Department of Computer Sciences

Permanent URI for this collection

https://repository.run.edu.ng/handle/123456789/72

Browse

Now showing 1 - 20 of 29

An Android Based Blood Bank Information Retrieval System
(Dovepress, 2019-10) Kayode, Aderonke Anthonia
Background: Blood Bank record keeping has been carried out manually over the past decades using paper file management system which is slow for information retrieval and processing and also prone to errors in an emergency situation. Materials and methods: This research work solves the above-mentioned problem with the development of both web-based and Android-based blood bank information retrieval system. The web application is used by various blood banks system administrators to update their available blood inventory information and the mobile application which has the mobile search engine is used to search for blood supplies from the registered blood banks. Results and conclusion: The system also has a feature that allows registered blood banks to send a notification to registered blood donors on the application requesting for blood donation.
Application of Data Mining Algorithms for Feature Selection and Prediction of Diabetic Retinopathy
(Springer Nature Switzerland, 2019-06) Kayode, Aderonke Anthonia
Diabetes Retinopathy is a disease which results from a prolonged case of diabetes mellitus and it is the most common cause of loss of vision in man. Data mining algorithms are used in medical and computer fields to find effective ways of forecasting a particular disease. This research was aimed at determining the effect of using feature selection in predicting Diabetes Retinopathy. The dataset used for this study was gotten from diabetes retinopathy Debrecen dataset from the University of California in a form suitable for mining. Feature selection was executed on diabetes retinopathy data then the Implementation of k-Nearest Neighbour, C4.5 decision tree, Multi-layer Perceptron (MLP) and Support Vector Machines was conducted on diabetes retinopathy data with and without feature selection. There was access to the algorithms in terms of accuracy and sensitivity. It is observed from the results that, making use of feature selection on algorithms increases the accuracy as well as the sensitivity of the algorithms considered and it is mostly reflected in the support vector machine algorithm. Making use of feature selection for classification also increases the time taken for the prediction of diabetes retinopathy.
Application of Data Mining and Knowledge Management for Business Improvement: An Exploratory Study
(Foundation of Computer Science FCS, New York, USA, 2015-02) Kayode, Aderonke Anthonia
In recent years, there have been a lot of approaches employed by organizations to satisfy their customers and gain competitive advantage. Continuous development of Information System applications is also changing the ways in which businesses are conducted. From scanning barcodes at point of sale (POS) to shopping on the web, businesses are generating large volume of data about products and consumers which are being stored in different data repositories. While a lot of useful knowledge about products, sales and customers that can assist in business decisions are locked away in these databases unexploited. However, the need for organizations to survive in this dynamic business environment depends on how proactive they change these data into useful knowledge which can aid value creation. Presently, customer relationship management and marketing turn out to be the domains which have the potentials to utilize data mining techniques for decision support. This paper examines how business can improve on their performance through utilization of knowledge management (KM) and data mining (DM) applications to manage and support their strategies. Lastly, synergies and challenges of implementation of KM and DM as a tool in business are also critically analysed.
An Automated Mammogram Classification System using Modified Support Vector Machine.
(Dovepress, 2019-08-15) Kayode, Aderonke Anthonia
Purpose: Breast cancer remains a serious public health problem that results in the loss of lives among women. However, early detection of its signs increases treatment options and the likelihood of cure. Although mammography has been established to be a proven technique of examining symptoms of cancer in mammograms, the manual observation by radiologists is demanding and often prone to diagnostic errors. Therefore, computer aided diagnosis (CADx) systems could be a viable alternative that could facilitate and ease cancer diagnosis process; hence this study. Methodology: The inputs to the proposed model are raw mammograms downloaded from the Mammographic Image Analysis Society database. Prior to the classification, the raw mammograms were preprocessed. Then, gray level co-occurrence matrix was used to extract fifteen textural features from the mammograms at four different angular directions: θ={0°, 45°, 90°, 135°}, and two distances: D={1,2}. Afterwards, a two-stage support vector machine was used to classify the mammograms as normal, benign and malignant. Results: All of the 37 normal images used as test data were classified as normal (no false positive) and all 41 abnormal images were correctly classified to be abnormal (no false negative), meaning that the sensitivity and specificity of the model in detecting abnormality is 100%. After the detection of abnormality, the system further classified the abnormality on the mammograms to be either “benign” or “malignant”. Out of 23 benign images, 21 were truly classified as benign. Also, out of 18 malignant images, 17 were truly classified to be malignant. From these findings, the sensitivity, specificity, positive predictive value, and negative predictive value of the system are 94.4%, 91.3%, 89.5%, and 95.5%, respectively. Conclusion: This article has further affirmed the prowess of automated CADx systems as a viable tool that could facilitate breast cancer diagnosis by radiologists.
Automatic Segmentation of Retinal Blood Vessels of Diabetic Retinopathy Patients using Dempster-shafer Edge Based Detector
(ANSInet, 2019-06-15) Kayode, Aderonke Anthonia
Background and Objective: Diabetic Retinopathy (DR) is a micro-vascular complication of diabetes which results in the alteration or total damage of retinal blood vessels. This is responsible for most partial loss of sight and blindness among diabetic patients across nations of the world. Early examination of retinal blood vessels could help in the detection and diagnosis of the symptoms of DR thereby curtailing its effects. Methodology: Dempster-shafer edge based detector was used to segment retinal blood vessels from retinal images sourced from Digital Retinal Image for Vessel Extraction (DRIVE). Prior to the segmentation, median filter, Contrast Limited Adaptive Histogram Equalization (CLAHE) and mahalanobis distance algorithms were used to preprocess the raw retinal images so that accurate blood vessels detection and segmentation will be achieved. Results: A segmentation accuracy of 0.9765 was recorded when receiver operating characteristics of the technique was computed. This showed that an acceptable degree of blood vessel segmentation was achieved. Furthermore, the segmented blood vessels are publicly available for academic and research purposes. Conclusion: Dempster-shafer edge based detector has been further shown to be an effective algorithm for blood vessels segmentation in healthy as well as DR retinal images.
Comparative Study of Two Divide and Conquer Sorting Algorithms: Quicksort and Mergesort.
(Elsevier, 2020-04) Kayode, Aderonke Anthonia
Divide and Conquer is a well-known technique for designing algorithms. Many of the existing algorithms are a product of this popular algorithm design technique. Such include Quick sort and Merge sort sorting algorithms. These two algorithms have been widely employed for sorting, however, determining the most efficient among the two has always been a contentious issue. Most of the existing literature have compared these algorithms using machine dependent factors such as computational complexity but few have employed machine independent factors such as internal/external sorting, algorithm complexity: best, average, and worst cases, memory usage, stability etc. This study intends to contribute to this discuss using both machine dependent and independent factors. The implementation was carried out in MATLAB programming environment and the internal system clock was set to keep track of the time required for sorting. Results obtained revealed that in terms of computational speed using array of small sizes, Quick sort algorithm is faster, though Merge sort algorithm is faster with array of large sizes. Also, both algorithms are of O(nlogn) best case and average case complexity while the worst case for quicksort is O(n2) and that of merge sort remains unchanged. In terms of stability, Quick sort is stable while Merge sort is not. Despite the excellent performance of Merge sort algorithm, the need for an auxiliary memory for sorting makes it less preferable than Quick sort algorithm for applications where a good cache locality is of paramount importance.
Computational Investigation of Consistency and Performance of the Biochemical Network of the Malaria Parasite, Plasmodium falciparum
(Springer Nature Switzerland, 2019-06) Kayode, Aderonke Anthonia
Malaria has been a problem in the public health sector and Sub-saharan African. The most prevalent symptoms of this disease is caused by Plasmodium falciparum, a blood borne pathogen, there has also been a disclosure of resistance to anti malaria drugs in Pf. An intimate process of acquiring insight to an organism’s metabolism is to analyze her network topology deploying computational techniques. In this research, the Flux Balance Analysis (FBA) of the metabolism of malaria parasite, Plasmodium falciparum that has been converted to a System Biology Markup Language (SBML) format in another work (Segun et al. 2014) was used to predict the metabolic activities and to investigate the consistency of the multi-compartment biochemical metabolic network of the parasite using FASIMU software. With a projected output in view, a flux-balance computation was first deployed on an energy model and redox metabolism of the human red blood cells to learn the internal structure of FASIMU, this was a simpler model compared to Plasmodium falciparum model. The results of the analysis generated a file that consists of the flux values, reaction identifiers, equilibrium constants adopted and the concentration values. It was also discovered that transporters conveyed metabolites among the various cellular compartments of the organism. Further results of the flux balance analysis of the compartmented Plasmodium falciparum metabolic network generated a comprehensive list of target metabolites indispensable to the growth of the organism, which have been confirmed by recent literature. It is evident that the results generated from this research represent a significant step towards discovering drug targets.
Data Mining Techniques for Predicting Immunize-able Diseases: Nigeria as a Case Study
(Foundation of Computer Science FCS, New York, USA, 2013-05) Kayode, Aderonke Anthonia
Disease rates vary between different locations particularly in the rural areas. While a database of diseases occurrence could be easily found, studies have been limited to descriptive statistical analysis, and are mostly restricted to diseases affecting adults. This paper therefore presents a Mathematical Model (MM) for predicting immunize-able diseases that affect children between ages 0 - 5 years. The model was adapted and deployed for use in six (6) selected localized areas within Osun State in Nigeria. Using the MATLAB's ANN toolbox, the Statistics toolbox for classification and regression, and the Naïve Bayesian classifier the MM was developed. The MM is robust in that it takes advantage of three (3) data mining techniques: ANN, Decision Tree Algorithm and Naïve Bayes Classifier. These data mining techniques provided the means by which hidden information were discovered for detecting trends within databases, and thus facilitate the prediction of future disease occurrence in the tested locations. Results obtained showed that diseases have peak periods depending on their epidemicity, hence the need to adequately administer immunization to the right places at the right time. Therefore, this paper argues that using this model would enhance the effectiveness of routine immunization in Nigeria.
Decision Support System for Histopathological Diagnosis of Breast Diseases in Women
(IJCSI International Journal of Computer Science Issues,, 2011-03) Kayode, Aderonke Anthonia
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
A Deep Convolutional Encoder-Decoder Architecture for Retinal Blood Vessels Segmentation
(Springer, 2019-06) Kayode, Aderonke Anthonia
Over the last decades, various methods have been employed in medical images analysis. Some state-of-the arts techniques such as deep learning have been recently applied to medical images analysis. This research proposes the application of deep learning technique in performing segmentation of retinal blood vessels. Analyzing and segmentation of retina vessels has assisted in diagnosis and monitoring of some diseases. Diseases such as age-related fovea degeneration, diabetic retinopathy, glaucoma, hypertension, rteriosclerosis and choroidal neovascularization can be effectively managed by the analysis of retinal vessels images. In this work, a Deep Convolutional Encoder -Decoder Architecture for the segmentation of retinal vessels images is proposed. The proposed method is a deep learning system composed of an encoder and decoder mechanism allows a low resolution image set of retinal vessels to be analyzed by set of convolutional layers in the encoder unit before been sent into a decoder unit for final segmented output. The proposed system was evaluated using some evaluation metrics such as dice coefficient, jaccard index and mean of intersection. The review of the existing works was also carried out. It could be ,shown that the proposed system outperforms many existing methods in the segmentation of retinal vessels images.
Development of a Real Time Smishing Detection Mobile Application using Rule Based Techniques.
(Procedia Computer Science,, 2022) Kayode, Aderonke Anthonia
The introduction of alternative messaging platforms on mobile devices have not been able to phase off Short Messaging Service (SMS) as the most widely used means of textual communication. Over the decades, SMS has remained the most responsive way of communication that has been embraced by individuals and organizations in passing information across to their intended recipients. However, hackers have been employing this tool as a way to deceive the gullible into divulging sensitive information about their financial dealings as well as gain access to their mobile devices. A lot of innocent but ignorant individuals have become victims of this smishing acts and have lost huge sum of money as a result. Though existing research have extensively proposed and implemented different techniques for detecting and separating spam SMS from ham SMS, a mobile application that uses a rule-based RIPPER and C4.5 classifiers in detecting smishing acts is proposed. The mrule-based classifiers were used to formulate rules used in detecting and separating spam from ham while a mobile application was developed to use the rule-based model in smishing detection. An Application Programming Interface (API) was designed to intercept incoming SMS, forward them to the rule-based model for analysis and then relay the results to the user via the developed mobile application. The user then decides to either retain or discard the SMS.
Development of a Virtual Reality Guided Tour Mobile App of Landmark University Teaching and Research Farm.
(International Journal of Interactive Mobile Technologies (IJIM), 2019-05) Kayode, Aderonke Anthonia
In this work, we designed and developed a Virtual Reality guided tour mobile app for Landmark University farms, LF-ViT. We were motivated by the need to circumvent the problem of bio-security caused by incessant visit to the farm by visitors, tourists or customers.The guided tour was implemented using the storytelling technique. Other technical details of the design and implementation process are discussed
Development of a Web Based Intelligent Dietetic System
(International Research Publication House., 2020) Kayode, Aderonke Anthonia
“Health is wealth” a healthy diet is the friend of the soul, everybody needs to take a healthy diet that contains equal proportions of nutrients which is very essential to basic development of human body system. This work addressed the problem encountered in everyday life, most people feed wrongly which may also sometimes lead to malnutrition that can result in various diseases. In this paper, a web based intelligent dietetic system which aids individual in picking the appropriate food content with the right nutrition that their body needs is developed. The work also helps in creating a balanced diet to an individual based on their work schedule, Body mass index (BMI), and ailment if any. This work suggests the appropriate diet for an individual with a particular type of ailment. The system create a possible list of food and fruits that will not further cause any form of harm but give aid to the healing process of such individual. This work will serve as a foundation for information on medical system that will enhance easy nutritional knowledge on what to eat and what not to eat, bringing the dietician to your door step, getting all the essential nutritional information needed will be useful to nutritionist and dieticians and enable the users to get the needed nutritional value to enhance their health status.
A Distributed Information System for Health Care Facilities in Nigeria: A Web-based Spatial Approach
(Foundation of Computer Science FCS, New York, USA, 2013-08) Kayode, Aderonke Anthonia
Today, the Internet has further improved the functionalities of computers. A computer and Internet based technology offering a radically different way to manage spatial data is the GIS. Its useful digital maps are needful and very useful in managing healthcare related affairs and communities as well as industry base issues. Therefore, we describe a distributive information system that uses a web-based GIS spatial approach to aid the distribution of tertiary health facilities in Nigeria. The system would assist its users to identify where health care facilities are concentrated, and how and where to locate them anytime. Some of the resources employed in the system’s development include: Macromedia dreamweaver, Java Scripting, PHP, MYSQL; the WAMP server; while the UML was used for the system’s design. Implementing the system showed that stakeholders were able to visualize the distribution of tertiary hospitals in Nigeria, and make useful inferential decisions with ease. Conclusively, we believe the system will aid in locating the nearest tertiary hospital, as well as help stakeholders make more informed decisions.
A Dynamic Round Triple Data Encryption Standard Cryptographic Technique for Data Security
(Springer Nature Switzerland, 2020-10-05) Kayode, Aderonke Anthonia
Cryptographic techniques have been widely employed to protect sensitive data from unauthorized access and manipulation. Among these cryptographic techniques, Data Encryption Standard (DES) has been widely employed, however, it suffers from key and differential attacks. To overcome these attacks, several DES modifications have been proposed in literatures. Most modifications have focused on enhancing DES encryption key; however, the strength of a cryptographic technique is determined by the encryption key used and the number of encryption rounds. It is a known fact that Advanced Encryption Standard (AES) cryptographic technique with 14 encryption rounds is stronger than AES with 12 rounds while AES with 12 rounds is stronger than AES with 10 rounds. Therefore, this study proposed a DES cryptographic technique whose number of rounds is dynamic. Users are expected to specify the number of encryption and decryption rounds to be employed at run time. Moreover, a predefined number of shifting operations which is left circular shift 2 was chosen for each encryption round. As, a trade-off in complexity, the number of Substitution box (S-box) was also reduced to 4, so that the input to the S-boxes would be arranged in four 12-bit blocks for the X-OR operation and not six 8-bit blocks as in the traditional DES. Finally, three keys were used to encrypt, decrypt and encrypt the plaintext ciphertext as in triple DES. The modified DES yielded a better avalanche effect for rounds greater than 16 though its encryption and decryption time were greater than that of the traditional DES.
Electronic Medical Information Encryption Using Modified Blowfish Algorithm
(Springer Nature Switzerland, 2019-06) Kayode, Aderonke Anthonia
Security and privacy of patients’ information remains a major issue of concern among health practitioners. Therefore, measures must be put in place to ensure that unauthorized individual do not have access to this information. However, the adoption of digital alternative of retrieving and documenting medical information has further opened it up to more attacks. This article presents a modified blowfish algorithm for securing textual and graphical medical information. The F-function used in generating round sub-keys was strengthened so as to produce a strong key that could resist differential attacks. Number of Pixel Change Rate (NPCR) and Unified Average Changing Intensity (UACI) of 98.85% and 33.65% revealed that the modified algorithm is sensitive to changes in its key and also resistive to differential attacks. Furthermore, the modified algorithm demonstrated a better encryption and decryption time than the existing blowfish algorithm.
An Empirical Investigation of the Prevalence of Osteoarthritis in South West Nigeria: A Population-Based Study
(International Journal of Online Engineering (iJOE), 2020-01) Kayode, Aderonke Anthonia
Today, Osteoarthritis remains the most prevalent chronic joint disease and a potentially incapacitating joint illness. It is an enduring health problem which cannot be cure though it can be managed. Osteoarthritis remains a serious public health problem because its burden is high, people who live with it have a greater risk of developing anxiety / or depression and if it is not properly managed, it can bring about disability as well as impairing quality of life. This paper presents a statistical correlation between the reported risk factors of Osteoarthritis and its prevalence in Nigeria. Statistical tests were performed to investigate if there is enough evidence for inferring that the risk factors for Osteoarthritis are true for the whole of Nigerian population.
Enhancement and Segmentation of Mammograms for Further Analysis
(International Journal of Computer Science and Information Security (IJCSIS), 2017-06) Kayode, Aderonke Anthonia
Breast cancer is the most prevalent cancer and the leading terminal disease among women worldwide. At the present time, there are no effective ways to prevent breast cancer, because its cause is not yet fully known, therefore, early detection, which can be achieved by mammography, has become the only effective way to diagnose and manage breast cancer. To diagnose breast cancer, Radiologists need to examine mammograms to locate abnormalities like masses and calcifications that indicate breast cancer. These abnormalities are very tiny in size and are obscured by the fibroglandular tissue of the breast region. The fibroglandular region of the breast is being evaluated by the Radiologist in the interpretation of mammographic images. Nevertheless, the interpretation is subjective and varies from one Radiologist to another. In this paper, mammograms acquired from the Department of Radiology, Obafemi Awolowo University Teaching Hospital Complex (OAUTHC), Ile-Ife, Nigeria were enhanced and segmented to improve and make better further analysis of the images by Radiologists.
An Exploration of Prevalence of Repetitive Stress Injuries among Computer Operators in Nigeria
(International Journal of Computer Applications, 2015-01) Kayode, Aderonke Anthonia
Computers have revolutionized education and the workplace, people are doing excellent jobs using computer to process and analyse data, type and format documents, design graphics, etc. However, there has been far too little attention paid to the dangers of Repetitive Stress Injuries (RSIs) among computer operators who use computers often and extensively. There are simple safety skills and understandings that can be easily incorporated into computer usage. Six hundred (600) questionnaires were personally administered to computer operators and other computer-users ranging from Students, Lecturers, Bankers, Civil Servants to Health Workers in the major cities of South - West of Nigeria. The result of the survey was analysed using SPSS and descriptive statistical techniques. The study shows that computer operators spend more hours working with computers than other computer-users. 83.4% of these computer operators spend more than 6 hours, working with computers at a stretch per day, very few (16.6%) observe breaks in-between. The study also reveals that RSIs are more prevalent among computer operators than other computer users. Larger percentage of computer operators suffers some forms of RSI syndrome than other computer-users who rarely suffer more than one syndrome. Precautionary measures how these syndromes can be reduced are also highlighted in this study.
An Explorative Survey of Enhancement Techniques Used in Mammography
(IJCSI International Journal of Computer Science Issues, 2014-01) Kayode, Aderonke Anthonia
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 considered.

Browse

Browsing Department of Computer Sciences by Author "Kayode, Aderonke Anthonia"

Results Per Page

Sort Options