Abstract
Deep learning has rapidly increased in popularity, leading to the development of perception solutions for autonomous driving. The latter field leverages techniques developed for computer vision in other domains for accomplishing perception tasks such as object detection. However, the black-box nature of deep neural models and the complexity of the autonomous driving context motivates the study of explainability in these models that perform perception tasks. Moreover, this work explores explainable AI techniques for the object detection task in the context of autonomous driving. An extensive and detailed comparison is carried out between gradient-based and perturbation-based methods (e.g., D-RISE). Moreover, several experimental setups are used with different backbone architectures and different datasets to observe the influence of these aspects in the explanations. All the techniques explored consist of saliency methods, making their interpretation and evaluation primarily visual. Nevertheless, numerical assessment methods are also used. Overall, D-RISE and guided backpropagation obtain more localized explanations. However, D-RISE highlights more meaningful regions, providing more human-understandable explanations. To the best of our knowledge, this is the first approach to obtaining explanations focusing on the regression of the bounding box coordinates.

Abstract
Total evacuation time constitutes an important factor in the safety of any building. It is thus essential to devise an emergency evacuation plan, which will enable the safe evacuation of all the occupants in the shortest possible time. The main objective of this article was to examine and improve the evacuation process of a 4-star hotel located in the city of Porto, Portugal. To this end, one looked into 6 scenarios, by means of PathFinder simulation software, so as to determine the shortest total evacuation time and identify possible bottlenecks and congestion. The simulation model developed was tested to analyze the evacuation of 429 people from the hotel, based on the availability of the 3 accessible exit doors (central exit, side exit, spa exit) and elevators. Strategy 4 presented the shortest total evacuation time, with 536.0 s. Two other strategies which showed very similar times were 5 and 6, with 537.0 s and 537.5 s, respectively.

Abstract
Experimental assessment of different missing data imputation methods often compute error rates between the original values and the estimated ones. This experimental setup relies on complete datasets that are injected with missing values. The injection process is straightforward for the Missing Completely At Random and Missing At Random mechanisms; however, the Missing Not At Random mechanism poses a major challenge, since the available artificial generation strategies are limited. Furthermore, the studies focused on this latter mechanism tend to disregard a comprehensive baseline of state-of-the-art imputation methods. In this work, both challenges are addressed: four new Missing Not At Random generation strategies are introduced and a benchmark study is conducted to compare six imputation methods in an experimental setup that covers 10 datasets and five missingness levels (10% to 80%). The overall findings are that, for most missing rates and datasets, the best imputation method to deal with Missing Not At Random values is the Multiple Imputation by Chained Equations, whereas for higher missingness rates autoencoders show promising results.

Abstract
The evaluation of the diffusion properties of different molecules in tissues is a subject of great interest in various fields, such as dermatology/cosmetology, clinical medicine, implantology and food preservation. In this review, a discussion of recent studies that used kinetic spectroscopy measurements to evaluate such diffusion properties in various tissues is made. By immersing ex vivo tissues in agents or by topical application of those agents in vivo, their diffusion properties can be evaluated by kinetic collimated transmittance or diffuse reflectance spectroscopy. Using this method, recent studies were able to discriminate the diffusion properties of agents between healthy and diseased tissues, especially in the cases of cancer and diabetes mellitus. In the case of cancer, it was also possible to evaluate an increase of 5% in the mobile water content from the healthy to the cancerous colorectal and kidney tissues. Considering the application of some agents to living organisms or food products to protect them from deterioration during low temperature preservation (cryopreservation), and knowing that such agent inclusion may be reversed, some studies in these fields are also discussed. Considering the broadband application of the optical spectroscopy evaluation of the diffusion properties of agents in tissues and the physiological diagnostic data that such method can acquire, further studies concerning the optimization of fruit sweetness or evaluation of poison diffusion in tissues or antidote application for treatment optimization purposes are indicated as future perspectives.

Abstract
Simple Summary Due to limited proteomic data for rabbit spermatozoa and less comprehensive databases compared to humans, we conducted a combined bioinformatic analysis of the proteome of rabbit X (RX) and human X and Y (HX and HY) chromosomes to identify membrane-associated proteins, particularly those accessible from the cell surface, for potential applications in sperm sexing techniques. Our analysis found 100 (RX), 211 (HX), and 3 (HY) plasma membrane or cell surface-associated proteins, of which 61, 132, and 3 are potentially accessible from the cell surface. Notably, among the HX targets, 60 could serve as additional RX targets not previously identified, bringing the total to 121 RX targets. Furthermore, at least 53 out of the 114 potential common HX and RX targets chromosomes have been previously identified in human spermatozoa, emphasizing their potential as targets of X-chromosome-bearing spermatozoa. The utility of these proteins as targets of rabbit X-chromosome-bearing spermatozoa warrants further exploration.Abstract Studying proteins associated with sex chromosomes can provide insights into sex-specific proteins. Membrane proteins accessible through the cell surface may serve as excellent targets for diagnostic, therapeutic, or even technological purposes, such as sperm sexing technologies. In this context, proteins encoded by sex chromosomes have the potential to become targets for X- or Y-chromosome-bearing spermatozoa. Due to the limited availability of proteomic studies on rabbit spermatozoa and poorly annotated databases for rabbits compared to humans, a bioinformatic analysis of the available rabbit X chromosome proteome (RX), as well as the human X (HX) and Y (HY) chromosomes proteome, was conducted to identify potential targets that could be accessible from the cell surface and predict which of the potential targets identified in humans might also exist in rabbits. We identified 100, 211, and 3 proteins associated with the plasma membrane or cell surface for RX, HX, and HY, respectively, of which 61, 132, and 3 proteins exhibit potential as targets as they were predicted to be accessible from the cell surface. Cross-referencing the potential HX targets with the rabbit proteome revealed an additional 60 proteins with the potential to be RX targets, resulting in a total of 121 potential RX targets. In addition, at least 53 possible common HX and RX targets have been previously identified in human spermatozoa, emphasizing their potential as targets of X-chromosome-bearing spermatozoa. Further proteomic studies on rabbit sperm will be essential to identify and validate the usefulness of these proteins for application in rabbit sperm sorting techniques as targets of X-chromosome-bearing spermatozoa.

Abstract
Deep Learning models are automating many daily routine tasks, indicating that in the future, even high-risk tasks will be automated, such as healthcare and automated driving areas. However, due to the complexity of such deep learning models, it is challenging to understand their reasoning. Furthermore, the black box nature of the designed deep learning models may undermine public confidence in critical areas. Current efforts on intrinsically interpretable models focus only on classification tasks, leaving a gap in models for object detection. Therefore, this paper proposes a deep learning model that is intrinsically explainable for the object detection task. The chosen design for such a model is a combination of the well-known Faster-RCNN model with the ProtoPNet model. For the Explainable AI experiments, the chosen performance metric was the similarity score from the ProtoPNet model. Our experiments show that this combination leads to a deep learning model that is able to explain its classifications, with similarity scores, using a visual bag of words, which are called prototypes, that are learned during the training process. Furthermore, the adoption of such an explainable method does not seem to hinder the performance of the proposed model, which achieved a mAP of 69% in the KITTI dataset and a mAP of 66% in the GRAZPEDWRI-DX dataset. Moreover, our explanations have shown a high reliability on the similarity score.