Accurate heartbeat detection is an essential requirement in modern healthcare monitoring, offering critical insights into cardiac health and cardiorespiratory fitness. This chapter introduces a novel multimodal data fusion technique that leverages discrete wavelet transform (DWT) to enhance beat detection accuracy by integrating electrocardiogram (ECG) and photoplethysmogram (PPG) signals—especially in ambulatory and noise-prone environments. Key signal characteristics are extracted in the wavelet domain and merged into a unified feature signal through a weighted averaging process, where the weights are determined using a signal quality index tailored for periodic or quasi-periodic signals with varying morphologies. The final fused signal is then used for heartbeat peak detection. The performance of the algorithm is rigorously evaluated under diverse noise conditions and signal-to-noise ratios (SNRs), ranging from –30 to 50 dB. The method consistently achieves high sensitivity (99.69%), positive predictive value (99.64%), and low relative error in beat-to-beat interval detection, significantly outperforming state-of-the-art single-channel approaches. This chapter highlights the algorithm’s potential for real-time, robust heart rate monitoring in wearable and IoT-based healthcare systems, where conventional methods may fail due to noisy or incomplete data.