ensemble-temporal-weighting-causal-inference-hierarchical-attribution

Ensemble of Temporal Weighting, Causal Inference, and Hierarchical Attribution towards SHAP Optimization

During the past few years, the need for transparency and interpretability has been intensified owing to significant advancements in data-driven models, ...

Universidade Portucalense

The creation and usage of serious games on virtual reality (VR) and/or interactive platforms for the teaching of architecture, construction, urban planning, and other derived areas, such as security and risk prevention, require design processes, studies, and research that lead to further consolidation expansion. In that sense, this paper presents two main aims developed: the improvement of a virtual navigation system through the results of previous user studies and mixed research (quantitative and qualitative) improved based on the user perception for educational and professional uses. The VR system used is based on Unreal Engine programming of the HTC Vive sensor. This study is related to the GAME4City 3.0 and a broader project focused on gamified visualization and its educational uses in architectural and urban projects. The results reflect great interest, good usability, and high motivation for further usage for all types of users. However, an apparent resistance to deepen its use continues to be perceived in academia. Based on the research results, weak points of educational gamified systems have been identified, and the main differences and needs in user profiles' function. With these data, progress regarding implementing this kind of system at the teaching and professional levels must be pursued.

Mixed Assessment of Virtual Serious Games Applied in Architectural and Urban Design Education.

COVID-19 forced higher education institutions to reinvent themselves. The (usually) face-to-face education has swapped to distance contingency education. This change brought about numerous challenges that impose adjustments in several dimensions, such as pedagogical strategies and the dependence on teaching platforms and computer systems-and, above all, the new relationship between the various actors (students, teachers, and management staff). All the sudden changes, combined with uncertainty concerning what was happening, created several strategies and options. This paper has the main purpose of analyzing the scientific production on higher education of EU27 academic institutions during the 2020 COVID-19 pandemic in journals indexed in Clarivate Analytics' Web of Science and Elsevier's Scopus. The sample is composed of 22 articles in total. The results show that the articles were published in 19 journals; their main focuses are Higher Education, COVID-19, and distance learning. In our database, we find several types of concerns, which shows that HEIs have a wide range of dimensions. We intend this article to be an instrument, not only to identify what was done in 2020, but to point out clues for the future.

EU27 Higher Education Institutions and COVID-19, Year 2020.

Autism spectrum disorder (ASD) is a neurodevelopmental disorder defined as persistent difficulty in maturing the socialization process. Health professionals have used traditional methods in the therapies performed on patients with the aim of improving the expression of emotions by patients. However, they have not been sufficient to detect the different emotions expressed in the face of people according to different sensations. Therefore, different artificial intelligence techniques have been applied to improve the results obtained in these therapies. In this article, we propose the construction of an intelligent mirror to recognize five basic emotions: angry, scared, sad, happy and neutral. This mirror uses convolutional neural networks to analyze the images that are captured by a camera and compare it with the one that the patient should perform, thus supporting the therapies performed by health professionals in children with ASD. The proposal presents the platform and computer architecture, as well as the evaluation by specialists under the technology acceptance model.

Emo-mirror: a proposal to support emotion recognition in children with autism spectrum disorders.

Social sustainability is the generation of significant behaviors through balanced levels of education, learning and awareness so that the population has a good standard of living, achieves self-improvement and supports society. This can be achieved with various strategies, one of which is learning through games, which has gained popularity in recent years due to positive results. This is effectively achieved through serious gaming, which is growing steadily, mostly in education and healthcare. This type of strategy has been typically used in young populations with a transparent interaction with technological processes that facilitate its application. However, one cannot neglect other populations such as the elderly, who may experience a technology gap and may not perceive this type of initiative in the best light. The purpose of this article is to identify the different motivations that can encourage older adults to use serious games to encourage learning processes through technology. For this purpose, different previous research on gaming experiences with older adults has been identified, from which it was possible to categorize a series of factors that motivate this population. Subsequently, we represented these factors by means of a model of motivation for the elderly and, to be able to use it, we have defined a set of heuristics based on this model. Finally, we used the heuristics by means of a questionnaire to evaluate the design of serious gaming for older adults, obtaining positive results for the use of these elements to guide the design and construction of serious games for learning in older adults.

Meaningful learning: motivations of older adults in serious games.

As a consequence of technological advances, the number of devices has increased, with the emergence of different smartphones, tablets, and smartwatches present in both personal and professional activities. As a result, mobile applications have been developed, and with them comes the need for techniques and methods that provide support for conducting evaluation and prototyping since the current approaches are limited and cannot support the complexity and the need for understanding the context. The overall goal of the study is to evaluate the applicability of adopting a situated and embodied approach to mobile application usability testing. The aspects of postmodern and phenomenological approaches were taken into consideration. The study was conducted using the technique of digital ethnography, in particular the re-enactment technique, combined with qualitative research techniques to capture the evidence that the situated and embodied approach allows for capturing the perceptions and experience of the participants about the use of the application under evaluation. As motivation, there is the theoretical and methodological evolution and contribution and the proof that the postmodern and situated approach allows us to evaluate the usability of mobile applications in a complete way, considering the context and the user experience. The results show aspects of experience, reflections, perceptions, contingencies, practices, and meanings that go beyond the complexity of interactions and context with the use of the application, reinforcing the effectiveness of the use of the situated prototyping approach.

Effectiveness of embodied evaluation of mobile applications: A qualitative study.

Some previous studies have focused on using physiological signals to detect stress in individuals with ASD through wearable devices, yet few have focused on how to design such solutions. Wearable technology may be a valuable tool to aid parents and caregivers in monitoring the emotional states of individuals with ASD who are at high risk of experiencing very stressful situations. However, effective wearable devices for individuals with ASD may need to differ from solutions for those without ASD. People with ASD often have sensory sensitivity and may, therefore, not tolerate certain types of accessories and experience discomfort when using them. We used the Scopus, PubMed, WoS, and IEEE-Xplore databases to search for studies published from 2014 to 2024 to answer four research questions related to wearable solutions for individuals with ASD, physiological parameters, and techniques/processes used for stress detection. Our review found 31 articles; not all studies considered individuals with ASD, and some were beyond the scope of this review. Most of the studies reviewed are based on cardiac activity for stress monitoring using photoplethysmography (PPG) and electrocardiography (ECG). However, limitations include small sample sizes, variability in study conditions, and the need for customization in stress detection algorithms. In addition, there is a need to customize the stress threshold due to the device's high individual variability and sensitivity. The potential of wearable solutions for stress monitoring in ASD is evident, but challenges include the need for user-friendly and unobtrusive designs and integrating these technologies into comprehensive care plans.

Wearable Solutions Using Physiological Signals for Stress Monitoring on Individuals with Autism Spectrum Disorder (ASD): A Systematic Literature Review.

Fruit sorting and quality inspection using computer vision is a key tool to ensure quality and safety in the fruit industry. This study presents a systematic literature review, following the PRISMA methodology, with the aim of identifying different fields of application, typical hardware configurations, and the techniques and algorithms used for fruit sorting. In this study, 56 articles published between 2015 and 2024 were analyzed, selected from relevant databases such as Web of Science and Scopus. The results indicate that the main fields of application include orchards, industrial processing lines, and final consumption points, such as supermarkets and homes, each with specific technical requirements. Regarding hardware, RGB cameras and LED lighting systems predominate in controlled applications, although multispectral cameras are also important in complex applications such as foreign material detection. Processing techniques include traditional algorithms such as Otsu and Sobel for segmentation and deep learning models such as ResNet and VGG, often optimized with transfer learning for classification. This systematic review could provide a basic guide for the development of fruit quality inspection and classification systems in different environments.

Artificial Vision Systems for Fruit Inspection and Classification: Systematic Literature Review.

The advancement of the Internet of Medical Things (IoMT) has transformed healthcare delivery by enabling real-time health monitoring. However, it introduces critical challenges related to latency and, more importantly, the secure handling of sensitive patient data. Traditional cloud-based architectures often struggle with latency and data protection, making them inefficient for real-time healthcare scenarios. To address these challenges, we propose a Hybrid Fog-Edge Computing Architecture tailored for effective real-time health monitoring in IoMT systems. Fog computing enables processing of time-critical data closer to the data source, reducing response time and relieving cloud system overload. Simultaneously, edge computing nodes handle data preprocessing and transmit only valuable information-defined as abnormal or high-risk health signals such as irregular heart rate or oxygen levels-using rule-based filtering, statistical thresholds, and lightweight machine learning models like Decision Trees and One-Class SVMs. This selective transmission optimizes bandwidth without compromising response quality. The architecture integrates robust security measures, including end-to-end encryption and distributed authentication, to counter rising data breaches and unauthorized access in IoMT networks. Real-life case scenarios and simulations are used to validate the model, evaluating latency reduction, data consolidation, and scalability. Results demonstrate that the proposed architecture significantly outperforms cloud-only models, with a 70% latency reduction, 30% improvement in energy efficiency, and 60% bandwidth savings. Additionally, the time required for threat detection was halved, ensuring faster response to security incidents. This framework offers a flexible, secure, and efficient solution ideal for time-sensitive healthcare applications such as remote patient monitoring and emergency response systems.

A hybrid fog-edge computing architecture for real-time health monitoring in IoMT systems with optimized latency and threat resilience.

The fusion of deep-learning-based and federated methods has brought great progress in anomaly detection. Yet the systems of today still suffer from certain glaring issues. First, aggregation of data on a central entity poses dangerous privacy hazards. Second, such models could not scale and adapt to heterogeneous and distributed environments. Lastly, fine consideration has hardly been given to quantum-inspired computational paradigms that may promise to improve both speed and security of such systems. To fill in these gaps, this research proposes a completely novel quantum-inspired federated learning approach to anomaly detection that keeps data private and allows for further implementations of quantum computing applications.

Federated quantum-inspired anomaly detection using collaborative neural clients.

The rapid growth in wireless communication demands has led to a surge in research on technologies capable of enhancing communication reliability, coverage, and energy efficiency. Among these, uncrewed aerial vehicles (UAV) and reconfigurable intelligent surfaces (RIS) have emerged as promising solutions. Prior research on using deep reinforcement learning (DRL) to integrate RIS with UAV concentrated on enhancing signal quality and coverage, but it ignored the challenges caused by electromagnetic interference (EMI). This article introduces a novel framework addressing the challenges posed by EMI from Gallium nitride (GaN) power amplifiers in RIS-assisted UAV communication systems. By integrating DRL with quadrature phase shift keying (QPSK) modulation, the proposed system dynamically optimizes UAV deployment and RIS configurations in real-time, mitigating EMI effects, improving signal-to-interference-plus-noise ratio (SINR), and enhancing energy efficiency. The framework demonstrates superior performance, with an SINR improvement of up to 6.5 dB in interference-prone environments, while achieving a 38% increase in energy efficiency compared to baseline models. Additionally, the system significantly reduces EMI impact, with a mitigation rate of over 70%, and extends coverage area by 35%. The integration of QPSK and DRL allows for real-time decision-making that balances communication quality and energy consumption. These results show the system's potential to outperform traditional methods, particularly in dynamic and challenging environments such as urban, disaster recovery, and remote settings.

Enhancing reliable and energy-efficient UAV communications with RIS and deep reinforcement learning.

Mouth cancer represents a significant global public health challenge due to its high incidence rate and potentially fatal outcomes if not diagnosed early. Among the various types, oral cancer is notably prevalent and poses considerable diagnostic complexity due to its intricate histopathological architecture. According to the World Health Organization and recent epidemiological studies, oral cancer accounts for approximately 377,000 new cases and 177,000 deaths annually worldwide. Traditional diagnostic methodologies such as manual clinical inspection and biopsy analysis are often time-intensive, inherently subjective, and susceptible to inter-observer variability among pathologists. To address these limitations, this study proposes novel framework, termed Depthwise Separable Convolution U-Net (DWSU-Net), aimed at enhancing the accuracy and efficiency of mouth cancer detection. Unlike traditional U-Net, which employs computationally expensive standard convolutional layers, DWSU-Net integrates depthwise separable convolutional blocks into both encoder and decoder stages, reducing parameter count and training complexity while preserving representational power. This makes the model more lightweight, scalable, and suitable for real-time or resource-constrained clinical environments. The research utilizes histopathologic images of oral tissues obtained from the publicly available oral cancer detection dataset on Kaggle, which were captured using a Leica ICC50 HD microscope. The proposed approach initiates with a comprehensive data preprocessing pipeline involving multiple filtering techniques. Raw histopathological images are transformed using Sobel filtering, Otsu thresholding, Canny edge detection, and morphological reconstruction via erosion, thereby improving feature saliency and contrast in malignant regions. The preprocessed dataset is partitioned into training, validation, and testing subsets in an 80:10:10 ratio and evaluated using fivefold cross-validation to ensure the robustness and generalizability of the model. A comparative analysis was conducted using conventional CNN architectures to identify the most effective combination of model and filtering technique. Empirical results indicated that MobileNet and U-Net, when applied to images filtered through morphological reconstruction by erosion, yielded superior classification performance. Motivated by these findings, the proposed DWSU-Net architecture was developed by integrating the strengths of MobileNet and U-Net. The novelty of the DWSU-Net model lies in morphological reconstruction-based preprocessing, which enhances interpretability by making malignant regions more distinct for both the algorithm and pathologists, thereby bridging the gap between AI predictions and clinical understanding. By combining efficiency, robustness, and interpretability, DWSU-Net goes beyond accuracy gains, offering a clinically relevant decision-support framework. Experimental evaluations demonstrate that the proposed model achieves an outstanding classification accuracy of 99.74% in distinguishing between healthy and malignant oral tissue images, underscoring its potential for clinical deployment in automated cancer diagnostics.

Article	Year
Mixed Assessment of Virtual Serious Games Applied in Architectural and Urban Design Education. Sensors (Basel, Switzerland)\| PubMed ID: 33946868	2021
EU27 Higher Education Institutions and COVID-19, Year 2020. International journal of environmental research and public health\| PubMed ID: 34199415	2021
Emo-mirror: a proposal to support emotion recognition in children with autism spectrum disorders. Neural computing & applications\| PubMed ID: 34642548	2023
Meaningful learning: motivations of older adults in serious games. Universal access in the information society\| PubMed ID: 37361677	2023
Effectiveness of embodied evaluation of mobile applications: A qualitative study. Heliyon\| PubMed ID: 37484392	2023
Wearable Solutions Using Physiological Signals for Stress Monitoring on Individuals with Autism Spectrum Disorder (ASD): A Systematic Literature Review. Sensors (Basel, Switzerland)\| PubMed ID: 39771872	2024
Artificial Vision Systems for Fruit Inspection and Classification: Systematic Literature Review. Sensors (Basel, Switzerland)\| PubMed ID: 40096367	2025
A hybrid fog-edge computing architecture for real-time health monitoring in IoMT systems with optimized latency and threat resilience. Scientific reports\| PubMed ID: 40665167	2025
Federated quantum-inspired anomaly detection using collaborative neural clients. Frontiers in artificial intelligence\| PubMed ID: 40932890	2025
Enhancing reliable and energy-efficient UAV communications with RIS and deep reinforcement learning. PeerJ. Computer science\| PubMed ID: 40989447	2025
Enhanced Histopathologic Image Analysis for Mouth Cancer Classification Using Morphological Reconstruction and UNet. Journal of imaging informatics in medicine\| PubMed ID: 41083842	2025

Fernando Moreira

Biography

JoVE Journal Publications

Other Publications