Francisco Herrera

• Independent Researcher

Deep learning models have an intrinsic privacy issue as they memorize parts of their training data, creating a privacy leakage. Membership inference attacks (MIAs) exploit this to obtain confidential information about the data used for training, aiming to steal information. They can be repurposed as a measurement of data integrity by inferring whet...

The study of large language models (LLMs) is a key area in open-world machine learning. Although LLMs demonstrate remarkable natural language processing capabilities, they also face several challenges, including consistency issues, hallucinations, and jailbreak vulnerabilities. Jailbreaking refers to the crafting of prompts that bypass alignment sa...

Large Language Models (LLMs) have significantly advanced sentiment analysis, yet their inherent uncertainty and variability pose critical challenges to achieving reliable and consistent outcomes. This paper systematically explores the Model Variability Problem (MVP) in LLM-based sentiment analysis, characterized by inconsistent sentiment classifica...

Large Language Models (LLMs) offer powerful capabilities in text generation and are increasingly adopted across a wide range of domains. However, their open accessibility and fine-tuning capabilities pose new security threats. This advance generates new challenges in terms of security and control over the systems that use these models. We hypothesi...

The rapid development of artificial intelligence systems has amplified societal concerns regarding their usage, necessitating regulatory frameworks that encompass data privacy. Federated Learning (FL) is posed as potential solution to data privacy challenges in distributed machine learning by enabling collaborative model training {without data shar...

Deep learning models have an intrinsic privacy issue as they memorize parts of their training data, creating a privacy leakage. Membership Inference Attacks (MIA) exploit it to obtain confidential information about the data used for training, aiming to steal information. They can be repurposed as a measurement of data integrity by inferring whether...

Federated Learning presents a nascent approach to machine learning, enabling collaborative model training across decentralized devices while safeguarding data privacy. However, its distributed nature renders it susceptible to adversarial attacks. Integrating blockchain technology with Federated Learning offers a promising avenue to enhance security...

At the same time that artificial intelligence is becoming popular, concern and the need for regulation is growing, including among other requirements the data privacy. In this context, Federated Learning is proposed as a solution to data privacy concerns derived from different source data scenarios due to its distributed learning. The defense mecha...

In group decision making (GDM), consensus reaching process (CRP) is a very effective tool for decision makers to reach cooperative agreements. Generally, decision makers need to modify their preferences to reach a consensus, and preference-modifications often mean cost, which make the minimum cost consensus models popular. However, in real-world de...

Consistency is usually associated with transitive properties, among which the additive transitivity is one of the most popular methods. Although various linguistic additive consistency measurements have been proposed in the literature, the existing additive consistency measurements are usually directly proposed without a general definition with axi...

When data privacy is imposed as a necessity, Federated learning (FL) emerges as a relevant artificial intelligence field for developing machine learning (ML) models in a distributed and decentralized environment. FL allows ML models to be trained on local devices without any need for centralized data transfer, thereby reducing both the exposure of...

There exist a high demand to provide explainability to artificial intelligence systems, where decision making models are included. This paper focuses on crowd decision making using natural language evaluations from social media with the aim to provide explainability. We present the Explainable Crowd Decision Making based on Subgroup Discovery and A...

Federated learning is a machine learning paradigm that emerges as a solution to the privacy-preservation demands in artificial intelligence. As machine learning, federated learning is threatened by adversarial attacks against the integrity of the learning model and the privacy of data via a distributed approach to tackle local and global learning....

Land-Use and Land-Cover (LULC) mapping is relevant for many applications, from Earth system and climate modelling to territorial and urban planning. Global LULC products are continuously developing as remote sensing data and methods grow. However, there still exists low consistency among LULC products due to low accuracy in some regions and LULC ty...

Las redes sociales son una gran fuente de información que las personas tienden a usar para tomar decisiones aprovechando la sabiduría de la multitud. Afirmamos que la sabiduría de la multitud mejora la calidad de los modelos de toma de decisiones e introducimos el concepto de toma de decisiones de multitud (CDM). Presentamos un resumen del trabajo...

Applying CNN-based object detection models to the task of weapon detection in video-surveillance is still producing a high number of false negatives. In this context, most existing works focus on one type of weapons, mainly firearms, and improve the detection using different pre- and post-processing strategies. One interesting approach that has not...

Land use and land cover (LULC) mapping are of paramount importance to monitor and understand the structure and dynamics of the Earth system. One of the most promising ways to create accurate global LULC maps is by building good quality state-of-the-art machine learning models. Building such models requires large and global datasets of annotated tim...

Federated learning, as a distributed learning that conducts the training on the local devices without accessing to the training data, is vulnerable to Byzatine poisoning adversarial attacks. We argue that the federated learning model has to avoid those kind of adversarial attacks through filtering out the adversarial clients by means of the federat...

Federated Learning is a distributed machine learning paradigm vulnerable to different kind of adversarial attacks, since its distributed nature and the inaccessibility of the data by the central server. In this work, we focus on model-poisoning backdoor attacks, because they are characterized by their stealth and effectiveness. We claim that the mo...

In parallel with the development of information and network technology, large amounts of data are being generated by the Internet, and data-driven methodologies are now often being used in decision-making. Recent studies have investigated personalized individual semantics (PIS) in various decision-making contexts to model a fact that words mean dif...

In group decision making (GDM), opinion dynamics is a useful tool to investigate consensus formation. Notably, consensus convergence speed is of key importance to manage the consensus formation in GDM with opinion dynamics. Recently, social network DeGroot (SNDG) model has been widely used in opinion dynamics. Based on this, this article dedicates...

Land-Use and Land-Cover (LULC) mapping is relevant for many applications, from Earth system and climate modelling to territorial and urban planning. Global LULC products are continuously developing as remote sensing data and methods grow. However, there is still low consistency among LULC products due to low accuracy for some regions and LULC types...

The detection of critical infrastructures in large territories represented by aerial and satellite images is of high importance in several fields such as in security, anomaly detection, land use planning and land use change detection. However, the detection of such infrastructures is complex as they have highly variable shapes and sizes, i.e., some...

Land Use and Land Cover (LULCs) mapping and change detection are of paramount importance to understand the distribution and effectively monitor the dynamics of the Earth’s system. An unexplored way to create global LULC maps is by building good quality LULC-models based on state-of-the-art deep learning networks. Building such models requires large...

The latest Deep Learning (DL) models for detection and classification have achieved an unprecedented performance over classical machine learning algorithms. However, DL models are black-box methods hard to debug, interpret, and certify. DL alone cannot provide explanations that can be validated by a non technical audience such as end-users or domai...

The17 Sustainable Development Goals (SDGs) established by the United Nations Agenda 2030 constitute a global blueprint agenda and instrument for peace and prosperity worldwide. Artificial intelligence and other digital technologies that have emerged in the last years, are being currently applied in virtually every area of society, economy and the e...

Urban resettlement projects involve a large number of stakeholders and impose tremendous cost. Developing resettlement plans and reaching an agreement amongst stakeholders about resettlement plans at a reasonable cost are some of the key issues in urban resettlement. From this perspective, urban resettlement is a typical large-scale group decision-...

The latest Deep Learning (DL) models for detection and classification have achieved an unprecedented performance over classical machine learning algorithms. However, DL models are black-box methods hard to debug, interpret, and certify. DL alone cannot provide explanations that can be validated by a non technical audience. In contrast, symbolic AI...

Despite the constant advances in computer vision, integrating modern single-image detectors in real-time handgun alarm systems in video-surveillance is still debatable. Using such detectors still implies a high number of false alarms and false negatives. In this context, most existent studies select one of the latest single-image detectors and trai...

An important part of art history can be discovered through the visual information in monument facades. However, the analysis of this visual information, i.e, morphology and architectural elements, requires high expert knowledge. An automatic system for identifying the architectural style or detecting the architectural elements of a monument based o...

This article provides a brief tour through the main fuzzy and linguistic decision-making trends, studies, methodologies, and models developed in the last 50 years. Fuzzy and linguistic decision-making approaches allow to address complex real-world decision problems where humans exhibit vagueness, imprecision, and/or use natural language to assess d...

In computing with words, it has been stressed that words mean different things for different people, which entails that decision makers (DMs) have personalized individual semantics (PISs) attached to linguistic expressions in linguistic group decision making (GDM). In particular, the PISs of DMs are not fixed, and they will be changing during the c...

Distributed linguistic representations are powerful tools for modelling the uncertainty and complexity of preference information in linguistic decision making. To provide a comprehensive perspective on the development of distributed linguistic representations in decision making, we present the taxonomy of existing distributed linguistic representat...

Distributed linguistic representations are powerful tools for modelling the uncertainty and complexity of preference information in linguistic decision making. To provide a comprehensive perspective on the development of distributed linguistic representations in decision making, we present the taxonomy of existing distributed linguistic representat...

Crowd behaviour analysis is an emerging research area. Due to its novelty, a proper taxonomy to organise its different sub-tasks is still missing. This paper proposes a taxonomic organisation of existing works following a pipeline, where sub-problems in last stages benefit from the results in previous ones. Models that employ Deep Learning to solve...

Opinion dynamics are investigated extensively to describe the process of opinion formation in groups of individuals. Most of the existing opinion dynamics models assume that the individuals express the numerical opinions. However, this assumption does not consider the fact that people often express their opinions in a linguistic way. Particularly,...

The axiomatic distance-based method is a powerful tool to aggregate individual preferences, and the extant axiomatic distance-based aggregation methods are with regard to individual numerical preferences. However, in some real-world decision problems with qualitative aspects, it is more convenient and natural for individuals to express their prefer...

Ensemble methods have been widely used for improving the results of the best single classification model. A large body of works have achieved better performance mainly by applying one specific ensemble method. However, very few works have explored complex fusion schemes using heterogeneous ensembles with new aggregation strategies. This paper is th...

Consensus reaching process is a very powerful decision tool to eliminate the preference conflict in group decision making. In general, the consensus is achieved by the decision makers modifying their preferences (or opinions) towards a point of mutual consent, and the feedback mechanism aims to provide preference-modifications suggestions. In many...

A high-quality credit index system is essential for technological small and medium-sized enterprises (TSMEs) to obtain financing from various institutions, such as banks, venture capital. Some attempts have made to construct the credit index system for TSMEs. However, the current credit index systems for TSMEs have placed too much emphasis on their...

The capability of distinguishing between small objects when manipulated with hand is essential in many fields, especially in video surveillance. To date, the recognition of such objects in images using Convolutional Neural Networks (CNNs) remains a challenge. In this paper, we propose improving robustness, accuracy and reliability of the detection...

To date, a large number of consensus reaching processes (CRPs) have been reported in group decision making (GDM). Trust relationships should be an essential element in interactions among a group of individuals, leading to the evolution of individuals' preferences. Therefore, in this article, we present a trust relationships CRP with a feedback mech...

When people express their opinions, they often cannot provide the exact opinions but express uncertain opinions. Moreover, due to the differences in culture backgrounds and characters of agents, people who encounter uncertain opinions often show different uncertainty tolerances. By taking different uncertain opinions and different uncertainty toler...

Understanding consumer behaviors and how consumers react to marketing campaigns and viral word‐of‐mouth processes is crucial for marketers. Classical approaches try to infer this information from a global top‐down perspective. However, a more suitable and natural approach is to model consumer behaviors in a heterogeneous and decentralized bottom‐up...

The problem of Multiple Object Tracking (MOT) consists in following the trajectory of different objects in a sequence, usually a video. In recent years, with the rise of Deep Learning, the algorithms that provide a solution to this problem have benefited from the representational power of deep models. This paper provides a comprehensive survey on w...

Due to the development of intelligent decision-making, social network group decision-making (SNGDM) has become increasingly valued. Generally, real SNGDM cases involve not only the mathematical formulation of the social network analysis but also the experts’ psychological behaviors. Self-confidence, an expert's psychological implication of self-sta...

Evolutionary fuzzy systems are one of the greatest advances within the area of computational intelligence. They consist of evolutionary algorithms applied to the design of fuzzy systems. Thanks to this hybridization, superb abilities are provided to fuzzy modeling in many different data science scenarios. This contribution is intended to comprise a...

In this paper, we investigate how the agent's self-confidence level and the node degree influence the consensus opinion formation and the consensus convergence speed in the social network DeGroot model. We find that (1) the higher self-confidence will increase the agent's importance degree to determine the consensus opinion, but will also slow down...

Self-confidence as one of the human psychological behaviors has important influence on emergency management decision making, which has been ignored in existing methods. To fill this gap, we dedicate to design a group decision making approach considering self-confidence behaviors and apply it to the environmental pollution emergency management. In t...

Este estudio contempla el uso de un modelo sim- ple de comunicacion automatizada a trav ´ es de un chatbot de ´ Telegram, denominado EDUtrack, que se conecta a Moodle, un Sistema de Gestion del Aprendizaje. Est ´ a pensado para docentes ´ interesados en evaluar sus clases de alguna manera, as´ı como mantener informados a sus estudiantes sobre su re...

Preference relations have been widely used in group decision‐making (GDM) problems. Recently, a new kind of preference relations called fuzzy preference relations with self‐confidence (FPRs‐SC) has been introduced, which allow experts to express multiple self‐confidence levels when providing their preferences. This paper focuses on the analysis of...

In this paper we deal with the problem of addressing multi-class problems with decomposition strategies. Based on the divide-and-conquer principle, a multi-class problem is divided into a number of easier to solve sub-problems. In order to do so, binary decomposition is considered to be the most popular approach. However, when using this strategy w...

The automatic detection of cold steel weapons handled by one or multiple persons in surveillance videos can help reducing crimes. However, the detection of these metallic objects in videos faces an important problem: their surface reflectance under medium to high illumination conditions blurs their shapes in the image and hence makes their detectio...

Object detection models have known important improvements in the recent years. The state-of-the art detectors are end-to-end Convolutional Neural Network based models that reach good mean average precisions, around 73%, on benchmarks of high quality images. However, these models still produce a large number of false positives in low quality videos...

Este estudio contempla el uso de un modelo simple de comunicación automatizada a través de un chatbot de Telegram, denominado EDUtrack, que se conecta a Moodle, un Sistema de Gestión del Aprendizaje. Está pensado para docentes interesados en evaluar sus clases de alguna manera, así como mantener informados a sus estudiantes sobre su rendimiento aca...

En la educación actual la colaboración e interacción para el desarrollo de actividades mediante el uso de la tecnología y dispositivos móviles, así como la satisfacción del estudiante y la comunicación virtual estudiante-estudiante y estudiante-profesor que se genera al utilizar los dispositivos móviles como herramientas para la educación, son crit...

Este estudio contempla el uso de un modelo simple de comunicación automatizada a través de un chatbot de Telegram, denominado EDUtrack, que se conecta a Moodle, un Sistema de Gestión del Aprendizaje. Está pensado para docentes interesados en evaluar sus clases de alguna manera, así como mantener informados a sus estudiantes sobre su rendimiento aca...

Algorithm-level solutions can be seen as an alternative approach to data pre-processing methods for handling imbalanced datasets. Instead of focusing on modifying the training set in order to combat class skew, this approach aims at modifying the classifier learning procedure itself. This requires an in-depth understanding of the selected earning a...

Nowadays, the availability of large volumes of data and the widespread use of tools for the proper extraction of knowledge information has become very frequent, especially in large corporations. This fact has transformed the data analysis by orienting it towards certain specialized techniques included under the umbrella of Data Science. In summary,...

Most of the research in class imbalance are carried out in standard (binary or multi-class) classification problems. However, in recent years, researchers have addressed new classification frameworks beyond standard classification in different aspects. Several variations of class imbalance problem appear within these frameworks. This chapter review...

There are dozens of tools to automatically evaluate web accessibility. Some are online, and some are toolbars to complement web browsers. In order to select the best Web Accessibility Test Tool, various aspects should be considered. Among the various aspects, the evaluation environment has an important role to assume in the evaluation criteria of t...

Recently, large scale group decision making (LSGDM) problems are becoming a hotspot. This paper focuses on the hesitant fuzzy LSGDM problems, where decision makers (DMs) use hesitant fuzzy reciprocal preference relations (HFPRs) to express their assessment information. HFPRs can represent the fuzziness and hesitancy of DM assessment information wel...

In linguistic large-scale group decision making (LSGDM), it is often necessary to achieve a consensus. Particularly, when computing with words and linguistic decision we must keep in mind that words mean different things to different people. Therefore, to represent the specific semantics of each individual, we need to consider the personalized indi...

The individual consistency and the consensus degree are two basic measures to conduct group decision making with reciprocal preference relations. The existing frameworks to manage individual consistency and consensus degree have been investigated intensively and follow a common resolution scheme composed by the two phases: the consistency improving...

In decision making problems, decision makers may prefer to use more flexible linguistic expressions instead of using only one linguistic term to express their preferences. The recent proposals of hesitant fuzzy linguistic terms sets (HFLTSs) are developed to support the elicitation of comparative linguistic expressions in hesitant decision situatio...

Researchers in the topic of imbalanced classification have proposed throughout the years a large amount of different approaches to address this issue. To keep on developing this area of study, it is of extreme importance to make these methods available for the research community. This allows for a double advantage: (1) to analyze in depth the featu...

Class imbalance is present in many real-world classification datasets and consists in a disproportion of the number of examples of the different classes in the problem. This issue is known to hinder the performance of classifiers due to their accuracy oriented design, which usually makes the minority class to be overlooked. In this chapter the foun...

New developments in computation have allowed an explosion for both data generation and storage. The high value that is hidden within this large volume of data has attracted more and more researchers to address the topic of Big Data analytics. The main difference between addressing Big Data applications and carrying out traditional DM tasks is scala...

Dealing with multi-class problems is a hard issue, which becomes more severe in the presence of imbalance. When facing multi-majority and multi-minority classes, it is not straightforward to acknowledge a priori which ones should be stressed during the learning stage, as it was done in the binary case study. Additionally, most of the techniques pro...

The first mechanism to address the problem of imbalanced learning was the use of sampling methods. They consists of modifying a set of imbalanced data using different procedures to provide a balanced or more adequate data distribution to the subsequent learning tasks. In the specialized literature, many studies have shown that, for several types of...

Cost-sensitive learning is an aspect of algorithm-level modifications for class imbalance. Here, instead of using a standard error-driven evaluation (or 0–1 loss function), a misclassification cost is being introduced in order to minimize the conditional risk. By strongly penalizing mistakes on some classes, we improve their importance during class...

In this chapter existing ensemble solutions for the class imbalance problems are reviewed. In Data Science, classifier ensembles, that is, the combination of several classifiers into a single one, are known to improve the accuracy in comparison with the usage of a single classifier. However, ensemble learning techniques by themselves are neither ab...

One of the most successful data preprocessing techniques used is the reduction of the data dimensionality by means of feature selection and/or feature extraction. The key idea is to simplify the data by replacing the original features with new created that extract the main information or simply select a subset of original set. Although this topic h...

Although class imbalance is often pointed out as a determinant factor for degradation in classification performance, there are situations in which good performance can be achieve even in the presence of severe class imbalance. The identification of situation where the class imbalance is a complicating factor is an important research question. These...

Mining data streams is one of the most vital fields in the contemporary ML. Increasing number of real-world problems are characterized by both volume and velocity of data, as well as by evolving characteristics. Learning from data stream assumes that new instances arrive continuously and that their properties may change over time due to a phenomeno...

Analyzing the performance of learning algorithms under presence of class imbalance is a difficult task. For some widely-used measures, such as accuracy, the prevalence of more frequent classes may mask a poor classification performance in infrequent classes. To alleviate this problem, the choice of suitable measures is of fundamental importance. Th...

This book provides a general and comprehensible overview of imbalanced learning. It contains a formal description of a problem, and focuses on its main features, and the most relevant proposed solutions. Additionally, it considers the different scenarios in Data Science for which the imbalanced classification can create a real challenge. This book...

Boosting collaborative or participatory consumption is a priority for the European Commission. It is in line with the provisions of the Europe 2020 Strategy, which proposes that consumption of goods and services should take place in accordance with smart, sustainable and inclusive growth. These have motivated us to develop an online community for c...

In group decision making (GDM) dealing with Computing with Words (CW) has been highlighted the importance of the statement, words mean different things for different people, because of its influence in the final decision. Different proposals that either grouping such different meanings (uncertainty) to provide one representation for all people or u...

The One-vs-One strategy is among the most used techniques to deal with multi-class problems in Machine Learning. This way, any binary classifier can be used to address the original problem, since one classifier is learned for each possible pair of classes. As in every ensemble method, classifier combination becomes a vital step in the classificatio...

The use of evolutionary algorithms for designing fuzzy systems provides them with learning and adaptation capabilities, resulting on what is known as Evolutionary Fuzzy Systems. These types of systems have been successfully applied in several areas of Data Mining, including standard classification, regression problems and frequent pattern mining. T...

En clasificación multi-instancia (MIC en sus siglas en inglés) [1], los datos son colec-ciones de instancias (llamadas bolsas). Las instancias son similares a los ejemplos que se utilizan en problemas de clasificación tradicionales (mono-instancia) y cada bolsa puede tener un número distinto de instancias. La principal característica de la MIC es q...

En el ámbito de la toma de decisiones (TD) un problema tipo se caracteriza por una serie de alternativas sobre las que elegir, que son valoradas por expertos en el área. Los expertos son personas capaces de proporcionar valoraciones específicas sobre determinadas propieda-des de cada alternativa, de cara a que un proceso de computación determine cu...