<p>Accurate State of Charge estimation is critical for the reliable and efficient operation of lithium-ion batteries in applications such as electric vehicles, consumer electronics and energy storage systems. Traditional model-based approaches, such as Kalman Filters, have been widely used for SOC estimation; however, they are limited by their reliance on accurate system models and parameter tuning. In contrast, data-driven methods, particularly Artificial Intelligence techniques, have emerged as powerful alternatives due to their ability to learn complex nonlinear relationships from battery data. This paper presents a comparative study and hardware implementation of SOC estimation using Feedforward Neural Networks alongside Extended Kalman Filter and Unscented Kalman Filter methods. The performance of these techniques is evaluated in terms of accuracy, computational complexity, and real-time feasibility. The results demonstrate that AI-driven methods, particularly deep learning models, outperform traditional approaches in estimation accuracy, making them promising candidates for next-generation battery management systems. This study provides insights into the advantages, limitations, and practical considerations of AI-based SOC estimation, contributing to the advancement of intelligent battery monitoring and control.</p>