Abstract
Pet owners are increasingly becoming conscious of their pet's necessities and are paying more attention to their overall wellness. The well-being of their pets is intricately linked to their own emotional and physical well-being. Some veterinary system solutions are emerging to provide proactive healthcare options for pets. One such solution offers the continuous monitoring of a pet's activity through accelerometer tracking devices. Based on data collected by this application, in this paper, we study different time aggregation and three unsupervised machine learning techniques to identify anomalies in pet behaviour data. Specifically, three algorithms, Isolation Forest, Local Outlier Factor, and K-Nearest Neighbour, with various thresholds to differentiate between normal and abnormal events. Results conducted on ten pets (five cats and five dogs) show that the most effective approach is to use daily data divided into periods. Moreover, the Local Outlier Factor is the best algorithm for detecting anomalies when prioritizing the identification of true positives. However, it also produces a high false positive ratio.

Abstract
Breast cancer locoregional treatment can cause significant and long-lasting alterations to a patient's body. As various surgical options may be available to a patient and considering the impact that the aesthetic outcome may have on the patient's self-esteem, it is critical for the patient to be adequately informed of the possible outcomes of each treatment when deciding on the treatment plan. With the purpose of simulating how a patient may look like after treatment, we propose a deep generative model to transfer asymmetries caused by treatment from post-operative breast patients into pre-operative images, taking advantage of the inherent symmetry of breast images. Furthermore, we disentangle asymmetries related with the breast shape from the nipple within the latent space of the network, enabling higher control over the alterations to the breasts. Finally, we show the proposed model's wide applicability in medical imaging, by applying it to generate counterfactual explanations for cardiomegaly and pleural effusion prediction in chest radiographs.

Abstract

Abstract
The proliferation of wireless devices requires flexible network infrastructures to meet the increasing Quality of Service (QoS) requirements. Mobile Robotic Platforms (MRPs) acting as mobile communications cells are a promising solution to provide on-demand wireless connectivity in dynamic networking scenarios. However, the energy consumption of MRPs is a challenge that must be considered to maximize the availability of the wireless networks created. The main contribution of this paper is the experimental evaluation of the energy consumption of an MRP acting as a mobile communications cell. The evaluation considers different actions performed by a real MRP, demonstrating that energy consumption varies significantly with the type of action performed. The results obtained pave the way for optimizing MRP movement in dynamic networking scenarios, maximizing wireless network's availability while minimizing the MRP energy consumption.

Abstract
The rise of environmental crimes has become a major concern globally as they cause significant damage to ecosystems, public health and result in economic losses. The availability of vast sensor data provides an opportunity to analyze environmental data proactively. This helps to detect irregularities and uncover potential criminal activities. This paper highlights the critical role played by machine learning (ML) and remote sensing technologies in the continuously evolving scenarios of environmental crime. By examining some case studies on detecting illegal fishing, illegal oil spills, illegal landfills, and illegal logging, we delve into the practical implementation of data-driven approaches for environmental crime detection. Our goal with this study is to provide an overview of the existing research in this area and foster the use of ML and data science techniques to enhance environmental crime detection.

Abstract
Gastric cancer, ranking as the sixth most prevalent cancer globally and a leading cause of cancer-related mortality, follows a sequential progression known as Correa's cascade, spanning from chronic gastritis to eventual malignancy. Although endoscopy exams using NarrowBand Imaging are recommended by internationally accepted guidelines for diagnostic Gastric Intestinal Metaplasia, the lack of endoscopists with the skill to assess the NBI image patterns and the disagreement between endoscopists when assessing the same image, have made the use of biopsies the gold standard still used today. This proposal doctoral thesis seeks to address the challenge of developing a Computer-Aided Diagnosis solution for GIM detection in NBI endoscopy exams, aligning with the established guidelines, the Management of Epithelial Precancerous Conditions and Lesions in the Stomach. Our approach will involve a dataset creation that follows the standardized approach for histopathological classification of gastrointestinal biopsies, the Sydney System recommended by MAPS II guidelines, and annotation by gastroenterology experts. Deep learning models, including Convolutional Neural Networks, will be trained and evaluated, aiming to establish an internationally accepted AI-driven alternative to biopsies for GIM detection, promising expedited diagnosis, and cost reduction.