Faculty of Applied and Computer Science

Permanent URI for this community

https://hdl.handle.net/10352/31

Browse

Browsing Faculty of Applied and Computer Science by Author "Appiah, Martin, Dr."

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Facial and keystroke biometric recognition for computer based assessments
    (Vaal University of Technology, 2019-12) Adetunji, Temitope Oluwafunmilayo; Appiah, Martin, Dr.; Zuva, Tranos, Prof.
    Computer based assessments have become one of the largest growing sectors in both nonacademic and academic establishments. Successful computer based assessments require security against impersonation and fraud and many researchers have proposed the use of Biometric technologies to overcome this issue. Biometric technologies are defined as a computerised method of authenticating an individual (character) based on behavioural and physiological characteristic features. Basic biometric based computer based assessment systems are prone to security threats in the form of fraud and impersonations. In a bid to combat these security problems, keystroke dynamic technique and facial biometric recognition was introduced into the computer based assessment biometric system so as to enhance the authentication ability of the computer based assessment system. The keystroke dynamic technique was measured using latency and pressure while the facial biometrics was measured using principal component analysis (PCA). Experimental performance was carried out quantitatively using MATLAB for simulation and Excel application package for data analysis. System performance was measured using the following evaluation schemes: False Acceptance Rate (FAR), False Rejection Rate (FRR), Equal Error Rate (EER) and Accuracy (AC), for a comparison between the biometric computer based assessment system with and without the keystroke and face recognition alongside other biometric computer based assessment techniques proposed in the literature. Successful implementation of the proposed technique would improve computer based assessment’s reliability, efficiency and effectiveness and if deployed into the society would improve authentication and security whilst reducing fraud and impersonation in our society.
  • Thumbnail Image
    Item
    A mobile proximity job employment recommender system
    (Vaal University of Technology, 2020-12) Mpela, Motebang Daniel; Appiah, Martin, Dr.; Zuva, Tranos, Prof.
    With a rapid growth of internet technologies, many companies have transformed from the old traditional ways of recruiting employees to electronic recruitment (e-recruitment). E-recruiting channels achieved a solid advantage for both employers and job applicants by dropping advertising cost, applying cost as well as hiring time. Job recommender systems aim to help in people – job matching. In this research, a proposed mobile job employment recommender system is a client – server application that uses content – based filtering algorithm to enable the initial selection of a suitable leisure job seeker to a temporary job at a particular place and vice versa. A prototype of a mobile job recommendation application was developed to evaluate the algorithm. The evaluation matrix used to assess the prototype are precision, recall and the F-measure. The precision value was found to be 0.994, the recall value was 0.975 and the F1- score was 0.984. The experimental results of the proposed algorithm show the effectiveness of the system to recommend suitable candidates for jobs at a specified area. The recommender system was able to achieve its main aim of enabling the initial selection of suitable temporary job seekers to a temporary job at a particular place and vice versa. Thus, the results of the proposed algorithm are satisfactory.
  • Thumbnail Image
    Item
    A model for the adoption and acceptance of mobile farming platforms (MFPs) by smallholder farmers in Zimbabwe
    (Vaal University of Technology, 2022-01) Masimba, Fine; Appiah, Martin, Dr.; Zuva, Tranos, Prof.
    The agriculture sector is the lifeblood of the economies of the world's least developed countries (LDCs). In Zimbabwe, this sector is considered to be the backbone of Zimbabwe's economy, and as a result, it is the sector that supports the economic growth of the country, food security, and poverty eradication efforts. Furthermore, the use of mobile technology has continued to rise in Zimbabwe, and farmers now can obtain agricultural information through the use of mobile technology. Mobile phones are increasingly being integrated into current agricultural trade businesses, owing to the critical role they serve in facilitating information transmission between farmers and buyers. The potential of mobile phones in agriculture spawned mAgriculture, which is the use of mobile phones to provide agricultural information and services. Variousitechnology companies in iZimbabwe have come up with various mobile farming platforms as innovation, with the aim of improving overall performance among smallholder farmers. In order to find the usefullness of these mobile farming platforms, it imperative to measure the adoption and acceptance of this technology in the farming environment. The study sought to investigate the adoption and acceptance of mobile farming platforms in Zimbabwe through a more comprehensive model based on UTAUT 2 that encapsulates the key factors that influence user adoption and acceptance of mobile farming platforms. The main aim of the study was to inform technology start-up companies and other mobile application developers in the development of mobile farming platforms or applications that can be fully adopted and accepted by users, taking into cognisance all salient factors affecting their adoption and acceptance. The model has been used to investigate smallholder farmers in a developing country such as Zimbabwe. The model explores the effect of attitude as one of the key determinants that affect the behavioral intention to use mobile farming platforms. In addition, the model looked at the moderating effect of Hofstede's five cultural dimensions on the key determinants that influence behavioral intention as well as actual use of mobile farming platforms at individual level. A total of 411 questionnaires were received from smallholder farmers in Zimbabwe's three major provinces who were using mobile farming platforms. Structural Equation Modelling was utilized to test the hypothesized conceptual model. Reliability and validity checks were done to the model instrument. As hypothesized, the findings of this study revealed that performance expectancy (PE), effort expectancy (EE) and facilitating conditions (FC) are significant determinants of the newly added variable Attitude (AT). Attitude (AT), together with social influence (SI), facilitating conditions (FC), hedonic motivation (HM), price value (PV), and habit (HB) were found to be significant determinants of behavioral intention and usage of mobile farming platforms for smallholder farmers. The results also showed that cultural dimensions have a moderating effect on user acceptance of mobile farming platforms. According to the findings, attitude and culture are significant factors to consider when analyzing farmers' behavioral intentions and use of mobile farming platforms. The findings of the study contribute to the literature by validating and supporting the applicability of the extended UTAUT 2 for the adoption and acceptance of mobile farming platforms by smallholder farmers in developing countries. The theoretical contribution of the study was through the extension of UTAUT 2 where attitude was added as one of the new key determinants of behavioral intention and cultural dimensions were added as mediators. The other contribution is to the Zimbabwean farming community where the study was conducted.