Papers by Gregory M. Wajiga
ICST Transactions on Scalable Information Systems, 2018
Improving the accuracy of learning style detection models is a primary concern in the area of aut... more Improving the accuracy of learning style detection models is a primary concern in the area of automatic detection of learning style, which can be achieved either through, attribute/feature selection or classification algorithm. However, the role of facial expression in improving accuracy has not been fully explored in the research domain. On the other hand, deep learning solutions have become a new approach for solving complex problems using Deep Neural networks (DNNs); these DNNs have deep architectures that are capable of decomposing problems into multiple processing layers, enabling and devising multiple mapping of complex problems functions. In this paper, we investigate and compare the performance of Convolutional Neural Network (CNN) and MultiClass Neural Network (MCNN) for classification of learners into VARK learning-style dimensions (i.e Visual, Aural, Reading Kinaesthetic, including Neutral class) based on facial images. The performances of the two networks were evaluated and compared using square mean error MSE for training and accuracy metric for testing. The results show that MCNN offers better and robust classification performance of VARK learning style based on facial images. Finally, this paper has demonstrated a potential of a new method for automatic classification of VARK LS based on Facial Expressions (FEs). Based on the experimental results of the models, this approach can benefit both researchers and users of adaptive e-learning systems to uncover the potential of using FEs as identifier learning styles for recommendations and personalization of learning environments.
The Journal of the Operational Research Society, 1998
ABSTRACT Mortality differentials exist even among people of the same age and environmental risks.... more ABSTRACT Mortality differentials exist even among people of the same age and environmental risks. These differences are due to individual frailty (risks due to biological or behavioural reasons) not considered in the computation of conventional life-tables (where populations are assumed to be homogeneous). This note seeks to show empirically that life-expectancies computed from homogeneous population models are overstated for ages less than the mean, and are understated for higher ages. It is also shown that life-expectancy curves for both homogeneous and nonhomogeneous populations intersect at the mean survival age (when the most frail would have all died off) and at the maximum age lived in the population (when the last members of the cohort would have died off).
Education and Information Technologies, 2017
The study focused on the application of the design science research approach in the course of dev... more The study focused on the application of the design science research approach in the course of developing a mobile learning application, MobileEdu, for computing education in the Nigerian higher education context. MobileEdu facilitates the learning of computer science courses on mobile devices. The application supports ubiquitous, collaborative, and social aspects of learning among higher education students. Moreover, the application eases access to learning resources. The paper first describes analysis, design, and implementation activities related to the development of MobileEdu. Also, the paper deliberated on the characteristics and scope of the adherence of MobileEdu to the traits and ideas of design science research. To evaluate MobileEdu in a real-life learning setting, experiment was conducted with 142 third-year undergraduate students in a Nigerian university. Besides the learning achievement of the students using MobileEdu, the study examined the impact of MobileEdu on students' attitudes toward studying in a system analysis and design course. Experimental data were collected from pre-and post quizzes, interviews, and a questionnaire administered to students. The results of the evaluation are encouraging and showed that the MobileEdu application has a potential to improve students' learning achievements. In addition, the pedagogical experiences of students were mostly positive and students' attitudes toward the system analysis and design course through MobileEdu was better than those of students who studied the course via traditional methods. Finally, the study offered suggestions for how to implement effectively a mobile learning-supported course in computing curriculum. Keywords MobileEdu Mobile learning Design science research Blended learning Computing education Information and communication technology several platforms, such as mobile apps, web-based, or combined mobile learning environments. Mobile devices and wireless technologies are continuously evolving with time. These technologies have taken a center stage in every aspect of our society, especially in education, health, the economy, and commerce. The use of mobile devices, such as smartphones, mobile phones, tablets, PDAs, MP3s, and pocket PCs, for computing education is constantly gaining interest among researchers and educators (
This work deals with encoding algorithm that conveys a message that generates a "compressed" form... more This work deals with encoding algorithm that conveys a message that generates a "compressed" form with fewer characters only understood through decoding the encoded data which reconstructs the original message. The proposed factorization techniques in conjunction with lossless method were adopted in compression and decompression of data for exploiting the size of memory, thereby decreasing the cost of the communications. The proposed algorithms shade the data from the eyes of the cryptanalysts during the data storage or transmission.
Personal privacy is of utmost importance in the global networked world. One of the best tools to ... more Personal privacy is of utmost importance in the global networked world. One of the best tools to help people safeguard their personal information is the use of cryptography. In this paper we present new cryptographic algorithms that employ the use of asymmetric keys. The proposed algorithms encipher message into nonlinear equations using public key and decipher by the intended party using private key. If a third party intercepted the message, it will be difficult to decipher it due to the multilevel ciphers of the proposed application.
2014 IEEE 6th International Conference on Adaptive Science & Technology (ICAST), 2014
2013 8th EUROSIM Congress on Modelling and Simulation, 2013
2013 Fifth International Conference on Computational Intelligence, Communication Systems and Networks, 2013
ABSTRACT Next Generation Network (NGN) services and applications such as Digital Multimedia Broad... more ABSTRACT Next Generation Network (NGN) services and applications such as Digital Multimedia Broadcasting (DMB) and Internet Protocol Television (IPTV) will offer multicast features, but due to high traffic volume and high number of receivers there will be challenges of efficient multicast mechanisms for communication. With the rapid development of applications and networks, there is a need to optimize the transmission energy within a multicast group for efficient traffic in both wired and wireless channels. This paper discusses major algorithms for multicasting and then focuses on the analysis of Multicast Incremental Power (MIP) algorithm and the recently proposed Network coding based (NC) algorithm using energy-efficiency as metric. The performance of these algorithms are evaluated and optimized for energy reduction on communication networks. The results show a reduction in multicast energy as network size increases with decrease in multicast energy as the multicast group size increases for both wired and wireless networks.
The study focused on the application of the design science research approach in the course of dev... more The study focused on the application of the design science research approach in the course of developing a mobile learning application, MobileEdu, for computing education in the Nigerian higher education context. MobileEdu facilitates the learning of computer science courses on mobile devices. The application supports ubiquitous, collaborative, and social aspects of learning among higher education students. Moreover, the application eases access to learning resources. The paper first describes analysis, design, and implementation activities related to the development of MobileEdu. Also, the paper deliberated on the characteristics and scope of the adherence of MobileEdu to the traits and ideas of design science research. To evaluate MobileEdu in a real-life learning setting, experiment was conducted with 142 third-year undergraduate students in a Nigerian university. Besides the learning achievement of the students using MobileEdu, the study examined the impact of MobileEdu on students' attitudes toward studying in a system analysis and design course. Experimental data were collected from pre-and post quizzes, interviews, and a questionnaire administered to students. The results of the evaluation are encouraging and showed that the MobileEdu application has a potential to improve students' learning achievements. In addition, the pedagogical experiences of students were mostly positive and students' attitudes toward the system analysis and design course through MobileEdu was better than those of students who studied the course via traditional methods. Finally, the study offered suggestions for how to implement effectively a mobile learning-supported course in computing curriculum.
Uploads
Papers by Gregory M. Wajiga