inproceedings by Lebeko Poulo
IST-Africa Conference 2015, 2015
This paper outlines the use and applications of data mining in the health sector, tailor-made for... more This paper outlines the use and applications of data mining in the health sector, tailor-made for the land-locked Lesotho, in Southern Africa. The concepts discussed in this paper can easily be modified to fit several industries; higher education, the legal sector, the retail and telecommunications industries and the insurance sector. Healthcare management can be improved immensely with the use of data mining. The goal of our study is to discover patterns in the HIV/AIDS treatment among patients in Lesotho. Close monitoring of the disease progression is the most vital aspect as far as curbing fatalities is concerned. Using data mining tools, detailed patient information and treatment records can be used to determine if the course of treatment will work in order to keep a patient alive for a longer period of time.
SAICSIT Conference 2014, 2014
Modern digital library systems are increasingly handling massive data volumes; this content needs... more Modern digital library systems are increasingly handling massive data volumes; this content needs to be stored, indexed and made easily accessible to end users. Cloud computing promises to address some of these needs through a set of services that arguably support scalability of service provision. This paper discusses a set of experiments to assess the scalability of typical digital library services that use cloud computing facilities for core processing and storage. Horizontal scalability experiments were performed to benchmark the overall performance of the architecture with increasing load. The results of the experiments indicate that stable response times and some degree of variability are attainable due to multiple middleware servers when browsing and/or searching a collection of a fixed size. There is minimal variation in response times when varying collection sizes and equally after the caching phases. Most importantly, request sequencing proved that the quantity and age of requests have no impact on response times. The experimental results thus provide evidence to support the feasibility of building and deploying cloud-based Digital Libraries.
ZA-WWW 2009 Conference , 2009
Many human languages, an essential part of culture, are in danger of extinction. UNESCO estimates... more Many human languages, an essential part of culture, are in danger of extinction. UNESCO estimates that at least a half of the world's 6500 spoken languages will disappear within the next 100 years. This problem can be addressed to some extent by computer systems that collect, archive and disseminate dictionaries for various languages, thus performing the key function of preservation. The approach taken in this project was to develop a Web-based multilingual thesaurus, with mechanisms for the submission and retrieval of language data and metadata. This thesaurus was built on top of the FEDORA Web-based digital repository toolkit. Two distinct user interfaces were then developed as part of a proof of concept language preservation system, namely a Web interface and a cell phone interface. These were created using AJAX and J2ME+GPRS respectively. Both user interfaces were designed using an iterative User-Centred Design approach, and the back-end system was designed to meet the needs of the user interfaces, with a Web-based API. The resulting system proved to be useful as users indicated that they could preserve spoken languages by submitting and retrieving words in their own languages. The independent successful evaluations of the 2 user interfaces together demonstrate the feasibility of creating a preservation-directed archive as a layered Web-based digital repository, where the preservation function is separable and accessible through a well-defined Web-based API.
reports by Lebeko Poulo
Honours Project Report, 2008
There are several endangered languages around the world, some of which are now
almost extinct. T... more There are several endangered languages around the world, some of which are now
almost extinct. This leads to the loss of important elements of culture over the years. This can be addressed by computer systems that collect, archive and disseminate dictionaries for various languages. The aim of this project is to develop a Web-based system that collects and preserves languages. The system enables submission and retrieval of language data and metadata and comprises two interfaces, namely the Web interface and the Cellphone interface, both connecting to the back-end for archiving of language data and metadata. This report elaborates on the design, implementation and evaluation of the Cellphone interface.
The User-Centered Design (UCD) method was used in the design of the system. The Cellphone interface was implemented using the Java Micro Edition (J2ME) technology. J2ME was compared to other mobile development environments and was chosen for the development of the Cellphone interface as it is a cross-platform technology that exists on di fferent handsets.
The Cellphone interface was tested using black-box software testing methodology and evaluated through user testing. The results of interface evaluation showed that the interface was usable and users were able to submit and retrieve words to/from the system. Despite its flaws, as revealed by user evaluation, the system met its intended goals.
Work-in-progress paper by Lebeko Poulo
SAICSIT M&D Symposium, 2009
Digital libraries communities are working to increase the amount of data and information availabl... more Digital libraries communities are working to increase the amount of data and information available to ever-larger numbers of researchers, namely students and scholars. With an increasing use of information in recent years, the standard tools available for managing information cannot cope well and there is a need for new techniques to continue to provide useful and innovative services to users. This paper proposes an investigation into how information management systems can be made scalable by transparently using cloud/elastic computing resources efficiently and on-demand. To do this different cloud computing architectures will be studied, implemented and evaluated to decide on the one best suited to digital libraries.
Papers by Lebeko Poulo
Many human languages, an essential part of culture, are in danger of extinction. UNESCO estimates... more Many human languages, an essential part of culture, are in danger of extinction. UNESCO estimates that at least a half of the world's 6500 spoken languages will disappear within the next 100 years. This problem can be addressed to some extent by computer systems that collect, archive and disseminate dictionaries for various languages, thus performing the key function of preservation. The approach taken in this project was to develop a Web-based multilingual thesaurus, with mechanisms for the submission and retrieval of language data and metadata. This thesaurus was built on top of the FEDORA Web-based digital repository toolkit. Two distinct user interfaces were then developed as part of a proof of concept language preservation system, namely a Web interface and a cell phone interface. These were created using AJAX and J2ME+GPRS respectively. Both user interfaces were designed using an iterative User-Centred Design approach, and the back-end system was designed to meet the needs...
Cloud computing for digital libraries
Information management systems (digital libraries/repositories, learning management systems, cont... more Information management systems (digital libraries/repositories, learning management systems, content management systems) provide key technologies for the storage, preservation and dissemination of knowledge in its various forms, such as research documents, theses and dissertations, cultural heritage documents and audio files. These systems can make use of cloud computing to achieve high levels of scalability, while making services accessible to all at reasonable infrastructure costs and on-demand. This research aims to develop techniques for building scalable digital information management systems based on efficient and on-demand use of generic grid-based technologies such as cloud computing. In particular, this study explores the use of existing cloud computing resources offered by some popular cloud computing vendors such as Amazon Web Services. This involves making use of Amazon Simple Storage Service (Amazon S3) to store large and increasing volumes of data, Amazon Elastic Compu...
Applications of data mining in the health sector in Lesotho: A preliminary study
2015 IST-Africa Conference, 2015
This paper outlines the use and applications of data mining in the health sector, tailor-made for... more This paper outlines the use and applications of data mining in the health sector, tailor-made for the land-locked Lesotho, in Southern Africa. The concepts discussed in this paper can easily be modified to fit several industries; higher education, the legal sector, the retail and telecommunications industries and the insurance sector. Healthcare management can be improved immensely with the use of data mining. The goal of our study is to discover patterns in the HIV/AIDS treatment among patients in Lesotho. Close monitoring of the disease progression is the most vital aspect as far as curbing fatalities is concerned. Using data mining tools, detailed patient information and treatment records can be used to determine if the course of treatment will work in order to keep a patient alive for a longer period of time.
Proceedings of the Southern African Institute for Computer Scientist and Information Technologists Annual Conference 2014 on SAICSIT 2014 Empowered by Technology - SAICSIT '14, 2014
Modern digital library systems are increasingly handling massive data volumes; this content needs... more Modern digital library systems are increasingly handling massive data volumes; this content needs to be stored, indexed and made easily accessible to end users. Cloud computing promises to address some of these needs through a set of services that arguably support scalability of service provision. This paper discusses a set of experiments to assess the scalability of typical digital library services that use cloud computing facilities for core processing and storage. Horizontal scalability experiments were performed to benchmark the overall performance of the architecture with increasing load. The results of the experiments indicate that stable response times and some degree of variability are attainable due to multiple middleware servers when browsing and/or searching a collection of a fixed size. There is minimal variation in response times when varying collection sizes and equally after the caching phases. Most importantly, request sequencing proved that the quantity and age of requests have no impact on response times. The experimental results thus provide evidence to support the feasibility of building and deploying cloud-based Digital Libraries.
The approach taken in this project was to develop a Web-based multilingual thesaurus, with mechan... more The approach taken in this project was to develop a Web-based multilingual thesaurus, with mechanisms for the submission and retrieval of language data and metadata. This thesaurus was built on top of the FEDORA Web-based digital repository toolkit. Two distinct user ...
Proceedings of the Southern African Institute for Computer Scientist and Information Technologists Annual Conference 2014 on SAICSIT 2014 Empowered by Technology - SAICSIT '14, 2014
Modern digital library systems are increasingly handling massive data volumes; this content needs... more Modern digital library systems are increasingly handling massive data volumes; this content needs to be stored, indexed and made easily accessible to end users. Cloud computing promises to address some of these needs through a set of services that arguably support scalability of service provision. This paper discusses a set of experiments to assess the scalability of typical digital library services that use cloud computing facilities for core processing and storage. Horizontal scalability experiments were performed to benchmark the overall performance of the architecture with increasing load. The results of the experiments indicate that stable response times and some degree of variability are attainable due to multiple middleware servers when browsing and/or searching a collection of a fixed size. There is minimal variation in response times when varying collection sizes and equally after the caching phases. Most importantly, request sequencing proved that the quantity and age of requests have no impact on response times. The experimental results thus provide evidence to support the feasibility of building and deploying cloud-based Digital Libraries.
Uploads
inproceedings by Lebeko Poulo
reports by Lebeko Poulo
almost extinct. This leads to the loss of important elements of culture over the years. This can be addressed by computer systems that collect, archive and disseminate dictionaries for various languages. The aim of this project is to develop a Web-based system that collects and preserves languages. The system enables submission and retrieval of language data and metadata and comprises two interfaces, namely the Web interface and the Cellphone interface, both connecting to the back-end for archiving of language data and metadata. This report elaborates on the design, implementation and evaluation of the Cellphone interface.
The User-Centered Design (UCD) method was used in the design of the system. The Cellphone interface was implemented using the Java Micro Edition (J2ME) technology. J2ME was compared to other mobile development environments and was chosen for the development of the Cellphone interface as it is a cross-platform technology that exists on di fferent handsets.
The Cellphone interface was tested using black-box software testing methodology and evaluated through user testing. The results of interface evaluation showed that the interface was usable and users were able to submit and retrieve words to/from the system. Despite its flaws, as revealed by user evaluation, the system met its intended goals.
Work-in-progress paper by Lebeko Poulo
Papers by Lebeko Poulo