Oladimeji Ismaila | Ladoke Akintola University of Technology (original) (raw)

Uploads

Papers by Oladimeji Ismaila

In e-commerce, credit card fraud is an evolving problem. The growing number of credit card transa... more In e-commerce, credit card fraud is an evolving problem. The growing number of credit card transactions provides more opportunity for thieves to steal credit card numbers and subsequently commit fraud. Credit card fraud can be perpetrated through stolen cards, counterfeit card and stolen card details. The defensive measure issuing bank can take to overcome this liability is by introducing fraud detection systems (FDSs) in their database. Although different methods have been implemented to detect fraud but application of probability and selection of threshold value add an extra advantage for FDS to detect anomalies in on-line transactions. Therefore this paper implements another method of selecting threshold values (dynamic/adaptive) based on individual cardholder spending profile. In order to increase the confidence of the threshold values the results are verified using performance metrics. The two methods were compared and the results showed that adaptive method is suitable for det...

INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY, 2016

The ability to understand images is one of the key areas of research where the target is to under... more The ability to understand images is one of the key areas of research where the target is to understand the components of an image and interpret its meaning. The components of images are not easily understood and interpreted for analysis, therefore image segmentation technique is very necessary and should be taken as significant step during image processing and analysis. Repeatable experiments are required for this research field to progress as image segmentation needed for data processing cannot be adequately achieved in a particular technique. Hence performance analysis of various, commonly used techniques are often needed. However, in this work, three classes of image segmentation algorithms: Edge Detection, Clustering and Thresholding method were simulated in MatLab on infected bladder. The experiments were performed three times to confirm the accuracy of the results evaluated with Dice, Jaccard and cosine co-efficient of fitness values.

International Journal of Computer Applications, 2015

International Journal of Management, IT, and Engineering, 2018

Cloud computing provides a great collection of computing resources that can be rapidly and elasti... more Cloud computing provides a great collection of computing resources that can be rapidly and elastically provisioned and released based on users' demand to serve a wide and regularly expanding variety of information processing requirements. Due to its tremendous advantages this technology is maturing quickly and is being adopted in many applications including government, business, and education. This research employs the Cloud as a learning environment for teaching Computer Science and related courses by removing the locality constraints, while simultaneously improving students' understanding of the material provided through practical experience with the finer details and subjects' complexities. Most of the universities infrastructures are underutilized and in some cases over utilization of resources occurs, in order to balance the usage of the resources there is need for an elastic technology. In order to develop an e-Learning platform for virtual or open distance learning (ODL) undergraduate students of computer science new methodologies (like cloud based e-Learning) should be taken into consideration for project, problem based learning and virtual computorium. The research identified several potential Computer Science courses which could be launched and taught through Clouds. This framework addresses the services of cloud computing in a new dimension and each layer (in virtual classroom cloud-based system) specifies the essential components (that is matching of computer science courses with cloud layers) needed to construct an academic cloud in an open distance learning environment. And finally, a way of implementing the framework is proposed.

Shares or Stocks trading has been developed for over twenty years, and has gone deeply into all a... more Shares or Stocks trading has been developed for over twenty years, and has gone deeply into all aspects of daily economic life and attracted more and more investors' attentions. Therefore, researches on finding internal rules and establishing an efficient stock forecast model to help investors minimize risks and maximize returns are very practical and amazing. Computer science plays vital role to solve this problem. Different techniques are available for the prediction of stock market. Very popular some of these are Neural Network, Data Mining, Hidden Markov Model (HMM) And Neuro-Fuzzy system. From this Hidden Markov Model is the most leading machine learning techniques in stock market index prediction area. This paper is aimed at modeling and predicting the stock market situations with the concept of a Hidden Markov Model. The stock market signals considered for the model are hold, buy and sell for weekly and monthly data analysis. The model is being trained and tested HMM vari...

E-commerce theft involves using lost/stolen debit/credit cards, forging checks, misleading accoun... more E-commerce theft involves using lost/stolen debit/credit cards, forging checks, misleading accounting practices, etc. Due to carelessness of cardholders and criminality activities of fraudsters, the personal identification number (PIN) and using account level based fraud detection techniques methods are inadequate to cub the activities of fraudsters. In recent times, researchers have made efforts of improving cyber-security by employing biometrics traits based security system for authentication. This paper proposed a multi-level fraud detection system in automated teller machine (ATM) operations. The system included PIN level, account-level and biometric level. Acquired RealScan-F scanner was used to capture liveness fingers. Transactional data were generated for each individual fingerprint with unique PIN. The results of the simulation showed that (i) the classification at account level only yielded averages 84.3% precision, 94.5% accuracy and 5.25% false alarm rate; (ii) matching ...

This paper discussed the past works on fraud detection system and highlights their deficiencies. ... more This paper discussed the past works on fraud detection system and highlights their deficiencies. A probabilistic based model was proposed to serve as a basis for mathematical derivation for adaptive threshold algorithm for detecting anomaly transactions. The model was optimized with Baum-Welsh and hybrid posterior-Viterbi algorithms. A credit card transactional data was simulated, trained and predicted for fraud. And finally, the proposed model was evaluated with different metric. The results showed that with the optimization of parameters, posterior-Viterbi cum new detection model performed better than Viterbi cum old detection model.

The flexibility of WMNs affords their usage to provide broadband and communications services in m... more The flexibility of WMNs affords their usage to provide broadband and communications services in many environments including rural domains. Routing protocols are central to the design of rural networks to ensure data availability and efficient performance especially under dynamic conditions of resource-constrained rural areas. In this paper, we review four routing protocols utilized for rural deployments namely AODV, OLSR, OSPF and BATMAN vis-à-vis the most critical metrics for rural requirements. Specifically, the comparative analysis shows the need for an objective evaluation of protocols for rural WMN scenarios. We also noted that metrics such as protocol overhead, convergence time and topology control remains critical for the performance of rural WMNs. Consequently, we argue that an objective performance evaluation offers a reliable selection criterion regarding the most efficient routing protocol when deploying WMNs. The study will further conduct simulation experiments to advoc...

IJCSMC, 2021

E-commerce theft involves using lost/stolen debit/credit cards, forging checks, misleading accoun... more E-commerce theft involves using lost/stolen debit/credit cards, forging checks, misleading accounting practices, etc. Due to carelessness of cardholders and criminality activities of fraudsters, the personal identification number (PIN) and using account level based fraud detection techniques methods are inadequate to cub the activities of fraudsters. In recent times, researchers have made efforts of improving cyber-security by employing biometrics traits based security system for authentication. This paper proposed a multi-level fraud detection system in automated teller machine (ATM) operations. The system included PIN level, account-level and biometric level. Acquired RealScan-F scanner was used to capture liveness fingers. Transactional data were generated for each individual fingerprint with unique PIN. The results of the simulation showed that (i) the classification at account level only yielded averages 84.3% precision, 94.5% accuracy and 5.25% false alarm rate; (ii) matching ...

In e-commerce, credit card fraud is an evolving problem. The growing number of credit card transa... more In e-commerce, credit card fraud is an evolving problem. The growing number of credit card transactions provides more opportunity for thieves to steal credit card numbers and subsequently commit fraud. Credit card fraud can be perpetrated through stolen cards, counterfeit card and stolen card details. The defensive measure issuing bank can take to overcome this liability is by introducing fraud detection systems (FDSs) in their database. Although different methods have been implemented to detect fraud but application of probability and selection of threshold value add an extra advantage for FDS to detect anomalies in on-line transactions. Therefore this paper implements another method of selecting threshold values (dynamic/adaptive) based on individual cardholder spending profile. In order to increase the confidence of the threshold values the results are verified using performance metrics. The two methods were compared and the results showed that adaptive method is suitable for det...

INTERNATIONAL JOURNAL OF COMPUTERS & TECHNOLOGY, 2016

The ability to understand images is one of the key areas of research where the target is to under... more The ability to understand images is one of the key areas of research where the target is to understand the components of an image and interpret its meaning. The components of images are not easily understood and interpreted for analysis, therefore image segmentation technique is very necessary and should be taken as significant step during image processing and analysis. Repeatable experiments are required for this research field to progress as image segmentation needed for data processing cannot be adequately achieved in a particular technique. Hence performance analysis of various, commonly used techniques are often needed. However, in this work, three classes of image segmentation algorithms: Edge Detection, Clustering and Thresholding method were simulated in MatLab on infected bladder. The experiments were performed three times to confirm the accuracy of the results evaluated with Dice, Jaccard and cosine co-efficient of fitness values.

International Journal of Computer Applications, 2015

International Journal of Management, IT, and Engineering, 2018

Cloud computing provides a great collection of computing resources that can be rapidly and elasti... more Cloud computing provides a great collection of computing resources that can be rapidly and elastically provisioned and released based on users' demand to serve a wide and regularly expanding variety of information processing requirements. Due to its tremendous advantages this technology is maturing quickly and is being adopted in many applications including government, business, and education. This research employs the Cloud as a learning environment for teaching Computer Science and related courses by removing the locality constraints, while simultaneously improving students' understanding of the material provided through practical experience with the finer details and subjects' complexities. Most of the universities infrastructures are underutilized and in some cases over utilization of resources occurs, in order to balance the usage of the resources there is need for an elastic technology. In order to develop an e-Learning platform for virtual or open distance learning (ODL) undergraduate students of computer science new methodologies (like cloud based e-Learning) should be taken into consideration for project, problem based learning and virtual computorium. The research identified several potential Computer Science courses which could be launched and taught through Clouds. This framework addresses the services of cloud computing in a new dimension and each layer (in virtual classroom cloud-based system) specifies the essential components (that is matching of computer science courses with cloud layers) needed to construct an academic cloud in an open distance learning environment. And finally, a way of implementing the framework is proposed.

Shares or Stocks trading has been developed for over twenty years, and has gone deeply into all a... more Shares or Stocks trading has been developed for over twenty years, and has gone deeply into all aspects of daily economic life and attracted more and more investors' attentions. Therefore, researches on finding internal rules and establishing an efficient stock forecast model to help investors minimize risks and maximize returns are very practical and amazing. Computer science plays vital role to solve this problem. Different techniques are available for the prediction of stock market. Very popular some of these are Neural Network, Data Mining, Hidden Markov Model (HMM) And Neuro-Fuzzy system. From this Hidden Markov Model is the most leading machine learning techniques in stock market index prediction area. This paper is aimed at modeling and predicting the stock market situations with the concept of a Hidden Markov Model. The stock market signals considered for the model are hold, buy and sell for weekly and monthly data analysis. The model is being trained and tested HMM vari...

E-commerce theft involves using lost/stolen debit/credit cards, forging checks, misleading accoun... more E-commerce theft involves using lost/stolen debit/credit cards, forging checks, misleading accounting practices, etc. Due to carelessness of cardholders and criminality activities of fraudsters, the personal identification number (PIN) and using account level based fraud detection techniques methods are inadequate to cub the activities of fraudsters. In recent times, researchers have made efforts of improving cyber-security by employing biometrics traits based security system for authentication. This paper proposed a multi-level fraud detection system in automated teller machine (ATM) operations. The system included PIN level, account-level and biometric level. Acquired RealScan-F scanner was used to capture liveness fingers. Transactional data were generated for each individual fingerprint with unique PIN. The results of the simulation showed that (i) the classification at account level only yielded averages 84.3% precision, 94.5% accuracy and 5.25% false alarm rate; (ii) matching ...

This paper discussed the past works on fraud detection system and highlights their deficiencies. ... more This paper discussed the past works on fraud detection system and highlights their deficiencies. A probabilistic based model was proposed to serve as a basis for mathematical derivation for adaptive threshold algorithm for detecting anomaly transactions. The model was optimized with Baum-Welsh and hybrid posterior-Viterbi algorithms. A credit card transactional data was simulated, trained and predicted for fraud. And finally, the proposed model was evaluated with different metric. The results showed that with the optimization of parameters, posterior-Viterbi cum new detection model performed better than Viterbi cum old detection model.

The flexibility of WMNs affords their usage to provide broadband and communications services in m... more The flexibility of WMNs affords their usage to provide broadband and communications services in many environments including rural domains. Routing protocols are central to the design of rural networks to ensure data availability and efficient performance especially under dynamic conditions of resource-constrained rural areas. In this paper, we review four routing protocols utilized for rural deployments namely AODV, OLSR, OSPF and BATMAN vis-à-vis the most critical metrics for rural requirements. Specifically, the comparative analysis shows the need for an objective evaluation of protocols for rural WMN scenarios. We also noted that metrics such as protocol overhead, convergence time and topology control remains critical for the performance of rural WMNs. Consequently, we argue that an objective performance evaluation offers a reliable selection criterion regarding the most efficient routing protocol when deploying WMNs. The study will further conduct simulation experiments to advoc...

IJCSMC, 2021

E-commerce theft involves using lost/stolen debit/credit cards, forging checks, misleading accoun... more E-commerce theft involves using lost/stolen debit/credit cards, forging checks, misleading accounting practices, etc. Due to carelessness of cardholders and criminality activities of fraudsters, the personal identification number (PIN) and using account level based fraud detection techniques methods are inadequate to cub the activities of fraudsters. In recent times, researchers have made efforts of improving cyber-security by employing biometrics traits based security system for authentication. This paper proposed a multi-level fraud detection system in automated teller machine (ATM) operations. The system included PIN level, account-level and biometric level. Acquired RealScan-F scanner was used to capture liveness fingers. Transactional data were generated for each individual fingerprint with unique PIN. The results of the simulation showed that (i) the classification at account level only yielded averages 84.3% precision, 94.5% accuracy and 5.25% false alarm rate; (ii) matching ...