Department of Computer Science
Permanent URI for this collectionhttp://197.255.125.131:4000/handle/123456789/23129
Browse
68 results
Search Results
Item A cascading approach using se-resnext, resnet and feature pyramid network for kidney tumor segmentation(Heliyon, 2024) Appati, J. K.; Yirenkyi, I. A.Accurate segmentation of kidney tumors in CT images is very important in the diagnosis of kidney cancer. Automatic semantic segmentation of the kidney tumor has shown promising results to wards developing advance surgical planning techniques in the treatment of kidney tumor. However, the relatively small size of kidney tumor volume in comparison to the overall kidney volume, and its irregular distribution and shape makes it difficult to accurately segment the tu mors. In addressing this issue, we proposed a coarse to fine segmentation which leverages on transfer learning using SE-ResNeXt model for the initial segmentation and ResNet and Feature Pyramid Network for the final segmentation. The processes are related and the output of the initial results was used for the final training. We trained and evaluated our method on the KITS19 dataset and achieved a dice score of 0.7388 and Jaccard score 0.7321 for the final segmentation demonstrating promising results when compared to other approaches.Item 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.Item 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.Item 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.Item 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 systemsItem 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.Item 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.Item 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.Item 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 appsItem 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.