Pasar al contenido principal

DEEP LEARNING IN AIR POLLUTION FORECASTING

RTI2018-098160-B-I00

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos I+D+i Retos de Investigación
Año convocatoria 2018
Plan Estatal 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSIDAD DE CADIZ

Resultados relacionados

Resultados totales (Incluyendo duplicados): 9
Encontrada(s) 1 página(s)

Repositorio Institucional de la Universidad de Burgos (RIUBU)
Publicación Artículo científico (JournalArticle)

Artificial Neural Networks, Sequence-to-Sequence LSTMs, and Exogenous Variables as Analytical Tools for NO2 (Air Pollution) Forecasting: A Case Study in the Bay of Algeciras (Spain)

  • González Enrique, Francisco Javier
  • Ruiz Aguilar, Juan Jesús
  • Moscoso López, José Antonio
  • Urda Muñoz, Daniel
  • Deka, Lipika
  • Turias Domínguez, Ignacio J.
This study aims to produce accurate predictions of the NO2 concentrations at a specific station of a monitoring network located in the Bay of Algeciras (Spain). Artificial neural networks (ANNs) and sequence-to-sequence long short-term memory networks (LSTMs) were used to create the forecasting models. Additionally, a new prediction method was proposed combining LSTMs using a rolling window scheme with a cross-validation procedure for time series (LSTM-CVT). Two different strategies were followed regarding the input variables: using NO2 from the station or employing NO2 and other pollutants data from any station of the network plus meteorological variables. The ANN and LSTM-CVT exogenous models used lagged datasets of different window sizes. Several feature ranking methods were used to select the top lagged variables and include them in the final exogenous datasets. Prediction horizons of t + 1, t + 4 and t + 8 were employed. The exogenous variables inclusion enhanced the model’s performance, especially for t + 4 (ρ ≈ 0.68 to ρ ≈ 0.74) and t + 8 (ρ ≈ 0.59 to ρ ≈ 0.66). The proposed LSTM-CVT method delivered promising results as the best performing models per prediction horizon employed this new methodology. Additionally, per each parameter combination, it obtained lower error values than ANNs in 85% of the cases., This research was funded by MICINN (Ministerio de Ciencia e Innovación-Spain), grant number RTI2018-098160-B-I00, and grant “Ayuda para Estancias en Centros de Investigación del Programa de Fomento e Impulso de la actividad Investigadora de la Universidad de Cádiz”.
Repositorio Institucional de la Universidad de Burgos (RIUBU)
Publicación Artículo científico (JournalArticle)

Towards a Reliable Comparison and Evaluation of Network Intrusion Detection Systems Based on Machine Learning Approaches

  • Magán-Carrion, Roberto
  • Urda Muñoz, Daniel
  • Díaz-Cano, Ignacio
  • Dorronsoro, Bernabé
Presently, we are living in a hyper-connected world where millions of heterogeneous devices are continuously sharing information in different application contexts for wellness, improving communications, digital businesses, etc. However, the bigger the number of devices and connections are, the higher the risk of security threats in this scenario. To counteract against malicious behaviours and preserve essential security services, Network Intrusion Detection Systems (NIDSs) are the most widely used defence line in communications networks. Nevertheless, there is no standard methodology to evaluate and fairly compare NIDSs. Most of the proposals elude mentioning crucial steps regarding NIDSs validation that make their comparison hard or even impossible. This work firstly includes a comprehensive study of recent NIDSs based on machine learning approaches, concluding that almost all of them do not accomplish with what authors of this paper consider mandatory steps for a reliable comparison and evaluation of NIDSs. Secondly, a structured methodology is proposed and assessed on the UGR’16 dataset to test its suitability for addressing network attack detection problems. The guideline and steps recommended will definitively help the research community to fairly assess NIDSs, although the definitive framework is not a trivial task and, therefore, some extra effort should still be made to improve its understandability and usability further., The authors would like to acknowledge the Spanish Ministerio de Ciencia, Innovación y Universidades and ERDF for the support provided under contracts RTI2018-100754-B-I00 (iSUN) and RTI2018-098160-B-I00 (DEEPAPFORE).
RODIN. Repositorio de Objetos de Docencia e Investigación de la Universidad de Cádiz
Publicación Artículo científico (JournalArticle)

A Clustering-Based Hybrid Support Vector Regression Model to Predict Container Volume at Seaport Sanitary Facilities

  • Ruiz Águilar, Juan Jesús
  • Moscoso López, José Antonio
  • Urda, Daniel
  • González Enrique, Francisco Javier
  • Turias Domínguez, Ignacio José
An accurate prediction of freight volume at the sanitary facilities of seaports is a key factor to improve planning operations and resource allocation. This study proposes a hybrid approach to forecast container volume at the sanitary facilities of a seaport. The methodology consists of a three-step procedure, combining the strengths of linear and non-linear models and the capability of a clustering technique. First, a self-organizing map (SOM) is used to decompose the time series into smaller clusters easier to predict. Second, a seasonal autoregressive integrated moving averages (SARIMA) model is applied in each cluster in order to obtain predicted values and residuals of each cluster. These values are finally used as inputs of a support vector regression (SVR) model together with the historical data of the cluster. The final prediction result integrates the prediction results of each cluster. The experimental results showed that the proposed model provided accurate prediction results and outperforms the rest of the models tested. The proposed model can be used as an automatic decision-making tool by seaport management due to its capacity to plan resources in advance, avoiding congestion and time delays.
RODIN. Repositorio de Objetos de Docencia e Investigación de la Universidad de Cádiz
Publicación Artículo científico (JournalArticle)

Air pollution relevance analysis in the bay of Algeciras (Spain)

  • Rodríguez García, María Inmaculada
  • González Enrique, Francisco Javier
  • Moscoso López, José Antonio
  • Ruiz Águilar, Juan Jesús
  • Turias Domínguez, Ignacio José
The aim of this work is to accomplish an in-depth analysis of the air pollution in the two main cities of the Bay of Algeciras (Spain). A large database of air pollutant concentrations and weather measurements were collected using a monitoring network installed throughout the region from the period of 2010-2015. The concentration parameters contain nitrogen dioxide (NO2), sulphur dioxide (SO2) and particulate matter (PM10). The analysis was developed in two monitoring stations (Algeciras and La Linea). The higher average concentration values were obtained in Algeciras for NO2 (28.850 mu g/m(3)) and SO2 (11.966 mu g/m(3)), and in La Linea for PM10 (30.745 mu g/m(3)). The analysis shows patterns that coincide with human activity. One of the goals of this work is to develop a useful virtual sensor capable of achieving a more robust monitoring network, which can be used, for instance, in the case of missing data. By means of trends analysis, groups of equivalent stations were determined, implying that the values of one station could be substituted for those in the equivalent station in case of failure (e.g., SO2 weekly trends in Algeciras and Los Barrios show equivalence). On the other hand, a calculation of relative risks was developed showing that relative humidity, wind speed and wind direction produce an increase in the risk of higher pollutant concentrations. Besides, obtained results showed that wind speed and wind direction are the most important variables in the distribution of particles. The results obtained may allow administrations or citizens to support decisions.
RODIN. Repositorio de Objetos de Docencia e Investigación de la Universidad de Cádiz
Publicación Artículo científico (JournalArticle)

Forecasting air pollutants using classification models: a case study in the Bay of Algeciras (Spain)

  • Rodríguez García, María Inmaculada
  • Ribeiro Rodrigues, M.C.
  • González Enrique, Francisco Javier
  • Ruiz Águilar, Juan Jesús
  • Turias Domínguez, Ignacio José
The main goal of this work is to obtain reliable predictions of pollutant concentrations related to maritime traffic (SO2, PM10, NO2, NOX, and NO) in the Bay of Algeciras, located in Andalusia, the south of Spain. Furthermore, the objective is to predict future air quality levels of the principal maritime traffic-related pollutants in the Bay of Algeciras as a function of the rest of the pollutants, the meteorological variables, and vessel data. In this sense, three scenarios were analysed for comparison, namely Alcornocales Park and the cities of La Línea and Algeciras. A database of hourly records of air pollution immissions, meteorological measurements in the Bay of Algeciras region and a database of maritime traffic in the port of Algeciras during the years 2017 to 2019 were used. A resampling procedure using a five-fold cross-validation procedure to assure the generalisation capabilities of the tested models was designed to compute the pollutant predictions with different classification models and also with artificial neural networks using different numbers of hidden layers and units. This procedure enabled appropriate and reliable multiple comparisons among the tested models and facilitated the selection of a set of top-performing prediction models. The models have been compared using several quality classification indexes such as sensitivity, specificity, accuracy, and precision. The distance (d1) to the perfect classifier (1, 1, 1, 1) was also used as a discriminant feature, which allowed for the selection of the best models. Concerning the number of variables, an analysis was conducted to identify the most relevant ones for each pollutant. This approach aimed to obtain models with fewer inputs, facilitating the design of an optimised monitoring network. These more compact models have proven to be the optimal choice in many cases. The obtained sensitivities in the best models were 0.98 for SO2, 0.97 for PM10, 0.82 for NO2 and NOX, and 0.83 for NO. These results demonstrate the potential of the models to forecast air pollution in a port city or a complex scenario and to be used by citizens and authorities to prevent exposure to pollutants and to make decisions concerning air quality, 25 páginas
RODIN. Repositorio de Objetos de Docencia e Investigación de la Universidad de Cádiz
Publicación Artículo científico (JournalArticle)

Long Short-Term Memory Approach for Short-Term Air Quality Forecasting in the Bay of Algeciras (Spain)

  • Rodríguez García, María Inmaculada
  • Carrasco García, María Gema
  • González Enrique, Francisco Javier
  • Ruíz Aguilar, Juan Jesús
  • Turias Domínguez, Ignacio José
Predicting air quality is a very important task, as it is known to have a significant impact on health. The Bay of Algeciras (Spain) is a highly industrialised area with one of the largest superports in Europe. During the period 2017–2019, different data were recorded in the monitoring stations of the bay, forming a database of 131 variables (air pollutants, meteorological information, and vessel data), which were predicted in the Algeciras station using long short-term memory models. Four different approaches have been developed to make SO2 and NO2 forecasts 1 h and 4 h in Algeciras. The first uses the remaining 130 exogenous variables. The second uses only the time series data without exogenous variables. The third approach consists of using an autoregressive time series arrangement as input, and the fourth one is similar, using the time series together with wind and ship data. The results showed that SO2 is better predicted with autoregressive information and NO2 is better predicted with ships and wind autoregressive time series, indicating that NO2 is closely related to combustion engines and can be better predicted. The interest of this study is based on the fact that it can serve as a resource for making informed decisions for authorities, companies, and citizens alike.
RODIN. Repositorio de Objetos de Docencia e Investigación de la Universidad de Cádiz
Publicación Artículo científico (JournalArticle)

Improving the Reliability of Network Intrusion Detection Systems Through Dataset Integration

  • Magán Carrión, Roberto
  • Urda, Daniel
  • Díaz Cano, Ignacio
  • Dorronsoro Díaz, Bernabé
This work presents Reliable-NIDS (R-NIDS), a novel methodology for Machine Learning (ML) based Network Intrusion Detection Systems (NIDSs) that allows ML models to work on integrated datasets, empowering the learning process with diverse information from different datasets. We also propose a new dataset, called UNK22. It is built from three of the most well-known network datasets (UGR'16, USNW-NB15 and NLS-KDD), each one gathered from its own network environment, with different features and classes, by using a data aggregation approach present in R-NIDS. Therefore, R-NIDS targets the design of more robust models that generalize better than traditional approaches. Following R-NIDS, in this work we propose to build two well-known ML models for reliable predictions thanks to the meaningful information integrated in UNK22. The results show how these models benefit from the proposed approach, being able to generalize better when using UNK22 in the training process, in comparison to individually using the datasets composing it. Furthermore, these results are carefully analyzed with statistical tools that provide high confidence on our conclusions. Finally, the proposed solution is feasible to be deployed in network production environments, not usually taken into account in the literature., 16 páginas
RODIN. Repositorio de Objetos de Docencia e Investigación de la Universidad de Cádiz
Publicación Artículo científico (JournalArticle)

Artificial Neural Networks, Sequence-to-Sequence LSTMs, and Exogenous Variables as Analytical Tools for NO2 (Air Pollution) Forecasting: A Case Study in the Bay of Algeciras (Spain)

  • González Enrique, Francisco Javier
  • Ruiz Águilar, Juan Jesús
  • Moscoso López, José Antonio
  • Urda, Daniel
  • Deka, Lipika
  • Turias Domínguez, Ignacio José
This study aims to produce accurate predictions of the NO2 concentrations at a specific station of a monitoring network located in the Bay of Algeciras (Spain). Artificial neural networks (ANNs) and sequence-to-sequence long short-term memory networks (LSTMs) were used to create the forecasting models. Additionally, a new prediction method was proposed combining LSTMs using a rolling window scheme with a cross-validation procedure for time series (LSTM-CVT). Two different strategies were followed regarding the input variables: using NO2 from the station or employing NO2 and other pollutants data from any station of the network plus meteorological variables. The ANN and LSTM-CVT exogenous models used lagged datasets of different window sizes. Several feature ranking methods were used to select the top lagged variables and include them in the final exogenous datasets. Prediction horizons of t + 1, t + 4 and t + 8 were employed. The exogenous variables inclusion enhanced the model's performance, especially for t + 4 (rho approximate to 0.68 to rho approximate to 0.74) and t + 8 (rho approximate to 0.59 to rho approximate to 0.66). The proposed LSTM-CVT method delivered promising results as the best performing models per prediction horizon employed this new methodology. Additionally, per each parameter combination, it obtained lower error values than ANNs in 85% of the cases.
RODIN. Repositorio de Objetos de Docencia e Investigación de la Universidad de Cádiz
Publicación Artículo científico (JournalArticle)

Evaluating the impact of different Feature as a Counter data aggregation approaches on the performance of NIDSs and their selected features

  • Magán Carrión, Roberto
  • Urdal Muñoz, Daniel
  • Díaz Cano, Ignacio
  • Dorronsoro Díaz, Bernabé
There is much effort nowadays to protect communication networks against different cybersecurity attacks (which are more and more sophisticated) that look for systems’ vulnerabilities they could exploit for malicious purposes. Network Intrusion Detection Systems (NIDSs) are popular tools to detect and classify such attacks, most of them based on ML models. However, ML-based NIDSs cannot be trained by feeding them with network traffic data as it is. Thus, a Feature Engineering (FE) process plays a crucial role transforming network traffic raw data onto derived one suitable for ML models. In this work, we study the effects of applying one such FE technique in different ways on the performance of two ML models (linear and non-linear) and their selected features. This is the Feature as a Counter approach. The derived observations are computed from either with the same number of raw samples, (batch-based approaches) or by aggregating them by time intervals (timestamp-based approach). Results show that there is no significant differences between the proposed approaches neither in the performance of the models nor in the selected features that validate our proposal making it feasible to be widely used as a standard FE method.