Samuel R.

Key Skills

Software

Playment

Other

Top Subject Matter

No subject matter listed

Top Data Types

Document

Image

Text

Top Task Types

Classification

Computer Programming/Coding

Evaluation/Rating

Routing

Freelancer Overview

I have an experience in machine learning, data analytics, and AI model development, with a strong academic and professional background in computer science. Over the years, I have worked on research projects involving machine learning-driven threat prediction, sentiment analysis, early depression detection, and predictive modeling in IoT-enabled 5G networks, all of which required rigorous data preprocessing, labeling, and feature engineering. My publications demonstrate proficiency in applying supervised and unsupervised learning techniques, ensemble methods, and neuro-fuzzy systems, highlighting my ability to prepare, validate, and analyze complex datasets for AI applications. In addition to research, my teaching and consulting roles have equipped me with hands-on expertise in data management, annotation, and transformation for AI training pipelines

Labeling Experience

Machine Learning Approach for Path Loss Prediction in Urban Drive 5G Network Environments. International Journal of Microwave & Optical Technology

OtherTextClassificationFine-tuning

The study focuses on predicting path loss in IoT-enabled 5G networks within urban drive environments. IoT data was sourced from the Zenodo repository, and several empirical path loss models were analyzed. Their results were then compared with machine learning approaches. The findings revealed that machine learning methods outperformed conventional path loss models, offering greater efficiency and more reliable signal connectivity.

2024 - 2025

Enhancing Job Recruitment Prediction through Supervised Learning and Structured Intelligent System: A Data Analytics Approach

OtherDocumentRelationshipClassification

Data Analytics for optimal recruitment process in Akwa Ibom State

2024 - 2024

Early Depression Prediction among Nigerian University Students Using Adaptive Neuro- Fuzzy Inference System (ANFIS).

OtherTextRelationshipClassification

This study addresses the growing challenge of depression among Nigerian university students by developing an intelligent system for early prediction and detection. Using data collected on key psychological, academic, and demographic factors, the research applies an Adaptive Neuro-Fuzzy Inference System (ANFIS)—a hybrid model that integrates the learning ability of neural networks with the reasoning capability of fuzzy logic. The system analyzes input features to identify patterns and predict the likelihood of depression at an early stage. The results demonstrate that ANFIS provides improved accuracy and robustness compared to traditional statistical methods, offering a reliable decision-support tool for mental health monitoring. By enabling early detection, this work has significant implications for student well-being, targeted intervention programs, and the broader application of AI in mental health diagnostics within educational environments.

2022 - 2024

Education

Work History