Browsing by Author "Mbogho, Audrey J W"

Now showing 1 - 13 of 13
  • Thumbnail Image
    Item
    Open Access
    An application of brain-based education principles with ICT as a cognitive tool: a case study of grade 6 decimal instruction at Sunlands Primary School
    (2015) Le Roux, Zelda Joy; Mbogho, Audrey J W
    The larger population of South African learners do not learn effectively and struggle with low academic achievements currently. This can be attributed to various factors such as frequent changes in the curriculum, underqualified educators, ineffective teaching methods and barriers to learning existing in classrooms today. Learners need extra support, including cognitive support, but in reality the heavy workload of educators may prevent them from giving learners the needed support. If support is given, it is minimal or not effective enough. Computer technologies may afford both educators and learners such opportunities when used as a cognitive tool in activities that provide the needed support. This research is concerned with the use of computer technology as a cognitive tool to activate learners' cognitive processes, thus enhancing learning, based on Brain Based Education principles. The objective is to lay the foundation in using computer technologies as cognitive tools in educators' teaching practice and instructional design to make teaching and learning more effective, interactive, real world based, giving meaning to what is learnt and to enhance understanding.
  • Thumbnail Image
    Item
    Open Access
    Bridging the digital divide in African post-conflict countries : a case study of the DRC cities of Kinshasa and Kananga
    (2007) Maketa, Lutete Thomas; Mbogho, Audrey J W
    The digital divide is largely seen as the main problem that developing economies and societies must overcome to gain economic productivity and social welfare. In this document we state that modern western perception of the digital divide lured advancement of lCT into developing countries especially in Africa. lCT must not be seen as a goal in itself but as a means to service human needs. This study attempts to analyze the willingness of people to adopt existing lCT infrastructures and the factors impeding its use in the DRC's cities of Kinshasa and Kananga.
  • Thumbnail Image
    Item
    Open Access
    Bridging the digital divide in African post-conflict countries: a case study of the DRC cities in Kinshasa and Kananga
    (2007) Thomas, Nakela Lutele; Mbogho, Audrey J W
    The digital divide is largely seen as the main problem that developing economies and societies must overcome to gain economic productivity and social welfare. In this document we state that modern western perception of the digital divide lured advancement of ICT into developing countries especially in Africa. ICT must not be seen as a goal in itself but as a means to service human needs. This study attempts to analyze the willingness of people to adopt existing ICT infrastructures and the factors impeding its use in the DRC's cities of Kinshasa and Kananga
  • Thumbnail Image
    Item
    Open Access
    A cross-platform usability evaluation of 2D visual tagging systems
    (2007) King, Samuel Olugbenga; Mbogho, Audrey J W
    By encoding 2D bar codes that store URL links, SMS or plain text, 2D visual tags link infonnation about objects in the physical world to online or offline content. The existence of physical world hyperlinks in the fonn of 2D visual tags that are placed in the natural environment therefore makes new social and cultural interaction modes possible. Although 2D visual tagging systems have much potential to positively influence the way people, and Africans in particular, interact with the physical world, there has been no indepth evaluation or cross-platfonn usability assessment of available 2D visual tagging systems. Research in the field has primarily focused on the description and evaluation of prototype visual tagging applications. The deployment and use of 2D visual tagging systems have also not been comprehensively tested in Africa. To evaluate the 2D visual tagging paradigm, five 2D visual tagging systems were selected for this study.
  • Thumbnail Image
    Item
    Open Access
    Enabling visually impaired people to use touch screen phones
    (2015) Kivaisi, Alexander; Mbogho, Audrey J W
    Most mobile applications are not designed for visually impaired people. The concept of universal design is not adopted by most application developers. Therefore, interaction between a visually impaired user and the mobile application becomes cumbersome. Assistive technologies such as screen readers have been developed for different mobile device manufacturer s for visually impaired users. However, they only support the most popular languages spoken in the world such as English. To our knowledge, although research on assistive technologies for the use of mobile devices by visually impaired people has been done, information on that relating to minority languages such as Swahili is virtually non-existent. Therefore, this study investigated the challenges faced by visually impaired Swahili speakers when using mobile phones and then developed a mobile phone application which would enable them to use touch screen phones more independently. As a user center design methodology was adopted, visually impaired people were the focal point for this study. The mobile application was designed and implemented based on the feedback from the participants in all iteration phases and thereafter the final evaluation of a complete application was conducted. The results of the user evaluation showed that most of the visually impaired users were able to complete the tasks independently and were excited to practice even more. Although, the results showed that the sliding - text entry method had more problems than the Braille - method, still users showed preference for the former method. Furthermore, with regard to spoken feedback, the users were willing to use the app even though the quality of the voice was not natural. Overall, the mobile application developed was found to be usable and preferable. While the challenges were explored on the common basic features, it is believed that this work has laid a solid platform for future extensions.
  • Thumbnail Image
    Item
    Open Access
    Evaluation of the usability and usefulness of automatic speech recognition among users in South Africa
    (2011) Florence, Idowu Modupeola; Mbogho, Audrey J W
    An automatic speech recognition (ASR) system is a software application which recognizes human speech, processes it as input, and displays a text version of the speech as output or uses the input as commands for another application's usage. ASR can either be speaker-dependent or speaker-independent. A speaker-dependent ASR system required every user to perform training before its usage, while speaker-independent ASR requires no prior training before usage...This study involved the evaluation of commercially available English ASR systems, establishing their usability and usefulness among different language groups in South Africa which use English as a common language. Of particular interest was the effect of African accents on the performance of the ASR systems. ASR technology is widely used and researched in the developed world with reported recognition accuracy of up to 99%. However, English spoken with African accents may have adverse effect on the recognition accuracy...
  • Thumbnail Image
    Item
    Open Access
    Evaluation of the usability and usefulness of automatic speech recognition among users in South Africa [electronic resource]
    (2011) Idowu, Modupeola Florence; Mbogho, Audrey J W
    An automatic speech recognition (ASR) system is a software application which recognizes human speech, processes it as input, and displays a text version of the speech as output or uses the input as commands for another application’s usage. ASR can either be speaker-dependent or speakerindependent. A speaker-dependent ASR system requires every user to perform training before its usage, while speaker-independent ASR requires no prior training before usage. The technology of ASR is based on identification and comparison of sound patterns; these sound patterns are combinations of the smallest units of sound called phonemes. The phonemes constitute fragments of uttered sounds in speech and their combination gives meaningful sound patterns in languages. There exists a set of phonemes for every language group, and associated with each group is the method of pronunciation called the accent. A language group could be identified by the accent in their speech; accent is the set of pronunciation rules of a language group. Accent reflects the cultural divide of a multi cultural society with a common language such as English. Some commercially available ASR systems are designed based on the accents of the following language groups: English, French, German, Italian, Dutch, and Spanish. These language groups are European with none having any similarities with African languages and accents, (except Afrikaans and English, which, though spoken in Africa, originated from Proto-Indo-European languages). This study involved the evaluation of commercially available English ASR systems, establishing their usability and usefulness among different language groups in South Africa which use English as a common language. Of particular interest was the effect of African accents on the performance of the ASR systems. ASR technology is widely used and researched in the developed world with reported recognition accuracy of up to 99%. However, English spoken with African accents may have adverse effect on the recognition accuracy. Despite the fact that most existing ASR systems are not designed for English spoken with South Africans’ accents, one can easily purchase them over the shelf in South Africa. The systems used in this study are: 1. Nuance Dragon NaturallySpeaking, Version10.0 (NDNS). 2. Windows Speech Recognition, Windows Vista version (WSR). The result of this study indicated that accent has influence on the ASR recognition accuracy. It also indicated that users’ satisfaction was greatly affected by the recognition accuracy obtained. The results also indicated poor performance in environments where speech cannot be loud, for example, in the library.
  • Thumbnail Image
    Item
    Open Access
    Improving searchability of automatically transcribed lectures through dynamic language modelling
    (2012) Marquard, Stephen; Mbogho, Audrey J W
    Recording university lectures through lecture capture systems is increasingly common. However, a single continuous audio recording is often unhelpful for users, who may wish to navigate quickly to a particular part of a lecture, or locate a specific lecture within a set of recordings. A transcript of the recording can enable faster navigation and searching. Automatic speech recognition (ASR) technologies may be used to create automated transcripts, to avoid the significant time and cost involved in manual transcription.
  • Thumbnail Image
    Item
    Open Access
    Integrating contextmapping and interaction design: designing with and for small-scale urban farmers in Soweto
    (2015) Fenn, Terence Kevin; Mbogho, Audrey J W
    This thesis describes and reflects on the effectiveness of integrating contextmapping as both a methodology and interaction design practice in order to co-­design digital products with and for developing communities. A Design as research methodology is applied in this study within the specific contexts of a co-design project involving small-­scale urban farmers in Soweto. The final design outcomes of the project are the interaction design documents reflecting the design requirements of a mobile application as well as a low-level prototype demonstrating a number of the identified requirements contained in the documentation. The study assumes a human-centred design ethos that positions problems facing users as contextual, complex and indeterminate and requiring a degree of consideration and understanding by the designer before they can be resolved. The design process applied in this study therefore focused on gaining an understanding of the farmers' life experiences in order to design effective and empathetic technological solutions that will be meaningful and useful to the farmers. For this purpose, contextmapping and interaction design theory, methods and tools were integrated. Examples of this integration include the application of Hassenzahl's Three Level Hierarchy of Needs model to guide the exploration of the farmers' experiences and contexts, the use of contextmapping's Sensitization Phase and generative tools to generate user research data and lastly, contemporary interaction design tools such as problem-­ecology maps, personas and user-journey diagrams to develop and communicate design concepts to the farmers. The study concludes that this integration of contextmapping and interaction design is effective, in particular through its enablement of community participation in contributing meaningfully to the co-­design process while further ensuring that contributions made by the participants are relevant and actionable to the interaction design.
  • Thumbnail Image
    Item
    Open Access
    Investigating prediction modelling of academic performance for students in rural schools in Kenya
    (2016) Mgala, Mvurya; Suleman, Hussein; Mbogho, Audrey J W
    Academic performance prediction modelling provides an opportunity for learners' probable outcomes to be known early, before they sit for final examinations. This would be particularly useful for education stakeholders to initiate intervention measures to help students who require high intervention to pass final examinations. However, limitations of infrastructure in rural areas of developing countries, such as lack of or unstable electricity and Internet, impede the use of PCs. This study proposed that an academic performance prediction model could include a mobile phone interface specifically designed based on users' needs. The proposed mobile academic performance prediction system (MAPPS) could tackle the problem of underperformance and spur development in the rural areas. A six-step Cross-Industry Standard Process for Data Mining (CRISP-DM) theoretical framework was used to support the design of MAPPS. Experiments were conducted using two datasets collected in Kenya. One dataset had 2426 records of student data having 22 features, collected from 54 rural primary schools. The second dataset had 1105 student records with 19 features, collected from 11 peri-urban primary schools. Evaluation was conducted to investigate: (i) which is the best classifier model among the six common classifiers selected for the type of data used in this study; (ii) what is the optimal subset of features from the total number of features for both rural and peri-urban datasets; and (iii) what is the predictive performance of the Mobile Academic Performance Prediction System in classifying the high intervention class. It was found that the system achieved an F-Measure rate of nearly 80% in determining the students who need high intervention two years before the final examination. It was also found that the system was useful and usable in rural environments; the accuracy of prediction was good enough to motivate stakeholders to initiate strategic intervention measures. This study provides experimental evidence that Educational Data Mining (EDM) techniques can be used in the developing world by exploiting the ubiquitous mobile technology for student academic performance prediction.
  • Thumbnail Image
    Item
    Open Access
    System requirements for service quality appraisal system (SQAS) to be used in commercial banks by blind customers
    (2008) Banabotlhe, Mogomotsi; Mbogho, Audrey J W
    In a fast moving competitive sector like banking, the customer service department often finds it difficult to keep up with the pace at which customer concerns are raised. On the other hand, the speed at which this department responds to customer concerns determines the difference between keeping a customer and losing one. Thus, most banks have moved to technology to expedite the process of capturing and processing customer complaints. Unfortunately, not every customer serviced by these banks finds the deployed technologies accessible and usable. Among the customers who find technologies in the banks inaccessible and unusable are blind customers. In part, the inaccessibility of technologies used in banks may be attributed to poor requirements engineering. Poorly elicited requirements lead to the design of products which fail to satisfy the needs of the diverse population they service. The purpose of this project is to specify neatly validated requirements using the SMART criterion for a system that can be used to evaluate levels of customer satisfaction with services offered to them by banks. The envisaged system should be able to cater for the needs of the blind customers served by these banks. Data for the study was collected from blind people in a vocational school in Botswana, customer care managers in five different bank brands and the system designers. Data was collected through guided interview sessions, which on average lasted for thirty minutes per respondent. Data from the respondents was analyzed qualitatively and quantitatively. Data was summarized into tables, graphs, diagrams and charts to reveal trends. Data was further analyzed to specify the requirements of a system that allows blind customers to provide feedback to their banks. In an attempt to align the requirements to the specific needs of blind customers the specified requirements were reviewed and validated, guided by the principles of the SMART criterion.
  • Thumbnail Image
    Item
    Open Access
    Uncertain input estimation with application to Kalman tracking
    (2011) Nashenda, Hubert Tangee; Mbogho, Audrey J W
    Many motion tracking systems average and integrate tracking measurements over a period of time in order to reduce the effects of device noise, external noise and other disturbances. The target (user) is likely to be moving throughout the sample time, introducing additional 'noise' (uncertainty) into the measurements. Without filtering, noise can cause small variations in the estimated tracking positions (tracking drift) over time. There are many filters and algorithms that account for uncertainty due to noise. The Kalman filter has been chosen in this study because of its ability to estimate tracking positions and to account for uncertainty in the tracked object's position where it is occluded by other stationary or moving objects. An inexpensive algorithm is presented which detects the slightest motion and then tracks the motion or the target very accurately.
  • Thumbnail Image
    Item
    Open Access
    A weather related causal analysis on consolidated delay at Newark Liberty International Airport
    (2013) O'Loghlen, Gerald Philip; Mbogho, Audrey J W
    The closure of the European airspace due to the eruption of the Icelandic volcano Eyjafjallajokull in 2010 proved a major challenge for airlines and aviation authorities on a global scale. In contrast, more seasonal adverse meteorological conditions afflict many airports in the northern eastern seaboard of the United States. Newark Liberty International Airport (KEWR) is a representative airport that endures severe weather based delays. This dissertation explores the utilisation of Bayesian Networks (BN) and heuristic analyses to investigate weather based delays at Newark Liberty International airport (KEWR). In particular, it aims to understand which weather variables (namely, precipitation, visibility and wind) have the most impact on weather based delays at KEWR in contrast to past studies that have studied more generic weather phenomena (e.g. thunderstorms) at the same airport. An analysis using temporal functionality with Bayesian Networks (BN) software and heuristic analyses was conducted. Data extracted from weather and aviation based websites was extracted using software. The quality of the information was cross referenced with official data sources and validated using BN tools. The results revealed a causal correlation chain between crosswinds above a certain threshold and high delays at KEWR at various points in the experimentation. Though other meteorological elements examined had an impact on delays, airport authorities and airlines can mitigate these factors to a certain scale using Federal Aviation Authority (FAA) approved technology and training. Consequently, the implications could be significant on existing FAA and regional policy with Ground Delay Program (GDP) and Noise Abatement Procedures (NAP). These policies can be profound and far reaching for airlines, in terms of operating procedures and fuel cost implications. These findings can further alter the balance between efficiency, public safety and airline costing affecting all major stakeholders as this dissertation will investigate.