Non-neural machine learning (ML) and deep learning (DL) are used to predict system failures in industrial maintenance. However, only a few studies have assessed the effect of varying the amount of past data used to make a prediction and the extension in the future of the forecast. This study evaluates the impact of the size of the reading window and of the prediction window on the performances of models trained to forecast failures in three datasets of (1) an industrial wrapping machine working in discrete sessions, (2) an industrial blood refrigerator working continuously, and (3) a nitrogen generator working continuously. A binary classification task assigns the positive label to the prediction window based on the probability of a failure to occur in such an interval. Six algorithms (logistic regression, random forest, support vector machine, LSTM, ConvLSTM, and Transformers) are compared on multivariate time series. The dimension of the prediction windows plays a crucial role and the results highlight the effectiveness of DL approaches in classifying data with diverse time-dependent patterns preceding a failure and the effectiveness of ML approaches in classifying similar and repetitive patterns preceding a failure.

Iconography studies the visual content of artworks by considering the themes portrayed in them and their representation. Computer Vision has been used to identify iconographic subjects in paintings and Convolutional Neural Networks enabled the effective classification of characters in Christian art paintings. However, it still has to be demonstrated if the classification results obtained by CNNs rely on the same iconographic properties that human experts exploit when studying iconography and if the architecture of a classifier trained on whole artwork images can be exploited to support the much harder task of object detection. A suitable approach for exposing the process of classification by neural models relies on Class Activation Maps, which emphasize the areas of an image contributing the most to the classification. This work compares state-of-the-art algorithms (CAM, Grad-CAM, Grad-CAM++, and Smooth Grad-CAM++) in terms of their capacity of identifying the iconographic attributes that determine the classification of characters in Christian art paintings. Quantitative and qualitative analyses show that Grad-CAM, Grad-CAM++, and Smooth Grad-CAM++ have similar performances while CAM has lower efficacy. Smooth Grad-CAM++ isolates multiple disconnected image regions that identify small iconographic symbols well. Grad-CAM produces wider and more contiguous areas that cover large iconographic symbols better. The salient image areas computed by the CAM algorithms have been used to estimate object-level bounding boxes and a quantitative analysis shows that the boxes estimated with Grad-CAM reach 55% average IoU, 61% GT-known localization and 31% mAP. The obtained results are a step towards the computer-aided study of the variations of iconographic elements positioning and mutual relations in artworks and open the way to the automatic creation of bounding boxes for training detectors of iconographic symbols in Christian art images.

Context. Ultraluminous X-ray sources (ULX) are extragalactic objects with observed X-ray luminosities largely above the Eddington limit for a 10 M_⊙ black hole. Currently, it is believed that ULXs host super-Eddington accreting neutron stars or stellar mass black holes. However, the exact proportion of the two populations of compact objects is not yet known. Aims. We investigate the properties of the ULX NGC 4559 X7 (hereafter X7), which shows flux variability up to a factor of five on both long (months to years) and short (hours to days) timescales. A flaring activity was also observed during the highest flux epochs of the source. Flares are unpredictable. They have different durations (but similar rising and decay times) and are all flat topped in flux. The latter suggests that at the flare peaks, there is likely a common switch-off mechanism for the accretion onto the compact object. Methods. We analysed all available XMM-Newton and Swift/XRT observations in order to fully investigate the spectral and temporal evolution of X7, looking for short- and long-term variability. We applied a Lomb-Scargle search to look for long-term periodicities. We also looked for coherent signals through accelerated searches that included orbital corrections. We described the X7 spectral properties with two thermal components plus a cut-off power-law model. Results. We found three well-defined spectral states where the spectral variability is mainly driven by the two harder components, with the thermal one clearly following a correlation between its temperature and luminosity. In addition, a pulsed signal at 2.6 s–2.7 s was detected in two XMM-Newton observations. The significance of these coherent signals is relatively weak, but they are found in two different observations with the same parameter space for the orbital properties. If confirmed, the pulsation would imply a high spin-down of 10⁻⁹ s s⁻¹, which could be extreme amongst the known pulsating ULXs, and X7 would become a new extragalactic ULX pulsar. Conclusions. We discuss the spectral and temporal results of X7 in the context of super-Eddington accretion onto a stellar-mass compact object. In particular, we suggest that the source might likely host a neutron star.

In both industrial and residential contexts, compressor-based machines, such as refrigerators, heat, ventilation, and air conditioning systems, heat pumps, and chillers, are essential to fulfil production and consumers’ needs. The diffusion of sensors and internet of things connectivity support the development of monitoring systems that can detect and predict faults, identify behavioural shifts, and forecast the operational status of machines and their components. The focus of this paper is to survey the recent research on such tasks as fault detection (FD), fault prediction (FP), forecasting, and change point detection (CPD) applied to multivariate time series characterizing the operations of compressor-based machines. These tasks play a critical role in improving the efficiency and longevity of machines by minimizing downtime and maintenance costs and improving energy efficiency. Specifically, FD detects and diagnoses faults, FP predicts such occurrences, forecasting anticipates the future value of characteristic variables of machines, and CPD identifies significant variations in the behaviour of the appliances, such as a change in the working regime. We identify and classify the approaches to the tasks mentioned above, compare the algorithms employed, highlight the gaps in the current state of the art, and discuss the most promising future research directions in the field.

Object Detection requires many precise annotations, which are available for natural images but not for many non-natural data sets such as artworks data sets. A solution is using Weakly Supervised Object Detection (WSOD) techniques that learn accurate object localization from image-level labels. Studies have demonstrated that state-of-the-art end-to-end architectures may not be suitable for domains in which images or classes sensibly differ from those used to pre-train networks. This paper presents a novel two-stage Weakly Supervised Object Detection approach for obtaining accurate bounding boxes on non-natural data sets. The proposed method exploits existing classification knowledge to generate pseudo-ground truth bounding boxes from Class Activation Maps (CAMs). The automatically generated annotations are used to train a robust Faster R-CNN object detector. Quantitative and qualitative analysis shows that bounding boxes generated from CAMs can compensate for the lack of manually annotated ground truth (GT) and that an object detector, trained with such pseudo-GT, surpasses end-to-end WSOD state-of-the-art methods on ArtDL 2.0 (≈41.5% mAP) and IconArt (≈17% mAP), two artworks data sets. The proposed solution is a step towards the computer-aided study of non-natural images and opens the way to more advanced tasks, e.g., automatic artwork image captioning for digital archive applications.

Gravitational lensing is the relativistic effect generated by massive bodies, which bend the space-time surrounding them. It is a deeply investigated topic in astrophysics and allows validating theoretical relativistic results and studying faint astrophysical objects that would not be visible otherwise. In recent years, machine learning methods have been applied to support the analysis of the gravitational lensing phenomena by detecting lensing effects in datasets consisting of images associated with brightness variation time series. However, the state-of-the-art approaches either consider only images and neglect time-series data or achieve relatively low accuracy on the most difficult datasets. This paper introduces DeepGraviLens, a novel multi-modal network that classifies spatio-temporal data belonging to one non-lensed system type and three lensed system types. It surpasses the current state-of-the-art accuracy results by $$\approx 3\%$$≈ 3 % to $$\approx 11\%$$≈ 11 % , depending on the considered data set. Such an improvement will enable the acceleration of the analysis of lensed objects in upcoming astrophysical surveys, which will exploit the petabytes of data collected, e.g., from the Vera C. Rubin Observatory.