Timi' Okoya

Lead City University , Ibadan Nigeria, Computer Science, Faculty Member

Follower

Following

Public Views

I am an AI and systems leader focused on building intelligent infrastructure and developing technical talent in emerging markets.

I currently serve as an Assistant Lecturer at Lead City University, where I teach and mentor the next generation of engineers while advancing work in artificial intelligence and data-driven systems.
I hold a Master’s degree in Artificial Intelligence and Robotics from Sapienza University of Rome, with research experience spanning human-robot interaction, intelligent systems, and applied machine learning.

I have led at the executive level as a CTO, where I worked on designing and scaling technology platforms, gaining firsthand insight into the realities of execution, failure, and system-level thinking.

My work sits at the intersection of AI, leadership, and strategy—focused not just on building systems, but on building people and institutions that can sustain them.

less

Interests

Uploads

Papers by Timi' Okoya

An Intelligent Conversational Assistant for Automobile Fault Diagnostics

Significant changes are sweeping through the worldwide automobile industry, which can largely be ... more Significant changes are sweeping through the worldwide automobile industry, which can largely be attributed to developments in Artificial Intelligence applied to vehicle maintenance. Artificial Intelligence techniques are used in fields like predictive maintenance, predictive quality, safety analytics, and warranty analytics. The system creates valuable insights from the data generated on these vehicles to help us predict and prevent failures. This technology can predict the remaining useful life and detect failures or degradation in performance at an early stage. However, despite the fact that the automotive industry has undergone profound transformations fueled by technological advancements, traditional methods of vehicle diagnostics continue to present significant challenges for both car owners and mechanics alike. Therefore, this study aims to develop an Intelligent Conversational Assistant for automobile fault diagnostics. The application was developed using the Google's Android Studio IDE in conjunction with the Kotlin programming languages for Android development. The study demonstrates the potential of Artificial Intelligence and natural language processing technologies in automotive diagnostics, in terms of better diagnostic accuracy, and improved positive user experience.

Download

ADVANCING MARINE ECOSYSTEM CONSERVATION: OBJECT DETECTION WITH AUVS AND REAL-TIME ALGORITHMS

Advancements in computer vision, particularly in the realms of image segmentation and object dete... more Advancements in computer vision, particularly in the realms of image segmentation and object detection, are pivotal for marine ecosystem monitoring, which is crucial for conservation endeavours. Given the inherent risks involved in human observation of marine environments, the development of Autonomous Underwater Vehicles (AUVs) is imperative for such tasks. In fisheries, especially in aquaculture, employing AUVs for fish monitoring holds significant importance in sustaining marine ecosystems. This research investigates real-time object detection utilising advanced algorithmsspecifically, masked convolutional neural networks implemented via Detectron2, a library for detection and segmentation algorithms developed by Meta AI Research. Leveraging the Google Open Images v7 dataset, which encompasses a wide array of fish types differing in size and shape, the study evaluates performance metrics including precision, recall, Intersection over Union (IoU), and mean Average Precision (mAP). Through multiple training iterations under a transfer learning paradigm and building on the LVIS large vocabulary instance segmentation pre-training dataset, the study achieves commendable detection performance, showcasing the effectiveness of the proposed framework for automated, scalable marine ecosystem monitoring.

Download

DEEP LEARNING PLATFORM COMPARISONS & A PREDICTIVE MODEL FOR REAL-TIME OFFLINE APPLICATION

This paper investigates predictive modelling, a mathematical technique for analyzing data pattern... more This paper investigates predictive modelling, a mathematical technique for analyzing data patterns to forecast future events and outcomes. As a key element of predictive analytics, predictive modelling leverages machine learning and data mining methods to anticipate activity, behavior, and trends based on both historical and current datasets. The study first compares various computing platforms suitable for deep learning applications. It then focuses on predicting the torque required by an exoskeleton system designed to assist users in lifting objects with minimal effort. Using sensor data embedded within the exoskeleton, torque predictions are performed in an offline, real-time setting, utilizing available feature inputs. The results demonstrate the effectiveness of predictive modelling for accurately estimating torque requirements based on historical sensor data. Finally, the paper discusses potential offline applications of the system, highlighting the broader implications of successful torque prediction for enhancing assistive technologies.

Download

EXPERIMENTAL STUDY ON LUMINANCE PREPROCESSING FOR ENERGY-AWARE HTTP-BASED MOBILE VIDEO STREAMING

In mobile multimedia services, preserving the battery life at the terminal is of utmost importanc... more In mobile multimedia services, preserving the battery life at the terminal is of utmost importance for user satisfaction, and suitable media processing at the device can be performed in order to reduce the brightness of the presented video, and to relent battery discharge. In this paper, we present a few experimental results assessing the impact, on the terminal power consumption, of a luminance preprocessing stage realized at the server side during mobile video streaming sessions. Based on these results, we recognize that luminance pre-processing at the server side reduces terminal consumption during mobile streaming much to the same extent as the processing realized at the client side. We further discuss the systems advantages of assigning this functionality to the server side. Specifically, this first result paves the way to further study on energyaware streaming systems, where the streamed video data can be selected not only based on the encoding rates, as in conventional streaming, but also of energy-demanding video characteristics.

Download

Timi' Okoya

Uploads

Papers by Timi' Okoya

Log In