social Support all impacts an individual’s Intention to continuously Use of a system. only Perceived Credibility was observed to impact Intention to Use continuously. The findings also proved that affective ties and mutual support on academic social networking sites influence behaviour.
Development and validation of an improved DeLone-McLean IS success model - application to the evaluation of a tax administration ERP
(International Journal of Accounting Information Systems, 2022) Akrong, G.B.; Owusu, E.; Yunfei, S.
Enterprise resource planning (ERP) is critical to an organization’s success. However, the factors that contribute to the success and usage of these ERP systems have received little attention. This study developed and validated an improved DeLone-McLean IS success model. Additionally, we examined the factors which influence ERP system usage, employee satisfaction, and information quality, service quality, and system quality, as well as the factors that influence the system’s overall success. The proposed model is based on a mixed-methods case study (MM-CS). The results show that the proposed model significantly measures the success of an ERP system. The organizational climate, the information quality, the system quality, and the service quality all have an impact on the usage of an ERP system. The proposed model also shows that the use of an ERP system, training and learning, and the three information (IS) quality constructs are all significant predictors of user satisfaction. The results also indicate that gender and years of ICT use on the path of ERP users have a moderating effect on the relationship between teamwork & support and use.
Speed Monitoring And Controlling Systems For Road Vehicle Safety: A Systematic Review
(Advances in Transportation Studies, 2022) Armah, Z.A.; Wiafe, I.; Owusu, E.; Koranteng, F.N.
Overspeeding continues to be one of the major causes of road fatalities, and accordingly, several interventions have been designed to combat it. In more recent times, several studies have proposed intelligent methods for detecting, monitoring and controlling over speeding effectively. This study investigated advancements, challenges and future research direction of the use of intelligent speed monitoring and control systems. using a systematic review approach, 47 studies were identified and reviewed. the review covered studies published from 2015 to 2019. the findings from the review indicated that road vehicle speed monitoring and control systems have witnessed commendable advancements over the past years. Four main types of speed measurement technologies dominate speed monitoring and control systems. out of the four, sensor based technologies are the most used, yet they are characterized by low speed measurement accuracy. also, studies in the domain use diverging evaluation methods and this makes it a challenge to compare system performance across the various studies. also, there seems to be a lack of interest in the usage of artificial intelligence and machine learning techniques for speed measurement. the study proposes increased attention to the use of artificial intelligence and machine learning techniques to promote effective speed monitoring and control systems
Persuasive social features that promote knowledge sharing among tertiary students on social networking sites: An empirical study
(Journal of Computer Assisted Learning, 2020) Wiafe, I.; Koranteng, F.N.; Owusu, E.; Ekpezu, A.O.; Gyamfi, S.A.
Persuasive system features have been widely adopted to encourage attitude and behaviour change. Recently, most social networking sites (SNS) adopt some form of persuasive system features that leverage social influence to deliberately induce pre scribed behaviours in their users. However, studies on how these features can be used to promote knowledge sharing are inadequate; particularly, regarding how SNS that have been developed solely for academic purposes can adopt these features to promote knowledge sharing. To address this knowledge gap, this study integrates constructs from the social capital theory and persuasive systems design model to investigate the impact of persuasive social features on knowledge sharing among stu dents of tertiary institutions on academic social networking sites. Data are quantita tively gathered from 218 respondents from tertiary institutions and statistically analyzed. The results suggest that perceived dialogue support and perceived social support have strong influences on knowledge sharing behaviour.
Empirical exploration of whale optimisation algorithm for heart disease prediction
(Scientific Reports, 2024) Atimbire, S.A.; Appati, J.A.; Owusu, E.
Heart Diseases have the highest mortality worldwide, necessitating precise predictive models for early risk assessment. Much existing research has focused on improving model accuracy with single datasets, often neglecting the need for comprehensive evaluation metrics and utilization of different datasets in the same domain (heart disease). This research introduces a heart disease risk prediction approach by harnessing the whale optimization algorithm (WOA) for feature selection and implementing a comprehensive evaluation framework. The study leverages five distinct datasets, including the combined dataset comprising the Cleveland, Long Beach VA, Switzerland, and Hungarian heart disease datasets. The others are the Z-AlizadehSani, Framingham, South African, and Cleveland heart datasets. The WOA-guided feature selection identifies optimal features, subsequently integrated into ten classification models. Comprehensive model evaluation reveals significant improvements across critical performance metrics, including accuracy, precision, recall, F1 score, and the area under the receiver operating characteristic curve. These enhancements consistently outperform state-of-the-art methods using the same dataset, validating the effectiveness of our methodology. The comprehensive evaluation framework provides a robust assessment of the model’s adaptability, underscoring the WOA’s effectiveness in identifying optimal features in multiple datasets in the same domain. Heart Disease (HD) is of utmost importance due to the heart’s critical role among other human organs. HD has high death rates worldwide, with approximately 17.9 million people dying from heart conditions in 20191. Heart diseases account for 32% of global deaths, with heart attacks and stroke alone making more than 85% of recorded deaths. Over 75% of cardiovascular deaths in 2019 occurred in underdeveloped nations, accounting for 38% of deaths under 70 years1. Since cardiovascular diseases are fatal, their early detection will enable medical professionals to provide timely healthcare to patients to avert death. Because of a scarcity of ultra-modern examination tools and medical experts, conventional medical methods for diagnosing heart diseases are challenging, complicated, time-consuming, and exorbitant, making the diagnosis of heart diseases difficult and sometimes unavailable, especially in developing countries2. Machine and deep learning methods have been recently used to analyze clinical data and make predictions3. Machine learning (ML) provides cost-efficient alternatives where already collected patient data serve as a data mine to perform predictive analysis for diagnostic purposes. To improve the accuracy of ML models, some existing works have focused on using various classifiers or their enhanced forms4– 7. Related works confirm that the feature selection reduces data dimensionality and improves model performance significantly8. Hence, some studies have utilized various methods to improve performance by varying the feature selection methods9,10. However, some works that utilize feature selection are fraught with redundant features that impact metrics recorded. This is affirmed when wrapper methods are used over filter methods and when embedded methods are used over filter and wrapper methods. It also explains why works, including feature selection, may only record better performance on some datasets if the technique is efficient. In addition, though the researchers do not present the reason some existing works have not reported on specific metrics, studies such as Hicks et al.11 have posited that in a clinical setting, a subset of metrics may give an erroneous outlook of how a model performs and not enabling holistic model performance evaluation. There is an avenue for more scientific work on feature selection methods capable of improving other metrics besides the accuracy metric. This helps to affirm the reliability of the model performance as the unavailability of multiple evaluation metrics is an indication of an unbalanced model not capable of being thoroughly assessed. This study proposes the use of the whale optimization algorithm (WOA) as a swarm-inspired feature selection algorithm on five (5) heart datasets on ten (10) models (classical ML, ensemble and deep learning models) for the selection of relevant datasets features. The approach contributes to the body of knowledge in the heart disease domain by providing a comprehensive assessment of five different datasets (in the same domain), ten different models and five evaluation metrics. The proposed methodology also validates the robustness of the WOA algorithm on five datasets of variable sizes in the same domain compared to most works, which do not test their methodologies on multiple datasets in the same domain.
A Hybrid Heuristic Model for Duty Cycle Framework Optimization
(International Journal of Distributed Sensor Networks, 2024) Ansah, K.; Appati, J.K.; Owusu, E.; Abdulai, J-D.
This paper proposes a hybrid metaheuristic approach to optimize a duty cycle framework based on Seagull and Mayfly Optimization (HSMO-DC) Algorithm. This approach becomes crucial as current clustering protocols are unable to efficiently tune the clustering parameters in accordance to the diversification of varying WSNs. The proposed HSMO-DC primarily has two parts, where the first part takes care of the online cluster head selection and network communication using the seagull algorithm while the second part performs parameter optimization using the mayfly algorithm. The seagull is aimed at improving the energy distribution in the network through an effective bandwidth allocation procedure while reducing the total energy dissipation. Comparatively, with other clustering protocols, our proposed methods reveal an enhanced network lifetime with an improved network throughput and adaptability based on selected standard metric of performance measurement.
Enhancing Perceived Health Competence: The Impact of Persuasive Social Support Features in Health and Fitness Apps
(International Journal of Human–Computer Interaction, 2023) Ekpezu, A.O.; Wiafe, I.; Oinas-Kukkonen, H.
This study investigates how users’ perception of persuasive social support features influences per ceptions of their health competence in health and fitness apps. Within the support of existing the ories/frameworks on social support, the study develops a research model and hypotheses. Quantitative data was collected from 469 health and fitness app users and analyzed using partial least squares structural equation modelling. The results demonstrates that providing users with a means to share their experiences out of the desire to boost their ego and gain social recognition as well as a means to learn new behaviors by observing and imitating other’s behaviors within the app increases their confidence in their capabilities to perform and maintain positive health and fitness behaviors and outcomes using the app. The findings suggest that users’ perception of their health competence can be significantly improved when social support features are incorpo rated into health and fitness apps
An Optimal Spacing Approach for Sampling Small-sized Datasets for Software Effort Estimation
(2023) Abedu, S.; Mensah, S.; Boafo, F.
Context: There has been a growing research focus in conventional machine learning techniques for software effort estimation (SEE). However, there is a limited number of studies that seek to assess the performance of deep learning approaches in SEE. This is because the sizes of SEE datasets are relatively small. Purpose: This study seeks to define a threshold for small-sized datasets in SEE, and investigates the performance of selected conventional machine learning and deep learning models on small-sized datasets. Method: Plausible SEE datasets with their number of project instances and features are extracted from existing literature and ranked. Eubank’s optimal spacing theory is used to discretize the ranking of the project instances into three classes (small, medium and large). Five conventional machine learning models and two deep learning models are trained on each dataset classified as small-sized using the leave-one-out cross-validation. The mean absolute error is used to assess the prediction performance of each model. Result: Findings from the study contradicts existing knowledge by demonstrating that deep learning models provide improved prediction performance as compared to the conventional machine learning models on small-sized datasets. Conclusion: Deep learning can be adopted for SEE with the application of regularisation techniques.
Fundus Image Classification: A Wavelet Feature Descriptor Approach
(IEEE Xplore, 2023) Appati, J.K.; Armah, B.; Owusu, E.; Soli, M.A.T.
Lately, many diabetic patients are experiencing diabetic retinopathy resulting in a loss of their sight. Even though the urgency and threat posed by this condition, there is insufficient data source to engage appropriate computational intelligence tools. The few that exist happen to be imbalanced. Leveraging on this imbalanced dataset, several activities have been carried out to propose improved detection and classification descriptors. Although some works have been done in this domain, the issue of accuracy still persists in the administration of an effective diagnosis. This paper harnessed the benefits of Gabor filters and the multi-resolution property of Discrete Wavelet Transforms (DWTs) to construct appropriate fundus feature descriptors. These discriminant features are fed into some selected but predominant classical machine learning classifiers. Numerical evaluation of the study gave a perfect (100%) average score for the fundus image classification using Gradient Boosting and Logistic Regression classifiers over Accuracy, F1-score, Precision and Recall evaluation metric. The tie in performance is further broken using their computation time, suggesting that Logistic Regression is more appropriate with 9min 32sec over Gradient Boosting or 1hr 10min 32sec.
A sentiment analysis framework to classify instances of sarcastic sentiments within the aviation sector
(International Journal of Information Management Data Insights, 2023) Iddrisu, A-M.; Mensah, S.; Boafo, F.; Yeluripati, G.R.; Kudjo, P.
Social media in our current dispensation has become an integral part of daily routines. As a result, it is abundant in user opinions. Amid a global pandemic, these online platforms have taken a center stage in the disbursement of relevant information such as travel, emergency and pandemic hotspots. For researchers, this situation has presented itself as a challenge and opportunity to leverage big data for analysis and making informed decisions. This study seeks to develop a framework comprising of three operators, namely Assemble+Deft, Edify+Authenticate and Forecast to classify opinion instances as sarcastic or non-sarcastic. The framework is tested with a Twitter dataset using key state-of-the-art techniques, namely Recurrent Neural Network (RNN) with Gated recurrent unit and Support Vector Machines (SVM). The dataset consists of opinions on effect of COVID-19 pandemic on air travel. The evaluation metrics used include precision, accuracy, recall and F1-score. The experimental analysis showed a significant increase from 9.28% under a standard sentiment review to 10.1% optimized sentiment analysis. The findings further show a significant improvement in the performance of optimized SVM yielding an improved prediction performance compared to RNN. The outcome of this study will support airlines to understand the frustration and complaints of customers and to make concrete decisions on how to improve their services. The framework will serve as a benchmark for future sentiment analysis in other sectors where customer views and comments are core to their services.
The Use of Machine Learning Algorithms in the Classification of Sound: A Systematic Review
(International Journal of Service Science, Management, Engineering, and Technology, 2023) Ekpezu, A.O.; Katsriku, F.; Yaokumah, W.; Wiafe, I.
This study is a systematic review of literature on the classification of sounds in three domains: bioacoustics, biomedical acoustics, and ecoacoustics. Specifically, 68 conferences and journal articles published between 2010 and 2019 were reviewed. The findings indicated that support vector machines, convolutional neural networks, artificial neural networks, and statistical models were predominantly used in sound classification across the three domains. Also, the majority of studies that investigated medical acoustics focused on respiratory sounds analysis. Thus, it is suggested that studies in biomedical acoustics should pay attention to the classification of other internal body organs to enhance diagnosis of a variety of medical conditions. With regard to ecoacoustics, studies on extreme events such as tornadoes and earthquakes for early detection and warning systems were lacking. The review also revealed that marine and animal sound classification was dominant in bioacoustics studies
Overcoming the Challenges of Enterprise Resource Planning (ERP): A Systematic Review Approach
(International Journal of Enterprise Information Systems, 2022) Akrong, G.B.; Shao, Y.; Owusu, E.
ABSTRACT The study presents the results of a comprehensive review conducted between 2005-2020 to identify enterprise resource planning (ERP) challenges, discover the divisions in which these challenges can be clustered, and provide general strategies to resolve these challenges. The study also found 25 categories that can be classified into ERP challenges. Sixty-five ERP challenges were identified based on the reviewed literature, of which 18 were not provided with adequate solutions as to how to resolve them, and the related solutions as mentioned in the reviewed literature are presented in-depth. The result will help both academics and practitioners involved with how to resolve ERP system challenges.
Evaluation of the quality constructs of a tax management system based on DeLone and McLean IS success mode
(AFRICA JOURNAL OF MANAGEMENT, 2022) Akrong, G.B.; Shao, Y.; Owusu, E.
We presented a novel method to analyze the impact tax management systems have on users (individual impact) in this study. The interrelationship among the three information system (IS) quality constructs is examined. The study is based on the evaluation undertaken in this paper of DeLone and Mclean’s (D & M) model. Quantitative data are gathered from a related Ghanaian enterprise. The structural equation modelling of partial least squares was utilized to model the system quality, information quality, and service quality. The result of the study shows that the three quality constructs of the D & M model positively influence the users of a tax management system (individual impact). The results also show that there is a significant positive interrelation among the IS quality constructs.
Implementation of Missing Data Imputation Schemes in Face Recognition Algorithm under Partial Occlusion
(Advances in Multimedia, 2022) Appati J.K.; Adu-Manu K.S.; Owusu E.
Face detection and recognition algorithms usually assume an image captured from a controlled environment. However, this is not always the case, especially in crowd control under surveillance or footage from a crime scene, where partial occlusions are unavoidable. Unfortunately, these occlusions have an adverse e ect on the performance of these classical recognition algorithms. In this study, the performance of some selected data imputation schemes is evaluated on SVD/PCA frontal face recognition algorithm. e experiment was done on two datasets: Ja e and MIT-CBCL, with immediate con rmation of the adverse e ect of occlusion on the facial algorithm without implementing the imputation scheme. Further experimentation shows that IA is an ideal missing data imputation scheme that works best with the SVD/PCA facial recognition algorithm.
WSN Protocols and Security Challenges for Environmental Monitoring Applications: A Survey
(Journal of Sensors, 2022) Adu-Manu, K.S.; Engmann, F.; Sarfo-Kantanka, G.; Baiden, G.E.; Dulemordzi, B.A.
In recent years, communication technology has improved exponentially, partly owing to the locations and nature of the deployment of sensor nodes. Wireless sensor networks (WSNs) comprise these sensor nodes and can provide real-time physical and environmental measurements. The sensor nodes have limited power, which reduces their lifespan, especially when placed in human-inaccessible locations. This paper reviews energy-efficient protocols for environmental monitoring applications and energy harvesting-wireless sensor networks. The dynamic deployment and communication challenges associated with environmental monitoring applications (EMAs) make this paper take into account the WSN protocol stack, focusing on the physical layer, network layer (routing), and medium access control (MAC). The paper will delve deeper into the security challenges of deploying sensor nodes for environmental monitoring applications (EMAs). The paper further describes scientific approaches that churn out innovative and engineering applications that must be followed to improve environmental monitoring applications.
Supporting to be Credible: Investigating Perceived Social Support as a Determinant of Perceived Credibility
(Springer, 2022) Wiafe, I.; Koranteng, F.N.; Ham, J.; Matzat, U.
Technological systems can be equipped with persuasive design principles that influence user perceptions. For instance, earlier research showed that Perceived Social Support can influence user perceptions such as effectiveness and knowledge sharing intentions. However, to our knowledge, how Perceived Social Support affects Perceived Credibility has not been investigated. This study investigates the influence of Perceived Social Support on Perceived Credibility. A survey questionnaire was employed to gather user perceptions of social support and credibility in the context of Academic Social Networking Sites (ASNSs). Analysis using Partial Least Square Structural Equation Modeling (PLS-SEM) confirmed Perceived Social Support as a determinant of Perceived Credibility. Also, Dialogue Support and Primary Task Support were identified to be predictors of Perceived Social Support. The study recommends that designers improve the social support features (e.g., through integrating machine learning and data mining techniques).
Assessing the impact of persuasive features on user’s intention to continuous use: the case of academic social networking sites
(Taylor & Francis Group, 2022) Wiafe, I.; Koranteng, F.N.; Kastrikua, F.A.; Gyamerac, G.O.
Social networking sites enable people to connect, communicate and share ideas. These sites have therefore become key for information sharing. Particularly, academics and researchers have adopted them for networking and collaborations. This study seeks to investigate how embedded persuasive features on social networking sites designed for academics and researchers affect continuous use intention. The study adopted an existing model for assessing the effectiveness of persuasive features on systems and sampled 416 participants who are engaged in academic research and analyzed their responses. The results indicate that Social Support, Computer–Human Dialogue Support and Primary Task Support significantly impact how users perceive social networking sites designed for effective academic work. Contrary to existing knowledge that Perceived Credibility, Perceived Effectiveness, Perceived Effort and Perceived Social Support all impact an individual’s Intention to Continuous Use of a system, only Perceived Credibility was observed to impact Intention to Use continuously. The findings also proved that affective ties and mutual support on academic social networking sites influence behaviour.
The impact of antimicrobial resistance awareness interventions involving schoolchildren, development of an animation and parents engagements: a pilot study
(Antimicrobial Resistance & Infection Control, 2022) Appiah, B.; Asamoah‑Akuoko, L.; Samman, E.; Koduah, A.; Kretchy, I.A.; Ludu, J.Y.; Odonkor, G.; Nam, S.H.; Gyansa‑Luterrodt, M.
Background: Antimicrobial resistance (AMR) is a global health challenge, particularly in low- and middle-income countries where antibiotics are widely available to consumers, leading to their misuse. However, AMR educational interventions for engaging parents of schoolchildren are mainly lacking in Sub-Saharan Africa. This study aimed to assess the potential of AMR animation and schoolchildren in influencing parents’ AMR knowledge, attitudes, and beliefs. Methods: Parents of schoolchildren aged 11–15 years in Tema, a city in Ghana, watched and discussed an AMR animation designed with ideas from the schoolchildren’s top stories and picture drawings. The children from two schools were first engaged with AMR lessons, with one school using storytelling, the other school using picture drawing, and none serving as a control. The children were then asked to discuss the lessons with their parents. Baseline surveys of parents of randomly selected children were conducted to assess AMR knowledge, attitudes and beliefs before engaging the students and parents, and immediately after the parents participated in viewing and discussing the animation. McNemar and t-tests were used to assess changes in AMR knowledge, attitudes and beliefs. Results: Parents who participated in the animation event, and whose schoolchildren were in the storytelling intervention school had significantly improved knowledge regarding the statement “Antibiotics will cure any infection” (p=0.021, χ2=0.711; 88% vs 50%) between baseline and endline. However, these parents also had statistically significant decreased scores regarding the statement “Antibiotics do not kill our good bacteria” (p=0.021, χ2=1.042; 71.4% vs 40%) between baseline and endline. There was no significant effect on any statement among parents whose children were in the picture drawing school. However, t-test results combining the statements as composite scores showed statistically significant difference in only the attitude construct among parents whose children participated in storytelling intervention (p=0.043) or picture drawing intervention (p=0.019). There were no statistically significant changes in knowledge and beliefs constructs. Conclusions: This study shows that interventions involving schoolchildren with parents engagements and AMR animation could influence parents’ AMR attitudes. The intervention could also positively or negatively impact parents’ AMR knowledge. Modifications of the interventions may be needed for tackling AMR.
A modifed distance‑based energy‑aware (mDBEA) routing protocol in wireless sensor networks (WSNs)
(Springer, 2022) Abdulai, J.D.; Adu‑Manu, K. S.; Katsriku, F. A.; Engmann, F.
Wireless sensor networks (WSNs) are used to collect data and detect phenomena in a real-time environment. There is considerable interest in the deployment of WSNs in remote, inaccessible and inhospitable locations; such use of WSNs throws up many challenges. WSNs come with numerous advantages, yet a notable limitation is that the battery life dictates the lifetime of the sensor node. Two critical factors that determine battery lifetime are the frequency of sensor readings and the transmission range of the sensor nodes. Some energy-efficient routing protocols have been proposed and adopted for use to extend the lifetime of sensor nodes. These protocols aim at optimizing the routes in the network. Given that multi-hop routes are energy ineficient, improving the lifetime of WSNs in a multi-hop routing environment will require the use of route optimization techniques. A modified distance-based energy-aware (mDBEA) routing protocol is proposed which is efficient and capable of minimizing the energy consumption of the sensor nodes and hence, maximizing network lifetime. Our approach addresses the problem by calculating the Euclidian distance between successive nodes to determine the short est distance that minimizes the energy required for transmission. The simulation results indicate that the mDBEA routing protocol reduced the amount of energy consumed in the network by choosing the minimum transmission distance between the source and its neighbour nodes that significantly prolonged the network's lifetime. Our greedy approach yielded about 95% Packet delivery ratio (PDR). Our next-hop and the direct-to-sink algorithms yielded about 82% PDR.

Browse

Recent Submissions