Saliha Benkerdagh

Cardiovascular diseases remain one of the primary causes of death worldwide, highlighting the importance of early detection. PhonoCardioGraphy (PCG) provides a non-invasive approach to identify cardiac abnormalities. However, its effectiveness is limited by scarce datasets and signal variability. Deep learning (DL) models have shown promising results, but their performance strongly depends on the availability of sufficient training data. In this study, PCG signals were converted into spectrogram representations, and four data augmentation techniques were applied individually and in combination, followed by a systematic evaluation. A baseline convolutional neural network (CNN) and several transfer learning models were trained on both original and augmented datasets. The results demonstrate that combining augmentation techniques yields the best performance. The proposed CNN achieved an accuracy of 94%, representing a 5.6% improvement over its performance without data augmentation. In contrast, transfer learning such as VGG16, ResNet50, and DenseNet121 showed improvements of 3.4%, 3.4%, and 2.2%, respectively. These findings indicate that the proposed augmentation strategy effectively improves the classification performance and generalization capability of DL models for heart sound classification.

Summary: Data dissemination in vehicular ad hoc network (VANET) is emerging as a critical area of research. One of the challenges posed by this domain is the reliability of connection, which depends on many parameters, such as the bandwidth consumption, transmission delay, and data quality of service (QoS). Dissemination of emergency messages is very critical since the network topology is changing frequently and rapidly, which leads to data loss. So, it is necessary to develop new protocols and enhance dissemination schemes in VANET to avoid more emergencies and hazards cases. In this regard, we have proposed a new strategy, which consists of data handling before dissemination process as the first step of our scheme. In this phase, the original message is optimized in order to reduce the number of exchanged packets. The second part of this proposition consists of constructing fast and stable clusters to improve the message delivery time and to procure efficient bandwidth consumption. This approach is based on a Fitness function, which takes into account different parameters such as the transmission period, the connectivity degree, the relative velocity, and the link lifetime validity. Since exchanging data in VANET is an important process, routing phase is proposed to perform data exchange among clusters. It is based on a rapid and real‐time heuristic (real‐time adaptive A* [RTAA*]). To evaluate the reliability of the proposed approach, an urban scenario is used with different simulation parameters. The simulation results show that our proposed approach presents a better stability and efficiency performance compared with the discussed approaches. The proposed approach improves the performance of cluster duration (5% − 25%), delivery rate (2% − 8%), and the overhead (5% − 35%) on average compared with the discussed approaches.