Atrial fibrillation (AF) is a common cardiac arrhythmia, and its early detection is crucial for timely treatment. Conventional methods, such as Electrocardiogram (ECG), can be intrusive and require specialized equipment, whereas Photoplethysmography (PPG) offers a non-invasive alternative. In this study, we present a feature fusion approach for AF detection using attention-based Bidirectional Long Short-Term Memory (BiLSTM) and PPG signals. We extract frequency domain (FD) and time domain (TD) features from PPG signals, combine them with deep learning features generated from an attention-based BiLSTM network, and pass the fusion features through a softmax function. Our approach achieves high accuracy (96.5%) and favorable performance metrics (recall 93.20%, precision 94.50%, and F-score 93.09%), improving AF prediction and diagnosis, and providing support for clinicians in their diagnostic processes.