Abstract

Abstract
Schizophrenia is a mental illness that affects an estimated 21 million people worldwide. The literature establishes that electroencephalography (EEG) is a well-implemented means of studying and diagnosing mental disorders. However, it is known that speech and language provide unique and essential information about human thought. Semantic and emotional content, semantic coherence, syntactic structure, and complexity can thus be combined in a machine learning process to detect schizophrenia. Several studies show that early identification is crucial to prevent the onset of illness or mitigate possible complications. Therefore, it is necessary to identify disease-specific biomarkers for an early diagnosis support system. This work contributes to improving our knowledge about schizophrenia and the features that can identify this mental illness via speech and EEG. The emotional state is a specific characteristic of schizophrenia that can be identified with speech emotion analysis. The most used features of speech found in the literature review are fundamental frequency (F0), intensity/loudness (I), frequency formants (F1, F2, and F3), Mel-frequency cepstral coefficients (MFCC's), the duration of pauses and sentences (SD), and the duration of silence between words. Combining at least two feature categories achieved high accuracy in the schizophrenia classification. Prosodic and spectral or temporal features achieved the highest accuracy. The work with higher accuracy used the prosodic and spectral features QEVA, SDVV, and SSDL, which were derived from the F0 and spectrogram. The emotional state can be identified with most of the features previously mentioned (F0, I, F1, F2, F3, MFCCs, and SD), linear prediction cepstral coefficients (LPCC), linear spectral features (LSF), and the pause rate. Using the event-related potentials (ERP), the most promissory features found in the literature are mismatch negativity (MMN), P2, P3, P50, N1, and N2. The EEG features with higher accuracy in schizophrenia classification subjects are the nonlinear features, such as Cx, HFD, and Lya.

Abstract
Myocardial infarction, known as heart attack, is one of the leading causes of world death. It occurs when blood heart flow is interrupted by part of coronary artery occlusion, causing the ischemic episode to last longer, creating a change in the patient’s ECG. In this work, a method was developed for predicting patients with MI through Frank 3-lead ECG extracted from Physionet’s PTB ECG Diagnostic Database and using instantaneous frequency and spectral entropy to extract features. Two neural networks were applied: Long Short-Term Memory and Bi-Long Short-Term Memory, obtaining a better result with the first one, with an accuracy of 78%. © 2023, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

Abstract
E-commerce has become a booming market for wildlife trafficking, as online platforms are increasingly more accessible and easier to navigate by sellers, while still lacking adequate supervision. Artificial intelligence models, and specifically deep learning, have been emerging as promising tools for the automated analysis and monitoring of digital online content pertaining to wildlife trade. Here, we used and fine-tuned freely available artificial intelligence models (i.e., convolutional neural networks) to understand the potential of these models to identify instances of wildlife trade. We specifically focused on pangolin species, which are among the most trafficked mammals globally and receiving increasing trade attention since the COVID-19 pandemic. Our convolutional neural networks were trained using online images (available from iNaturalist, Flickr and Google) displaying both traded and non-traded pangolin settings. The trained models showed great performances, being able to identify over 90 % of potential instances of pangolin trade in the considered imagery dataset. These instances included the showcasing of pangolins in popular marketplaces (e.g., wet markets and cages), and the displaying of commonly traded pangolin parts and derivates (e.g., scales) online. Nevertheless, not all instances of pangolin trade could be identified by our models (e.g., in images with dark colours and shaded areas), leaving space for further research developments. The methodological developments and results from this exploratory study represent an advancement in the monitoring of online wildlife trade. Complementing our approach with other forms of online data, such as text, would be a way forward to deliver more robust monitoring tools for online trafficking.

Abstract
Two-dimensional echocardiography is the most widely used non-invasive imaging modality due to its fast acquisition time, low cost, and high temporal resolution. Accurate segmentation of the left ventricle in echocardiography is vital for ensuring the accuracy of subsequent diagnosis. Currently, numerous efforts have been made to automatize this task and various public datasets have been released in recent decades to further develop present research. However, medical datasets acquired at different institutions have inherent bias caused by various confounding factors, such as operation policies, machine protocols, treatment preference, etc. As a result, models trained on one dataset, regardless of volume, cannot be confidently utilized for the others. In this study, we investigated model robustness to dataset bias using two publicly available echocardiographic datasets. This work validates the efficacy of a supervised deep learning model for left ventricle segmentation and ejection fraction prediction, outside the dataset on which it was trained. The exposure of this model to unseen, but related samples without additional training maintained a good performance. However, a performance decrease from the original results can be observed, while the impact of quality is also noteworthy with lower quality data leading to decreased performance.

Abstract
With the increase in renewable energy generation and its problems related to output instability, storage systems must be implemented in parallel to account for this effect. Therefore, it is valuable to deepen the study of these technologies' performances in their several application tiers, thus understanding the potential of each alternative, both per tier and as a whole. For this reason, a collaborative multi-criteria decision -aiding framework is proposed to rank the various available options in several layers of the energy storage market, constructed alongside experts and policy-makers from each tier that serve as actors of the decision -making process and using Portugal as a case study. Based on the Choquet multi-criteria preference aggregation model, to the best of the authors' knowledge, this framework is an unprecedented application in the energy sector. Beyond a critical review of the results, a scenario analysis was performed to explore interesting future possibilities that may aid governments to make decisions in the search for an energy sustainable development. Chemical storage solutions, such as Hydrogen and Methane, as well as several electrochemical batteries, especially Lithium-and Nickel-based ones, were the standout energy storage solutions. Chemical storage was shown to have the desired characteristics for the Long-term grid tier. Meanwhile, batteries, including Redox Flow in the first case, have overperformed in the Microgrid and Mobility tiers. No standout solutions appeared in the Short-term grid tier. Unsurprisingly, the aforementioned chemical storage systems, batteries, and Hot Water have presented themselves as the most politically interesting technologies, due to their multipurpose uses and intrinsic characteristics.