Epilepsy, a debilitating neurological disorder characterized by recurring seizures, affects millions of people around the world. This condition poses significant challenges for patients and healthcare systems. Shockingly, there are approximately 65 million cases of epilepsy globally with varying rates of occurrence in high-income and low-middle-income nations, ranging from 45 to 82 cases per 100,000 people annually. Alarmingly, more than 90% of epilepsy cases in these areas are undiagnosed and untreated, contributing to what is known as the epileptic diagnostic gap. An electroencephalogram, or EEG, is a medical test that captures electrical activity in the brain. EEG enables medical professionals to track brain activity and identify conditions like epilepsy. In countries with low incomes, epilepsy often goes unnoticed because there is a shortage of healthcare professionals and the expenses involved in acquiring EEG recording equipment are quite high. In this paper, an analytical method has proposed for the detection of epilepsy using dataset from Nigeria. The signal data trained the model with various machine learning algorithms, applied dimensionality reduction and implemented hyperparameter tuning. The paper can bridge the gap in epilepsy diagnosis and potentially revolutionize healthcare provision by offering trustworthy and accessible diagnostic procedures.