European Journal of Computer Science and Information Technology (EJCSIT)

EA Journals

Database

Performance Evaluation of Selected Classification Algorithms for Iris Recognition System (Published)

Quite a lot of techniques proven to be resourceful have been espoused to develop iris recognition system. Nearly hybridized, supervised and unsupervised artificial neural network techniques have been used individually in iris recognition system and other pattern recognitions but have not been compared based on some performance metrics. Counter Propagation Neural Network (CPNN) is a hybridized technique, Self-Organizing Feature Map (SOFM) is an unsupervised learning technique and Back Propagation Neural Network (BPNN) is a supervised learning technique. This research conducted a performance comparison of CPNN, SOFM and BPNN techniques to recognize iris dataset and establish the more efficient among the three techniques. A database of Three hundred (300) iris images was acquired from LAUIRIS dataset from LAUTECH Biometric Research Group database. The original images of 640*360 dimensions were resized to 200*200 without any alteration in the image using 80% for training and 20% for testing. Hough transform was applied to segment locate the iris region of eye image. Daugman’s Rubber Sheet Model was used to create a dimensionally consistent representation. Principle Component Analysis was applied for feature extraction and dimensionally reduction. Finally, classification and matching were done by using CPNN, SOFM and BPNN techniques. This was implemented using MATLAB (Matrix Laboratory) R2016b. The performance metrics used for classification were False Positive Rate (FPR), Sensitivity, Specificity, Re, cognition Accuracy and Recognition Time at 0.70 threshold value.The Recognition Accuracy (RA), Recognition Time (RT), False Acceptance Rate (FAR), Sensitivity and Specificity of the three selected techniques (CPNN, SOFM and BPNN) resulted in values of 95.17%, 177.48s, 6.33% and 93.67% for CPNN 92.50%, 179.69s, 9.00%, 94.00% and 90.99% for SOFM while BPNN had 91.17%, 187.88s, 10.33%, 92.67% and 89.67% respectively.This paper showed that CPNN classification technique performed best for iris recognition system in terms of RA and recognition time. This research output will serve as a basis to pre-inform and guide researchers in choosing an efficient kernel based feature extraction technique.

Citation: Oyebode O. O., Oladimeji O. A., Adelekun A.,  Akomolafe T. A. (2023) Performance Evaluation of Selected Classification Algorithms for Iris Recognition System, European Journal of Computer Science and Information Technology, Vol.11, No.2, pp.1-12

Keywords: Database, Images, finger print, input vector, segmentation process, sensitivity

The Power of USSD: A Solution to African Financial Transaction Problems (Published)

Paying mobile bills has now become simple with the help of Internet banking and credit cards, Customer adapted to prepaying and get credited by buying them online or at the store nearby. Whereas the post-pay adapted customer pays his bills by end of his service session through online money transfer or paying bills at the store. These payment processes are hard to make sometimes, considering the resources available in underdeveloped countries or in a place where the Internet is difficult to find. Unstructured Supplementary Service Data payments (USSD) also come in handy when a customer runs out of Internet credits or uses a phone which does not provide him internet on the go. With limited resources, USSD payment provides clients the advantage of getting a phone card credited on tap. To make this happen, network providers and banks must work together. The network provider creates a database to save bank card details and accesses them when required with permission of the respective customer whenever a transition is made through USSD. For every payment, an authentication protocol is performed to avoid hackers and make secured money transfer. This Journal highlights the downsides of financial exclusion in modern societies and how we can leverage the technology of mobile money to drive financial inclusion in our society with a particular interest in unbanked areas in Nigeria. The financial sector is a heavily regulated sector in Nigeria, so it will be essential to see what it takes to set up mobile money operations in Nigeria and make it accessible to people who actually need it and the availability of the technology needed to make that happen. Even though mobile money operation is not so new, adoption has been very slow and this study is going to primarily highlight how adoption can be improved and the infrastructure needed to drive that adoption. The result of this study shows that the adoption of Mobile money can increase financial inclusion in Nigeria to 95% and as well connect over 99% of the adult population to easy credit facilities and financial services. In conclusion, the study recommends the quick adoption of mobile money wallets for personal finance considering the literacy landscape of Nigeria and the ease with which it provides credits and financial services to people in remote areas of the country, improving the ease of doing business, and bringing much-needed financial literacy to the people.

Keywords: Database, mobile money, unstructured supplementary service data payments

An Adaptable Ontology for Easy and Efficient University Data Management in Niger Delta University (Published)

The structure, variety and quantity of some current web content is limited in efficient exploration due to difficulty in searching and locating a specific content.  A case is the Niger Delta University where there is no unified online structure holding relevant university data. This is because there is no common data model to manage the data for which such query can easily be interpreted semantically. Therefore, this paper presents the application of semantic web technology for the unification of university data management. This research prepares the ground for the advent of software agents and other applications that require structured data for its computational processes. The ontology development follows an iterative path of the Object-Oriented System Analysis and Design (OOSAD) methodology. SPARQL was used as the query language for testing the ontology. The result is a semantically structured data that is deployable which can be expended and adapted in other institutions.

Keywords: Database, Ontology, sparql

Using Data Mining Techniques to Identify the Causes of Deaths in Al-Gedaref Hospital (Published)

Data mining technology extensively used in managing relationship through a variety of approaches. There are many tools and methods for analyzing mortality data. The mining technology is one of these tools. The research aims to illustrate the concept of data mining and causes of deaths in Gedaref hospital. The methodology of data mining which used in deaths files is used to integrate two algorithms which are (clustering and classification) to help Gedaref state hospital on prediction and decision making. The study also aims to indicate the level of the interest in the exploration areas and the components of the structure of the application of exploration concepts and tools. One can concluded that the large proportion of deaths is caused by Malaria especially between male’s students and employees in early ages 32 year who live in Kassab village in Gedaref. We also recommended that the hospital administration have to provide training programs to workers

Keywords: Cause of Death, Computer Application, Data mining, Database

Scroll to Top

Don't miss any Call For Paper update from EA Journals

Fill up the form below and get notified everytime we call for new submissions for our journals.