Progress in Artificial Intelligence

We present Erato, a framework designed to facilitate the automated evaluation of poetry, including that generated by poetry generation systems. Our framework employs a diverse set of features, and we offer a brief overview of Erato’s capabilities and its potential for expansion. Using Erato, we compare and contrast human-authored poetry with automatically-generated poetry, demonstrating its effectiveness in identifying key differences. Our implementation code and software are freely available under the GNU GPLv3 license.

Artificial intelligence output are undeniably creative, but it has been argued that creativity should be assessed in terms of, not external products, but internal self-transformation through immersion in a creative task. Self-transformation requires a self, which we define as a bounded, self-organizing, self-preserving agent that is distinct from, and interacts with, its environment. The paper explores how self-hood, as well as self-transformation as a result of creative tasks, could be achieved in a machine using autocatalytic networks. The autocatalytic framework is ideal for modeling systems that exhibit emergent network formation and growth. The approach readily scales up, and it can analyze and detect phase transitions in vastly complex networks that have proven intractable with other approaches. Autocatalytic networks have been applied to both (1) the origin of life and the onset of biological evolution, and (2) the origin of minds sufficiently complex and integrated to participate in cultural evolution. The first entails the emergence of self-hood at the level of the soma, or body, while the second entails the emergence of self-hood at the level of a mental models of the world, or worldview; we suggest that humans possess both. We discuss the feasibility of an AI with creative agency and self-hood at the second (cognitive) level, but not the first (somatic) level.

As digital technologies are increasingly used in creative professions, the evolution of the relationship between designers and machines is growing in interest. Such topic is part of a broad debate on how cognitive processes and human intelligence development co-evolve in parallel with technology advancements in a process of technogenesis. In a complex socio-economic system, Artificial Intelligence-based technologies are both providing new tools and challenging the idea of creativity itself. We discuss how the creative process in the field of industrial design is commonly intended and we argue that the adoption of AI-based technologies is part of an ongoing process of symbiotic co-evolution between human and machine embedded in the creative process itself and, therefore, designers ought to develop synergic strategies to foster future innovation.

Inspired by cognitive theories of creativity, this paper introduces a computational model (AIGenC) that lays down the necessary components to enable artificial agents to learn, use and generate transferable representations. Unlike machine representations, which rely exclusively on raw sensory data, biological representations incorporate relational and associative information that embed a rich and structured concept space. The AIGenC model poses a hierarchical graph architecture with various levels and types of representations procured by the different components. The first component, Concept Processing, extracts objects and affordances from sensory input and encodes them into a concept space. The resulting representations are stored in a dual memory system and enriched with goal-directed and temporal information acquired through reinforcement learning, creating a higher-level of abstraction. Two additional and complementary components work in parallel to detect and recover relevant concepts through a matching process and create new ones, respectively, in a process akin to cognitive Reflective Reasoning and Blending. If Reflective Reasoning fails to offer a suitable solution, a blending operation creates new concepts by combining past information. We discuss the model’s capability to yield better out-of-distribution generalisation in artificial agents, thus advancing toward Artificial General Intelligence.

In this paper, I discuss the question of whether AI can be creative. I argue that AI-produced artworks can display features of creativity, but that the processes leading to the creative product are not creative. I distinguish between and describe the creative processes of humans and the generation-processes of AI. I identify one property of the former, which enables me to distinguish it from the latter: creative processes are instances of self-expression. An important feature of self-expressiveness, I argue, is that it can be retold in a self-narrative.

The depiction of a city’s facade can have various purposes, from purely decorative use to documentation for future restoration. This representation is often a manual and time-consuming process. This paper describes the co-creative system Evolving Urban Landscapes, which uses evolutionary computation to produce images that represent the landscape of an input city. In order to evaluate the creativity of the system, we conducted a study with 23 users. The results show that the system we created can be considered creative and, above all, that it generates diverse results, allowing the users to evolve landscapes according to their tastes.

We present a new large-scale emotion-labeled symbolic music dataset consisting of 12 k MIDI songs. To create this dataset, we first trained emotion classification models on the GoEmotions dataset, achieving state-of-the-art results with a model half the size of the baseline. We then applied these models to lyrics from two large-scale MIDI datasets. Our dataset covers a wide range of fine-grained emotions, providing a valuable resource to explore the connection between music and emotions and, especially, to develop models that can generate music based on specific emotions. Our code for inference, trained models, and datasets are available online.

A large amount of legal and legislative documents are generated every year with highly specialized content and significant repercussions on society. Besides technical, the produced information is not semantically standardized or format structured. Automating the document analysis, categorization, search, and summarization is essential. The Named Entity Recognition (NER) task is one of the tools that have the potential to extract information from legal documents with efficiency. This paper evaluates the state-of-the-art NER models BiLSTM+CRF and BERT+Fine-Tunning trained on Portuguese corpora through finetuning in the legal and legislative domains. The obtained results (F1-scores of 83.17% and 88.27%) suggest that the BERT model is superior, achieving better average results.

Legal Analytics (LA) techniques are a useful tool in the process of digitisation of judicial systems. However, they may imply processing of personal data contained in judicial rulings. This requires an assessment of the impact generated on the rights and freedoms of individuals. What happens if personal data are processed, with LA and AI systems, for research purposes, such as prediction? Should be taken additional technical and organisational measures for the protection of individuals, such as anonymisation or pseudonymisation? The EU legal framework does not interfere with data processing of courts acting in their judicial capacity, in order to safeguard the independence of the judiciary. Therefore, the decision to anonymise judgments is normally taken by the Court’s rules or procedures. The paper provides an overview of the different policies adopted by the different EU countries, investigating whether they should apply to researchers performing LA of judicial rulings. The paper also illustrates how such issues have been dealt within the Legal Analytics for Italian LAw (LAILA) project, funded by the Italian Ministry of Education and Research within the “PRIN programme”.

For the rule of law to work well, citizens should know their rights and obligations, especially in a day to day context such as when posing as a consumers. Despite being available online, the Portuguese Consumer law was not accessible to the point of being able easy to insert a sentence written in natural language in a search engine and getting a clear response without first having to scroll through multiple little applicable search results. To solve this issue, we introduce Legal Semantic Search Engine (LeSSE), an information retrieval system that uses a hybrid approach of semantic and lexical information retrieval techniques. The new system performed better than the lexical search system in production.

In this article, we explore the potential of ChatGPT to pass the Brazilian Bar Association exam, which consists of two parts. The first part includes 80 multiple-choice, single-answer, questions, with a maximum score of 80 points. The second part comprises a procedural document, worth 5 points, and 4 open-ended questions, worth 1.25 points each, and a human expert evaluates ChatGPT’s responses, in different domains of law. All three versions of ChatGPT performed well in the multiple-choice, single-answer, questions. GPT 4 ranks the highest, achieving a score of 70% of correct answers, followed by GPT 3.5 Default with 55%, then GPT 3.5 Legacy with 53%. However, when it comes to the second part the results are not as good. In the criminal exam, GPT 4 performs the worst, while GPT 3.5 Default performs the best, with GPT 3.5 Legacy coming in a close second. Regarding the business exam, GPT 3.5 Legacy had the worst performance, while GPT 4 achieved the highest score: 5.02. Overall, all ChatGPT versions performed well in the multiple-choice questions, but their responses to open-ended questions were underwhelming.

Many information retrieval systems use lexical approaches to retrieve information. Such approaches have multiple limitations, and these constraints are exacerbated when tied to specific domains, such as the legal one. Large language models, such as BERT, deeply understand a language and may overcome the limitations of older methodologies, such as BM25. This work investigated and developed a prototype of a Semantic Search System to assist the Supremo Tribunal de Justiça (Portuguese Supreme Court of Justice) in its decision-making process. We built a Semantic Search System that uses specially trained BERT models (Legal-BERTimbau variants) and a Hybrid Search System that incorporates both lexical and semantic techniques by combining the capabilities of BM25 and the potential of Legal-BERTimbau. In this context, we obtained a $$335\%$$ 335 % increase on the discovery metric when compared to BM25 for the first query result. This work also provides information on the most relevant techniques for training a Large Language Model adapted to Portuguese jurisprudence and introduces a new technique of Metadata Knowledge Distillation.

The general approach of the Draft of AI Act (December 2022) expanded the scope to explicitly include General Purpose Artificial Intelligence. This paper presents an overview of the new proposals and analyzes their implications. Although the proposed regulation has the merit of regulating an expanding field that can be applied in different domains and on a large scale due to its dynamic context, it has some flaws. It is essential to ascertain whether we are dealing with a general-risk category or a specific category of high-risk. Moreover, we need to clarify the allocation of responsibilities and promote cooperation between different actors. Finally, exemptions to the regulation should be properly balanced to avoid liability gaps.

The widespread of distributed renewable energy is leading to an increased need for advanced energy management solutions in buildings. The variability of generation needs to be balanced by consumer flexibility, which needs to be accomplished by keeping the consumption cost as low as possible, while guaranteeing consumer comfort. This paper proposes a rule-based system with the aim of generating recommendations for actions regarding the energy management of different energy consumption devices, namely lights and air conditioning. The proposed set of rules considers the forecasted values of building generation, consumption, user presence in different rooms and energy prices. In this way, building energy management systems are endowed with increased adaptability and reliability considering the lowering of energy costs and maintenance of user comfort. Results, using real data from an office building, demonstrate the appropriateness of the proposed model in generating recommendations that are in line with current context.

With the remnants of a COVID-19 pandemic still crippling the European economy, and the Russo-Ukrainian war propagating this crisis even further, it has become more than crucial to invest in renewable energy resources to mitigate energy dependencies. As a result, these crises have lowered the competitiveness of European manufacturers when compared to the rest of the world. Nevertheless, machine longevity is also essential to consider in manufacturing environments, since maintenance costs due to poor load management can lead to considerable additional monetary costs in the long term. The premise of the present paper is to propose a production scheduling algorithm that focuses on optimizing the total energy costs and machine longevity in a flexible job shop manufacturing layout. To achieve this, a Genetic Algorithm is employed to shift tasks in order to reduce load during peak demand times, utilize locally generated energy to its potential, minimize single-machine task overload, and consider imposed constraints in the production schedule. To validate the proposed methodology, a case study from the literature that uses real-production data is explored and compared to the present paper’s solution. Results show that the proposed methodology was capable of reducing single-machine task overload, that is, improving machine longevity, by 87.8%, while only increasing the energy costs, as a consequence, by 12.8%.

The combination of genetic programming with federated learning could solve the computational distribution while promoting a collaborative learning environment. This paper proposes a federated learning configuration that enables the use of genetic programming for its global model. In addition, this paper also proposes a new aggregation algorithm that enables the collaborative evolution of genetic programming individuals in federated learning. The case study uses flexible genetic programming, an existing and successful algorithm for image classification, integrated into a federated learning framework. The results show that the use of genetic programming with federated learning achieved a classification error rate of 1.67%, better than the scenario without federated learning, that had an error rate of 3.33%, considering a configuration with three clients with different datasets each.

Energy load disaggregation can contribute to balancing power grids by enhancing the effectiveness of demand-side management and promoting electricity-saving behavior through increased consumer awareness. However, the field currently lacks a comprehensive overview. To address this gap, this paper conducts a scoping review of load disaggregation domains, data types, and methods, by assessing 72 full-text journal articles. The findings reveal that domestic electricity consumption is the most researched area, while others, such as industrial load disaggregation, are rarely discussed. The majority of research uses relatively low-frequency data, sampled between 1 and 60 s. A wide variety of methods are used, and artificial neural networks are the most common, followed by optimization strategies, Hidden Markov Models, and Graph Signal Processing approaches.

Atrial fibrillation (AF) is frequently asymptomatic and at the same time a relevant risk factor for stroke and heart failure. Thus, the identification of patients at high risk of future development of AF from rapid and low-cost exams such as the electrocardiogram (ECG) is of great interest. In this work we trained a deep learning model to predict the risk to develop AF from ECG signals and electronic health records (EHR) data, integrating time-to-event in the model and accounting for death as a competing risk. We showed that our model outperforms the CHARGE-AF clinical risk score and we verified that training the model with both ECGs and EHR data led to better performances with respect to training on single modalities. Models were evaluated both in terms of discrimination and calibration.

Within the medical image analysis domain, the lack of extensive and well-balanced datasets has posed a significant challenge to traditional machine learning approaches, resulting in poor generalization ability of the models. In light of this, we propose a novel approach to evaluate the efficacy of neural network learning on small imbalanced datasets. The proposed methodology uncovers the relationships between model generalization ability, neural network properties, model complexity, and dataset resizing. This research highlights several key findings: (1) data augmentation techniques effectively enhance the generalization ability of neural network models; (2) a neural network model with a minimal number of each layer type can achieve superior generalization ability; (3) regularization layers prove to be a crucial factor in achieving higher generalization ability; (4) the number of epochs is not a determining factor in enhancing generalization ability; (5) complexity measures exhibit no significant correlation with generalization ability in the described scenarios. The findings from this study offer a practical roadmap for model selection, architecture search, and evaluation of the methods’ effectiveness in medical image analysis.

Glioma is a family of brain tumors with three main types exhibiting different progressions, which lack effective therapeutic options and specific molecular biomarkers. In this work, we propose a pipeline for multi-omics integrated analysis aimed at identifying features that could impact the development of different gliomas, assigned according to the latest classification guidelines. We estimate networks of genes and proteins based on human data, via the graphical lasso, as a network-based step towards variable selection. The estimated glioma networks were compared to disclose molecular relations that can be important for the development of a certain tumor type. Our outcomes were validated both mathematically, and through principal component analysis to determine if the selected subset of variables carries enough biological information to distinguish the three glioma types in a reduced dimensional subspace. The results highlight an overall agreement in variable selection across the two omics. Features exclusively selected by each glioma type appear as more representative of the pathological condition, making them suitable as potential diagnostic biomarkers. The comparison between glioma-type networks and with known protein-protein interactions reveals the presence of molecular relations that could be associated to a pathological condition. The 59 features identified by our analysis will be further considered to extend our work by integrating targeted biological evaluation.

The combination of the phenomenon of overcrowding with inefficient management of resources is a major obstacle to the good performance of hospital units and consequently the degradation of the medical service provided. This paper provides an analysis to understand the correlation between poor bed allocation and hospital performance. The lack of an efficient resource planning among the various medical specialties can negatively impact the quality of service. Four different techniques were compared to realize which is better suited for optimizing the allocation of beds in Hospital units. Hill Climbing and the Genetic Algorithm stood out the others, the latter presenting greater consistency and a shorter computation time. When tested with real data from Centro Hospitalar do Tâmega e Sousa, attained a total of 0 wrongly allocated patients against 92 when compared with former methods. This translates into better patient service, reduced waiting time and staff workload, which means increased performance in all adjacent medical issues.

AI applications in hospital frameworks can improve patient-care quality and efficient workflows and assist in digital transformation. By designing Smart Hospital infrastructures, creating an efficient framework enables patient information exchange between hospitals, point of care, and remote patient monitoring. Deep learning (DL) solutions play important roles in these infrastructures’ digital transformation process and architectural design. Literature review shows that DL solutions based on Automatic Speech Recognition (ASR) and Natural Language Processing (NLP) are rising concerning clinical data digitalisation, population health management, and improving patient care. Nevertheless, one of the literature’s shortcomings highlights the limited research using these solutions in real-world medical environments. As part of smart hospitals, smart medical scribes have been presented in several studies as a promising solution. However, just a few studies have tested it in real settings. Moreover, it was limited to non-existent studies on non-English systems, even yet to be found similar studies for European Portuguese. The proposed study evaluates NLP-based solutions in real-life Portuguese clinical settings focused on patient care for Smart Healthcare applications.

Transthyretin (TTR)-related familial amyloid polyneuropathy (ATTRv) is a life-threatening autosomal dominant disease and the age of onset represents the moment when first symptoms are felt. Accurately predicting the age of onset for a given patient is relevant for risk assessment and treatment management. In this work, we evaluate the impact of combining prediction models obtained from neighboring time windows on prediction error. We propose Symmetric (Sym) and Asymmetric (Asym) models which represent two different averaging approaches. These are incorporated with a weighting mechanism as to create Symmetric (Sym), Symmetric-weighted (Sym-w), Asymmetric (Asym), and Asymmetric-weighted (Asym-w). These four ensemble models are then compared to the original approach which is focused on individual regression base learners namely: Baseline (BL), Decision Tree (DT), Elastic Net (EN), Lasso (LA), Linear Regression (LR), Random Forest (RF), Ridge (RI), Support Vector Regressor (SV) and XGBoost (XG). Our results show that by aggregating predictions from neighbor models the average mean absolute error obtained by each base learner decreases. Overall, the best results are achieved by regression-based ensemble tree models as base learners.

Predicting post-discharge complications in cardiothoracic surgery is of utmost importance to improve clinical outcomes. Machine Learning (ML) techniques have been successfully applied in similar tasks, aiming at short time windows and in specific surgical conditions. However, as the target horizon is extended and the impact of unpredictable external factors rises, the complexity of the task increases, and traditional predictive models struggle to reproduce good performances. This study presents a two-step hybrid learning methodology to address this problem. Building up from identifying unique sub-groups of patients with shared characteristics, we then train individual supervised classification models for each sub-group, aiming at improved prediction accuracy and a more granular understanding of each decision. Our results show that specific sub-groups demonstrate substantially better performance when compared to the baseline model without sub-divisions, while others do not benefit from specialised models. Strategies such as the one presented may catalyse the success of applied ML solutions by contributing to a better understanding of their behaviour in different regions of the data space, leading to an informed decision-making process.

This work describes applying a transformer-based ranking solution to the specific problem of ordering ICD diagnoses codes. Taking advantage of the TFR-BERT framework and adapting it to the biomedical context using pre-trained and publicly available language representation models, namely BioBERT, BlueBERT and ClinicalBERT (Bio + Discharge Summary BERT Model), we demonstrate the effectiveness of such a framework and the strengths of using pre-trained models adapted to the biomedical domain. We showcase this by using a benchmark dataset in the healthcare field—MIMIC-III—showing how it was possible to learn how to sequence the main or primary diagnoses and the order in which the secondary diagnoses are presented. A window-based approach and a summary approach (using only the sentences with diagnoses) were also tested in an attempt to circumvent the maximum sequence length limitation of BERT-based models. BioBERT demonstrated superior performance in all approaches, achieving the best results in the summary approach.

Shellfish accumulation of marine biotoxins at levels unsafe for human consumption may severely impact their harvesting and farming, which has been grown worldwide in response to the growing demand for nutritious food and protein sources. In Southern European countries, diarrhetic shellfish poisoning (DSP) toxins are the most abundant and frequent toxins derived from algal blooms, affecting shellfish production yearly. Therefore, it is essential to understand the natural phenomenon of DSP toxins accumulation in shellfish and the meteorological and biological parameters that may regulate and influence its occurrence. In this work, we studied the relationship between the time series of several meteorological and biological variables and the time series of the concentration of DSP toxins in mussels on the Portuguese coast, using the Pearson’s correlation coefficient, time series regression modeling, Granger causality, and dynamic Bayesian networks using the MAESTRO tool. The results show that, for the models tested, the mean sea surface and air temperature time series with a one, two, or three-week lag can be valuable candidate predictors for forecasting the DSP concentration in mussels. Overall, this proof-of-concept study emphasizes the importance of statistical learning methodologies for analyzing time series environmental data and illustrates the importance of several variables in predicting DSP biotoxins concentration, which can help the shellfish production sector mitigate the negative impacts of DSP biotoxins accumulation.

Agricultural robots are exposed to adverse conditions reducing the components’ lifetime. To reduce the number of inspection, repair and maintenance activities, we propose using audio-based systems to diagnose and detect anomalies in these robots. Audio-based systems are non-destructive/intrusive solutions. Besides, it provides a significant amount of data to diagnose problems and for a wiser scheduler for preventive activities. So, in this work, we installed two microphones in an agricultural robot with a mowing tool. Real audio data was collected with the robotic mowing tool operating in several conditions and stages. Besides, a Sound-based Anomalies Detector (SAD) is proposed and tested with this dataset. The SAD considers a short-time Fourier transform (STFT) computation stage connected to a Support Vector Machine (SVM) classifier. The results with the collected dataset showed an F1 score between 95% and 100% in detecting anomalies in a mowing robot operation.

Grape varieties play an important role in wine’s production chain, its identification is crucial for controlling and regulating the production. Nowadays, two techniques are widely used, ampelography and molecular analysis. However, there are problems with both of them. In this scenario, Deep Learning classifiers emerged as a tool to automatically classify grape varieties. A problem with the classification of on-field acquired images is that there is a lot of information unrelated to the target classification. In this study, the use of segmentation before classification to remove such unrelated information was analyzed. We used two grape varieties identification datasets to fine-tune a pre-trained EfficientNetV2S. Our results showed that segmentation can slightly improve classification performance if only unrelated information is removed.

AI-based pest detection is gaining popularity in data-centric scenarios, providing farmers with excellent performance and decision support for pest control. However, these approaches often face challenges that require complex architectures. Alternatively, data-centric approaches aim to enhance the quality of training data. In this study, we present an approach that is particularly relevant when dealing with low data. Our proposed approach improves annotation quality without requiring additional manpower. We trained a model with data of inferior annotation quality and utilized its predictions to generate new annotations of higher quality. Results from our study demonstrate that, using a small dataset of 200 images with low resolution and variable lighting conditions, our model can improve the mean average precision (mAP) score by 1.1 points.

Selective thinning is a crucial operation to reduce forest ignitable material, to control the eucalyptus species and maximise its profitability. The selection and removal of less vigorous stems allows the remaining stems to grow healthier and without competition for water, sunlight and nutrients. This operation is traditionally performed by a human operator and is time-intensive. This work simplifies selective thinning by removing the stem selection part from the human operator’s side using a computer vision algorithm. For this, two distinct datasets of eucalyptus stems (with and without foliage) were built and manually annotated, and three Deep Learning object detectors (YOLOv5, YOLOv7 and YOLOv8) were tested on real context images to perform instance segmentation. YOLOv8 was the best at this task, achieving an Average Precision of 74% and 66% on non-leafy and leafy test datasets, respectively. A computer vision algorithm for automatic stem selection was developed based on the YOLOv8 segmentation output. The algorithm managed to get a Precision above 97% and a 81% Recall. The findings of this work can have a positive impact in future developments for automatising selective thinning in forested contexts.

Grape moths are a significant pest in vineyards, causing damage and losses in wine production. Pheromone traps are used to monitor grape moth populations and determine their developmental status to make informed decisions regarding pest control. Smart pest monitoring systems that employ sensors, cameras, and artificial intelligence algorithms are becoming increasingly popular due to their ability to streamline the monitoring process. In this study, we investigate the effectiveness of using segmentation as a pre-processing step to improve the detection of grape moths in trap images using deep learning models. We train two segmentation models, the U-Net architecture with ResNet18 and InceptionV3 backbonesl, and utilize the segmented and non-segmented images in the YOLOv5s and YOLOv8s detectors to evaluate the impact of segmentation on detection. Our results show that segmentation pre-processing can significantly improve detection by 3% for YOLOv5 and 1.2% for YOLOv8. These findings highlight the potential of segmentation pre-processing for enhancing insect detection in smart pest monitoring systems, paving the way for further exploration of different training methods.

We propose a novel approach for limiting possible sexual harassment during taxi rides, where penalizing harassing drivers and matching them to passengers play key roles. In this paper, we focus on the matching part. In particular, we propose a novel two-sided market model, with drivers on one side and passengers on another side, where drivers have (1) safety preferences, (2) profit preferences, and (3) gender preferences, for passengers, and passengers have (1) safety preferences, (2) delay preferences, and (3) gender preferences, for drivers. Given these three-layer preferences, we study increasing the safety and stability in matchings, thus possibly reducing the chance of sexual harassment. In addition, we combine safety and stability with maximizing total profit or minimizing total delay. We design a number of algorithms throughout the paper and measure their safety, stability, and efficiency.

Matching addresses is a critical task for companies and post offices involved in the processing and delivery of packages. The ramifications of incorrectly delivering a package to the wrong recipient are numerous, ranging from harm to the company’s reputation to economic and environmental costs. This research introduces a deep learning-based model designed to increase the efficiency of address matching for Portuguese addresses. The model comprises two parts: (i) a bi-encoder, which is fine-tuned to create meaningful embeddings of Portuguese postal addresses, utilized to retrieve the top 10 likely matches of the un-normalized target address from a normalized database, and (ii) a cross-encoder, which is fine-tuned to accurately re-rank the 10 addresses obtained by the bi-encoder. The model has been tested on a real-case scenario of Portuguese addresses and exhibits a high degree of accuracy, exceeding 95% at the door level. When utilized with GPU computations, the inference speed is about 4.5 times quicker than other traditional approaches such as BM25. An implementation of this system in a real-world scenario would substantially increase the effectiveness of the distribution process. Such an implementation is currently under investigation.

Intelligent Transport Systems (ITS) is a fast evolving domain with an increasingly important role in shaping the future of transport and a significant impact on a wide range of issues, many of which have ethical implications. On the other hand, Ethics is essential to ensure that ITS are safe, fair, accountable, trustworthy, and respectful of privacy. This study reflects on the ethical concerns around transport system and its impact on economic, social and environmental dimensions, from the spirit of the foundational concepts of Ethics to the specific issues raised by intelligent transport, including those enhanced by Artificial Intelligence (AI) and Machine Learning (ML) systems. The primordial ethical concerns of transport have, in some extent, been mitigated with the introduction of the ITS paradigm, but others have arisen as a result of emerging technologies. Ethics is therefore critical in intelligent transport because of its potential to significantly impact individuals, communities, and society as a whole, and is an important tool to design more sustainable, equitable, and fair transport systems.

During the COVID-19 pandemic, the measures imposed to slow the spread of the virus had a profound impact on population dynamics around the world, producing unprecedented changes in mobility. Spatial data on human activity, including Call Detail Records (CDRs), have become a valuable source of information for understanding those changes. In this paper we study the population’s mobility after the first wave of the pandemic within Portugal, using CDR data. We identify the movements and stops of the citizens, at an antenna level, and compare the results in the first months after the lifting of most of the contingency measures with the same period of the following year, highlighting the advantages of using CDRs to analyze mobility in pandemic contexts. Results based on two mobile phone datasets showed a significant difference in mobility in the two periods.

Fog computing has recently attracted great attention as an emerging computing paradigm, avoiding the latency concerns of the cloud. However, because of the distributed, decentralized nature of the fog, several security and privacy issues arise when fog nodes interact and exchange data in specific tasks. Fog servers must be trustworthy for delegation since they are close to the end user and can obtain sensitive information. Yet, normal cryptographic solutions cannot be used to control internal attacks, i.e., from a rogue node that has been authenticated to join the network, raising the concern of how to establish a trustworthy communication between the fog nodes. Trust Management Systems (TMS) have been developed to calculate the level of assurance between fog nodes based on their communication behavior to detect the rogue nodes in the network. Password-based, Traditional authentication methods, i.e., biometric-based and certificated-based, do not fit the fog because of its uniqueness architecture, consuming substantially additional processing power and provoking latency. Thus, several research issues remain open for TMS in the fog, including creating trusted execution environments, trust and security during fog orchestration, collusion attack and access control. In this paper, we investigate using artificial intelligence techniques to tackle the main challenges of TMS in fog computing. We conducted a comparative study to evaluate the major TMS in literature and identify their advantages and disadvantages. We then highlight 17 primary insights and recommendations to improve TMS using artificial intelligence to have more efficient TMS in fog computing.

In recent years, the need for writing effective, reusable, and high-quality source code has grown exponentially. Writing source code is an integral part of building any software system; the development phase of the software lifecycle contains code implementation, refactoring, maintenance, and fixing bugs. Software developers implement the desired solution by turning the system requirements into viable software products. For the most part, the implementation phase can be challenging as it requires a certain level of problem-solving skills and the ability to produce high-quality outcomes without decreasing productivity rates or not meeting the business plans and deadlines. Programmers’ daily tasks might also include writing large amounts of repetitive boilerplate code, which can be tedious, not to mention the potential bugs that could arise from human errors during the development process. The ability to automatically generate source code will save significant time and effort invested in the software development process by increasing the speed and efficiency of software development teams. In this survey, we review and summarize the recent studies on deep learning approaches used to generate source code in different programming languages such as Java, Python, and SQL (Structured Query Language). We categorize the surveyed work into two groups, Natural Language-based solutions for approaches that use natural text as input and Computer Vision-based solutions which generate code based on images as input.

The “smart supply chain” is a new way of doing business made possible by smart, sustainable business and IT trends. Sustainable supply chains are a creative movement that uses information technology to improve the quality of operations at their sites so that activities can be changed to meet social and environmental needs. IoT is one of the most critical parts of smart's technological foundation in this way. This paper shows how to set up a sustainable supply chain based on IoT. Based on the IoT's four-stage architecture, this framework was made by looking at the research, surveying general people, and evaluating the opinions of people who work in this field. This way of thinking makes it easy to make good environmental decisions throughout the supply chain. It also shows the direct link between data collection and how it interacts with sectors that are affected by environmental sustainability. Experts in the supply chain have approved this framework, which can help technology-focused industrial organizations adopt the smart supply chain.

In the milling process of micro-machining, the optimization process is one of the keys to reduce production cost. By monitoring the tool wear and detecting when it is no longer acceptable, the machining process can be adjusted more accurately. This research explores four approaches using different machine learning models to predict machining tool wear during the milling process. The study is based on a dataset created with a face milling operation on stainless steel (AISI 303) round material. The machining is divided into a number of stairs and is performed with a 3 mm tungsten carbide. Three different types of sensors are used to measure the wearing process, with acoustic emission, accelerometers and axis currents. The better approach achieved a F1-score of 73% on five classes with an Extra-Trees Classifier.

Digital twin technology has gained considerable traction in recent years, with diverse applications spanning multiple sectors. However, due to the inherent complexity and substantial costs associated with constructing digital twins, systematic development methodologies are essential for fully capitalizing on their benefits. Therefore, this paper firstly provides an exhaustive synthesis of related literature, highlighting: (1) ten core advantages of implementing digital twin technology; (2) five primary domains in which digital twin applications have been prevalently employed; and (3) ten principal objectives of digital twin applications. Subsequently, we propose a seven-step digital twin application development process, encompassing: (i) Digital Twin Purposing; (ii) Digital Twin Scoping; (iii) Physical Twin Modeling; (iv) Calibration and Validation; (v) Application Logic Development; (vi) External System Integration; and (vii) Deployment and Operation. This structured approach aims to demystify the intrinsic complexity of twinned systems, ensuring that the deployment of digital twin-based solutions effectively addresses the target problem while maximizing the derived benefits.

In the last decades most efforts to catalog and characterize the built environment for multi-hazard risk assessment have focused on the exploration of census data, cadastral datasets, and local surveys. The first approach is only updated every 10 years and does not provide building locations, the second type of data is only available for restricted urban centers, and the third approach requires surveyors with an engineering background, which is cost-prohibitive for large-scale risk studies. It is thus clear that methods to characterize the built environment for large-scale risk analysis at the asset level are currently missing, which hampers the assessment of the impact of natural hazards for the purposes of risk management. Some recent efforts have demonstrated how deep learning algorithms can be trained to recognize specific architectural and structural features of buildings, which is needed for earthquake risk analysis. In this paper we describe how convolutional neural networks can be combined with data from OpenStreetMap and Google Street View to help develop exposure models for multi-hazard risk analysis. This project produced an original comprehensively annotated (15 characteristics) dataset of approximately 5000 images of buildings from the parish of Alvalade (Lisbon, Portugal). The dataset was used to train and test different deep learning networks for building exposure models. The best results were obtained with ResNet50V2, InceptionV3 and DenseNet201, all with accuracies above 82%. These results will support future developments for assessing exposure models for seismic risk analysis. The novelty of our work consists in the number of characteristics of the images in the dataset, the number of deep learning models trained and the number of classes that can be used for building exposure models.

With the growth of IoT (Internet of Things) technologies, there has been a significant increase in opportunities to enhance various aspects of our daily lives. One such application is the prediction of car park occupancy using car park movement data, which can be further improved by incorporating weather data. This paper focuses on investigating how weather conditions influence car park occupancy prediction and aims to identify the most effective prediction algorithm. To achieve more accurate results, the researchers explored two primary approaches: Classification and Regression. These approaches allow for a comprehensive analysis of the parking scenario, catering to both qualitative and quantitative aspects of predicting car park occupancy. In this study, a total of 24 prediction models, encompassing a wide range of algorithms were induced. These models were designed to consider various details, including parking features, location specifics, time-related factors and crucially, weather conditions. Overall, this study showcased the potential of leveraging IoT technologies, car park movement data, and weather information to predict car park occupancy effectively. By exploring both classification and regression approaches, each yielding accuracy and R2Score values surpassing 85%.

Machine learning has significant potential for optimizing various industrial processes. However, data acquisition remains a major challenge as it is both time-consuming and costly. Synthetic data offers a promising solution to augment insufficient data sets and improve the robustness of machine learning models. In this paper, we investigate the feasibility of incorporating synthetic data into the training process of the injection molding process using an existing Long Short-Term Memory architecture. Our approach is to generate synthetic data by simulating production cycles and incorporating them into the training data set. Through iterative experimentation with different proportions of synthetic data, we attempt to find an optimal balance that maximizes the benefits of synthetic data while preserving the authenticity and relevance of real data. Our results suggest that the inclusion of synthetic data improves the model’s ability to handle different scenarios, with potential practical industrial applications to reduce manual labor, machine use, and material waste. This approach provides a valuable alternative for situations where extensive data collection and maintenance has been impractical or costly and thus could contribute to more efficient manufacturing processes in the future.

Real Estate Agents perform the tedious job of selecting and filtering pictures of houses manually on a daily basis, in order to choose the most suitable ones for their websites and provide a better description of the properties they are selling. However, this process consumes a lot of time, causing delays in the advertisement of homes and reception of proposals. In order to expedite and automate this task, Computer Vision solutions can be employed. Deep Learning, which is a subfield of Machine Learning, has been highly successful in solving image recognition problems, making it a promising solution for this particular context. Therefore, this paper proposes the application of Vision Transformers to indoor room classification. The study compares various image classification architectures, ranging from traditional Convolutional Neural Networks to the latest Vision Transformer architecture. Using a dataset based on well-known scene classification datasets, their performance is analyzed. The results demonstrate that Vision Transformers are one of the most effective architectures for indoor classification, with highly favorable outcomes in automating image recognition and selection in the Real Estate industry.