Nayat Sanchez-Pi - Profile on Academia.edu (original) (raw)

Papers by Nayat Sanchez-Pi

Sensors (Basel, Switzerland), 2022

Frost forecast is an important issue in climate research because of its economic impact on severa... more Frost forecast is an important issue in climate research because of its economic impact on several industries. In this study, we propose GRAST-Frost, a graph neural network (GNN) with spatio-temporal architecture, which is used to predict minimum temperatures and the incidence of frost. We developed an IoT platform capable of acquiring weather data from an experimental site, and in addition, data were collected from 10 weather stations in close proximity to the aforementioned site. The model considers spatial and temporal relations while processing multiple time series simultaneously. Performing predictions of 6, 12, 24, and 48 h in advance, this model outperforms classical time series forecasting methods, including linear and nonlinear machine learning methods, simple deep learning architectures, and nongraph deep learning models. In addition, we show that our model significantly improves on the current state of the art of frost forecasting methods.

2020 IEEE Congress on Evolutionary Computation (CEC), 2020

Data Governance, a Knowledge Model Through Ontologies

Communications in Computer and Information Science, 2021

Journal of Applied Logic, 2016

Anomaly detection has to do with finding patterns in data that do not conform to an expected beha... more Anomaly detection has to do with finding patterns in data that do not conform to an expected behavior. It has recently attracted the attention of the research community because of its real-world application. The correct detection unusual events empower the decision maker with the capacity to act on the system in order to correctly avoid, correct, or react to the situations associated with them. Petroleum industry is one of such real-world application scenarios. In particular, heavy extraction machines for pumping and generation operations like turbomachines are intensively monitored by hundreds of sensors each that send measurements with a high frequency for damage prevention. For dealing with this and with the lack of labeled data, in this paper we describe a combination of a fast and high quality segmentation algorithm with a one-class support vector machine approach for efficient anomaly detection in turbomachines. As a result we perform empirical studies comparing our approach to another using Kalman filters in a real-life application related to oil platform turbomachinery anomaly detection.

Using Collective Intelligence to Support Multi-objective Decisions: Collaborative and Online Preferences

2015 30th IEEE/ACM International Conference on Automated Software Engineering Workshop (ASEW), 2015

This research indicates a novel approach of evolutionary multi-objective optimization algorithms ... more This research indicates a novel approach of evolutionary multi-objective optimization algorithms meant for integrating collective intelligence methods into the optimization process. The new algorithms allow groups of decision makers to improve the successive stages of evolution via users' preferences and collaboration in a direct crowdsourcing fashion. They can, also, highlight the regions of Pareto frontier that are more relevant to the group of decision makers as to focus the search process mainly on those areas. As part of this work we test the algorithms performance when face with some synthetic problem as well as a real-world case scenario.

Proceedings of the Genetic and Evolutionary Computation Conference Companion

This paper introduces Multi-Objective Physics-Informed Neural Networks (MOPINNs). MOPINNs use an ... more This paper introduces Multi-Objective Physics-Informed Neural Networks (MOPINNs). MOPINNs use an EMO algorithm to find the set of trade-offs between the data and physical losses of PINNs and therefore allow practitioners to correctly identify which of these trade-offs better represent the solution they want to reach. We discuss how MOPINNs overcome the complexity of weighting the different loss functions and to the best of our knowledge this is the first work relating multi-objective optimization problems (MOPs) and PINNs via evolutionary algorithms. We provide an exploratory analysis of this technique in order to determine its feasibility by applying MOPINNs on PDEs of particular interest: the heat, waves, and Burgers equations. CCS CONCEPTS • Computing methodologies → Neural networks; Genetic algorithms; Multi-task learning; Modeling methodologies; • Mathematics of computing → Partial differential equations; • Applied computing → Environmental sciences.

Antipolis: Inria-Institut national de recherche en sciences et technologies du numérique. hal: ha... more Antipolis: Inria-Institut national de recherche en sciences et technologies du numérique. hal: hal-01882235. url: http : / / oceania.inria.cl @book{oceania-white-book-2021, title = {{Oc\'{e}anIA}: {AI}, Data, and Models for Understanding the Ocean and Climate Change},

sms-eda-mec: Matlab reference implementation for the S-Metric Selection Estimation of Distribution Algorithm based on Multivariate Extension of Copulas (SMS-EDA-MEC)

ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal

This paper presents a multi-agent framework using Net- Logo to simulate human and collective beha... more This paper presents a multi-agent framework using Net- Logo to simulate human and collective behaviors during emergency evacuations. Emergency situation appears when an unexpected event occurs. In indoor emergency situation, evacuation plans defined by facility manager explain procedure and safety ways to follow in an emergency situation. A critical and public scenario is an airportwhere there is an everyday transit of thousands of people. In this scenario the importance is related with incidents statistics regarding overcrowding and crushing in public buildings. Simulation has the objective of evaluating building layouts considering several possible configurations. Agents could be based on reactive behavior like avoid danger or follow other agent, or in deliberative behavior based on BDI model. This tool provides decision support in a real emergency scenario like an airport, analyzing alternative solutions to the evacuation process.

Evolutionary Multi-Objective System Design

Advances in Intelligent and Soft Computing, 2012

Evaluations for context-aware systems can not be conducted in the same manner evaluation is under... more Evaluations for context-aware systems can not be conducted in the same manner evaluation is understood for other software systems where the concept of large corpus data, the establishment of ground truth and the metrics of precision and recall are used. Evaluation for changeable systems like context-aware and specially developed for AmI environments needs to be conducted to assess the impact and awareness of the users. E-Health represent a challenging domain where users(patients, patients' relatives and healthcare professionals) are very sensitive to systems' response. If system failure occurs it can conducts to a bad diagnosis or medication, or treatment. So a user-centred evaluation system is need to provide the system with users' feedback. In this paper, we present an evaluation method for context aware systems in AmI environments and specially to e-Heatlh domain.

Context-Aware Approach for Orally Accessible Web Services

2009 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology, 2009

Abstract In this paper, we present a context-aware architecture to facilitate adaptable web servi... more Abstract In this paper, we present a context-aware architecture to facilitate adaptable web services. In our approach, users interact with the system by means of a speech-based engine that allows using spontaneous speech to access the different services. These ...

Designing a Distributed Context-Aware Multi-Agent System

Atlantis Ambient and Pervasive Intelligence, 2009

... Multi-Agent System Virginia Fuentes, Nayat Sánchez-Pi, Javier Carbó and José M. Molina Univer... more ... Multi-Agent System Virginia Fuentes, Nayat Sánchez-Pi, Javier Carbó and José M. Molina University Carlos III of Madrid, Computer Science Department, Applied Artificial Intelligence Group (GIAA), Avda. Universidad Carlos III 22, 28270 Colmenarejo, Spain ...

Whitestein Series in Software Agent Technologies and Autonomic Computing, 2008

The increasing role and importance of ubiquitous computing and mobile environments in our daily l... more The increasing role and importance of ubiquitous computing and mobile environments in our daily lives implies the need for new solutions. The characteristics of agents and multi-agent systems make them very appropriate for constructing ubiquitous and mobile systems. The aim of this chapter is to present some of the advances in practical and theoretical applications of multiagent systems in the fields of ubiquitous computing and mobile environments carried out by several AgentCities.ES research groups.

Due to highly dynamism of the nowadays environments, the software agents running on these complex... more Due to highly dynamism of the nowadays environments, the software agents running on these complex environments have to face problems of adaptation to user needs. That means that the initial states that prompt the software's decision making process in the first place may dynamically change while the decision making process is still going on just because the user's opinion. So to cope with these problems, such systems should be able to acquire user's opinion and also self-adapt according to it. That is why there is a need of special kind of system that will combine ubiquity, context-awareness, intelligence, natural interaction and adaptation in an AmI environment. Research in context-aware systems has been moving towards reusable and adaptable architectures for managing more advanced human-computer interfaces. In this paper, we assume that the adaptation decisions are taken with the goal of maximizing the user benefit of the applications or services. We estimate their QoS by using the U2E system developed in previuos work and finally propose a methodology for service adaptation.

Anomaly detection is the problem of finding patterns in data that do not conform to an a priori e... more Anomaly detection is the problem of finding patterns in data that do not conform to an a priori expected behavior. This is related to the problem in which some samples are distant, in terms of a given metric, from the rest of the dataset, where these anomalous samples are indicated as outliers. Anomaly detection has recently attracted the attention of the research community, because of its relevance in real-world applications, like intrusion detection, fraud detection, fault detection and system health monitoring, among many others. Anomalies themselves can have a positive or negative nature, depending on their context and interpretation. However, in either case, it is important for decision makers to be able to detect them in order to take appropriate actions. The petroleum industry is one of the application contexts where these problems are present. The correct detection of such types of unusual information empowers the decision maker with the capacity to act on the system in order to correctly avoid, correct or react to the situations associated with them. In that application context, heavy extraction machines for pumping and generation operations, like turbomachines, are intensively monitored by hundreds of sensors each that send measurements with a high frequency for damage prevention. In this paper, we propose a combination of yet another segmentation algorithm (YASA), a novel fast and

A Compact Encoding for Efficient Character-level Deep Text Classification

2018 International Joint Conference on Neural Networks (IJCNN)

This paper puts forward a new text to tensor representation that relies on information compressio... more This paper puts forward a new text to tensor representation that relies on information compression techniques to assign shorter codes to the most frequently used characters. This representation is language-independent with no need of pretraining and produces an encoding with no information loss. It provides an adequate description of the morphology of text, as it is able to represent prefixes, declensions, and inflections with similar vectors and are able to represent even unseen words on the training dataset. Similarly, as it is compact yet sparse, is ideal for speed up training times using tensor processing libraries. As part of this paper, we show that this technique is especially effective when coupled with convolutional neural networks (CNNs) for text classification at character-level. We apply two variants of CNN coupled with it. Experimental results show that it drastically reduces the number of parameters to be optimized, resulting in competitive classification accuracy values in only a fraction of the time spent by one-hot encoding representations, thus enabling training in commodity hardware.

Human Interface and the Management of Information: Supporting Learning, Decision-Making and Collaboration

This paper presents a proposal for a Decision Support System sensitive to the user's context in t... more This paper presents a proposal for a Decision Support System sensitive to the user's context in the area of investment. This area is especially complicated due to the complex nature of the stock market. Therefore, a context-sensitive decision support can be a great support for investors. In the literature survey on DSS for investments in the stock market could be found that very little has been explored regarding the investor profile in financial decisions-making systems. Any practical experiment was not found where the investor profile has been applied on the recommendations for investment in the stock market. The work emphasized the main points to be considered in the User Context implementation for decision support systems development. The main motivation for this work was to demonstrate how the performance of Decision Support Systems for investment in stock market could be improved through the application of user context to their recommendation models. A recommendation system for buying and selling of stocks, based on genetic algorithms, was implemented and measured the performance in various test scenarios, with user profiles and without user profile features. The system configured without user profile, often performed below results than the different profiles modeled and implemented. To confirm the preliminary results, the ANOVA test was conducted and the null hypothesis was refuted at 0.0001 level.

Temporal Attention Modules for Memory-Augmented Neural Networks