ABSTRACT During sleep, some people experience breathing difficulties, leading to a condition known as sleep apnoea, which can result in suffocation. This study focuses on detecting sleep apnoea using Artificial Neural Network (ANN) and Support Vector Machine (SVM) classifiers, incorporating discrete wavelet transform for feature extraction. The proposed method aims to denoise Electrocardiography (ECG) signals and extract four statistical features, focusing on the gamma-band of the ECG signal. By comparing accuracy and speed of the models with varying bit representations on Field Programmable Gate Array (FPGA) technology, the study achieved high accuracy (92% for ANN and 88% for SVM with 32 bits). Implementing the models on FPGA allows real-world applications like home-based sleep monitoring systems. Utilizing wavelet transform and statistical features hold potential to further improve the detection accuracy. Overall, this study showcases an effective approach for sleep apnoea detection.