Cervical cancer screening remains highly unequal across regions, with low and middle income countries facing limited access to expert cytology and laboratory infrastructure. This work frames low-cost cervical cytology screening as an intelligent healthcare environment in which image acquisition, quality enhancement, embedded AI inference, and clinician-oriented decision support are combined at the point of care. We present the AI core of such an environment, designed for integration into a low-cost digital cytology acquisition station operating under heterogeneous imaging conditions and limited connectivity. First, we model realistic quality variability by generating datasets with multiple degradation profiles and apply a restoration stage based on Real-ESRGAN to enhance low-quality inputs. Second, we train a compact convolutional neural network whose hyperparameters are selected via Bayesian optimization, aiming at an accuracy-efficiency trade-off suitable for embedded edge inference. Finally, we apply TinyML-oriented compression, combining pruning and INT8 quantization with export to Tensor-Flow Lite. On an internal held-out test split, the baseline model achieved 0.888 accuracy, while the mixed-quality enhanced configuration reached 0.922, indicating improved robustness under more realistic acquisition conditions. Model compression reduced the footprint from 21.18 MB to 2.74 MB, supporting feasibility for deployment on constrained hardware. Overall, the results suggest that quality-aware training, image enhancement, and TinyML compression can enable privacy-preserving, offline, and scalable intelligent point-of-care environments for cervical cytology triage in resource-constrained clinical settings.

This paper presents a novel Multi-DL Fuzzy Approach aimed at performing image recognition in the development of a real-time traffic alert system, addressing the problem of traffic congestion and related incidents. Traditional monitoring by road operators predominantly relies on fixed location cameras, yielding limited and sometimes ambiguous information. This study proposes leveraging Twitter (now known as ‘X’) as a more comprehensive data source alongside employing fuzzy techniques with Deep Learning (DL) neural networks such as CNN, VGG16, and Xception to analyze and classify traffic images. The innovative integration of these technologies augments the precision in categorizing varying traffic conditions, namely fluid and dense traffic, accidents and fires. Thus, this proposal mitigates the ambiguities prevalent in traffic image interpretation, and reduces the dependency on static data sources. The proposed models showed improved results by combining information from the DL models, elevating accuracy from 84% in crisp classification to 90% utilizing fuzzy information.

Nowadays, Generative Large Language Models (GLLMs) have made a significant impact in the field of Artificial Intelligence (AI). One of the domains extensively explored for these models is their ability as generators of functional source code for software projects. Nevertheless, their potential as assistants to write the code needed to generate and model Machine Learning (ML) or Deep Learning (DL) architectures has not been fully explored to date. For this reason, this work focuses on evaluating the extent to which different tools based on GLLMs, such as ChatGPT or Copilot, are able to correctly define the source code necessary to generate viable predictive models. The use case defined is the forecasting of a time series that reports the indoor temperature of a greenhouse. The results indicate that, while it is possible to achieve good accuracy metrics with simple predictive models generated by GLLMs, the composition of predictive models with complex architectures using GLLMs is still far from improving the accuracy of predictive models generated by human data scientists.

When analyzing the energy consumption of a car, several studies estimate that the air-conditioning system can account for up to 10% of such consumption. Other studies have found that the cabin temperature may exceed 60°C when it is exposed to direct sunlight, but it can be reduced by more than 15°C if the vehicle is covered. Hence, this chapter introduces TICKET, an intelligent parking space allocation system for greater energy efficiency. TICKET informs drivers of which parking space they should occupy within the parking lot so that when the driver returns to collect the vehicle, the cabin temperature is as low as possible. To do so, the system considers multiple environmental factors such as the sunlight movement or the weather conditions in the target parking lot and also combines predictive algorithms like hidden Markov models for demand estimation. Finally, TICKET has been tested in a real parking-lot premises with promising results.

We are witnessing the digitalization era, where artificial intelligence (AI)/machine learning (ML) models are mandatory to transform this data deluge into actionable information. However, these models require large, high-quality datasets to predict high reliability/accuracy. Even with the maturity of Internet of Things (IoT) systems, there are still numerous scenarios where there is not enough quantity and quality of data to successfully develop AI/ML-based applications that can meet market expectations. One such scenario is precision agriculture, where operational data generation is costly and unreliable due to the extreme and remote conditions of numerous crops. In this paper, we investigated the generation of synthetic data as a method to improve predictions of AI/ML models in precision agriculture. We used generative adversarial networks (GANs) to generate synthetic temperature data for a greenhouse located in Murcia (Spain). The results reveal that the use of synthetic data significantly improves the accuracy of the AI/ML models targeted compared to using only ground truth data.

In recent years, there has been an increasing interest in the exploitation of geo-tagged documents posted on Online Social Networks (OSN) for human-mobility pattern mining. These patterns can ease the development of effective and intelligent location-based systems of different scenarios. However, the validation of OSN geo-data as a reliable source for human mobility has not been fully studied in literature. Therefore, this study proposes a comprehensive comparison of a nation-scale Twitter (TWT) dataset with an official mobility study published by the Spanish Ministry of Development. Both feeds have been compared considering different variables, such as population density and spatial granularity, among others. Results show that TWT can be a reliable source for human-mobility mining but only when certain socioeconomic, temporal, and spatial factors co-occur.

Abstract Nowadays, Generative Large Language Models (GLLMs) have taken the Artificial Intelligent field by storm. One of the fields where these models have been extensively evaluated is in their role as generators of functional source code for software projects. However, their potential as assistants for writing the code necessary to generate and model machine learning or deep learning architectures has not been fully explored to date. For this reason, this work focuses on evaluating the extent to which different tools based on GLLMs, such as ChatGPT or Copilot, are capable of correctly defining the source code necessary to generate viable predictive models. The use case defined is the forecasting of a time series of atmospheric temperatures. The results show that, while it is true that the models obtained can obtain good accuracy metrics with simple predictive models, the composition of models with complex architectures is still far from the alternative of generating them by human data scientists.

Tourism has become a very active ecosystem to deploy solutions based on Information and Communication Technologies. Indeed, it is now possible to analyse the mobility behaviour of tourists in great detail. However, current solutions aimed at anticipating tourist flows usually follow a limited approach based on the local (e.g., to predict the next landmark to visit) or regional (e.g., to predict the incoming number of tourists in a city) level. This paper states a novel approach to solve the problem of tourist inflow forecasting on a broader nationwide scale by defining it as an edge prediction task. To do so, we model the tourist mobility of a country as a graph which fuses heterogeneous tourism data obtained from multiple sources related to the country's mobility and infrastructure features. Then, as a major contribution, an ensemble of Graph Neural Networks are fed with the graph models to provide the final prediction. The proposed solution has been tested in Spain showing a F1 score higher than 0.7.

League of Legends (LoL) is a multiplayer online battle arena video game developed and published by Riot Games. It is a team-based game with over 140 characters to make epic plays with. The game blends the speed and intensity of an real-time strategy game (RTS) with role-playing game (RPG) elements. Two teams of powerful champions, each with unique designs and play styles, battle head-to-head across multiple maps and game modes. Exploratory data analysis (EDA) is a statistical technique that can be used to analyze this data to extract valuable information for both researchers and players. By using EDA techniques on LoL match data, players can identify patterns, trends, and relationships that can help optimize their gameplay strategy. EDA can also help players identify their strengths and weaknesses and important statistics for their gameplay. The paper provides an introduction to the treatment of LoL match data using EDA techniques. It presents the most common data analysis techniques and explores some examples of how to apply these techniques to LoL match data. Furthermore, the paper discusses some ways in which data analysis can help LoL players improve their game, such as identifying their strengths and weaknesses, patterns and trends, important statistics, and meta changes.

During the last years, the analysis of spatio-temporal data extracted from Online Social Networks (OSNs) has become a prominent course of action within the human-mobility mining discipline. Due to the noisy and sparse nature of these data, an important effort has been done on validating these platforms as suitable mobility proxies. However, such a validation has been usually based on the computation of certain features from the raw spatio-temporal trajectories extracted from OSN documents. Hence, there is a scarcity of validation studies that evaluate whether geo-tagged OSN data are able to measure the evolution of the mobility in a region at multiple spatial scales. For that reason, this work proposes a comprehensive comparison of a nation-scale Twitter (TWT) dataset and an official mobility survey from the Spanish National Institute of Statistics. The target time period covers a three-month interval during which Spain was heavily affected by the COVID-19 pandemic. Both feeds have been compared in this context by considering different mobility-related features and spatial scales. The results show that TWT could capture only a limited number features of the latent mobility behaviour of Spain during the study period.

Due to the COVID-19 pandemic, most universities have adapted their learning infrastructure to an increasing demand for online training modalities. However, this type of learning, usually through Learning Management Systems (LMSs), suffer from a lack of direct feedback between students and the educational staff. For that reason, the present work introduces the EMO-learning project, whose key goal is to capture the emotions of students. This is done by means of a deep learning approach, able to timely analyse the face expressions of the students during online lectures. The module has been tested with different students during the academic year 2020-21, showing quite promising results.

Nowadays, cities are the most relevant type of human settlement and their population has been endlessly growing for decades. At the same time, we are witnessing an explosion of digital data that capture many different aspects and details of city life. This allows detecting human mobility patterns in urban areas with more detail than ever before. In this context, based on the fusion of mobility data from different and heterogeneous sources, such as public transport, transport-network connectivity and Online Social Networks, this study puts forward a novel approach to uncover the actual land use of a city. Unlike previous solutions, our work avoids atime-invariantapproach and it considers the temporal factor based on the assumption that urban areas are not used by citizens all the time in the same manner. We have tested our solution in two different cities showing high accuracy rates.

Artificial intelligence (AI) has emerged in dermatology with some studies focusing on skin disorders such as skin cancer, atopic dermatitis, psoriasis, and onychomycosis. Alopecia areata (AA) is a dermatological disease whose prevalence is 0.7%-3% in the United States, and is characterized by oval areas of nonscarring hair loss of the scalp or body without evident clinical variables to predict its response to the treatment. Nonetheless, some studies suggest a predictive value of trichoscopic features in the evaluation of treatment responses. Assuming that black dots, broken hairs, exclamation marks, and tapered hairs are markers of negative predictive value of the treatment response, while yellow dots are markers of no response to treatment according to recent studies, the absence of these trichoscopic features could indicate favorable disease evolution without treatment or even predict its response. Nonetheless, no studies have reportedly evaluated the role of AI in AA on the basis of trichoscopic features. This study aimed to develop an AI algorithm to predict, using trichoscopic images, those patients diagnosed with AA with a better disease evolution. In total, 80 trichoscopic images were included and classified in those with or without features of negative prognosis. Using a data augmentation technique, they were multiplied to 179 images to train an AI algorithm, as previously carried out with dermoscopic images of skin tumors with a favorable response. Subsequently, 82 new images of AA were presented to the algorithm, and the algorithm classified these patients as responders and non-responders; this process was reviewed by an expert trichologist observer and presented a concordance higher than 90% with the algorithm identifying structures described previously. Evolution of the cases was followed up to truly determine their response to treatment and, therefore, to assess the predictive value of the algorithm. In total, 32 of 40 (80%) images of patients predicted as nonresponders scarcely showed response to the treatment, while 34 of 42 (81%) images of those predicted as responders showed a favorable response to the treatment. The development of an AI algorithm or tool could be useful to predict AA evolution and its response to treatment. However, further research is needed, including larger sample images or trained algorithms, by using images previously classified in accordance with the disease evolution and not with trichoscopic features.

Floods are expected to increase in the coming years due to global warming. The early identification of water-based disasters can be lifesaving, and the challenge is to identify appropriate and timely warning measures. Social-media tools such as Twitter provide citizens with a real-time communication channel for reporting problems related to our environment, which allows humans to act as social sensors. In this article, we show the main results and lessons learned from the research project WATERoT, funded by the Spanish government. In this project, we designed a social sensing application (called WATERSensing) for the prevention and evaluation of water-related disasters with the participation of individuals through social networks. This tool crawls microtexts from different social networks such as Twitter, RSS feeds, or Telegram, which are analyzed with natural language processing techniques. A case study of Storm Gloria, a Mediterranean storm that heavily affected eastern Spain in January 2020, is presented to evidence that the system can correlate data from social media with actual events. We demonstrate that the analysis of different sources of information opens up new opportunities in the development of warning systems for the prevention, early identification, and management of natural disasters.

The development of Road Information Acquisition Systems (RIASs) based on the Mobile Crowdsensing (MCS) paradigm has been widely studied for the last years. In that sense, most of the existing MCS-based RIASs focus on urban road networks and assume a car-based scenario. However, there exist a scarcity of approaches that pay attention to rural and country road networks. In that sense, forest paths are used for a wide range of recreational and sport activities by many different people and they can be also affected by different problems or obstacles blocking them. As a result, this work introduces SAMARITAN, a framework for rural-road network monitoring based on MCS. SAMARITAN analyzes the spatio-temporal trajectories from cyclists extracted from the fitness application Strava so as to uncover potential obstacles in a target road network. The framework has been evaluated in a real-world network of forest paths in the city of Cieza (Spain) showing quite promising results.

Social sensing leverages user-contributed data from social media by considering participants as "social sensors", i.e. agents that provide information about their environment through social-media services such as Twitter, Facebook or Instagram. Social sensors may serve as a complementary source to physical sensors as (1) they can explain why or how specific events occurred, and (2) they can be deemed to be an alternative source in case that physical sensors malfunction or a sensor network cannot be afforded. However, one of the main challenges for social sensors is to know where a particular event has occurred. Social-media services rely on user preferences to geolocate their opinions, which is not really a widespread practice and, therefore, it limits the success of these techniques as early warning systems. In this paper, we analyze the spaCy named entity recognizer (NER), an open-source tool widely used by the community, to identify named entities in Spanish microtexts taken from social networks. The spaCy NER is based on Artificial Neural Networks, and our preliminary results show that further training should be undertaken to increase its accuracy. Indeed, it is well known that supervised methods are domain dependent, so their performance tends to decrease when dealing with target documents that come from a domain different from that of the training dataset. For this purpose, a training tool has been designed to automatically generate datasets suitable for spaCy NER's training with Twitter-based microtexts in Spanish. Using the dataset generated by this tool, the spaCy NER tool increases its accuracy to 0.7 F-score, defeating by a wide margin the use of other classic datasets such as AnCora, WIKINER or CONLL for training.

Social sensing leverages user-contributed data from social media by considering participants as “social sensors”, i.e. agents that provide information about their environment through social-media services such as Twitter, Facebook or Instagram. Social sensors may serve as a complementary source to physical sensors as (1) they can explain why or how specific events occurred, and (2) they can be deemed to be an alternative source in case that physical sensors malfunction or a sensor network cannot be afforded. However, one of the main challenges for social sensors is to know where a particular event has occurred. Social-media services rely on user preferences to geolocate their opinions, which is not really a widespread practice and, therefore, it limits the success of these techniques as early warning systems. In this paper, we analyze the spaCy named entity recognizer (NER), an open-source tool widely used by the community, to identify named entities in Spanish microtexts taken from social networks. The spaCy NER is based on Artificial Neural Networks, and our preliminary results show that further training should be undertaken to increase its accuracy. Indeed, it is well known that supervised methods are domain dependent, so their performance tends to decrease when dealing with target documents that come from a domain different from that of the training dataset. For this purpose, a training tool has been designed to automatically generate datasets suitable for spaCy NER’s training with Twitter-based microtexts in Spanish. Using the dataset generated by this tool, the spaCy NER tool increases its accuracy to 0.7 F-score, defeating by a wide margin the use of other classic datasets such as AnCora, WIKINER or CONLL for training.

Social sensing can provide useful information to help detect, manage and solve problems related to people’s lifes and physical surroundings. Because of the huge amount of content generated on social media, the problem of social sensing is the varying quality of data, so it is necessary to filter out the irrelevant content returned by search requests. The goal of our research is to develop a knowledge-based system that is able to analyse tweets in Spanish to select the most salient posts with respect to a given problem (e.g. flood events). The main contribution of this article is to describe a measure that computes the salience of tweets by integrating the text-oriented perception of the problem with the networkoriented impact of the message. The system was tested with the natural disaster of a DANA that struck Spain in September 2019.

During times of disasters, users can act as powerful social sensors, because of the significant amount of data they generate on social media. Indeed, they contribute to creating situational awareness by informing what is happening in the affected community during the incident. In this context, this article focuses on the text-processing module in CASPER, a knowledge-based system that integrates event detection and sentiment tracking. The performance of the system was tested with the natural disaster of wildfires.

Social media networks such as Facebook and Twitter can be used as a valuable tool to report on environmentally-related problems, e.g. landslides or wildfires, that are about to occur or have just occurred, so that response actions can be promptly executed. The goal of this article is to describe a knowledge-based system that is able to analyse tweets in Spanish to detect a variety of such problems. This research resulted in the implementation of CASPER, a proof-of-concept workbench where multi-domain problem detection has been devised as a two-fold task: topic categorisation and sentiment analysis. (C) 2018 IAgrE. Published by Elsevier Ltd. All rights reserved.