Advancing deep learning-based acoustic leak detection methods towards application for water distribution systems from a data-centric perspective.

Against the backdrop of severe leakage issue in water distribution systems (WDSs), numerous researchers have focused on the development of deep learning-based acoustic leak detection technologies. However, these studies often prioritize model development while neglecting the importance of data. This research explores the impact of data augmentation techniques on enhancing deep learning-based acoustic leak detection methods. Five random transformation-based methods-jittering, scaling, warping, iterated amplitude adjusted Fourier transform (IAAFT), and masking-are proposed. Jittering, scaling, warping, and IAAFT directly process original signals, while masking operating on time-frequency spectrograms. Acoustic signals from a real-world WDS are augmented, and the efficacy is validated using convolutional neural network classifiers to identify the spectrograms of acoustic signals. Results indicate the importance of implementing data augmentation before data splitting to prevent data leakage and overly optimistic outcomes. Among the techniques, IAAFT stands out, significantly increasing data volume and diversity, improving recognition accuracy by over 7%. Masking enhances performance mainly by compelling the classifier to learn global features of the spectrograms. Sequential application of IAAFT and masking further strengthens leak detection performance. Furthermore, when applying a complex model to acoustic leakage detection through transfer learning, data augmentation can also enhance the effectiveness of transfer learning. These findings advance artificial intelligence-driven acoustic leak detection technology from a data-centric perspective towards more mature applications.

Trapezoidal pile-up nuclear pulse parameter identification method based on deep learning transformer model.

Pile-up between adjacent nuclear pulses is unavoidable in the actual detection process. Some scholars have tried to apply deep learning techniques to identify pile-up nuclear pulse parameters. However, traditional deep learning recurrent neural networks (RNNs) suffer from inefficient pulse recognition and poor recognition of pile-up nuclear pulses with short intervals between adjacent pulses. In this paper, a Transformer model with an attention mechanism as the core to recognize pile-up nuclear pulses is innovatively applied, aiming to provide a more accurate and efficient method for pile-up nuclear pulse recognition. Thus, it gives a better help for the spectrum correction with a high count rate.