Papers by Afolabi S Babajide
Semantic Medical Image Analysis
Advanced Concepts, Methods, and Applications in Semantic Computing, 2021
The recent advancement in imaging technology, together with the hierarchical feature representati... more The recent advancement in imaging technology, together with the hierarchical feature representation capability of deep learning models, has led to the popularization of deep learning models. Thus, research tends towards the use of deep neural networks as against the hand-crafted machine learning algorithms for solving computational problems involving medical images analysis. This limitation has led to the use of features extracted from non-medical data for training models for medical image analysis, considered optimal for practical implementation in clinical setting because medical images contain semantic contents that are different from that of natural images. Therefore, there is need for an alternative to cross-domain feature-learning. Hence, this chapter discusses the possible ways of harnessing domain-specific features which have semantic contents for development of deep learning models.
Impact of international cooperation on curricular, teaching methods and evolution of internationally accepted engineers: The African perspective
... The African perspective LO Kehinde & BS Afolabi Faculty of Technology, Obafemi Awolowo Un... more ... The African perspective LO Kehinde & BS Afolabi Faculty of Technology, Obafemi Awolowo University, Ile-Ife, Nigeria ... For most developing countries, stable electricity and reliable telecommunications infrastructure are among the most important factors that determine success. ...
Evaluating Web-based Technologies: The Paradigm of User-centricity
Journal of Applied Computer Science & Mathematics, 2016
User's activities in the adaptation and restructuring of an information system
International audienc
Quality of Service Evaluation in a High Delay Sensitive Traffic in IEEE 802.11a
Development of a Scalable Architecture for Dynamic Web-Based Applications
Web-based applications play a major role in the development and deployment of online services. Du... more Web-based applications play a major role in the development and deployment of online services. Due to their unique medium of operation, they also have unique requirements when it comes to data storage. Most web applications use databases as their primary data storage mechanism, which does not only provide well-developed routines for data management, but also can be accessed via common interfaces such as Microsoft’s Object Linking and Embedding Database (OLEDB) and Sun’s JAVA Database Connectivity (JDBC). Scalability poses a significant challenge for today's web applications, mainly due to the large population of potential users. As a result, we attempt to present a scalable architectural model that could be adopted by web application developers in order to implement scalable systems with good quality of service. This will ensure that required information is available during critical times irrespective of sudden load increase.
Assessing Network Services and Security in Nigeria Universities
Journal of Computer Science and Its Application, 2012
The paper investigated sources of threats and vulnerabilities to Nigerian university computer net... more The paper investigated sources of threats and vulnerabilities to Nigerian university computer networks and assessed the adequacy of security controls in place to mitigate the occurrence of successful intrusion. This was with a view to enhancing the integrity of data transactions on the Universities' computer networks. Data for the study were sourced from 18 purposively selected universities in Southwestern Nigeria. Three universities, each representing federal, state and private were selected from each of the six states in the zone. Primary data were obtained through the use of validated questionnaire. The result revealed that 81.3% of the universities had internet presence. The Universities' Organisation Information Criticality Matrix (OICM) showed the bursary unit with highest weighted average. The result further showed that web services posed the greatest source of threat and vulnerability to the university networks. Indeed, 72% of the universities ran e-portal services that incorporated electronic payment but none of the universities was digitally signed with Certificate Authority (CA). The result also showed that single factor authentication using usernames and passwords were the only network access identifier employed by all the universities. The study noted that the security controls to safe guard the integrity and non-repudiation of network transactions in the universities were weak and high potential existed for possible compromise of the network system. The study therefore concluded by proposing a layered approach to managing security on the university network.
Diagnosis of Breast Diseases in Women
This paper presents a representation of histological features for histopathological diagnosis of ... more 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 diagnos...
International Journal of Computer Applications, 2014
In this paper, we are presenting a model for implementation of ontology through invoking a semi-a... more In this paper, we are presenting a model for implementation of ontology through invoking a semi-automatic process from web data tables. The singularity of this method is the implementation of cosine similarity for filtering the documents. We present the framework for the development of generic method concerning data integration. The data warehouse is composed of several data tables extracted from the web and it has been supplemented by the existing local data sources. Documents pertaining to different domains can be supplemented as input to the data sources which are stored in data ware house and then are converted into XML/RDF data. We have used cosine similarities to measure the similarity of two documents which are likely to be same in terms of their subjects. It is a semi automatic method to extract and integration of web documents by using ontology.
International Journal of Information Engineering and Electronic Business, 2016
Breast cancer is the most common cancer found in women in the world. Mammography has become indis... more Breast cancer is the most common cancer found in women in the world. Mammography has become indispensable for early detection of breast cancer. Radiologists interpret patients' mammograms by looking for some significant visual features for decision making. These features could have different interpretations based on expert's opinion and experience. Therefore, to solve the problem of different interpretations among experts, the use of computer in facilitating the processing and analysis of mammograms has become necessary. This study enhanced and segmented suspicious areas on mammograms obtained from Radiology Department,
International Journal of Computer Applications, 2016
Fingerprints are patterns formed on the epidermis of fingertip and they are characterized with mi... more Fingerprints are patterns formed on the epidermis of fingertip and they are characterized with minutiae and their overall ridge flow patterns. In this paper, fingerprint minutiae are considered to have both the quantitative and qualitative properties which could help to ensure accurate verification of fingerprint if properly utilized. The hybrid architecture of minutiae-based verification is in effect a model that caters for enhancement in terms of minutiae quantity and quality on fingerprint. While researches have proven that good quality of fingerprint minutiae can guarantee accurate verification of the fingerprint, false acceptance and rejection rates are still being recorded largely because the improvement associated with the quality of minutiae may not be sufficient to address the problems associated with fingerprint during sensing. Nevertheless, an improvement in the number (i.e. quantity) of minutiae extracted from fingerprint could be useful in many instances. Therefore, this paper introduces a dimension whereby necessary and sufficient condition is set for the selection of quantity of minutiae needed for verification. This approach is designed to complement existing minutiae quality enhancement approach aimed at achieving accurate verification in Automated Fingerprint
International Journal on Advances in ICT for Emerging Regions (ICTer), 2015
This paper evaluate the internal and external factors influencing software development in Nigeria... more This paper evaluate the internal and external factors influencing software development in Nigeria. The significance of these factors were also examined and the level of acceptability of the locally developed software products. The ICT firms that specialized in software development, educational institutions and other major stakeholders, including users of software packages were also covered. Data were collected using sets of questionnaire and from secondary sources. The questionnaire was administered on purposively selected software developers in select ICT firms and elicited information on factors influencing the indigenous software product development in Nigeria. A five-point Likert scale rating of 5 to 1 was used to determine the relative weight of the influencing variables. The result indicated the internal factors influencing software development were human resources (3.69), on the job training (3.58), R&D activities (3.48) and working experience (3.37).While access to technical information and support (3.65), competition with international market (3.59), economic factor (3.46), access to professional skill from the labour market (3.39) were the external factors that influence software development in Nigeria with significant difference F= 8.60 p≤0.05. Acceptability of locally developed software in Nigeria, was on the average, relatively low compared with the foreign software products. This was due to the problem of reliability, efficiency, security and scope of functionality. These were circumstances that made users prefer foreign software products. Similarly, the result revealed that the desirable and critical role of government support and policy to drive the software industry for growth were lacking. This imply the need for effective policy framework for the development of software in the short, mid and long term prognosis within the earlier opportunity niches and should be accorded the desirable national attention and priority.
International Journal of Information Technology and Computer Science, 2012
The histopathological d iagnosis of breast diseases requires highly trained and experienced exper... more The histopathological d iagnosis of breast diseases requires highly trained and experienced experts, and often strains pathologists' cognitive capabilit ies. Accurate and timely d iagnosis of breast diseases is essential for the appropriate management of the patients. The paper presents a knowledge base system that uses a comb ination of rule -based and case-based techniques to achieve the diagnosis. Rule-based systems handle problems with well-defined knowledge bases this limits the flexibility of such system. Casebased reasoning has been adopted to overcome this inherent weakness of rule-based systems by incorporating previous cases in the generation of new cases to improve the performance of the system. The result of this research shows that the system is capable of assisting pathologists in making accurate, consistent and timely diagnoses. The system also aid in eliminating errors of o mission that have been viewed as a prominent cause of medical errors . In conclusion this paper investigated the histological features used in the diagnosis of breast diseases and proposed an integrated knowledge base system based on the features.
Arxiv preprint cs/0608043, 2006
This paper takes a look at the general characteristics of business or economic intelligence syste... more This paper takes a look at the general characteristics of business or economic intelligence system. The role of the user within this type of system is emphasized. We propose two models which we consider important in order to adapt this system to the user. The first model is based on the definition of decisional problem and the second on the four cognitive phases of human learning. We also describe the application domain we are using to test these models in this type of system.
International Journal of …
This paper presents a representation of histological features for histopathological diagnosis of ... more 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.
An Explorative Survey of Image Enhancement Techniques Used in Mammography
Breast cancer is the most common disease in women and it remains a leading cause of cancer deaths... more Breast cancer is the most common disease in women and it remains a leading cause of cancer deaths among women in many parts of the world. Mammography has become indispensable for early detection of breast cancer. However, interpretation of the resulting images requires sophisticated image enhancement algorithms that enhance visual interpretation and aid the radiologists in the interpretation task. MATLAB software presents several enhancement algorithms which can be used for mammogram enhancement. In this survey, several enhancement techniques for mammographic images are
American Journal of Computer Science and Technology, 2019
A scenario known as conflict in face recognition may arise as a result of some disparity-related ... more A scenario known as conflict in face recognition may arise as a result of some disparity-related issues (such as expression, distortion, occlusion and others) leading to a compromise of someone's identity or contradiction of the intended message. However, addressing this requires the determination and application of appropriate procedures among the various conflict theories both in terms of concepts as well as resolution strategies. Theories such as Marxist, Game theory (Prisoner's dilemma, Penny matching, Chicken problem), Lanchester theory and Information theory were analyzed in relation to facial images conflict and these were made possible by trying to provide answers to selected questions as far as resolving facial conflict is concerned. It has been observed that the scenarios presented in the Marxist theory agree with the form of resolution expected in the analysis of conflict and its related issues as they relate to face recognition. The study observed that the issue of conflict in facial images can better be analyzed using the concept introduced by the Marxist theory in relation to the Information theory. This is as a result of its resolution strategy which tends to seek a form of balance as result as opposed to the win or lose case scenarios applied in other concepts. This was also consolidated by making reference to the main mechanisms and result scenario applicable in Information theory.
PLOS ONE, 2020
Studies have linked the large percentage of maternal and neonatal mortality that occur in postnat... more Studies have linked the large percentage of maternal and neonatal mortality that occur in postnatal period to low uptake of postnatal care (PNC) services. Mobile health (mHealth) intervention through message reminders has resulted in significant increase in antenatal care utilisation in previous studies. However, its use in PNC services' uptake has not been adequately investigated in Nigeria. This study aimed to evaluate the effect of a mobile health intervention on PNC attendance among mothers in selected primary healthcare facilities in Osun State, Nigeria. A quasi-experimental research design was utilised. Participants were allocated to Intervention Group and Control Group. One hundred and ninety pregnant mothers were recruited in each group. A mobile health intervention software was developed and used to send educational and reminder messages to mothers in the intervention group from the 35th week of pregnancy to six weeks after delivery. Uptake of PNC services was assessed at birth, 3 days, 10 days and 42 days after delivery. Data were analysed using descriptive statistics, chi-square and logistic regression models. About one-third (30.9%) of respondents in the intervention group had four postnatal care visits while only 3.7% in the control group had four visits (p < 0.001). After controlling for the effect of confounding variables, group membership remained a significant predictor of PNC uptake. (AOR: 10.869, 95% CI: 4.479-26.374). Mobile health intervention significantly improved utilisation of the recommended four postnatal care visits.
Modelling User-Centered Attributes: The Web Search Engine as a Case
KNOWLEDGE ORGANIZATION, 2015
Uploads
Papers by Afolabi S Babajide