Search

There are abundance of existing biomedical ontologies such as the National Cancer Institute\ud Thesaurus (NCIT), the Foundational Model of Anatomy (FMA) and the Systematized\ud Nomenclature of Medicine-Clinical Terms (SNOMED CT). Implementing these ontologies in\ud a particular system however, may cause unnecessary high usage of memory and slows down\ud the systems’ performance. On the other hand, building a new ontology from scratch will\ud require additional time and efforts. Therefore, this research explores the ontology reuse\ud approach in order to develop an Abdominal Ultrasound Ontology (AUO) by extracting\ud concepts from existing biomedical ontologies. This paper presents the reader with a step by\ud step method in reusing ontologies together with suggestions of the off-the-shelf tools that can\ud be used to ease the process. The result shows that ontology reuse is beneficial especially in\ud the biomedical field as it allows for developers from the non-technical background to build\ud and use domain specific ontology with ease. It also allows for developers with technical\ud background to develop ontologies with minimal involvements from domain experts. The\ud methodology proposed is also adaptable as it allows the ontology to be updated fairly easily.

The examination of plantar fascia (PF) ultrasound (US) images is subjective and based on the visual perceptions and manual biometric measurements carried out by medical experts. US images feature extraction, characterization and classification have been widely introduced for improving the accuracy of medical assessment, reducing its subjective nature and the time required by medical experts for PF pathology diagnosis. In this paper, we develop an automated supervised classification approach using the Support Vector Machine (Linear and Kernel) to distinguishes between symptomatic and asymptomatic PF cases. Such an approach will facilitate the characterization and the classification of the PF area for the identification of patients with inferior heel pain at risk of plantar fasciitis. Six feature sets were extracted from the segmented PF region. Additionally, features normalization, features ranking and selection analysis using an unsupervised infinity selection method were introduced for the characterization and the classification of symptomatic and asymptomatic PF subjects.\ud \ud The performance of the classifiers was assessed using confusion matrix attributes and some derived performance measures including recall, specificity, balanced accuracy, precision, F-score and Matthew’s correlation coefficient. Using the best selected features sets, Linear SVM and Kernel SVM achieved an F-Score of 97.06 and 98.05 respectively.

In this paper, we make freely accessible ANETAC, our English-Arabic named entity transliteration and classification dataset that we built from freely available parallel translation corpora. The dataset contains 79, 924 instances, each instance is a triplet (e, a, c), where e is the English named entity, a is its Arabic transliteration and c is its class that can be either a Person, a Location, or an Organization. The ANETAC dataset is mainly aimed for the researchers that are working on Arabic named entity transliteration, but it can also be used for named entity classification purposes. This dataset was developed and used as part of a previous research study done by Hadj Ameur et al. [1].

The abundance of biomedical ontologies is beneficial to the\ud development of biomedical related systems. However, existing biomedical\ud ontologies such as the National Cancer Institute Thesaurus (NCIT),\ud Foundational Model of Anatomy (FMA) and Systematized Nomenclature\ud of Medicine-Clinical Terms (SNOMED CT) are often too large to be\ud implemented in a particular system and cause unnecessary high usage of\ud memory and slow down the system’s processing time. Developing a new\ud ontology from scratch just for the use of a particular system is deemed as\ud inefficient since it requires additional time and causes redundancy. Thus,\ud a potentially better method is by reusing existing ontologies. However,\ud currently there are no specific methods or tools for reusing ontologies.\ud This paper aims to provide readers with a step by step method in reusing\ud ontologies together with the tools that can be used to ease the process.

Despite the development and the wide use of E-Learning,\ud developing an adaptive personalised E-Learning system tailored to the\ud needs of individual learners remains a challenge. In an early work, the\ud authors proposed APELS that extracts freely available resources on\ud the web using an ontology to model the leaning topics and optimise\ud the information extraction process. APELS takes into consideration the\ud leaner’s needs and background. In this paper, we developed an approach\ud to evaluate the topics’ content extracted previously by APELS against a\ud set of learning outcomes as defined by standard curricula. Our validation\ud approach is based on finding patterns in part of speech and grammatical\ud dependencies using the Stanford English Parser. As a case study, we use\ud the computer science field with the IEEE/ACM Computing curriculum\ud as the standard curriculum.

Artificial intelligences techniques such as knowledge based systems, neural networks, fuzzy logic and data mining have been advocated by many researchers and developers as the way to improve many of the software development activities. As with many other disciplines, software development quality improves with the experience, knowledge of the developers, past projects and expertise. Software also evolves as it operates in changing and volatile environments. Hence, there is significant potential for using AI for improving all phases of the software development life cycle. This chapter provides a survey on the use of AI for software engineering that covers the main software development phases and AI methods such as natural language processing techniques, neural networks, genetic algorithms, fuzzy logic, ant colony optimization, and planning methods

Polarity estimation in large-scale and multi-topic domains is a difficult issue. Most state-of-the-art solutions essentially rely on frequencies of sentiment-carrying words (e.g., taken from a lexicon) when analyzing the sentiment conveyed by natural language text. These approaches ignore the structural aspects of a document, which contain valuable information. Rhetorical Structure Theory (RST) provides important information about the relative importance of the different text spans in a document. This knowledge could be useful for sentiment analysis and polarity classification. However, RST has only been studied for polarity classification problems in constrained and small scale scenarios. The main objective of this paper is to explore the usefulness of RST in large-scale polarity ranking of blog posts. We apply sentence-level methods to select the key sentences that convey the overall on-topic sentiment of a blog post. Then, we apply RST analysis to these core sentences in order to guide the classification of their polarity and thus to generate an overall estimation of the document’s polarity with respect to a specific topic. Our results show that RST provides valuable information about the discourse structure of the texts that can be used to make a more accurate ranking of documents in terms of their estimated sentiment in multi-topic blogs.

Specifications provide the foundation upon which a system can be formally developed. If a specification is wrong, then no matter what method of design is used, or what quality assurance procedures are in place, they will not result in a system that meets the requirements. The specification of a system involves people of different profiles who favour different representations. At the beginning natural language is used because the specification document acts as a contract between the user and the developers. Most of the time, the only representation that users understand and agree on is natural language. At the other end, developers find natural language specifications ambiguous and incomplete and may therefore prefer formal specifications. The transition from informal specifications to formal ones is an error prone and time consuming process. This transition must be supported to ensure that the formal specifications are consistent with the informal ones. In this research we propose an interactive approach for producing formal specifications from English specifications. The approach uses research in the area of natural language understanding to analyse English specifications in order to detect ambiguities. The method used for analysing natural language text is based on McCord’s approach. This method consists of translating natural language sentences into a logical form language representation. This helps to identify ambiguities present in natural language specifications and to identify the entities and relationships. These entities and relationships are used as a basis for producing VDM data types. We also investigate the production of data type invariants for restricted sentences and the production of some common specifications. We test our approach by implementing it in Prolog-2 and apply it to an independent case study.

Privacy has been identified by many studies as the main problem why customers are not completing their online transactions. They fear to provide sensitive information such as personal and financial details. It is not surprising that most websites nowadays include privacy statements in their websites to encourage customers to complete their transactions. However, only few customers can find this information easily on merchants’ websites rendering the use of this information obsolete. The aim of this paper is two folds. First it identifies the link or document dealing with private policies on the website for the customer to consult. However, as the current research shows, these documents are long, tedious to read and contain information that may not be relevant to customers. The second aim of this paper is to automatically extract the most relevant information to the customer in the form of short statement. These statements include information on sharing and selling of personal details, the use of secure technologies, customer satisfaction with the goods purchased, the use of cookies and unsolicited communications. We use the Semantic distance similarity model as the basis to develop the information extraction component.

Le carcinome tubulo-mucineux et fusiforme de bas grade de malignité est une tumeur rare décrite comme entité nouvelle dans la classifi cation OMS 2004. Nous rapportons le cas d\'une femme de 42 ans qui s\'est présentée à la consultation pour des lombalgies chroniques gauche et chez qui l\'examen tomodensitométrique a révélé la présence d\'une masse rénale gauche de 10 cm de grand axe. La patiente a été traitée par néphrectomie élargie gauche dont l\'examen macroscopique a montré la présence d\'une tumeur médio-rénale bien limitée de 8,2 cm de grand axe d\'aspect charnu avec des remaniements hémorragiques et nécrotiques. L\'évaluation microscopique a confi rmé qu\'il s\'agissait d\'un carcinome tubulo-mucineux et à cellules fusiformes aux contours non infi ltrants sans envahissement du hile. L\'étude immunohistochimique a révélé une positivité à la CK (KL1), CK7, CK20, EMA, vimentine et CD15 et une négativité au CD10. Le but de notre travail est de rapporter un cas de cette entité rare dont la reconnaissance par les pathologistes et les cliniciens est primordiale, en raison de son évolution tout à fait favorable. Keywords: Rein, carcinome rénal, tubulo-mucineux, fusiforme, bas grade, immunohistochimieAfrican Journal Of Urology Vol.14 (3) 2007: pp. 179-183

No Abstract. African Journal of Urology Vol. 12(2) 2006: 111-114

No Abstract. African Journal of Urology Vol. 12(1) 2006: 51-54

No Abstract.African Journal of Urology Vol. 11(4) 2005: 323-325

No Abstract. African Journal of Urology Vol. 11(3) 2005: 250-252

Lack of trust has been identified as one of the reasons why many visits to eCommerce\ud websites do not turn into proper transactions. To support trust, an information framework\ud model based on research on eCommerce trust has been developed. The model identifies\ud the kind of information a consumer expects to find on an eCommerce website and that is\ud shown to increase his trust toward the online merchant. An information extraction system\ud has been developed to help gather the required information from the websites. In this\ud paper, we first validate the information model through a questionnaire using a consumer\ud sample. This is then followed by an evaluation of the current implementation of\ud eCommerce websites with regards to the developed trust information model.

No Abstract Available African Journal of Urology Vol.10(4) 2004: 285-286

eCommerce is a faceless business arrangement where the process of creating trust towards merchants is still a big challenge. One of the methods that can be used to facilitate the creation of trust is through transference of trust from merchant to third party and then back to the consumer. This can be achieved by placing third party endorsements or seals on the merchants’ websites. Currently, this method has been implemented in many web sites. Current evaluation on its implementation needs to be done due to its diversity and implementation integrity problems

The cost of maintaining legacy software systems has spiralled and\ud their maintenance became a burden for many organisations. In this\ud paper we present the first prototype of the LOBS-COQ system\ud that attempts to transform COBOL legacy systems into relational\ud database schema and produce SQL statements for data querying.\ud The approach first transforms the COBOL source code into XML\ud files, which are then processed to create tables and develop SQL\ud statements. Frames are used to develop the SQL statements.\ud COBOL statements are parsed and the information extracted is\ud used to fill the frames’ slots.

Female Urinary Incontinence in Morocco: Descriptive Study Effected in an Urban Area Objective : The aim of this study was to assess female urinary incontinence in Morocco with respect to its prevalence, its severity, the degree of impairment of the daily activities due to the problem and the women's attitude towards their handicap. Material et Methods : In 1999 we performed a survey including 368 moroccan women living in an urban area (Casablanca). They were recruited from different socio-economic classes. Their age ranged from 18 to 75 years. The questionnaire was evaluated by an expert committee (urologists, gynaecologists, epidemiologists). Results : The overall prevalence of urinary incontinence among the interviewed women was 31% with stress urinary incontinence in 13.5% and urge incontinence in 17.5%. 50% of the women suffering from incontinence were older than 50 years. 53.5% of them were menopaused, 26% were nullipares while 52% had more than 3 children. The urine loss is bothersome and influences all daily activities. 70% of those who lose urine more than once daily are bothered especially during prayer time. Conclusion In Morocco, 31% of the female population suffers from urinary incontinence. The risk factors are: advanced age, multiparity, menopause, obstetrical trauma. However other factors like ethnical, environmental and anatomic factors may play a role, too. An impairment of the daily activities is present in almost all patients, however, most of our women suffering from urinary incontinence live with the discomfort. Out of those women asking for medical help, the majority consults the general practitioners. From this fact it becomes evident that training these general practioners is necessary to help improving the detection and management of this disease. Résumé Objectif D'évaluer les taux de prévalence de l'incontinence urinaire chez la femme marocaine, le degré de la gêne, le retentissement sur les différentes activités quotidiennes ainsi que la stratégie de la femme face à cette incapacité. Matériel et Méthodes Au cours de l'année 1999 nous avons mené une enquête auprès de 368 marocaines issues de milieu urbain (Casablanca) de classes socio-économiques différentes, dans le but d'approcher l'épidémiologie de l'incontinence urinaire, d'évaluer son rétentissement psychosocial et l'attitude de la femme vis-à-vis de cette pathologie. Les patientes étaient âgées de 18 à 75 ans. La validation du contenu du questionnaire a été faite par un comité de spécialistes (urologues, gynécologues, épidémiologistes). Résultats 31% des femmes interrogées souffrent d'incontinence urinaire. 13,5% ont une incontinence urinaire d'effort et 17,5% une incontinence par impériosité. 50% des femmes incontinentes sont âgées de plus de 50 ans. 53,5% des femmes incontinentes sont ménopausées. 26% sont nullipares, tandis que 52% ont plus de 3 enfants. La gêne occasionnée par la perte d'urines intéresse toutes les activités de la vie quotidienne et 70% des femmes qui perdent leurs urines plusieurs fois/jour sont très gênées, particulièrement lors de la prière. Conclusion Au Maroc l'incontinence urinaire affecte 31% des femmes. Les facteurs de risque retenus sont : l'âge avancé, la multiparité, la ménopause, les traumatismes obstétricaux. Cependant, d'autres facteurs peuvent être incriminés : ethniques, environnementaux, anatomiques. Les répercussions sur la vie quotidienne peuvent être importantes. La majorité de nos femmes cependant vivent avec leur incontinence. Le plus grand pourcentage des consultations se fait chez les médecins généralistes, d'où l'importance de l'information et de la formation de ces médecins en vue d'un dépistage et d'une prise en charge correcte de cette pathologie. Mots Clés épidémiologie, incontinence urinaire feminine, facteurs de risqué, qualité de vie. (African Journal of Urology: 2002 8 (4): 173-184)

eCommerce is a faceless business arrangement where the process of creating trust towards merchants, hereby referred to as merchant trust, is still a big challenge. Merchant trust framework can be created by using factors such as existence, affiliation, performance and policy. In this paper, we present an information model for a merchant trust based on the previously cited factors. We then provide a framework for the implementation of the model using intelligent agents. Gathering the required information on the merchant is the first step in helping consumers to evaluate merchant trust in an eCommerce setting.

There is a need for review in mathematical education to satisfy a growing demand for graduates that can support research and development in many technical fields. Dissatisfaction with current curriculum has pushed many institutions and countries to review their programs and their teaching methods. Due to the availability of technology, many are looking at its use to improve mathematics teaching. At the same time there is few support from the existing software methodologies for educational software. In this paper we describe a framework for developing educational software. The first prototype of the framework is presented together with Disc-Maths, a web-based software which is used to validate the proposed framework. Disc-Maths aims at introducing the learning of discrete mathematics at an early age.

Educational institutions are faced with many problems. In one hand they face a shortage of staff and funding and at the same time the number of students enrolled is ever increasing. The lecturers are faced with large and sometimes huge classes. Providing a quality course using traditional methods of teaching- learning becomes very difficult if not impossible. This calls for a shift in the teaching-learning paradigm whereby the traditional modes become inadequate to both deal with the large number of students and to provide an interactive learning environment. Technology-based and student-centred approaches need to be employed to overcome the space-time barriers in this new environment. \ud \ud In this paper we present our experience in conducting the TMX2012, “IT Tools for Knowledge Workers” course, which had 670 students enrolled. We will describe the various aspects of course management such as the laboratory and tutorial booking system, access to course material, modes of communication and interaction with students, administration of assessments and the monitoring of student progress. We will also describe how Information Technology has been used extensively throughout the course.