6th ANNUAL INTERNATIONAL CONFERENCE ON COMPUTING AND ICT RESEARCH - ICCIR 10
|View Full Text Document|
|Part One: Information Technology|
|Adele B., Darelle V., Arlien E.||A Mobile Human-Computer Interaction Perspective on Mobile Learning |Abstract
Applying a Mobile Human Computer Interaction (MMHCI) view to the domain of
education using Mobile Learning (MMlearning), the research outlines its understanding
of the influences and effects of different interactions on the use of mobile technology
in education.This research therefore evaluates specific mlearning projects,informed
and directed from a MHCI perspective.The objective of this would be to highlight
additional benefits,challenges,influences and effects of using mobile technology as
an ICT in education. This investigation has led our research to suggest additional
insights for MHCI and simultaneously provided a better understanding of the
development and implementation f mobiles in eaching and learning.
Categories and Subject Descriptors:H.1.2 [User/Machine Systems ]:Human Factors
and J.1 [Administrative data processing ]:Education
|Abanti Cyrus Makori and Laban Oenga||A Survey of Information Security Incident
Reporting for Enhanced Digital Forensic
This paper examined the extent of the breach of the organizations’ information security safeguards, analyzed whether they conduct cyber intelligence within the company,investigated the adherence of employees to Incident Response Plan [IRP ], and analyzed the application and users awareness of digital forensic techniques. Lastly the security incident reporting model was developed for adoption by novice users from eveloping countries like enya. The methodology employed to achieve the stated objective was the questionnaire designed, developed and distributed to twenty randomly selected sample populations. Two hypotheses were stated and tested using statistical tools. The ISO 17799 Theoretical Framework for security and control was adopted for this study. The research ound ut hat 70% f the employees were in greement hat reporting information security events and weaknesses is crucial to the well being of the organization while 30% disagreed. On the investigation about the existence of Incident Response Plan, 47.55% are aware but 15% conduct cyber intelligence against 65% who don’t know about computer forensic policies and procedures in The research survey was limited in a number of ways. The main limitation was that the research sample study was small hence the findings may not be generalized in.
|Fridah Katushemererwe (Ms), Thomas Hanneforth||Fsm2 nd the morphological nalysis of Bantu nouns – first experiences from
This paper describes the implementation of Finite State methods,fsm2 in particular, in automatic analysis of Bantu nouns in one of the under resourced languages, Runyakitara.This is the first effort towards computational analysis of Runyakitara.A detailed description of Runyakitara noun classes and how they were analysed using fsm2 is given.In the current state of developing the system,80%of Runyakitara nouns are correctly analysed.This is a positive step in confirming the success of fsm2 in the analysis of morphology of Bantu languages. Key words: Finite-SState methods, fsm2, morphological analysis, Bantu languages, Analysis f Runyakitara.
|Jennifer S.o, Dr. Peter J.||An artificial neural network model for
regulating legislative drafting practices in
This study presents how the legislative knowledge pertinent to the passage and/or consequently non passage of legislation is captured and processed using artificial neural network techniques.Qualitative data on the influence the environmental factors (ssocial, political, economical, cultural and other emerging factors) have on legislative drafting practices were collected given their role in determining Two classifier techniques,artificial neural networks and the nearest neighbour were trained using 200 legislative data and tested using 100 legislative data and the performance results were at 0.71 for the nearest neighbour technique and 0.72 for the artificial neural network for passable legislation.Artificial neural network model is proposed for purposes of this study given its performance and flexibility. Artificial Intelligence,Artificial Neural Network,Nearest Neighbour Classification,Legislative Drafting,Model,Optimization.
|Part Two: Information Systems|
|Michael M.,Emmanuel M., Joyce N.,Peter N.||Towards Web-based Productivity
Analysis and Reporting |Abstract
In this paper,we propose a Web-based Productivity Analysis and Reporting Tool (W-PART)for applications that necessitate gathering productivity data from remote sites for a given business entity.W-PART is aimed at reducing on productivity data entry and analysis workload from a central input point.Other benefits that we expect to realize from the tool include reduction of data loss and time taken entering productivity data. The tool is generally aimed for utilization by any given organization in a ‘developing area ’,but relies on availability of the Internet in any form.We report on the current status in the development of the tool and discuss its software implementation prospects.For the purpose of discussing different aspects concerning the tool,we use banks as a case study.We avail general implementation requirements for the tool which we expect should lead to a variety of options for implementation.
|Paul B. Muyinda, Jude L., Kathy L., Theo P.van der Weide||MOBILE LEARNING OBJECTS
DEPLOYMENT AND UTILIZATION IN
DEVELOPING COUNTRIES |Abstract
The increasing ability to access Internet via mobile devices means that learning objects can be deployed and utilized on those devices.Increasing research attention has been accorded to the design and development of reusable learning objects for tethered and mobile based learning management systems. Little research has been undertaken in regard to pedagogical models geared towards effective deployment and utilization of mLearning objects in different contexts and particularly of developing countries. This paper uses the Design Research approach to develop a UML based model for instantiating applications for deploying and utilizing learning objects on multi-generation rder mobile hones in eveloping countries of Africa. KEYWORDS mLearning,eLearning,mLearning Objects,Learning Objects,mLearning Object Model,mLearning Objects Utilization.
|Aminah Z., Jude L., Saul K., and Irene N.||Methodological Pluralism: And Emerging
Paradigmatic Approach to Information
Systems Research |Abstract
The alienation of information systems (IIS) research from practice is blamed on the dominance of the positivist paradigm which may not always produce practically relevant knowledge that is practicably adopted. To date most IS research is hinged on a positivist approach mainly because IS has evolved by adopting concepts from other disciplines that use the same paradigm for research. Research in IS however, is a multi-activity process that may require different research approaches. Use of mono-mmethods poses potential inadequacies in solving IS problems since strengths and weaknesses of various methods for the different stages of research differ. The purpose of using multi-method research is meant to address these potential drawbacks of the individual methods by exploiting the strengths of each method at the various stages of research. Analysis of the epistemological assumptions for each of the methods is therefore essential not only to establish the appropriateness of use of a method in a phase of research but also the compatibility of methods to be The strength of methodological pluralism therefore depends on how well the epistemological characteristics of the research methods are matched. This paper reviews leading works in IS research paradigms and proposes an approach that uses a matrix to guide methodological pluralism analysis which is the major contribution of the paper to literature.The matrix has a six phase logical flow criteria of analysis that can iteratively guide a user to decide whether or not to use methodological pluralism through sequencing or triangulation that is augmented by a similar logical flow chart.
|Mercy A.,Josephine N.,Henk G.||Decision Enhancement and Improving
Business Process Agility |Abstract
Achieving Business process agility requires organisations to be able to identify change in their business environment and respond promptly. In addition, they should be able to identify internal and external drivers for improvement. Business Process Management (BBPM) suites have thus been developed to support the business process lifecycle by enabling timely changes to be made on process models. However, most BPM suites give little attention to the decision process that takes place when analyzing a business process and deciding on how to improve it. This research therefore proposes to develop a platform (SStudio) that will provide an interactive environment to enhance the decision process involved in coming up with alternative solutions on how to improve the business process in response to changes,and identified internal and external drivers for improvement. The design science research method that emphasizes he utility’ f developed artifacts is ollowed during his research.
|Irene N., Dr.Ddembe W., Prof. Arco A.||Modeling Enterprise Information Systems
Integration Evaluation as
a Dynamic System |Abstract
With the increasing interoperation of information systems (ISs)within and between companies, the problem of Enterprise Application Integration (EEAI) is becoming increasingly challenging and pressing. This is attributed to the dynamic and rapid pace of emerging trends with a diversity of EAI solutions for business domains. Attaining a consummate EAI solution for a specific business domain is still a challenge to enhancing suitability analysis amongst a diversity of correct EAI solutions for specific business domains.Other researchers have established the interdependences between the EAI evaluation criteria factors; however, to the best of our knowledge, what is missing is a method to support feedback analysis between these factors to support complete evaluation of EAI solutions for business domains. In addition, most EAI evaluation methodologies provide insights from one or two evaluation perspectives and yet in reality, evaluation of EAI solutions should arise from an aggregate of various perspectives to enhance a comprehensive EAI solutions evaluation. Therefore, there is still lack of a holistic methodology that supports complete evaluation criteria factor analysis from the different stakeholder perceptives
|Part Three: ICT ustainableDevelopment|
|Walter O., Theo Vav Der Weide, Jude T.L.||Knowledge Management Research Using
Grounded Theory Strategy: Applicability,
Limitations and Ways Forward |Abstract
Knowledge management (KKM) is currently an emerging discipline in higher education, and its effective implementation is becoming a precondition for success in an increasingly globalized economy. Because it is interdisciplinary in nature, carrying out a research in KM requires that one uses appropriate research strategies that should be used to enable objectives of a study to be undertaken to be achieved. Based on review and analysis of available literatures, this paper looks at the paradigms in M research nd xamines in etails the applicability and limitations of grounded theory strategy in carrying out KM research. Using the explanation that KM research is a human activity system which requires both soft and hard systems methodologies to achieve study goals, a research methodological strategy is proposed for carrying out research to develop a framework for KM using ICT in higher ducation n Uganda s part f an n-going study. As well as contributing theoretically to the literatures on KM by providing insights into the applicability and limitations of grounded theory strategy in carrying out KM research, this paper further seeks to propose a methodological strategy that can be used n carrying ut imilar r related tudies. Keywords: Knowledge Management; Research Strategy; Grounded Theory; Applicability; Limitations
|Kasomo M. M., Njonjo R.W, Rodrigues A.J||LipaNet: Financial Services Integrated
Platform and Gateway Using
Mobile Technology |Abstract
This paper discusses LipaNet,an online platform that integrates different financial services and provides the infrastructure that allows these services to be easily accessed and used via mobile phone technology. LipaNet implements layered service architecture to integrate different mobile client technologies such as WAP,J2ME and SMS. As a gateway, it provides Application Programmers Interfaces (AAPIs) through web services to allow mobile clients to access financial services such as banking, money transfer, scrow nd ayment ervices. LipaNet was developed with the aim of providing financial services for those with mobile phones but who lacked access to such services as is the case in many African countries. It provides a secure means of branchless mobile banking for the largely unbanked population in Africa by allowing individuals to deposit and withdraw their funds, send and receive money and access escrow and payment facilities essential especially or mall nd edium Enterprises (SSMEs).. The technologies implemented, the model and architecture of the system, the design, development and implementation processes involved in building the system are highlighted.A comparison is also made with other mobile financial technology tools. Categories and Subject Descriptors:H.3.3 [Online Information Services ]:– Commercial Services;Data sharing;Web-based Services;J.1 [Administrative Data Processing ]:-Business;Financial;K.4.4 [Electronic Commerce ]-Cybercash, digital cash; Distributed commercial transactions; Electronic data interchange (EEDI); ayment chemes; ecurity; General Terms: esign, conomics, uman Aspects, ecurity Additional Key Words and Phrases:Integrated Platform,Gateway,mobile technologies,financial services.
|Ssemaluulu Paul, Muma Wycliff, Mwase Maria, Katongole Paul||Maternal Monitoring: Lowering Child Mortality by Use of ICTs |Abstract
In this paper, we describe the creation and development of an Electronic Health Records System that automates record keeping procedures for both patients and medical practitioners in a health facility. We also demonstrate how maternal monitoring by use of ICTs can lower child mortality in developing countries. It should be realized that lowering child mortality is one of the 8 Millennium Development Goals to be achieved by less developed countries by 2015. The Infant and Maternal Monitoring System (IMM System) seeks to lower infant mortality rates by encouraging pregnant women, as well as mothers to take their new born babies and infants to visit the nearest health centers for required healthcare checkups, vaccinations, or immunizations. This can be achieved through the creation and use of SMS functionality on the created system. This system improves communication and collaboration between medical practitioners through discussion forums, thus increasing the rapidity and quality of patient care Keywords: ICTs, Maternal, Mortality.
|Masuki, K. F. Ga*., Mowo, J. Gb., Kamugisha, Rc., Tanui, Jb., Tukahirwa, Ja and Adera E. Od.||INTEGRATED INFORMATION AND COMMUNICATION TECHNOLOGIES FOR FARM-LEVEL ACCESS TO
NATURAL RESOURCE MANAGEMENT INFORMATION: A CASE OF SOUTH WESTERN UGANDA |Abstract
Small-scale farmers inhabiting the highly dissected highlands in Kabale district, Uganda, lack access to appropriate information necessary to apply methods and technologies for sustainable land management for increased agricultural productivity. The farmers’ information needs are characteristically changing over time while access to information is often poor due to limitations in communication services. To address this shortcoming, African highlands Initiative (AHI) implemented a project which integrated information and communication technologies that connected farmers to appropriate information using multiple information sources and media including telecentres and village information centres. The centres were equipped with portable phones, printed materials like leaflets, brochures, pamphlets, research reports and books. This paper discusses the dynamics of using integrated information and communication technologies among smallholder farmers isolating challenges and opportunities while analysing insights associated with results patterns. Research findings showed that rural communities appreciated the use of integrated information and communication technologies as a convenient way to communicate and get desired information. Farmers were more excited about the use of phones than other information and communication technologies like radio and the print media. There was a dynamic use of mobile phones for accessing information at parish level. The radio messages also offered prices of selected commodities in different markets within the district and in other neighbouring towns in the region. The information enabled the farmers to bargain for higher produce prices. Print media were particularly useful for information on sustainable land management. Different print media in the form of leaflets, pamphlets, booklets and posters were developed both in English and local languages and disseminated to village information centres and telecentres. Key word: Integrated information and communication technologies, knowledge management, mobile phone, radio, print media.
|Florence Tushabe, Baryamureeba Venansius, Frida Katushemererwe||TRANSLATION OF THE
GOOGLE INTERFACE INTO RUNYAKITARA |Abstract
This paper describes how the first software localisation venture for the Runyakitara language i.e. the translation of Google interface into Runyakitara was accomplished. Runyakitara is a Bantu language that standardizes four linguistically closely-related languages of western Uganda which are Runyoro, Rukiga, Runyankore and Rutooro. The IT jargon was localized into terminologies that convert the original western material to better reflect African notions. This report describes how all the strings that are inbuilt in the Google interface were translated and how the new terminologies were formulated. It also highlights the major challenges that were encountered and provides some recommendations for future endeavors. Keywords Google, Runyakitara, localization, Ugandan languages, software translation, African language.
|Kiptalam, G.K, Rodrigues, A.J||ACCESSIBILITY AND UTILIZATION OF ICTS AMONG SECONDARY SCHOOL TEACHERS
IN KENYA |Abstract
This paper looks at levels of access and extent of use of Information and Communication Technologies (ICTs) among teachers in selected Kenyan secondary schools. For the past few years, an assortment of ICTs such as computers, lap tops, projectors, printers, e-blackboards and mobile phones have been available to teachers for use in integration of teaching and learning in schools. The paper attempts to establish how many teachers have access to the schools’ computers, their ICT literacy skills level and the level of ICT integration in subjects taught. The findings show that the use of ICT and its integration in the teaching and learning in secondary education is getting more widespread; and increasingly used among teachers as a means of communication and for information searching. Access rates for teachers have been observed to be much higher in educational institutions that have made effective ICT investments in education, translating into better utilization of ICT related technologies. Strategies have been suggested on how to utilize ICT to improve educational outcomes and recommendations given, on issues that touch on ICT access and infrastructure; human resources and training, policy environment, financing and ICT investment, curriculum development and locally relevant content.
|Anthony J. Rodrigues||Development Policy Coherence:
Can ICTs Facilitate? |Abstract
Unequal distribution and utilization of knowledge is a barrier to peaceful, sustainable development. Only if there is equitable access to knowledge will it be possible in the long term to balance differing interests and points of view. This balance of interests to achieve sustainable development is the goal to be realised In a globalised world, knowledge and information play an ever greater role in economic and social development. Development partnerships must respond to this process and adapt their policies and instruments accordingly. Underdeveloped countries must be suitably positioned to take advantage of the benefits arising from globalization whilst managing the risks. The opportunities for knowledge and information including ICTs that shape globalization are re-assessed. Information and Communication Technologies (ICTs) have spread quickly across East Africa and are regarded as essential to the region’s economic development, democratisation, social advancement, cultural progress, as well as for its global presence and competitiveness. The available statistics for Internet usage and mobile telephones – two of the newest technologies demonstrate the recent developments in ICTs in EAC region. In general, for an ICT Policy to be robust, relevant and effective, it needs to take a balance between: monopoly and competition ‘markets’, domestic and foreign ownership and controls, centralized and decentralized administrative controls, and also private and public initiatives. This would enable greater exploration of global advantages of ICT. The traditional self perception of development policy was the promotion of economic and social development in developing countries. Now, however, development policy is seen as having to be founded on the emergence of stable regional security partnerships Unequal distribution and utilization of knowledge is a barrier to peaceful, sustainable development. Only if there is equitable access to knowledge will it be possible in the long term to balance differing interests and points of view. This balance of interests to achieve sustainable development is the goal to be realised> In a globalised world, knowledge and information play an ever greater role in economic and social development. Development partnerships must respond to this process and adapt their policies and instruments accordingly. Underdeveloped countries must be suitably positioned to take advantage of the benefits arising from globalization whilst managing the risks. The opportunities for knowledge and information including ICTs that shape globalization are re-assessed. Information and Communication Technologies (ICTs) have spread quickly across East Africa and are regarded as essential to the region’s economic development, democratisation, social advancement, cultural progress, as well as for its global presence and competitiveness. The available statistics for Internet usage and mobile telephones – two of the newest technologies demonstrate the recent developments in ICTs in EAC region. In general, for an ICT Policy to be robust, relevant and effective, it needs to take a balance between: monopoly and competition ‘markets’, domestic and foreign ownership and controls, centralized and decentralized administrative controls, and also private and public initiatives. This would enable greater exploration of global advantages of ICT. The traditional self perception of development policy was the promotion of economic and social development in developing countries. Now, however, development policy is seen as having to be founded on the emergence of stable regional security partnerships.
|Part Four: Data Communication and Computer Networks|
|Grace Selah Penuel||“Saidia Mtoto,” Information Architecture Designed for
an Emergency Medical System
With the Involvement of
End Users |Abstract
This paper reports the results of an information architecture [ IA] designed for an emergency medical system with end user involvement in Nairobi, Kenya. The overall purpose of the design task was to help save infant lives thus reducing mortality. This was achieved by empowering parents to know what to do when an infant needs timely medical attention. Four methods were used. The first was benchmarking where the benchmarks were a First Aid kit for a heart defibrillator at Aalborg University in Denmark, and an information piece designed by Hvidovre hospital in Denmark to help new parents perform first aid for their new born babies. The second method used was interviewing the end users to determine schema that could be used for making the designed product easy to assimilate, while the third method was a task analysis to determine how the end users would interact with the finished Information Architecture product, and the fourth method was persona testing to see the contexts of use. The findings were that the IA designed was a good low cost solution to the problem of reducing infant mortality. One limitation of this work was that we had to rely on data collected through a mobile phone interview, which was expensive and at times posed a difficulty when interview questions had to be expounded to the interviewee. Another limitation was that the information ecology needed to be researched well, before introducing this IA change to the particular ecology, otherwise a “water hyacinth” problem could result in the future. Information ecology is defined as a system of people, practices, technologies, and values in a local environment.[Nardi and O'day 2000] The implications of this work is that there is great potential for IA on mobile phones to be designed for similar contexts to stimulate learning and information finding among target groups, who do not have access to expensive Internet connections. The limitations and implication of the Saidia Mtoto have necessitated the continuation into the second phase of this research work, where there is focus on the exploration of the information ecology. This research work has created avenues for using information architecture to fill gaps and provide solutions that reduce infant mortality among the low income target groups in Kenya and other African countries with related contexts. The demand for efficient communication to enable rapid action is most critical in emergency medical systems.
|Ruth M. Mutebi, Idris .A.Rai||An Integrated Victim-based Approach Against IP Packet Flooding
Denial of Service |Abstract
In this work, we designed a detection technique from a combination of three existing anomaly detection algorithms to detect attacks at the victim machine. The technique is a combination the cumulative sum algorithm (CUSUM), the source IP monitoring algorithm (SIM), and the adaptive threshold algorithm. It is made up of parallel and sequential steps where by the CUSUM and SIM algorithms are designed to work in parallel terms, while the adaptive threshold algorithm is run in case the results from the two (i.e., CUSUM and SIM) are conflicting. We used simulations to evaluate the performance of the proposed technique under various attack scenarios. The results show that the proposed integrated approach is capable of detecting a much wider range of attacks and even flash crowds, compared to the individual algorithms in isolation. Keywords: Denial of service (DoS) attacks, Anomaly detection Algorithms, Internet Protocol (IP), Transmission control Protocol (TCP), Hypertext transfer protocol (HTTP).
|Janet L., WESSON||Using Context-awareness to
Support Adaptive Multimodal Mobile
Multimodal mobile notification can enable natural and implicit notification in a mobile context by adapting the output modality according to the user’s context. There are several existing models for adaptive mobile notification using context awareness. A comparison of two of these models identified several shortcomings. The IBM INS model was selected as the most appropriate model and extended to support context history and mode switching. This paper discusses the proposed model for adaptive multimodal mobile notification together with the development of a prototype, called Mercury, based on this model. The aim of this research was to determine the usefulness and accuracy of adaptive multimodal mobile notification using the user’s context to adapt the mode of notification. Mercury was evaluated using an extensive field study conducted over a period of two months. The results obtained show that the users found the adaptive mobile notification service to be useful and accurate, but that they had some concerns about the level of interruptions. Categories and Subject Descriptors: H5.2 [Information Interfaces and Presentation]: User Interfaces - Evaluation/methodology; Graphical user interfaces; Interaction styles; Screen design; User-centered design General Terms: Human factors, Experimentation, Measurement, Verification, Design Key Words: adaptive systems, context-awareness, mobile notification services, multimodality, usability evaluation
|Lowu Francis Xavier||On Enhanced Patient Monitoring and Data
Analysis using Mobile Messaging Technology |Abstract
Health issues in developing countries are becoming more serious day by day, as different diseases attack and infect people making the public health sector overwhelmed. This has made it difficult for healthy workers to accurately study the trend of different diseases in many cases, thus failing to analyze the way patients behave after being diagnosed. At the same time there is an increased use of mobile information technology gadgets in this wireless communication error, which can be used as a way to minimize on the gap between health centers and patients. Monitoring and evaluation also becomes a problem as most of the health centers in the country luck personnel that can analyze the collected data to effectively give reports that reflect what is on the ground. In this paper we propose the use of mobile messaging technologies facilitated through a health management system (HMS) to enhance health monitoring and patient data analysis. The study, groups patients depending on their complications and each group is given a health access key (HAKEY) which is used on mobile phones and other mobile wireless communication systems to access patient information from the health centers. Patients reply to the health workers’ request via short message services (SMS). We find that this mobile information technology facilitates the health workers with information which they use to effectively monitor and evaluate health performance of different patients in a short time. Keyword: Mobile Messaging Technology, Wireless Communication, Patient, Health Monitoring, Information Technology.
|Joseph M. Kizza, Lindsay Bramlett and Elizabeth Morgan||Using Subgraph Isomorphism as a Zero Knowledge Proof Authentication in Timed Wireless Mobile Networks |Abstract
In networks with sensitive resources and time critical missions, user identification and authentication is essential and critical for all secure access communications originating from outside into the networks. However, there are networks and times when entity identification is not required and indeed in some networks, for the security of the outside entity seeking authentication, identity must not be revealed thus preserving the secrecy and privacy of such entities. Zero knowledge protocol (ZKP) using subgraph isomorphism to authenticate new entities requiring entry into existing mobile network while preserving entity privacy and identity works well in these instances.
|Part Five: Computer Science|
|Wangunyu P.W, Opiyo E.T.O and Rodrigues A.J.||License Plate Recognition System: Localization for Kenya |Abstract
This paper describes the development of a reliable and accurate License Plate Recognition (LPR) system. In view of its potential application in traffic monitoring systems and highway toll collection, LPR systems have recently attracted considerable interest as part of an Intelligent Transport System. While much commercial work has been done for Iranian, Korean, Chinese, European and US license plates, little work has been done for developing country LPR systems [Jameel 2003]. In general LPR consists of four stages; Image acquisition and processing, License plate extraction, License plate segmentation and License plate recognition. This paper utilizes algorithms for the extraction stage, based on vertical edge detection. The segmentation stage is performed using two algorithms: division by eight and the horizontal and vertical projection profile also known as the peak to valley method. Finally two approaches of performing recognition are investigated, namely, template matching and artificial neural networks, particularly the multilayer perceptron. The system was implemented using Matlab 7.6 (R2008a), Microsoft Visual Studio and Wamp Server tools. The performance of the system on about seventy real images resulted in a predictive accuracy of about 86.99% using the template matching recognition algorithm after segmenting with the peak to valley method. Due to time and resource constraints, this application was not able to cater for foreign and special license plates. However, its development is a big step forward in our country Kenya in terms of technology and if deployed to the different application areas, it would be of great benefit. This is in terms of revenue collection and enforcing security. Keywords Plate Localization, Connected Component Analysis, Segmentation, Vertical Projection Profile, Template Matching, Peak to Valley, Optical Character Recognition.
|Zablon O. Ochomo, Elisha Opiyo, William Okello-Odongo||AGENT BASED MODEL FOR LOCALIZED SECURE PAYMENT SYSTEMS INTEGRATION |Abstract
In East Africa and Africa in general, we have several innovations in the payments processing sector that are each aimed at solving a critical business function. Currently, we have payment systems such as mobile payment systems from Telco providers, instant remittance systems, card based payment systems from banks, Electronic Funds Transfer systems and Real Time Gross Settlement systems. Each type of payment systems has its own standards and protocols for integration to client facing applications. Mobile payment systems use telecommunication protocols such as: GSM, SMPP, CDMA, GPRS, and microwave. Card based systems use protocols meant for secure card payments such as: magnetic strip cards and smart/chip cards. Electronic Funds Transfer use interchange specification formats that are based on ISO 8583 standards. To tackle the issue of incompatibilities among the above diverse protocols, this paper explores an agent-based model for coordination and its impact in unifying payments from various industries. In this paper, an agent-based model for coordination is designed and an illustration on how to use open source tools such as: jPOS, Java and XML to implement such models. Categories and Subject Descriptors: I.2. [ARTIFICIAL INTELLIGENCE]: Distributed Artificial Intelligence - Coherence and coordination; Intelligent agents; Multiagent systems; K.4.4 [Electronic Commerce]: Distributed commercial transactions General Terms: Online payments, Real Time Gross Settlement, ISO 8583, Electronic Funds Transfer, agent coordination * Zablon O. Ochomo (firstname.lastname@example.org), Elisha Opiyo (email@example.com), William Okello-Odongo (firstname.lastname@example.org), School of Computing and Informatics, University of Nairobi, P.O. Box 30197-00100, Nairobi, Kenya.
|Jennifer Rose Aduwo and Acellam Guy||Assessing the Performance of two Artificial Neural Networks in the Classification of Cassava Mosaic Disease |Abstract
Cassava Mosaic disease (CMD) has caused severe losses to cassava production, In Uganda, production losses due to CMD is estimated at US$ 60 million annually and region wide losses in East Africa have been estimated in excess of US$ 100 million annually. The impact of the CMD is food security crisis and widespread poverty in districts where cassava is used for food crop and commercial purposes. To enhance the management of the CMD pandemic, timely information about the disease is required. Such information currently takes long to be obtained due to problems with the availability of competent staff and coordination of paper reports. Yet timely information on the health of cassava plants is vital for the proper management of the disease in the country. In this paper, we propose a classification system based on Artificial Neural Network (ANN) techniques to provide a more efficient solution. We compare the relative performances of two approaches (multi-layer perceptron (MLP) and radial basis neural network (RBNN) built using matlab R2007. The data used in the study came from the C3P field survey of pests and disease of six districts in Eastern Uganda, collected by Namulonge Crops Resources Research Institute in 2007. It was divided into training and testing data sets. We used the number of white fly nymphs, number of white fly Adults, extent of white fly damage, sooty mould severity and CMD severity as inputs to the ANN models. We found that RBNN performed better than MLP on this data. The performance of the models was evaluated using mean square error (MSE) and the Receiver operating characteristics (ROC) curve. The results indicate that MLP and RBNN computing techniques can be employed successfully in the classification of CMD data. Keywords: Cassava Mosaic Disease (CMD), Artificial Neural Networks (ANN),Multi-layer perceptron(MLP),Radial Basis Function Neural Network(RBFNN).
|Lawrence Mukhongo1, Riham Khalil1, David D.J. Stockton1 and Maria M.J. Schilstra2||Finite Capacity Scheduling –
Borrowing the Best Practices of
Biological Control |Abstract
Rules governing scheduling and sequencing have accumulated overtime, driven by the manufacturing firms quest for improved operations against key performance metrics. While lead time dictates the need to preserve a focus on manufacturing efficiency, these needs must be balanced with demand-driven requirements especially at the process level, based on the finite capacity that is true of real systems. Investigation into the processes of biological systems presents an intriguing way to investigate how autonomous decision making can be improved in industrial operation systems. There are a number of reasons for this, (i) biological systems are easy to conceptualise, (ii) they have been well characterised and (iii) the study of their operations has produced abundant genomic data currently available that has led to the construction of genomic-scale models of microbial metabolism. Most importantly though, protein synthesis for gene expression in biological systems is a highly autonomous process and it is this inherent ability to self regulate that is of acute interest to the industrial operations engineer. Increasing levels of autonomous decision making will be required when designing, planning and controlling the manufacturing process in order to respond effectively to changes in increasingly competitive market and service environments. This paper describes a framework for the development of an algorithm using biological control to aid in enabling autonomous decision making functionality in operations planning in manufacturing and service industry. Key words: Gene transcription and translation, Biological control, finite capacity scheduling, manufacturing parameters, Gene regulation, discrete event simulation, biological processes.
|Ernestr M., John Q.||Finding Predictive Relationships Between Notifi able Diseases with Markov Blanket Discovery |Abstract
Most countries collect surveillance data at least weekly on several notifiable diseases. This data is to inform policy formulation as well as aid in forward planning. Knowing the relationships between these diseases is not only helpful for preventative planning but for predictive purposes as well. In this paper we present a computational method for analysing the relationships that exist amongst these diseases. We employ the Incremental Association-Based Markov Blanket algorithm to find sets of mutually informative diseases with high predictive power in a dataset covering the 80 districts of Uganda. Results indicate sufficiency of our methods in obtaining non-spurious relationships amongst notifiable diseases. The predictive relationships we identify could be used to improve the accuracy of existing disease monitoring systems. Categories and Subject Descriptors: I.2.1 [Computing Methodologies]: Artificial Intelligence– Medicine and Science. General Terms: Disease Association learning, Causal Analysis, Markov Blanket Analysis, Notifiable diseases, Biosurveillance.
|Jean V., , Magda H.||Investigating
E-government Knowledge Base Ontology Supporting Development Projects Monitoring in Sub Saharan Africa |Abstract
In recent years, a number of developed countries have employed ontology in e-government projects. On the other hand, Sub Saharan African (SSA) countries have followed the trends towards e-government and adoption of new technologies during the past eight years, resulting in many applications developed in various government departments. However, little work has been done in building knowledge base ontologies that facilitate communication amongst stakeholders and that specify processes and data description of these applications; thereby, guaranteeing their maintainability, interoperability and sustainability. This paper presents a case study of constructing ontology in support of e-government initiatives in the domain of development projects monitoring in a Sub Saharan African country. Case studies of development projects conducted in different SSA countries as well as related published works in various fields including project management, project monitoring and evaluation, and capacity building are reviewed and the features of the ontology are extracted. The main purposes of the ontology encompass; providing developers of potential e-government applications for development projects monitoring in Sub Saharan Africa and the developing world at large, with key concepts and activities of the domain, facilitating communication amongst all the role players involved in development projects implementation by providing a common and shared representation of concepts and activities of the domain, and serving as a knowledge base system to the monitoring and evaluation activities of development projects - thereby, strengthening efficiency, effective and sustainable implementation of development projects in Sub Saharan Africa. Further, the study aims at sensitizing and serving as a practical case study of building ontology in support of e-government adoption processes in Sub Saharan Africa. Categories and Subject Descriptors: J.1 [Computer Applications]: General; D.2.10 [Software Engineering]: Design - Methodologies; Representation Additional Key Words: E-government, Ontology, Knowledge Base System, Development Project, Protégé
|Richard Ssekibuule||Shilling Countermeasures in
Autonomic E-Markets |Abstract
Electronic transactions have become the norm for the modern world. Development of new digi¬tal technologies are transforming business paradigms and creating new opportunities for Internet based trading. New developments in autonomic systems are already replacing roles previously played by humans in trading activities such as product identifi cation, negotiation and decision making. In addition to creating new possibilities for electronic trading, new challenges related to digital security have emerged as well. Shilling is the process through which syndicating individuals help other individuals or organizations to sell or promote their goods or services. This article eval¬uates the state-of-the-art techniques for detecting and preventing shilling in autonomic electronic markets. We further present similarities between auction markets and reputation systems in the perspective of shilling attacks. Various threats that are usually mounted in electronic bidding and reputation systems are presented and possible countermeasures discussed. Effectiveness of shilling detection and prevention techniques is analyzed and improvements suggested. Categories and Subject Descriptors: D.2.7 [Computer Science]: Expert and Intelligent Systems; H.4.0 [Security]: Shilling—Countermeasures; I.7.2 [Electronic Markets]: Autonomic General Terms: Auction; Reputation; Shilling; Autonomic