Gamma spectroscopy is a technique for identifying radioactive sources and evaluating their activity. Reliable estimation of activity levels remains challenging due to various physical effects, such as the pile-up effect and dead time. In numerous applications, it is critical to provide an accurate estimation of the source activity from short-duration signals. This study compares three deep neural network (DNN) architectures: Unet, Long Short Term Memory (LSTM), and an application-tailored convolutional neural network (CNN). Due to the lack of annotated datasets in the field, experiments are performed on simulated yet realistic signals and demonstrate that the application-tailored CNN outperforms both Unet and LSTM architectures. We show that the provided activity estimators have a lower variance than current state-of-the-art methods, which makes the approach well-adapted to analyze short-time signals. However, results on real signals illustrate the necessity of fully simulating pulses to match real pulse shapes, indicating that current approaches still face challenges in practical applications for a large class of detectors.

One of the main measurements performed in a nuclear spectroscopy experiment is the activity of an unknown radioactive source. The use of digital apparatus and physical perturbations, known as pile-up effect, make this measurement difficult when the activity of the source is high. In recent contributions, the use of compressive sensing methods yielded good estimates of this activity. This paper presents an improvement of a previously described method. It takes into account the fact that the signal used for the activity estimation is sampled, and introduces another plug-in estimation to counterbalance the bias introduced by the sampling. Results on simulations and real data validate the proposed approach, but illustrate that a good fit between the dictionary used and the signal at hand is required.

The electrocardiogram (ECG) was the first biomedical signal for which digital signal processing techniques were extensively applied. By its own nature, the ECG is typically a sparse signal, composed of regular activations (QRS complexes and other waveforms, such as the P and T waves) and periods of inactivity (corresponding to isoelectric intervals, such as the PQ or ST segments), plus noise and interferences. In this work, we describe an efficient method to construct an overcomplete and multi-scale dictionary for sparse ECG representation using waveforms recorded from real-world patients. Unlike most existing methods (which require multiple alternative iterations of the dictionary learning and sparse representation stages), the proposed approach learns the dictionary first, and then applies a fast sparse inference algorithm to model the signal using the constructed dictionary. As a result, our method is much more efficient from a computational point of view than other existing algorithms, thus becoming amenable to dealing with long recordings from multiple patients. Regarding the dictionary construction, we located first all the QRS complexes in the training database, then we computed a single average waveform per patient, and finally we selected the most representative waveforms (using a correlation-based approach) as the basic atoms that were resampled to construct the multi-scale dictionary. Simulations on real-world records from Physionet’s PTB database show the good performance of the proposed approach.

Gamma-ray spectroscopy is essential in nuclear science, enabling the identification of radioactive materials through energy spectrum analysis. However, high count rates lead to pile-up effects, resulting in spectral distortions that hinder accurate isotope identification and activity estimation. This phenomenon highlights the need for automated and precise approaches to pile-up correction. We propose a novel deep learning (DL) framework plugging count rate information of pile-up signals with a 2D attention U-Net for energy spectrum recovery. The input to the model is an Energy–Duration matrix constructed from preprocessed pulse signals. Temporal and spatial features are jointly extracted, with count rate information embedded to enhance robustness under high count rate conditions. Training data were generated using an open-source simulator based on a public gamma spectrum database. The model’s performance was evaluated using Kullback–Leibler (KL) divergence, Mean Squared Error (MSE) Energy Resolution (ER), and Full Width at Half Maximum (FWHM). Results indicate that the proposed framework effectively predicts accurate spectra, minimizing errors even under severe pile-up effects. This work provides a robust framework for addressing pile-up effects in gamma-ray spectroscopy, presenting a practical solution for automated, high-accuracy spectrum estimation. The integration of temporal and spatial learning techniques offers promising prospects for advancing high-activity nuclear analysis applications.

Standard recordings of electrocardiograhic signals are contaminated by a large variety of noises and interferences, which impair their analysis and the further related diagnosis. In this paper, we propose a method, based on compressive sensing techniques, to remove the main noise artifacts and to locate the main features of the pulses in the electrocardiogram (ECG). The motivation is to use Trend Filtering with a varying proximal parameter, in order to sequentially capture the peaks of the ECG, which have different functional regularities. The practical implementation is based on an adaptive version of the ADMM (alternating direction method of multiplier) algorithm. We present results obtained on simulated signals and on real data illustrating the validity of this approach, showing that results in peak localization are very good in both cases and comparable to state of the art approaches.