Abstract
Learning environments unquestionably enable learners to develop their pedagogical and scientific processes efficiently and effectively. Thus, considering the impossibility of not having conditions of autonomy over the routine underlying the studies and, consequently, not having guarantees of the learning carried out makes the learners experience gaps in the domain of materials adequate to their actual needs. The paper's objective is to present the relevance of the applicability of Artificial Intelligence in Recommendation Systems, reinforced through the Assurance of Learning, oriented towards adaptive-personalized practice in corporate e-learning contexts. The research methodology underlying the work fell on Design Science Research, as it is considered adequate to support the research, given the need to carry out the design phases, development, construction, evaluation, validation of the artefact and, finally, communication of the results. The main results instigate the development of an Adaptive-Personalized Learning framework for corporate e-learning, provided with models of Artificial Intelligence and guided using the Assurance of Learning process. It becomes central that learners can enjoy adequate academic development. In this sense, the framework has an implicit structure that promotes the definition of personalized attributes, which involves recommendations and customizations of content per profile, including training content that will be suggested and learning activity content that will be continuously monitored, given the specific needs of learners.

Abstract
Since digital media has become increasingly popular, video processing has expanded in recent years. Video processing systems require high levels of processing, which is one of the challenges in this field. Various approaches, such as hardware upgrades, algorithmic optimizations, and removing unnecessary information, have been suggested to solve this problem. This study proposes a video saliency map based method that identifies the critical parts of the video and improves the system's overall performance. Using an image registration algorithm, the proposed method first removes the camera's motion. Subsequently, each video frame's color, edge, and gradient information are used to obtain a spatial saliency map. Combining spatial saliency with motion information derived from optical flow and color-based segmentation can produce a saliency map containing both motion and spatial data. A nonlinear function is suggested to properly combine the temporal and spatial saliency maps, which was optimized using a multi-objective genetic algorithm. The proposed saliency map method was added as a preprocessing step in several Human Action Recognition (HAR) systems based on deep learning, and its performance was evaluated. Furthermore, the proposed method was compared with similar methods based on saliency maps, and the superiority of the proposed method was confirmed. The results show that the proposed method can improve HAR efficiency by up to 6.5% relative to HAR methods with no preprocessing step and 3.9% compared to the HAR method containing a temporal saliency map.

Abstract
The implementation of novel regulatory and technical requirements for the distribution of vehicle axle weights in road freight transport introduces a new set of constraints on vehicle routing. Until now, axle weight distribution in determining the load plan for freight transport units has been overlooked in the vehicle routing process. Compliance with these axle weight constraints has become paramount for road freight transport companies, since noncompliance with the axle weight distribution legislation translates into heavy fines. This work aims to provide a tool capable of generating cargo loading plans and routing sequences for a palletised cargo distribution problem. The problem addressed integrates the capacitated vehicle routing problem with time window and the two-dimensional loading problem with load balance constraints. Two integrative solution approaches are proposed, one giving greater importance to the routing and the other prioritising the loading. In addition, a novel MILP model is proposed for the 2D pallet loading problem with load-balance constraints that take advantage of the standard dimension of the pallets. Extensive computational experiments were performed with a set of well-known literature benchmark instances, extended to incorporate additional features. The computational results show the effectiveness of the proposed approaches.

Abstract
Context. Temporal variability in the photometric and spectroscopic properties of protoplanetary disks is common in young stellar objects. However, evidence pointing toward changes in their morphology over short timescales has only been found for a few sources, mainly due to a lack of high-cadence observations at high angular resolution. Understanding this type of variation could be important for our understanding of phenomena related to disk evolution. Aims. We study the morphological variability of the innermost circumstellar environment of HD 98922, focusing on its dust and gas content. Methods. Multi-epoch observations of HD 98922 at milliarcsecond resolution with VLTI/GRAVITY in the K-band at low (R = 20) and high (R = 4000) spectral resolution are combined with VLTI/PIONIER archival data covering a total time span of 11 yr. We interpret the interferometric visibilities and spectral energy distribution with geometrical models and through radiative transfer techniques using the code MCMax. We investigated high-spectral-resolution quantities (visibilities and differential phases) to obtain information on the properties of the HI Brackett-gamma (Br gamma)-line-emitting region. Results. Comparing observations taken with similar (u,v) plane coverage, we find that the squared visibilities do not vary significantly, whereas we find strong variability in the closure phases, suggesting temporal variations in the asymmetric brightness distribution associated to the disk. Our observations are best fitted by a model of a crescent-like asymmetric dust feature located at similar to 1 au and accounting for similar to 70 % of the near-infrared (NIR) emission. The feature has an almost constant magnitude and orbits the central star with a possible sub-Keplerian period of similar to 12 months, although a 9 month period is another, albeit less probable, solution. The radiative transfer models show that the emission originates from a small amount of carbon-rich (25%) silicates, or quantum-heated particles located in a low-density region. Among different possible scenarios, we favor hydrodynamical instabilities in the inner disk that can create a large vortex. The high spectral resolution differential phases in the Br gamma line show that the hot-gas compact component is offset from the star and in some cases is located between the star and the crescent feature. The scale of the emission does not favor magnetospheric accretion as a driving mechanism. The scenario of an asymmetric disk wind or a massive accreting substellar or planetary companion is discussed. Conclusions. With this unique observational data set for HD 98922, we reveal morphological variability in the innermost 2 au of its disk region. This property is possibly common to many other protoplanetary disks, but is not commonly observed due to a lack of high-cadence observation. It is therefore important to pursue this approach with other sources for which an extended dataset with PIONIER, GRAVITY, and possibly MATISSE is available.

Abstract
Motion estimation in echocardiography is critical when assessing heart function and calculating myocardial deformation indices. Nevertheless, there are limitations in clinical practice, particularly with regard to the accuracy and reliability of measurements retrieved from images. In this study, deep learning-based motion estimation architectures were used to determine the left ventricular longitudinal strain in echocardiography. Three motion estimation approaches, pretrained on popular optical flow datasets, were applied to a simulated echocardiographic dataset. Results show that PWC-Net, RAFT and FlowFormer achieved an average end point error of 0.20, 0.11 and 0.09 mm per frame, respectively. Additionally, global longitudinal strain was calculated from the FlowFormer outputs to assess strain correlation. Notably, there is variability in strain accuracy among different vendors. Thus, optical flow-based motion estimation has the potential to facilitate the use of strain imaging in clinical practice.

Abstract
Semantic measure (SM) algorithms allow software to mimic the human ability of assessing the strength of the semantic relations between elements such as concepts, entities, words, or sentences. SM algorithms are typically evaluated by comparison against gold standard datasets built by human annotators. These datasets are composed of pairs of elements and an averaged numeric rating. Building such datasets usually requires asking human annotators to assign a numeric value to their perception of the strength of the semantic relation between two elements. Large language models (LLMs) have recently been successfully used to perform tasks which previously required human intervention, such as text summarization, essay writing, image description, image synthesis, question answering, and so on. In this paper, we present ongoing research on LLMs capabilities for semantic relations assessment. We queried several LLMs to rate the relationship of pairs of elements from existing semantic measures evaluation datasets, and measured the correlation between the results from the LLMs and gold standard datasets. Furthermore, we performed additional experiments to evaluate which other factors can influence LLMs performance in this task. We present and discuss the results obtained so far.