INESC TEC

Machine learning systems are becoming increasingly ubiquitous. These systems’s adoption has been expanding, accelerating the shift towards a more algorithmic society, meaning that algorithmically informed decisions have greater potential for significant social impact. However, most of these accurate decision support systems remain complex black boxes, meaning their internal logic and inner workings are hidden to the user and even experts cannot fully understand the rationale behind their predictions. Moreover, new regulations and highly regulated domains have made the audit and verifiability of decisions mandatory, increasing the demand for the ability to question, understand, and trust machine learning systems, for which interpretability is indispensable. The research community has recognized this interpretability problem and focused on developing both interpretable models and explanation methods over the past few years. However, the emergence of these methods shows there is no consensus on how to assess the explanation quality. Which are the most suitable metrics to assess the quality of an explanation? The aim of this article is to provide a review of the current state of the research field on machine learning interpretability while focusing on the societal impact and on the developed methods and metrics. Furthermore, a complete literature review is presented in order to identify future directions of work on this field.

The context in which service is delivered and experienced has, in many respects, fundamentally changed. For instance, advances in technology, especially information technology, are leading to a proliferation of revolutionary services and changing how customers serve themselves before, during, and after purchase. To understand this changing landscape, the authors engaged in an international and interdisciplinary research effort to identify research priorities that have the potential to advance the service field and benefit customers, organizations, and society. The priority-setting process was informed by roundtable discussions with researchers affiliated with service research centers and networks located around the world and resulted in the following 12 service research priorities: stimulating service innovation, facilitating servitization, service infusion, and solutions, understanding organization and employee issues relevant to successful service, developing service networks and systems, leveraging service design, using big data to advance service, understanding value creation, enhancing the service experience, improving well-being through transformative service, measuring and optimizing service performance and impact, understanding service in a global context, and leveraging technology to advance service. For each priority, the authors identified important specific service topics and related research questions. Then, through an online survey, service researchers assessed the subtopics’ perceived importance and the service field’s extant knowledge about them. Although all the priorities and related topics were deemed important, the results show that topics related to transformative service and measuring and optimizing service performance are particularly important for advancing the service field along with big data, which had the largest gap between importance and current knowledge of the field. The authors present key challenges that should be addressed to move the field forward and conclude with a discussion of the need for additional interdisciplinary research.

Traditional imagery—provided, for example, by RGB and/or NIR sensors—has proven to be useful in many agroforestry applications. However, it lacks the spectral range and precision to profile materials and organisms that only hyperspectral sensors can provide. This kind of high-resolution spectroscopy was firstly used in satellites and later in manned aircraft, which are significantly expensive platforms and extremely restrictive due to availability limitations and/or complex logistics. More recently, UAS have emerged as a very popular and cost-effective remote sensing technology, composed of aerial platforms capable of carrying small-sized and lightweight sensors. Meanwhile, hyperspectral technology developments have been consistently resulting in smaller and lighter sensors that can currently be integrated in UAS for either scientific or commercial purposes. The hyperspectral sensors’ ability for measuring hundreds of bands raises complexity when considering the sheer quantity of acquired data, whose usefulness depends on both calibration and corrective tasks occurring in pre- and post-flight stages. Further steps regarding hyperspectral data processing must be performed towards the retrieval of relevant information, which provides the true benefits for assertive interventions in agricultural crops and forested areas. Considering the aforementioned topics and the goal of providing a global view focused on hyperspectral-based remote sensing supported by UAV platforms, a survey including hyperspectral sensors, inherent data processing and applications focusing both on agriculture and forestry—wherein the combination of UAV and hyperspectral sensors plays a center role—is presented in this paper. Firstly, the advantages of hyperspectral data over RGB imagery and multispectral data are highlighted. Then, hyperspectral acquisition devices are addressed, including sensor types, acquisition modes and UAV-compatible sensors that can be used for both research and commercial purposes. Pre-flight operations and post-flight pre-processing are pointed out as necessary to ensure the usefulness of hyperspectral data for further processing towards the retrieval of conclusive information. With the goal of simplifying hyperspectral data processing—by isolating the common user from the processes’ mathematical complexity—several available toolboxes that allow a direct access to level-one hyperspectral data are presented. Moreover, research works focusing the symbiosis between UAV-hyperspectral for agriculture and forestry applications are reviewed, just before the paper’s conclusions.

The scientific study of hate speech, from a computer science point of view, is recent. This survey organizes and describes the current state of the field, providing a structured overview of previous approaches, including core algorithms, methods, and main features used. This work also discusses the complexity of the concept of hate speech, defined in many platforms and contexts, and provides a unifying definition. This area has an unquestionable potential for societal impact, particularly in online communities and digital media platforms. The development and systematization of shared resources, such as guidelines, annotated datasets in multiple languages, and algorithms, is a crucial step in advancing the automatic detection of hate speech.

Many real-world data-mining applications involve obtaining predictive models using datasets with strongly imbalanced distributions of the target variable. Frequently, the least-common values of this target variable are associated with events that are highly relevant for end users (e.g., fraud detection, unusual returns on stock markets, anticipation of catastrophes, etc.). Moreover, the events may have different costs and benefits, which, when associated with the rarity of some of them on the available training data, creates serious problems to predictive modeling techniques. This article presents a survey of existing techniques for handling these important applications of predictive analytics. Although most of the existing work addresses classification tasks (nominal target variables), we also describe methods designed to handle similar problems within regression tasks (numeric target variables). In this survey, we discuss the main challenges raised by imbalanced domains, propose a definition of the problem, describe the main approaches to these tasks, propose a taxonomy of the methods, summarize the conclusions of existing comparative studies as well as some theoretical analyses of some methods, and refer to some related problems within predictive modeling.

Breast cancer is one of the main causes of cancer death worldwide. The diagnosis of biopsy tissue with hematoxylin and eosin stained images is non-trivial and specialists often disagree on the final diagnosis. Computer-aided Diagnosis systems contribute to reduce the cost and increase the efficiency of this process. Conventional classification approaches rely on feature extraction methods designed for a specific problem based on field-knowledge. To overcome the many difficulties of the feature-based approaches, deep learning methods are becoming important alternatives. A method for the classification of hematoxylin and eosin stained breast biopsy images using Convolutional Neural Networks (CNNs) is proposed. Images are classified in four classes, normal tissue, benign lesion, in situ carcinoma and invasive carcinoma, and in two classes, carcinoma and non-carcinoma. The architecture of the network is designed to retrieve information at different scales, including both nuclei and overall tissue organization. This design allows the extension of the proposed system to whole-slide histology images. The features extracted by the CNN are also used for training a Support Vector Machine classifier. Accuracies of 77.8% for four class and 83.3% for carcinoma/non-carcinoma are achieved. The sensitivity of our method for cancer cases is 95.6%.

The increasing incidence of melanoma has recently promoted the development of computer-aided diagnosis systems for the classification of dermoscopic images. Unfortunately, the performance of such systems cannot be compared since they are evaluated in different sets of images by their authors and there are no public databases available to perform a fair evaluation of multiple systems. In this paper, a dermoscopic image database, called PH², is presented. The PH² database includes the manual segmentation, the clinical diagnosis, and the identification of several dermoscopic structures, performed by expert dermatologists, in a set of 200 dermoscopic images. The PH² database will be made freely available for research and benchmarking purposes.

We address the problem of position trajectory-tracking and path-following control design for underactuated autonomous vehicles in the presence of possibly large modeling parametric uncertainty. For a general class of vehicles moving in either 2- or 3-D space, we demonstrate how adaptive switching supervisory control can be combined with a nonlinear Lyapunov-based tracking control law to solve the problem of global boundedness and convergence of the position tracking error to a neighborhood of the origin that can be made arbitrarily small. The desired trajectory does not need to be of a particular type (e.g., trimming trajectories) and can be any sufficiently smooth bounded curve parameterized by time. We also show how these results can be applied to solve the path-following problem, in which the vehicle is required to converge to and follow a path, without a specific temporal specification. We illustrate our design procedures through two vehicle control applications: a hovercraft (moving on a planar surface) and an underwater vehicle (moving in 3-D space). Simulations results are presented and discussed.

Forecasting has always been at the forefront of decision making and planning. The uncertainty that surrounds the future is both exciting and challenging, with individuals and organisations seeking to minimise risks and maximise utilities. The large number of forecasting applications calls for a diverse set of forecasting methods to tackle real-life challenges. This article provides a non-systematic review of the theory and the practice of forecasting. We provide an overview of a wide range of theoretical, state-of-the-art models, methods, principles, and approaches to prepare, produce, organise, and evaluate forecasts. We then demonstrate how such theoretical concepts are applied in a variety of real-life contexts. We do not claim that this review is an exhaustive list of methods and applications. However, we wish that our encyclopedic presentation will offer a point of reference for the rich work that has been undertaken over the last decades, with some key insights for the future of forecasting theory and practice. Given its encyclopedic nature, the intended mode of reading is non-linear. We offer cross-references to allow the readers to navigate through the various topics. We complement the theoretical concepts and applications covered by large lists of free or open-source software implementations and publicly-available databases. © 2021 The Author(s)

BACKGROUND: The process of generating raw genome sequence data continues to become cheaper, faster, and more accurate. However, assembly of such data into high-quality, finished genome sequences remains challenging. Many genome assembly tools are available, but they differ greatly in terms of their performance (speed, scalability, hardware requirements, acceptance of newer read technologies) and in their final output (composition of assembled sequence). More importantly, it remains largely unclear how to best assess the quality of assembled genome sequences. The Assemblathon competitions are intended to assess current state-of-the-art methods in genome assembly. RESULTS: In Assemblathon 2, we provided a variety of sequence data to be assembled for three vertebrate species (a bird, a fish, and snake). This resulted in a total of 43 submitted assemblies from 21 participating teams. We evaluated these assemblies using a combination of optical map data, Fosmid sequences, and several statistical methods. From over 100 different metrics, we chose ten key measures by which to assess the overall quality of the assemblies. CONCLUSIONS: Many current genome assemblers produced useful assemblies, containing a significant representation of their genes and overall genome structure. However, the high degree of variability between the entries suggests that there is still much room for improvement in the field of genome assembly and that approaches which work well in assembling the genome of one species may not necessarily work well for another.

Breast cancer is the most common invasive cancer in women, affecting more than 10% of women worldwide. Microscopic analysis of a biopsy remains one of the most important methods to diagnose the type of breast cancer. This requires specialized analysis by pathologists, in a task that i) is highly time- and cost-consuming and ii) often leads to nonconsensual results. The relevance and potential of automatic classification algorithms using hematoxylin-eosin stained histopathological images has already been demonstrated, but the reported results are still sub-optimal for clinical use. With the goal of advancing the state-of-the-art in automatic classification, the Grand Challenge on BreAst Cancer Histology images (BACH) was organized in conjunction with the 15th International Conference on Image Analysis and Recognition (ICIAR 2018). BACH aimed at the classification and localization of clinically relevant histopathological classes in microscopy and whole-slide images from a large annotated dataset, specifically compiled and made publicly available for the challenge. Following a positive response from the scientific community, a total of 64 submissions, out of 677 registrations, effectively entered the competition. The submitted algorithms improved the state-of-the-art in automatic classification of breast cancer with microscopy images to an accuracy of 87%. Convolutional neuronal networks were the most successful methodology in the BACH challenge. Detailed analysis of the collective results allowed the identification of remaining challenges in the field and recommendations for future developments. The BACH dataset remains publicly available as to promote further improvements to the field of automatic classification in digital pathology.

The goal of ensemble regression is to combine several models in order to improve the prediction accuracy in learning problems with a numerical target variable. The process of ensemble learning can be divided into three phases: the generation phase, the pruning phase, and the integration phase. We discuss different approaches to each of these phases that are able to deal with the regression problem, categorizing them in terms of their relevant characteristics and linking them to contributions from different fields. Furthermore, this work makes it possible to identify interesting areas for future research.

We study distributed optimization problems when N nodes minimize the sum of their individual costs subject to a common vector variable. The costs are convex, have Lipschitz continuous gradient (with constant L), and bounded gradient. We propose two fast distributed gradient algorithms based on the centralized Nesterov gradient algorithm and establish their convergence rates in terms of the per-node communications K and the per-node gradient evaluations k. Our first method, Distributed Nesterov Gradient, achieves rates O( logK/K) and O(logk/k). Our second method, Distributed Nesterov gradient with Consensus iterations, assumes at all nodes knowledge of L and μ(W) - the second largest singular value of the N ×N doubly stochastic weight matrix W. It achieves rates O( 1/ K <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2-ξ</sup> ) and O( 1/k <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> ) ( ξ > 0 arbitrarily small). Further, we give for both methods explicit dependence of the convergence constants on N and W. Simulation examples illustrate our findings.

Scientific research adopts qualitative and quantitative methodologies in the modeling and analysis of numerous phenomena. The qualitative methodology intends to understand a complex reality and the meaning of actions in a given context. On the other hand, the quantitative methodology seeks to obtain accurate and reliable measurements that allow a statistical analysis. Both methodologies offer a set of methods, potentialities and limitations that must be explored and known by researchers. This paper concisely maps a total of seven qualitative methods and five quantitative methods. A comparative analysis of the most relevant and adopted methods is done to understand the main strengths and limitations of them. Additionally, the work developed intends to be a fundamental reference for the accomplishment of a research study, in which the researcher intends to adopt a qualitative or quantitative methodology. Through the analysis of the advantages and disadvantages of each method, it becomes possible to formulate a more accurate, informed and complete choice. Article visualizations:

With the expansion of smart meters, like the Advanced Metering Infrastructure (AMI), and the Internet of Things (IoT), each smart city is equipped with various kinds of electronic devices. Therefore, equipment and technologies enable us to be smarter and make various aspects of smart cities more accessible and applicable. The goal of the current paper is to provide an inclusive review on the concept of the smart city besides their different applications, benefits, and advantages. In addition, most of the possible IoT technologies are introduced, and their capabilities to merge into and apply to the different parts of smart cities are discussed. The potential application of smart cities with respect to technology development in the future provides another valuable discussion in this paper. Meanwhile, some practical experiences all across the world and the key barriers to its implementation are thoroughly expressed.

COVID-19 has caused dramatic effects on the world economy, business activities, and people. But digitization is also helping many companies to adapt and overcome the current situation caused by COVID-19. The growth in the use of technology in the daily lives of people and companies to face this exceptional situation is an evidence of the digital acceleration process. This exploratory study analyzes the impact of digital transformation processes in three business areas: labor and social relations, marketing and sales, and technology. The impact of digitalization is expected to be transversal to each area and will encourage the emergence of new digital products and services based on the principle of flexibility. Additionally, new ways of working will foster the demand for new talent regardless of people's geographical location. Moreover, cybersecurity and privacy will become two key elements that will support the integrated development of the Internet of Things technology solutions, artificial intelligence, big data, and robotics.

The integration of artificial intelligence (AI) into medical imaging has guided in an era of transformation in healthcare. This literature review explores the latest innovations and applications of AI in the field, highlighting its profound impact on medical diagnosis and patient care. The innovation segment explores cutting-edge developments in AI, such as deep learning algorithms, convolutional neural networks, and generative adversarial networks, which have significantly improved the accuracy and efficiency of medical image analysis. These innovations have enabled rapid and accurate detection of abnormalities, from identifying tumors during radiological examinations to detecting early signs of eye disease in retinal images. The article also highlights various applications of AI in medical imaging, including radiology, pathology, cardiology, and more. AI-based diagnostic tools not only speed up the interpretation of complex images but also improve early detection of disease, ultimately delivering better outcomes for patients. Additionally, AI-based image processing facilitates personalized treatment plans, thereby optimizing healthcare delivery. This literature review highlights the paradigm shift that AI has brought to medical imaging, highlighting its role in revolutionizing diagnosis and patient care. By combining cutting-edge AI techniques and their practical applications, it is clear that AI will continue shaping the future of healthcare in profound and positive ways.

Melanoma is one of the deadliest forms of cancer; hence, great effort has been put into the development of diagnosis methods for this disease. This paper addresses two different systems for the detection of melanomas in dermoscopy images. The first system uses global methods to classify skin lesions, whereas the second system uses local features and the bag-of-features classifier. This paper aims at determining the best system for skin lesion classification. The other objective is to compare the role of color and texture features in lesion classification and determine which set of features is more discriminative. It is concluded that color features outperform texture features when used alone and that both methods achieve very good results, i.e., Sensitivity = 96% and Specificity = 80% for global methods against Sensitivity = 100% and Specificity = 75% for local methods. The classification results were obtained on a data set of 176 dermoscopy images from Hospital Pedro Hispano, Matosinhos.

Abstract The COVID‐19 pandemic situation has pushed many higher education institutions into a fast‐paced, and mostly unstructured, emergency remote education process. In such an unprecedented context, it is important to understand how technology is mediating the educational process and how teachers and students are experiencing the change brought by the pandemic. This research aims to understand how the learning was mediated by technology during the early stages of the pandemic and how students and teachers experienced this sudden change. Data were collected following a qualitative research design. Thirty in‐depth and semi‐structured interviews (20 students and 10 teachers) were obtained and analysed following a thematic analysis approach. Results provide evidence on the adoption of remote education technologies due to the pandemic with impacts on the education process, ICT platforms usage and personal adaptation. The emergency remote education context led to mixed outcomes regarding the education process. Simultaneously, ICT platforms usage was mostly a positive experience and personal adaptation was mostly a negative experience. These results bring new insights for higher education organizations on actions they could take, such as curating the learning experience with standard, institutional‐wide platforms, appropriate training for students and teachers, and suitable remote evaluation practices. Practitioner notes What is already known about this topic The COVID‐19 pandemic has pushed the world's education environment into an unstructured, emergency remote education process. There is a lack of understanding of how ICT tools mediated learning during pandemic's early stages and how actors experienced this sudden change. In technology‐mediated learning contexts, participant beliefs, knowledge, practices and the environment mutually influence one another and affect the lived experience. What this paper adds The paper identifies and characterizes the educational process, the technological tools used in this new educational setting and personal adaptation of higher education students and teachers during these unprecedented times. The results show the following: an increase in teacher–student interaction (outside classes), new opportunities and content development; difficulties in control evaluation fraud, constraints in attaining the desired learning outcomes and lack of training; resilience to adapt and adopt the new technologies, despite the negative personal experience lived in terms of productivity, motivation, workload and mental health. Implications for practice and/or policy The paper makes evidence‐based recommendations on how higher education institutions can leverage this experience to prepare for future disruptions and increase the use of ICT tools in their regular learning environment.

In medical image analysis applications, the availability of the large amounts of annotated data is becoming increasingly critical. However, annotated medical data is often scarce and costly to obtain. In this paper, we address the problem of synthesizing retinal color images by applying recent techniques based on adversarial learning. In this setting, a generative model is trained to maximize a loss function provided by a second model attempting to classify its output into real or synthetic. In particular, we propose to implement an adversarial autoencoder for the task of retinal vessel network synthesis. We use the generated vessel trees as an intermediate stage for the generation of color retinal images, which is accomplished with a generative adversarial network. Both models require the optimization of almost everywhere differentiable loss functions, which allows us to train them jointly. The resulting model offers an end-to-end retinal image synthesis system capable of generating as many retinal images as the user requires, with their corresponding vessel networks, by sampling from a simple probability distribution that we impose to the associated latent space. We show that the learned latent space contains a well-defined semantic structure, implying that we can perform calculations in the space of retinal images, e.g., smoothly interpolating new data points between two retinal images. Visual and quantitative results demonstrate that the synthesized images are substantially different from those in the training set, while being also anatomically consistent and displaying a reasonable visual quality.