Early diagnosis of cardiac abnormalities depends on accurate classification of heart sounds, but centralized training methods run the danger of violating patient privacy. We thus propose a privacy-preserving and reliable heart sound abnormality detection system combining Blockchain Technology with Federated Learning (FL). Training is spread among seven clients, each simulating an independent data source, using a preprocessed dataset from the PhysioNet Challenge 2016 to enable distributed learning without sharing raw data. CNN-LSTM model using FedAvg achieved the best performance: 94\% accuracy, 0.90 precision, 0.96 recall, and an AUC of 0.98 among five deep learning architectures evaluated with FedAvg and FedProx strategies. Along with metadata including client ID and round number, SHA-256 hashes of local and global model weights were recorded on a local Ethereum blockchain following every communication round to guarantee model integrity. The hash of the final model is revalidated against the blockchain to confirm authenticity prior to deployment. It then guarantees safe, distributed, clinically valuable AI-based diagnostics by real-time classification of heart sounds as normal or abnormal.
Many are wary of storing and processing data in the cloud because of the prevalence of hostile assaults on mobile and wireless communication networks, which raises serious privacy and security concerns. Using Blockchain as an example, this article investigates the feasibility of developing a trustworthy decentralized authentication system. Utilizing a blockchain technique to enhance the heftiness of multiple data checks and an optimized number of secured features from the bioacoustics signal, in place of traditional biometric features, ensure high security for the bioacoustics signal authentication mechanism. Verified authentication and monitoring of terminal activities are both made possible by it. Then, to provide security at every terminal and edge node, lightweight cryptography (LWC) is created. Lastly, the bastion of the catching approach is the belief-propagation(BP) strategy, which retrains the bioacoustics signal’s attributes. The hit ratio is improved and the delay time is decreased. With a blockchain paradigm for data openness, the investigational setup utilizes bioacoustics signals for authentication instead of standard biometric features, and the efficiency of numerous checks is improved. Both security and privacy are enhanced when this occurs. The association between MFCC and LPCC was 0.9517.