Dr. Oluwaseyi Olorunshola | Air Force Institute of Technology (original) (raw)

Uploads

Papers by Dr. Oluwaseyi Olorunshola

Advances in information security, privacy, and ethics book series, Oct 24, 2023

Advances in artificial intelligence research, Oct 28, 2023

Nile Journal of Engineering and Applied Science, 2023

Due to its numerous applications and new technological advancements, object detection has gained ... more Due to its numerous applications and new technological advancements, object detection has gained more attention in the last few years. This study examined various uses of some deep learning object detection algorithms. These algorithms are divided into two-stage detectors like Region Based Convolutional Neural Network (R-CNN), Fast Region Based Convolutional Neural Network (Faster R-CNN), and Faster Region Based Convolutional Neural Network (Faster R-CNN), and one-stage detectors like Single Shot MultiBox Detector (SSD) and You Only Look Once (YOLO) algorithms that are used in text and face detection, image retrieval, security, surveillance, traffic control, traffic sign/light detection, pedestrian detection and in medical areas among others. This research primarily focuses on three applications: drone surveillance, applications relating to traffic, and medical fields. Findings from the performed analysis indicate that YOLO stands out as the predominant algorithm for drone surveillance among different deep learning models used in various application fields and being a one-stage detector. In terms of usage in traffic-related applications, SSD proved to be a prominent one-stage detector alongside Faster R-CNN which gained popularity as a two-stage detector preferred for applications in the medical field.

Springer eBooks, Jul 27, 2021

This paper assesses the impact of information and communication technologies (ICTs) on the perfor... more This paper assesses the impact of information and communication technologies (ICTs) on the performance of microfinance institutions (MFIs) in Niger, West Africa. MFIs play a pivotal role in improving financial inclusion in Niger because the majority of the country's poor live in rural areas, with only limited and costly access to formal financial services. Using an unbalanced panel of 23 MFIs spanning 2005-2013, single-step generalized moments method (GMM) estimations are run to appraise whether ICT investments improve the financial and the social performance of MFIs. The results show a positive relationship between investments in ICTs and MFIs' financial performance. Investing more in technologies enables managers to reduce the frequency of operational errors, increase the speed of task execution, decrease operating costs, and increase the likelihood of higher financial profits. The findings also reveal a positive effect of institutional affiliation on the financial performance of MFIs. Namely, MFIs affiliated with a network and investing in ICTs tend to perform better. The impact of ICT investments on the social performance of MFIs is rather weak. From a policy perspective, developing ICT infrastructure can yield substantial performance dividends and should remain a top developmental priority in Niger. RÉSUMÉ Cet article evalue l'impact des technologies de l'information et de la communication (TIC) sur la performance des institutions de microfinance (IMF) au Niger, Afrique de l'Ouest. Les IMF jouent un rôle central dans l'am elioration de l'inclusion financi ere au Niger parce que la majorit e des pauvres du pays vivent dans des zones rurales et n'ont qu'un acc es limit e et coûteux aux services financiers formels. A partir d'un panel non equilibr e de 23 IMF couvrant la p eriode 2005-2013, des estimations sont r ealis ees selon la m ethode des moments g en eralis es (MMG) en une seule etape pour v erifier si les investissements dans les TIC am eliorent la performance financi ere et sociale des IMF. Les r esultats montrent un rapport positif entre les investissements dans les TIC et les performances financi eres des IMF. Investir davantage dans les technologies permet aux managers de r eduire la fr equence des ARTICLE HISTORY

2019 15th International Conference on Electronics, Computer and Computation (ICECCO)

The usage of the Android Operating System (OS) has surpassed all other operating systems and as a... more The usage of the Android Operating System (OS) has surpassed all other operating systems and as a result, it has become the primary target of attackers. Many attacks can be geared towards Android phones mainly using application installation. These third-party applications first seek permission from the user before installation. Some of the permissions can be elusive evading the users’ attention. With the type of harm that can be done which include illegal extraction and transfer of the users’ data, spying on the users and so on there is a need to have a heuristic approach in the detection of malware. In this research work, some classification algorithms were tested to determine the best performing algorithm when it comes to the detection of android malware detection. An android application dataset was obtained from figshare and used in the Waikato Environment for Knowledge Analysis (WEKA) for training and testing, it was measured under accuracy, false-positive rate, precision, recall, f-measure, Receiver Operating Curve (ROC) and Root Mean Square Error (RMSE). It was discovered that multi-layer perceptron performs best with an accuracy of 99.4%.

Information and Communication Technology for Competitive Strategies (ICTCS 2020), 2021

There are different system development models, tools and applications that have been designed and... more There are different system development models, tools and applications that have been designed and developed before the use of computers for processing of information and there is an increase in demand of software with cheaper cost, having more functionality, faster delivery, and of high quality than how it was previously. Therefore, there is need to know the methods and their applications that would conform to the organizational requirements for successful system deployment. Each method has constructive criticisms with various advantages and disadvantages to the system that are of importance for deploying software in a manner such that it helps in good decision making on a chosen method for delivery within deadline and proper quality. This paper explained four commonly used System Development methods namely; Waterfall, Iterative, Agile and Rapid Application Development (RAD). It thereafter, categorically assesses these methods on a comprehensive set of features and made an alternative analysis of the applicability of the methods based on system development life cycle tools which are requirement, design, implementation, and testing. This paper describes the System Development Life Cycle (SDLC) tools and applications for successful system deployment and the constructive comparison that should serve as a tool in model selection for system development.

Journal of Computing and Social Informatics

This paper presents a comparative analysis of the widely accepted YOLOv5 and the latest version o... more This paper presents a comparative analysis of the widely accepted YOLOv5 and the latest version of YOLO which is YOLOv7. Experiments were carried out by training a custom model with both YOLOv5 and YOLOv7 independently in order to consider which one of the two performs better in terms of precision, recall, mAP@0.5 and mAP@0.5:0.95. The dataset used in the experiment is a custom dataset for Remote Weapon Station which consists of 9,779 images containing 21,561 annotations of four classes gotten from Google Open Images Dataset, Roboflow Public Dataset and locally sourced dataset. The four classes are Persons, Handguns, Rifles and Knives. The experimental results of YOLOv7 were precision score of 52.8%, recall value of 56.4%, mAP@0.5 of 51.5% and mAP@0.5:0.95 of 31.5% while that of YOLOv5 were precision score of 62.6%, recall value of 53.4%, mAP@0.5 of 55.3% and mAP@0.5:0.95 of 34.2%. It was observed from the experiment conducted that YOLOv5 gave a better result than YOLOv7 in terms of...

Journal of Computing and Social Informatics, 2023