Abstract
When never produced as much data as today, and tomorrow will probably produce even more data. The increase is due not only to the larger number of data sources, but also because the source can continuously produce more recent data. The discovery of temporal patterns in continuously generated data is the main goal in many forecasting tasks, such as the average value of a currency or the average temperature in a city, in the next day. In these tasks, it is assumed that the time difference between two consecutive values produced by the same source is constant, and the sequence of values form a time series. The importance, and the very large number, of time series forecasting tasks make them one of the most popular data analysis application, which has been dealt with by a large number of different methods. Despite its popularity, there is a dearth of research aimed at comprehending the conditions under which these methods present high or poor forecasting performances. Empirical studies, although common, are challenged by the limited availability of time series datasets, restricting the extraction of reliable insights. To address this limitation, we present tsMorph, a tool for generating semi-synthetic time series through dataset morphing. tsMorph works by creating a sequence of datasets from two original datasets. The characteristics of the generated datasets progressively depart from those of one of the datasets and a convergence toward the attributes of the other dataset. This method provides a valuable alternative for obtaining substantial datasets. In this paper, we show the benefits of tsMorph by assessing the predictive performance of the Long Short-Term Memory Network and DeepAR forecasting algorithms. The time series used for the experiments come from the NN5 Competition. The experimental results provide important insights. Notably, the performances of the two algorithms improve proportionally with the frequency of the time series. These experiments confirm that tsMorph can be an effective tool for better understanding the behaviour of forecasting algorithms, delivering a pathway to overcoming the limitations posed by empirical studies and enabling more extensive and reliable experiments. Furthermore, tsMorph can promote Responsible Artificial Intelligence by emphasising characteristics of time series where forecasting algorithms may not perform well, thereby highlighting potential limitations.

Abstract
In the field of vital signs monitoring, there is a growing trend towards transposing monitoring technologies into people’s daily lives. Currently, the work revolves around wearables. However, wearables have known limitations, mainly the need for voluntary actions to acquire the signals of interest, low battery life, and abandonment, which leads to the search for new solutions. An evolution is the integration of sensors into the environment or everyday objects through invisible devices (also known as “off the person” sensing). Properly assessing and matching the patient and their caregiver to the appropriate monitoring technology, while considering the suitability of the home environment for device operation and maintenance is a challenge that depends on sound human factors principles. This article reviews the current key features and technologies to provide an overview of the existing invisibles landscape.

Abstract
Breast cancer locoregional treatment causes alterations to the physical aspect of the breast, often negatively impacting the self-esteem of patients unaware of the possible aesthetic outcomes of those treatments. To improve patients' self-esteem and enable a more informed choice of treatment when multiple options are available, the possibility to predict how the patient might look like after surgery would be of invaluable help. However, no work has been proposed to predict the aesthetic outcomes of breast cancer treatment. As a first step, we compare traditional computer vision and deep learning approaches to reproduce asymmetries of post-operative patients on pre-operative breast images. The results suggest that the traditional approach is better at altering the contour of the breast. In contrast, the deep learning approach succeeds in realistically altering the position and direction of the nipple.

Abstract
Phobias are characterized as the excessive or irrational fear of an object or situation, and specific phobias affect about 10% of the world population. Blood-injection-injury phobia is a specific phobia that has a unique physical response to phobic stimuli, that is, a vasovagal syncope that causes the person to faint. Phobos is a serious game intended for blood phobia treatment that was created to be played in virtual reality with an HTC Vive that has photorealistic graphics to provide a greater immersion. We also developed a console application in C# for electrocardiography sensor connectivity and data acquisition, which gathers a 1 min baseline reading and then has continuous data acquisition during gameplay. Usability tests were conducted with self-reported questionnaires and with a case study population of 10 testers, which gave insight into the previous game experience of the tester for both digital games and virtual reality games, evaluating the discomfort for hardware on both the sensor and the virtual reality headset, as well as the game regarding usability, user experience, level of immersion, and the existence of motion sickness and its source. The results corroborate that the immersion of the game is good, which suggests that it will help with triggering the phobia.

Abstract
The calibration of sensors stationed along a cable in marine observatories is a time-consuming and expensive operation that involves taking the mooring out of the water periodically. In this paper, we present a method that allows an underwater vehicle to approach a mooring, in order to take reference measurements along the cable for in-situ sensor calibration. We use the vehicle's Mechanically Scanned Imaging Sonar (MSIS) to identify the cable's reflection within the sonar image. After pre-processing the image to remove noise, enhance contour lines, and perform smoothing, we employ three detection steps: 1) selection of regions of interest that fit the cable's reflection pattern, 2) template matching, and 3) a track-before-detect scheme that utilized the vehicle's motion. The later involves building a lattice of template matching responses for a sequence of sonar images, and using the Viterbi algorithm to find the most probable sequence of cable locations that fits the maximum speed assumed for the surveying vessel. Performance is explored in pool and sea trials, and involves an MSIS onboard an underwater vehicle scanning its surrounding to identify a steel-core cable. The results show a sub-meter accuracy in the multi-reverberant pool environment and in the sea trial. For reproducibility, we share our implementation code.

Abstract
The dark compact object at the centre of the Milky Way is well established to be a supermassive black hole with mass M-center dot similar to 4.3 x 10(6) M-circle dot, but the nature of its environment is still under debate. In this work, we used astrometric and spectroscopic measurements of the motion of the star S2, one of the closest stars to the massive black hole, to determine an upper limit on an extended mass composed of a massive vector field around Sagittarius A*. For a vector with effective mass 10(-19) (less than or similar to) m(s less than or similar to) 10(-18) eV, our Markov chain Monte Carlo analysis shows no evidence for such a cloud, placing an upper bound M-cloud (less than or similar to) 0.1 % M-center dot at 3 sigma confidence level. We show that dynamical friction exerted by the medium on S2 motion plays no role in the analysis performed in this and previous works, and can be neglected thus.