Abstract Computational intelligence focuses on intelligent computer systems that mimic human nature and linguistic reasoning. Sentiment analysis is an area of considerable relevance within computational intelligence. Multimodal sentiment analysis is an extension of textual sentiment analysis, where the sentiments of people’s opinions are analysed by including multimedia content in addition to textual content. This mode of sentiment analysis faces multiple problems, as the sentiments of text and multimedia content may be contradictory. In addition, another added factor is the imbalance of the data that these problems suffer from in certain topics, which causes a problem when generating intelligent models. In this paper, we design a novel approach for multimodal sentiment analysis, proposing a new way of labelling tweets, not always prioritising polarized classes but using annotator confidence. Moreover, during this design, an information integration and fusion methodology is proposed for the construction of a metamodel that includes fuzzy logic to perform information weighting according to the confidence of the annotator. This proposal has been applied a public unbalanced dataset of tweets with text and images, with a large unbalance towards the negative class label. Applying the proposed fuzzy methodology, we reached a macro-F1 score of 0.493 for the negative class, 0.681 for the neutral class, and 0.832 for the positive class. The model obtains satisfactory performance since the individual image and text sentiment analysis results are worse, especially the negative class, which in initial image classification achieves an F1 score of 0.08.

The management of road traffic incidents is a problem faced by governments in many countries. Normally, road operators have the infrastructure in place to monitor such incidents, albeit in a reactive manner. In Spain, there are traffic cameras on major roads to check for possible incidents, however, incident notification is slow and not automated. As an alternative, this paper proposes a system for automatic real-time traffic alerts. Thus, 1,500 camera images from the Dirección General de Tráfico (DGT) deployed on the main Spanish roads are analyzed in real time every 4 minutes. These images are not preprocessed, they have different qualities and are also affected by weather conditions such as fog, rain, sun reflections, etc. The system uses several Deep Learning classification models trained on a well-known dataset of traffic images including flowing traffic, dense traffic, accidents and fires. These models are used to classify the DGT images in real time, with satisfactory initial results, detecting both flowing traffic and dense traffic.

Abstract 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.

Summary Agriculture is one of the key sectors where technology is opening new opportunities to break up the market. The Internet of Things (IoT) could reduce the production costs and increase the product quality by providing intelligence services via IoT analytics. However, the hard weather conditions and the lack of connectivity in this field limit the successful deployment of such services as they require both, ie, fully connected infrastructures and highly computational resources. Edge computing has emerged as a solution to bring computing power in close proximity to the sensors, providing energy savings, highly responsive web services, and the ability to mask transient cloud outages. In this paper, we propose an IoT monitoring system to activate anti‐frost techniques to avoid crop loss, by defining two intelligent services to detect outliers caused by the sensor errors. The former is a nearest neighbor technique and the latter is the k‐means algorithm, which provides better quality results but it increases the computational cost. Cloud versus edge computing approaches are analyzed by targeting two different low‐power GPUs. Our experimental results show that cloud‐based approaches provides highest performance in general but edge computing is a compelling alternative to mask transient cloud outages and provide highly responsive data analytic services in technologically hostile environments.

The numerical value discretization is an important task of the data preprocessing phase within the intelligent data analysis. This process allows us to reduce the number of values (among other advantages) with which techniques work, reducing the computational cost when it comes to working with large amounts of data. In this paper a numerical value discretization technique is proposed. Specifically, we discretize numerical values using a type of Cauchy distribution obtained from fuzzy clustering technique, being this technique a modification of the well-known Fuzzy C-Means clustering technique. Finally, to test the quality of the membership function we use a neural network technique over several datasets. The results obtained are compared and validated by means of statistical tests, obtaining satisfactory results.

Currently, many of the elements that surround us in daily life need software systems that work from the information available in the domain (data-driven application domains) by performing a process of data mining from it. Between the data mining techniques used in everyday problems we find the k-Nearest Neighbors technique. However, in domains and real situations it is very common to find vague, ambiguous and noisy data, that is, imperfect information.Although this imperfect information is inevitable, most applications have traditionally ignored the need for developing appropriate approaches for representing and reasoning with such data imperfections. The soft computing field has dealt with the development of techniques that can work with this kind of information as discipline whose main characteristic is tolerance to inaccuracy and uncertainty.In this work, we extend the k-Nearest Neighbors technique using concepts and methods provided by Soft Computing. The aim is to carry out the processes of instance selection and classification in everyday problems from imperfect information making the technique more realistic.

The behavior of university students is a field of study on the rise, whose main objective is the search for patterns that help improve their learning process. This paper analyzes the use of Learning Management Systems (LMS) in Higher Education and the interactions with their different tools from the students' viewpoint. For the analysis of the student activity statistical techniques and algorithms are extending to be used for big data platform. The information extracted from each student is based both on the events held in each session and on the number of sessions held. The analyzed data belongs to subjects of different modalities (on-campus, blended, online). The results of the methods are compared and discussed regarding the learning modalities. The results are interpreted in a discussion focus obtaining satisfactory knowledge for the identification of patterns of behavior.

Internet of Things (IoT) is considered a disruptive technology that is expected to change our everyday-life and contribute to the economic development. In particular, agriculture is a domain that can greatly benefit from the application of emerging technologies in the IoT field in order to reduce production costs and increase product quality. This work proposes a system based on Internet of Things (IoT) technology intended to fight against a critical weather inclemency: the crop frost. The proposed system consists of an IoT-based network architecture in charge of the acquisition of weather attributes directly taken from the crop field. Additionally, our solution integrates a data processing system that forecasts crop frost considering not only the real weather attributes recovered from the network but also weather forecasts obtained from specialized services. The implemented prototype has been evaluated in a real farmland located in Murcia (Spain). The results demonstrate the viability of our system to accurately forecast the occurrence of frosts in a certain area and opens new research challenges that need to be addressed before obtaining a fully operational forecasting system.

Currently, most datasets from real-world problems contain low-quality data. In particular, within soft computing and data mining areas, the research and development of techniques that can deal with this type of data has been increased recently. In order to facilitate the design of experiments in this field and with these data, an experimenter environment in NIP imperfection processor software tool has been developed. This environment allows the generation of datasets with low-quality data, allowing the researcher to design experiments that analyze the robustness of different techniques which utilize this type of information in an easy and intuitive way.

An important aspect to consider in applications which work with great volumes of data is that frequently these data are of low quality and also cannot be use other types of data. The field of Soft Computing has dealt, among other things, with developing techniques that will be able to work with these types of low quality data in a suitable way, respecting the true origin of these data. In this paper we present a method to carry out the imputation of missing values from information that may be of low quality when another possibility is not available. The method is based on a predictable model. The imputation method developed is incorporated into the software tool NIP increasing its functionality of imputation/replacement of low quality values.

Nowadays in the world of Soft Computing there is a new challenge which consists of working with low quality data. To test the techniques that are designed in this area, there is the need for repositories of low quality datasets. Currently we can find various data mining techniques that are designed to handle some kind of low quality data. But, as far as we get our knowledge, it has not yet designed a software tool focused on the creation/management of low quality datasets that will help us to create repositories to facilitate the testing and comparison of the above techniques. We present in this paper a software tool which can create/manage low quality data. Even if a technique doesn't manage low quality data, the tool permits to transform the low quality data by other data that technique can manage.

Imperfect information inevitably appears in real situations for a variety of reasons. Although efforts have been made to incorporate imperfect data into classification techniques, there are still many limitations as to the type of data, uncertainty and imprecision that can be handled. In this paper, we will present a Fuzzy Random Forest ensemble for classification and show its ability to handle imperfect data into the learning and the classification phases. Then, we will describe the types of imperfect data it supports. We will devise an augmented ensemble that can operate with others type of imperfect data: crisp, missing, probabilistic uncertainty and imprecise (fuzzy and crisp) values. Additionally, we will perform experiments with datasets used in other papers to show the advantage of being able to express the true nature of imperfect information.

When individual classifiers are combined appropriately, we usually obtain a better performance in terms of classification precision. Classifier ensembles are the result of combining several individual classifiers. In this work we propose and compare various consensus based combination methods to obtain the final decision of the ensemble based on fuzzy decision trees in order to improve results. We make a comparative study with several datasets to show the efficiency of the various combination methods.

Instrument errors or noise interference during experiments may lead to incomplete data when measuring a specific attribute. Obtaining models from imperfect data is a topic currently being treated with more interest. In this paper, we present the learning phase of a Fuzzy Random Forest ensemble for classification from imperfect data. We perform experiments with imperfect datasets created for this purpose and datasets used in other papers to show the express the true nature of imperfect information.