The paper proposes a novel approach for extraction of useful information and blind source separation of signal components from noisy data in the time-frequency domain. The method is based on the local Rényi entropy calculated inside adaptive, data-driven 2D regions, the sizes of which are calculated utilizing the improved, relative intersection of confidence intervals (RICI) algorithm. One of the advantages of the proposed technique is that it does not require any prior knowledge on the signal, its components, or noise, but rather the processing is performed on the noisy signal mixtures. Also, it is shown that the method is robust to the selection of time-frequency distributions (TFDs). It has been tested for different signal-to-noise-ratios (SNRs), both for synthetic and real-life data. When compared to fixed TFD thresholding, adaptive TFD thresholding based on RICI rule and the 1D entropy-based approach, the proposed adaptive method significantly increases classification accuracy (by up to 11.53%) and F1 score (by up to 7.91%). Hence, this adaptive, data-driven, entropy-based technique is an efficient tool for extracting useful information from noisy data in the time-frequency domain.

No abstract

No abstract

Network analysis has been successfully applied in software engineering to understand structural effects in the software. System software is represented as a network graph, and network metrics are used to analyse system quality. This study is motivated by a previous study, which represents the software structure as three-node subgraphs and empirically identifies that software structure continuously evolves over system releases. Here, the authors extend the previous study to analyse the relation of structural evolution and the defectiveness of subgraphs in the software network graph. This study investigates the behaviour of subgraph defects through software evolution and their impact on system defectiveness. Statistical methods were used to study subgraph defectiveness across versions of the systems and across subgraph types. The authors conclude that software versions have similar behaviours in terms of average subgraph type defectiveness and subgraph frequency distributions. However, different subgraph types have different defectiveness distributions. Based on these conclusions, the authors motivate the use of subgraph-based software representation in defect predictions and software modelling. These promising findings contribute to the further development of the software engineering discipline and help software developers and quality management in terms of better modelling and focusing their testing efforts within the code structure represented by subgraphs.