Browsing by Author "Afolabi, Babajide"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Open Access
    Decision Support System for Histopathological Diagnosis of Breast Diseases in Women.
    (IJCSI, 2011-03) Kayode, Aderonke Anthonia; Akhigbe, Bernard Ijesunor; Afolabi, Babajide; Udo, Ifiok; Ominiyi, Adedayo O
    This paper presents a representation of histological features for histopathological diagnosis of breast diseases in women. Hence, a Decision Support System (DSS) for histopathological interpretation and diagnosis of breast diseases was implemented and evaluated. The Expert knowledge used was elicited through interview and literature search. The needed diagnostic knowledge was represented using diseases’ profile in the form of frame. UML, JAVA and MYSQL were used for the design and implementation of the system. 150 samples of retrospective cases were used for the system’s implementation, while a Consultant Pathologist’s interpretation was used to evaluate the system. Results for Sensitivity, Specificity, Positive Prediction Value and the Negative Prediction Value are 97.7%, 95.0%, 99.2% and 86.3% respectively. Thus, the result showed that the system is capable of assisting an inexperience pathologist in making accurate, consistent and timely diagnoses, also in the study of diagnostic protocol, education, self-assessment, and quality control
  • Thumbnail Image
    Item
    Open Access
    An Empirical Model for Information Retrieval System Evaluation: The User's perspective
    (Computer Engineering and Intelligent Systems, 2011-01) Akhigbe, Bernard Ijesunor; Afolabi, Babajide; Adagunodo, Emmanuel Rotimi
    The aspect of time has become an issue since computers were introduced into management studies and thus highlights the need for efficient paradigm that will enable easy access to information, with much ease. But this is not the case yet, since finding the desired search engine and learning how to use them for this purpose is still time consuming. The continued dominance of measures for use in the system-centered aspect of IR evaluation, which is weak for use in user-centered IR system evaluation process, remains a challenge. Therefore the purpose of this study is to present usable measures through using an empirical from user’s perspective for use in the evaluation of IR system. The survey method, a robust multivariate mathematical model and the factor analytic method were experimented upon. Results showed that the model presented is promising concerning the challenges highlighted. Therefore user’s own knowledge, experience and searching abilities could be harnessed and implicated in IR design and evaluation. This study therefore serves as a test bed and guide to studies in this area, which results could contribute immensely to the overall improvement of the system. However, more data and a larger sample size are required to verify the proposed model in future, with other extraction techniques.
  • No Thumbnail Available
    Item
    Open Access
    Modelling User-Centered Attributes: The Web Search Engine as a Case
    ( Knowledge Organization, 2015-01-26) Akhigbe, Ijesunor; Afolabi, Babajide; Adagunodo, Rotimi
    This paper modeled user-centered attributes with which First and Second-order Measurement Models (I'SoMM) were proposed using factor analysis in a quantitative evaluative procedure. There was need to relate users needs as requirements for Web Search Engines (WeSKs) in a dynamic context. This informed the motivation for formulating the FSoMM to possess baseline properties with reasonable validity and reliability. This was achieved by considering how users "seek out and use" information as useful characteristics that can suffice as users' attributes. This is because of the belief in this paper that factors modelled from users' attributes encapsulate users' needs. With the qualitative evaluative approach these factors were translated into users' requirements for WeSEs' development. Results obtained showed that both models demonstrated reasonable model fit. Therefore, users' requirements can be communicated with measurement models. As illustrated in this paper, both the qualitative and quantitative evaluative approach remain an invaluable resource in this respect. We therefore infer that WeSEs' success in the delivery of assistance to users, particularly in a dynamic context must be based, not only on the progress of technology, but also on users' requirements.