Search

The construction sector in Greece has been developing radically in the field of building renovations. The foremost problem for projects in the building construction industry is producing an accurate and reliable cost estimate at the onset of construction. The artificial neural network (AΝΝ) approach, using data available at the early stages of the project, can help resolve or prevent any kind of difficulty that could make the successful completion of a building less likely. ANNs have been highly efficient in gaining results which could prevent the failure of building constructions projects. The ultimate goal is to highlight the usefulness of the adoption of ANNs models to predict the final cost of a building renovation project. Thus, construction companies could avoid financial failure, provided that the gap between cost prediction and final cost for renovation projects is minimized. This paper presents an artificial neural network (ANN) approach for predicting renovation costs in Greek construction projects. The study, based on a comprehensive literature review and real renovation data from construction companies, employs IBM SPSS Statistics software to build, train, and test the ANN model. The model, which uses initial cost, estimated time, and initial demolition cost as inputs, is based on the radial basis function procedure. The model presents high performance with up to 2% sum of squares error and near zero relative error, demonstrating the ANN's effectiveness in estimating total renovation costs. [ABSTRACT FROM AUTHOR]

This paper addresses the gap in the scientific literature regarding construction cost estimates for the construction of underground metro stations. It provides preliminary cost estimation models using linear regression for use by the Greek underground metro public transport authority for planning future extensions to the Athens and Thessaloniki networks. At the same time, it contributes to the body of knowledge by proposing material quantity prediction models and presents a two-stage preliminary cost estimation model for the construction of civil engineering works of underground metro stations. Stage one uses the construction cost budgets of six metro stations in Greece to develop a multilinear regression equation for the prediction of the overall cost for construction of civil engineering works; stage two provides estimates of material quantities using linear regression, key quantity ratios, and artificial neural networks. The data analyzed are from the prior measurements of quantities for the construction of the Chaidari to Piraeus extension of the Athens Metro Line 3. After comparing the actual values of costs and quantities with the corresponding predictions, acceptable discrepancies are observed. All models provide estimates within ±25% discrepancies, which are acceptable at the conceptual planning phase in order to initiate project funding quests. [ABSTRACT FROM AUTHOR]

Featured Application: Early diagnosis and warning mechanisms are essential in every health condition. The research described in this paper can provide the means for the development of medical assistance applications. The correlation between the kind of cesarean section and post-traumatic stress disorder (PTSD) in Greek women after a traumatic birth experience has been recognized in previous studies along with other risk factors, such as perinatal conditions and traumatic life events. Data from early studies have suggested some possible links between some vulnerable factors and the potential development of postpartum PTSD. The classification of each case in three possible states (PTSD, profile PTSD, and free of symptoms) is typically performed using the guidelines and the metrics of the version V of the Diagnostic and Statistical Manual of Mental Disorders (DSM-V) which requires the completion of several questionnaires during the postpartum period. The motivation in the present work is the need for a model that can detect possible PTSD cases using a minimum amount of information and produce an early diagnosis. The early PTSD diagnosis is critical since it allows the medical personnel to take the proper measures as soon as possible. Our sample consists of 469 women who underwent emergent or elective cesarean delivery in a university hospital in Greece. The methodology which is followed is the application of random decision forests (RDF) to detect the most suitable and easily accessible information which is then used by an artificial neural network (ANN) for the classification. As is demonstrated from the results, the derived decision model can reach high levels of accuracy even when only partial and quickly available information is provided. [ABSTRACT FROM AUTHOR]

In this paper, we develop an automatic valuation model for property valuation using a large database of historical prices from Greece. The Greek property market is an inefficient, non-homogeneous market, still at its infancy and governed by lack of information. As a result modelling the Greek real estate market is a very interesting and challenging problem. The available data cover a wide range of properties across time and include the financial crisis period in Greece which led to tremendous changes in the dynamics of the real estate market. We formulate and compare linear and non-linear models based on regression, hedonic equations and artificial neural networks. The forecasting ability of each method is evaluated out-of-sample. Special care is given on measuring the success of the forecasts but also on identifying the property characteristics that lead to large forecasting errors. Finally, by examining the strengths and the performance of each method we apply a combined forecasting rule to improve forecasting accuracy. Our results indicate that the proposed methodology constitutes an accurate tool for property valuation in a non-homogeneous, newly developed market. [ABSTRACT FROM AUTHOR]

In this paper, a novel combination of deep learning recurrent neural network and Lyapunov time is proposed to forecast the consumption of electricity load, in Greece, in normal/abrupt change value areas. Our method verifies the chaotic behavior of load time series through chaos time series analysis and with the application of deep learning recurrent neural networks produces predictions for 10 and 20 days ahead. Specifically, four different neural network models constructed (a) feed forward neural network, (b) gated recurrent unit (GRU) neural network, (c) long short-term memory (LSTM) recurrent and (d) bidirectional LSTM neural network to implement the prediction in a prediction horizon, produced through the extraction of maximum Lyapunov exponent. We constructed sequences of algorithms to feed the neural networks, creating three scenarios (a) 1-step, (b) 10-step and (c) 20-step sequences. For each neural network model, we used its predictions as inputs to predict steps forward, iteratively, to examine the accuracy of the proposed models, for horizons that are both inside and outside to that defined by Lyapunov time. The results show that the deep learning GRU neural network produces iterative predictions of high accuracy and stability, following the trend evolution of actual values, even outside the safe horizon for 1-step and 10-step cases. [ABSTRACT FROM AUTHOR]

This paper looks into the Greek-Turkish arms race a decade after an earlier contribution to the issue that relied heavily on artificial neural networks. The time period between the two papers contributes to the reliability of the results derived, not just by increasing the number of observations, but also mainly by incorporating the progress made in the realm of artificial intelligence. The focus on the case of both countries unlike the paper mentioned above that dealt with just the Greek side provides ample room for comparative purposes regarding the determinants of defense expenditure on both sides. The results derived in terms of input significance estimation support the findings of the earlier research as indicated above, pointing to the leading role of the demographic preponderance of Turkey over Greece. The paper also points to the fact that 10 years later, Turkey continues to set the arms race rules against its rival by determining the defense expenditure of Greece, whereas the role of the latter in affecting the military spending of Turkey is non-existent. [ABSTRACT FROM AUTHOR]

Several roundabout capacity methods and approaches have been proposed until now. They are mainly based either on regression equations of observed capacity and gap acceptance or on stochastic models through simulation techniques. However, all of them rely on different variables and factors and are being adapted to local driving behavior. Hence, it is not clear if existing techniques are appropriate for reliable capacity estimations and optimal design of Greek roundabouts. This paper presents the results of an experimental research that has been conducted as a first step in the optimization of roundabouts capacity estimation, based on a dataset of 11 roundabouts in Greece. The study firstly aims to understand what geometric roundabout features and driving behavior parameters influence capacity. Artificial neural networks (NN) were tested and developed to predict accurate roundabout capacities. Appropriate roundabouts were selected for the analysis and their operational performance was filmed using a UAV and a stabilized camera during peak periods. Video image processing techniques and algorithms allowed the extraction of empirical data (traffic flows, gap acceptance parameters) and accurate geometric characteristics. The results demonstrate that artificial neural networks can predict the capacity of roundabouts accurately. [ABSTRACT FROM AUTHOR]

In order to improve the prediction accuracy of ionospheric total electron content (TEC), a combined intelligent prediction model (MMAdapGA-BP-NN) based on a multi-mutation, multi-cross adaptive genetic algorithm (MMAdapGA) and a back propagation neural network (BP-NN) was proposed. The model combines the international reference ionosphere (IRI), statistical machine learning (SML), BP-NN, and MMAdapGA. Compared with the IRI, SML-based, and other neural network models, MMAdapGA-BP-NN has higher accuracy and a more stable prediction effect. Taking the Athens station in Greece as an example, the root mean square errors (RMSEs) of MMAdapGA-BP-NN in 2015 and 2020 are 2.84TECU and 0.85TECU, respectively, 52.27% and 72.13% lower than the IRI model. Compared with the single neural network model, the MMAdapGA-BP-NN model reduced RMSE by 28.82% and 24.11% in 2015 and 2020, respectively. Furthermore, compared with the neural network optimized by a single mutation genetic algorithm, MMAdapGA-BP-NN has fewer iterations ranging from 10 to 30. The results show that the prediction effect and stability of the proposed model have obvious advantages. As a result, the model could be extended to an alternative prediction scheme for more ionospheric parameters. [ABSTRACT FROM AUTHOR]

This paper presents and assesses various machine learning methods that aim at predicting path loss in rural environment. For this purpose, models such as artificial neural network (ANN), support vector regression (SVR), random forest (RF), and bagging with k-nearest neighbor (B-kNN) learners, are exploited and evaluated. They are trained and tested with path loss data collected from an extensive measurement campaign that have been carried out in diverse rural areas in Greece. The results demonstrate that all the proposed machine learning models outperform the empirical ones, exhibiting, in any case, root-mean-square-error (RMSE) values between 4.0 and 6.5 dB. The poorest prediction of the measured data is encountered for SVR with Polynomial kernel. Furthermore, B-kNN and RF algorithms preserve comparable path loss approximations with remarkably low RMSE on the order of 4.2–4.3 dB. The error metrics also reveal that increasing the number of hidden layers in ANNs, their performance is gradually enhanced. However, deeper layouts with more than three hidden layers do not markedly improve any further the prediction accuracy. Finally, the best prediction is achieved when employing a three-hidden layered ANN with 51 neurons evenly distributed among the layers. The specific layout exhibits the lowest RMSE value (4.0 dB), thus being highly recommended for accurate path loss predictions in rural locations. [ABSTRACT FROM AUTHOR]

Human behavior pattern recognition exploited using Artificial Neural Networks (ANN) is at the core of Artificial Intelligence (AI) classification applications. School trip transport forecasting mode selection based upon ANN forecasting ability provided an easy-to-use scientific toolkit for sustainable urban policies designing and implementation. The paper capitalized acknowledged forecasting ability of ANN to recognize and classify behavior patterns leading to parental decisions of school mode choice. Main stages of this research included the conduction of an extended questionnaire survey in 512 parents of school students in Thessaloniki (northern Greece) and the investigation whether ANN forecasting model could classify school mode choice. Research provided promising results (forecasting ability ranging from 76% to 93%) on school mode parental selection forecasting models based on ANN classifier, providing a solid proof of concept for further investigation. [ABSTRACT FROM AUTHOR]

Copyright of Economic Annals-XXI / Ekonomìčnij Časopis-XXI is the property of Institute of Society Transformation and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Modeling the elasticity modulus of unbound granular pavement materials has attracted significant research interest because of its importance in pavement design particularly in PPP/BOT projects. These efforts have been hampered by three factors: (i) inability to capture the correlations between the asphalt and granular layers and the subgrade, (ii) inadequate modeling of the effects of external factors on the elasticity modulus of unbound materials, and (iii) widespread use of linear statistical relationships to model a complex and non-linear phenomenon. In this paper genetically optimized neural networks and falling weight deflectometer (FWD) back-analysis results from a newly constructed BOT project in Athens, Greece, are employed in order to evaluate pavement section design parameters. It is shown that parameter values adopted during design do not co-inside with those observed from the back-analysis studies. Further, the results indicate that the relative estimation error for the modulus of elasticity of the unbound material does not exceed 25%, while the correlation between actual and predicted values is 86%, both suggesting that the proposed approach models the physical phenomenon adequately, a finding with important practical implications particularly in PPP projects. [ABSTRACT FROM AUTHOR]

Ensuring sea surface tranquility within port basins is of paramount importance for safe and efficient port operations and vessels' accommodation. The present study aims to introduce a robust numerical model based on mild-slope equations, capable of accurately simulating wave disturbance and resonance in ports. The model is further enhanced by the integration of an artificial neural network (ANN) to address partial reflection, and its efficiency is optimized by developing a parallel algorithm based on OpenMP, allowing for a reduction in the required simulation times for real port areas spanning several kilometers horizontally. Numerous numerical experiments focusing on wave reflection against a vertical wall were conducted to develop the ANN. This neural network was designed to determine the appropriate value of the eddy viscosity coefficient, a crucial parameter in the momentum equation of the mild-slope model, tailored to incident wave characteristics. The model's validity was confirmed through rigorous validation against experimental measurements, covering wave disturbance, rectangular harbor resonance, and Bragg resonance. The model consistently demonstrated a more than satisfactory performance across all considered scenarios. In a practical application, the model was deployed in the Port of Rethymno, Crete Island, Greece, effectively capturing and describing dominant phenomena within the port area. The implementation of a parallel algorithm significantly reduced the simulation times by ~92%, compared to the serial algorithm, thereby enhancing the model's efficiency and applicability in real-world port environments. [ABSTRACT FROM AUTHOR]

This paper introduced a new ensemble learning approach, based on evolutionary fuzzy cognitive maps (FCMs), artificial neural networks (ANNs), and their hybrid structure (FCM-ANN), for time series prediction. The main aim of time series forecasting is to obtain reasonably accurate forecasts of future data from analyzing records of data. In the paper, we proposed an ensemble-based forecast combination methodology as an alternative approach to forecasting methods for time series prediction. The ensemble learning technique combines various learning algorithms, including SOGA (structure optimization genetic algorithm)-based FCMs, RCGA (real coded genetic algorithm)-based FCMs, efficient and adaptive ANNs architectures, and a hybrid structure of FCM-ANN, recently proposed for time series forecasting. All ensemble algorithms execute according to the one-step prediction regime. The particular forecast combination approach was specifically selected due to the advanced features of each ensemble component, where the findings of this work evinced the effectiveness of this approach, in terms of prediction accuracy, when compared against other well-known, independent forecasting approaches, such as ANNs or FCMs, and the long short-term memory (LSTM) algorithm as well. The suggested ensemble learning approach was applied to three distribution points that compose the natural gas grid of a Greek region. For the evaluation of the proposed approach, a real-time series dataset for natural gas prediction was used. We also provided a detailed discussion on the performance of the individual predictors, the ensemble predictors, and their combination through two well-known ensemble methods (the average and the error-based) that are characterized in the literature as particularly accurate and effective. The prediction results showed the efficacy of the proposed ensemble learning approach, and the comparative analysis demonstrated enough evidence that the approach could be used effectively to conduct forecasting based on multivariate time series. [ABSTRACT FROM AUTHOR]

This paper aimed to investigate the potential of using spectral and textural features in the Meteosat Second Generation-Spinning Enhanced Visible and Infrared Imager (MSG-SEVIRI) data for developing techniques capable of classifying convective and stratiform rain areas in the satellite image. Two different classification methods were introduced that use the brightness temperature (BT) T and brightness temperature differences T- T T- T T- T T- T T- T T- T, and T- T as spectral parameters, along with textural parameters derived from the thermal infrared MSG-SEVIRI channel to discriminate between convective and stratiform rainy clouds. The first is an algorithm based on the probability of convective rainfall (PCR) for each pixel of the MSG satellite data and the second is an artificial neural network multilayer perceptron (MLP) model that relies on the correlation of satellite data with convective and stratiform rain. Both schemes were trained using as reference convective/stratiform classification data from 88 stations in Greece for 20 rainy days with high convective activity and evaluated against an independent dataset of gauge data for six rainy days. Two PCR and two MLP algorithms were constructed based on the previous results: the PCR1 and MLP1 algorithms that use only spectral measures and the PCR2 and MLP2 algorithms based on both spectral and textural measures. It was found that the introduction of textural parameters as additional information to a technique (PCR2 and MLP2 ) works in improving the delineation between convective and stratiform rainy pixels compared to the techniques based only on spectral information (PCR1 and MLP1). The comparison of the two schemes revealed a clear outperformance of the MLP techniques over the PCR techniques. Best skill is provided by MLP2 (POD = 74.5 %, FAR = 44.3 %, POFD = 22.5 %, CSI = 0.47, ETS = 0.31, bias = 1.34) followed by MLP1 and the two PCR techniques. All algorithms overestimate the convective rain occurrences observed by the rain gauge network. These findings showed that the combined use of spectral and textural features in the MSG-SEVIRI imagery can be beneficial for the classification of convective and stratiform precipitating clouds. [ABSTRACT FROM AUTHOR]

In this paper we suggest the use of diffusion-neural-networks, (neural networks with intrinsic fuzzy logic abilities) to assess the relationship between isoseismal area and earthquake magnitude for the region of Greece. It is of particular importance to study historical earthquakes for which we often have macroseismic information in the form of isoseisms but it is statistically incomplete to assess magnitudes from an isoseismal area or to train conventional artificial neural networks for magnitude estimation. Fuzzy relationships are developed and used to train a feed forward neural network with a back propagation algorithm to obtain the final relationships. Seismic intensity data from 24 earthquakes in Greece have been used. Special attention is being paid to the incompleteness and contradictory patterns in scanty historical earthquake records. The results show that the proposed processing model is very effective, better than applying classical artificial neural networks since the magnitude macroseismic intensity target function has a strong nonlinearity and in most cases the macroseismic datasets are very small. [ABSTRACT FROM AUTHOR]

This paper presents the development of a non-parametric forecast model based on artificial neural networks for the direct assessment of Arias Intensity corresponding to a historic earthquake using seismic intensity data. The neural models allow complex and nonlinear behaviour to be tracked. Application of this methodology on earthquakes with known instrumental data from Greece, showed that the artificial neural network forecast model have excellent data synthesis capability. [ABSTRACT FROM AUTHOR]

The difficulty in forecasting concentration trends with a reasonable error is still an open problem. In this paper, an effort has been made to this purpose. Artificial Neural Networks are used in order to forecast the maximum daily value of the European Regional Pollution Index as well as the number of consecutive hours, during the day, with at least one of the pollutants above a threshold concentration, 24 to 72 h ahead. The prediction concerns seven different places within the Greater Athens Area, Greece. The meteorological and air pollution data used in this study have been recorded by the network of the Greek Ministry of the Environment, Physical Planning, and Public Works over a 5-year period, 2001–2005. The hourly values of air pressure and global solar irradiance for the same period have been recorded by the National Observatory of Athens. The results are in a very good agreement with the real-monitored data at a statistical significance level of p < 0.01. [ABSTRACT FROM AUTHOR]

An integrated methodological approach to the development of a coastal flood early-warning system is presented in this paper to improve societal preparedness for coastal flood events. The approach consists of two frameworks, namely the Hindcast Framework and the Forecast Framework. The aim of the former is to implement a suite of high-credibility numerical models and validate them according to past flooding events, while the latter takes advantage of these validated models and runs a plethora of scenarios representing distinct sea-state events to train an Artificial Neural Network (ANN) that is capable of predicting the impending coastal flood risks. The proposed approach was applied in the flood-prone coastal area of Rethymno in the Island of Crete in Greece. The performance of the developed ANN is good, given the complexity of the problem, accurately predicting the targeted coastal flood risks. It is capable of predicting such risks without requiring time-consuming numerical simulations; the ANN only requires the offshore wave characteristics (height, period and direction) and sea-water-level elevation, which can be obtained from open databases. The generic nature of the proposed methodological approach allows its application in numerous coastal regions. [ABSTRACT FROM AUTHOR]

• Forecasting urban growth via machine learning models can improve city planning. • We turn pan-European spatial data into tabular data for our predictive model. • We apply our Artificial Neural Network model in five major Greek cities. • We present our training and validation process using goodness-of-fit metrics. • We make an urban growth prediction for each city for a 12-year cycle to the year 2030. Urban development if not planned and managed adequately can be unsustainable. Urban growth models have been a powerful toolkit to help tackling this challenge. In this paper, we use a machine learning approach, to apply an urban growth model to five of the largest cities in Greece. Specifically, we first develop a methodology to collect, organise, handle and transform historical open spatial data, concerning various impact factors, into machine learning data. Such factors involve social, economic, biophysical, neighbouring-related and political driving forces, which must be transformed into tabular data. We also provide an artificial neural network (ANN) model and the methodology to train and evaluate it using goodness-of-fit metrics, which in turn provide the best weights of impact factors. Finally, we execute a prediction for 2030, presenting the results and output maps for each of the five case study cities. As our study is based on pan-European datasets, our model can be used for any area within Europe, using the open-source utility developed to support it. In this sense, our work provides local policy-makers and urban planners with an instrument that could help them analyse various future development scenarios and take the right decisions going forward. [ABSTRACT FROM AUTHOR]

Industrial automation uses robotics and software to operate equipment and procedures across industries. Many applications integrate IoT, machine learning, and other technologies to provide smart features that improve the user experience. The use of such technology offers businesses and people tremendous assistance in successfully achieving commercial and noncommercial requirements. Organizations are expected to automate industrial processes owing to the significant risk management and inefficiency of conventional processes. Hence, we developed an elaborative stepwise stacked artificial neural network (ESSANN) algorithm to greatly improve automation industries in controlling and monitoring the industrial environment. Initially, an industrial dataset provided by KLEEMANN Greece was used. The collected data were then preprocessed. Principal component analysis (PCA) was used to extract features, and feature selection was based on least absolute shrinkage and selection operator (LASSO). Subsequently, the ESSANN approach is proposed to improve automation industries. The performance of the proposed algorithm was also examined and compared with that of existing algorithms. The key factors compared with existing technologies are delay, network bandwidth, scalability, computation time, packet loss, operational cost, accuracy, precision, recall, and mean absolute error (MAE). Compared to traditional algorithms for industrial automation, our proposed techniques achieved high results, such as a delay of approximately 52%, network bandwidth accomplished at 97%, scalability attained at 96%, computation time acquired at 59 s, packet loss achieved at a minimum level of approximately 53%, an operational cost of approximately 59%, accuracy of 98%, precision of 98.95%, recall of 95.02%, and MAE of 80%. By analyzing the results, it can be seen that the proposed system was effectively implemented. [ABSTRACT FROM AUTHOR]

The aim of the study was to investigate the utility of artificial neural networks (ANNs) for the estimation of reference evapotranspiration (ETo) on the Peloponnese Peninsula in Greece for two representative months of wintertime and summertime during 2016–2019 and to test if using fewer inputs could lead to satisfactory predictions. Datasets from sixty-two meteorological stations were employed. The available inputs were mean temperature (Tmean), sunshine (N), solar radiation (Rs), net radiation (Rn), vapour pressure deficit (es-ea), wind speed (u2) and altitude (Z). Nineteen Multi-layer Perceptron (MLP) and Radial Basis Function (RBF) models were tested and compared against the corresponding FAO-56 Penman Monteith (FAO PM) estimates of a previous study, via statistical indices. The MLP1 7-2 model with all the variables as inputs outperformed the rest of the models (RMSE = 0.290 mm d−1, R2 = 98%). The results indicate that even ANNs with simple architecture can be very good predictive models of ETo for the Peloponnese, based on the literature standards. The MLP1 model determined Tmean, followed by u2, as the two most influential factors for ETo. Moreover, when one input was used (Tmean, Rn), RBFs slightly outperformed MLPs (RMSE < 0.385 mm d−1, R2 ≥ 96%), which means that even a sole-input ANN resulted in satisfactory predictions of ETo. [ABSTRACT FROM AUTHOR]

The significant increase of wind energy production worldwide revealed the necessity of its accurate forecasting. However, this is a very complex and, despite the progress made, more accurate forecasting methods are still needed. Accurate forecasts will contribute to a better power plant and grid management by solving problems related to the distribution and storage of the produced electricity, maximizing thus the profits of wind energy investments, contributing ultimately to their further enhancement. Here we present the development and validation of selected artificial neural network (ANN) wind energy forecasting models that produce hourly forecasts for 24 hours forecast horizon. The models are developed and validated using wind speed, direction, and energy produced by a wind power plant located at a semi-mountainous area in Western Greece. The ANN forecasts are compared against those of the persistence method using the Root Means Square Error (RMSE) and the Mean Absolute Percentage Error (MAPE) statistics. [ABSTRACT FROM AUTHOR]

TROPOMI (TROPOspheric Monitoring Instrument) measurements of tropospheric NO2 columns provide powerful information on emissions of air pollution by ships on open sea. This information is potentially useful for authorities to help determine the (non-) compliance of ships with increasingly stringent NOx emission regulations. We find that the information quality is improved further by recent upgrades in the TROPOMI cloud retrieval and an optimal data selection. We show that the superior spatial resolution of TROPOMI allows for the detection of several lanes of NO2 pollution ranging from the Aegean Sea near Greece to the Skagerrak in Scandinavia, which have not been detected with other satellite instruments before. Additionally, we demonstrate that under conditions of sun glint TROPOMI's vertical sensitivity to NO2 in the marine boundary layer increases by up to 60 %. The benefits of sun glint are most prominent under clear-sky situations when sea surface winds are low but slightly above zero (±2 m s -1). Beyond spatial resolution and sun glint, we examine for the first time the impact of the recently improved cloud algorithm on the TROPOMI NO2 retrieval quality, both over sea and over land. We find that the new FRESCO + (Fast Retrieval Scheme for Clouds from the Oxygen A band) wide algorithm leads to 50 hPa lower cloud pressures, correcting a known high bias, and produces 1– 4×1015 molec. cm -2 higher retrieved NO2 columns, thereby at least partially correcting for the previously reported low bias in the TROPOMI NO2 product. By training an artificial neural network on the four available periods with standard and FRESCO + wide test retrievals, we develop a historic, consistent TROPOMI NO2 data set spanning the years 2019 and 2020. This improved data set shows stronger (35 %–75 %) and sharper (10 %–35 %) shipping NO2 signals compared to co-sampled measurements from OMI. We apply our improved data set to investigate the impact of the COVID-19 pandemic on ship NO2 pollution over European seas and find indications that NOx emissions from ships reduced by 10 %–20 % during the beginning of the COVID-19 pandemic in 2020. The reductions in ship NO2 pollution start in March–April 2020, in line with changes in shipping activity inferred from automatic identification system (AIS) data on ship location, speed, and engine. [ABSTRACT FROM AUTHOR]

The scope of the present study is the estimation of the concentration of nitrates (N O 3 −) in groundwater using artificial neural networks (ANNs) based on easily measurable in situ data. For the purpose of the current study, two feedforward neural networks were developed to determine whether including land use variables would improve the model results. In the first network, easily measurable field data were used, i.e., pH, electrical conductivity, water temperature, air temperature, and aquifer level. This model achieved a fairly good simulation based on the root mean squared error (RMSE in mg/L) and the Nash–Sutcliffe Model Efficiency (NSE) indicators (RMSE = 26.18, NSE = 0.54). In the second model, the percentages of different land uses in a radius of 1000 m from each well was included in an attempt to obtain a better description of nitrate transport in the aquifer system. When these variables were used, the performance of the model increased significantly (RMSE = 15.95, NSE = 0.70). For the development of the models, data from chemical and physical analyses of groundwater samples from wells located in the Kopaidian Plain and the wider area of the Asopos River Basin, both in Greece, were used. The simulation that the models achieved indicates that they are a potentially useful tools for the estimation of groundwater contamination by nitrates and may therefore constitute a basis for the development of groundwater management plans. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents an artificial intelligence approach integrated with geographical information systems (GISs) for modeling urban evolution. Fuzzy logic and neural networks are used to provide a synthetic spatiotemporal methodology for the analysis, prediction and interpretation of urban growth. The proposed urban model takes into account the changes over time in population and building use patterns. A GIS is used for handling the spatial and temporal data, performing contingency analysis and mapping the results. Spatial entities with similar characteristics are grouped together in clusters by the use of a fuzzy c-means algorithm. Each cluster represents a specific level of urban growth and development. A two-layer feed-forward multilayer perceptron artificial neural network is then used to predict urban growth. The model, applied to the prefecture of Attica, Greece, delineates the current and future evolution trends of the Athens metropolitan area, which are illustrated by maps of the urban growth dynamics. The proposed methodology aims to assist planners and decision makers in gaining insight into the transition from rural to urban. [Copyright &y& Elsevier]

Abstract: In this paper we propose a methodology consisting of specific computational intelligence methods, i.e. principal component analysis and artificial neural networks, in order to inter-compare air quality and meteorological data, and to forecast the concentration levels for environmental parameters of interest (air pollutants). We demonstrate these methods to data monitored in the urban areas of Thessaloniki and Helsinki in Greece and Finland, respectively. For this purpose, we applied the principal component analysis method in order to inter-compare the patterns of air pollution in the two selected cities. Then, we proceeded with the development of air quality forecasting models for both studied areas. On this basis, we formulated and employed a novel hybrid scheme in the selection process of input variables for the forecasting models, involving a combination of linear regression and artificial neural networks (multi-layer perceptron) models. The latter ones were used for the forecasting of the daily mean concentrations of PM10 and PM2.5 for the next day. Results demonstrated an index of agreement between measured and modelled daily averaged PM10 concentrations, between 0.80 and 0.85, while the kappa index for the forecasting of the daily averaged PM10 concentrations reached 60% for both cities. Compared with previous corresponding studies, these statistical parameters indicate an improved performance of air quality parameters forecasting. It was also found that the performance of the models for the forecasting of the daily mean concentrations of PM10 was not substantially different for both cities, despite the major differences of the two urban environments under consideration. [Copyright &y& Elsevier]

Abstract: Missing data are omnipresent in forestry research, and this poses problems in the analysis of primary data. Many statistical problems have been viewed as missing data problems. To cope with incomplete data, several methods are currently being used. They are all based on assumptions some of which might not be valid in a particular case. The choice mostly depends on the objective of the study. Considerable mensuration research is motivated by the need for yield projections that can support forest management decisions. This paper is focused on a new approach for filling gaps in diameter measurements on standing tree boles. Dealing with this problem, an attempt was made to examine the applicability of artificial neural network models for missing data estimation and to use the estimated values in the subsequent analysis. The procedure that should be followed in the development of such models is outlined. The results show good performance of the examined ANN models compared to regression treatments for missing data and ANN models demonstrate their adequacy and potential for filling gaps in diameter measurements on standing tree boles. The ANN models applied in this study are sufficiently general and have great potential to be applicable for estimating the missing values of many variables in environmental applications. [Copyright &y& Elsevier]

Abstract: Air pollution modelling is necessary for simulating the atmospheric environment system in terms of pollutants and meteorological conditions, taking into account the nonlinearities of the underlying phenomena. In the current paper, Artificial Neural Networks are used for modelling ozone, and for simulating its behaviour in relation to other atmospheric parameters of interest, for the city of Thessaloniki, Greece. This behaviour is also investigated with the aid of Principal Component Analysis (PCA). Results suggest the operational capabilities of such models, and the research potential in the application of computational intelligence methods for the environmental sector. [Copyright &y& Elsevier]

Due to the fact of water resource deterioration from human activities and increased demand over the last few decades, optimization of management practices and policies is required, for which more reliable data are necessary. Cost and time are always of importance; therefore, methods that can provide low-cost data in a short period of time have been developed. In this study, the ability of an artificial neural network (ANN) and a multiple linear regression (MLR) model to predict the electrical conductivity of groundwater samples in the GallikosRiver basin, northern Greece, was examined. A total of 233 samples were collected over the years 2004--2005 from 89 sampling points. Descriptive statistics, Pearson correlation matrix, and factor analysis were applied to select the inputs of the water quality parameters. Input data to the ANN and MLR were Ca, Mg, Na, and Cl. The best results regarding the ANN were provided by a model that included one hidden layer of three neurons. The mean absolute percentage error, modeling efficiency, and root mean square error were used to evaluate the performances of the methods and to compare the prediction capabilities of the ANN and MLR. We concluded that the ANN and MLR models were valid and had similar accuracy (using the same inputs) with a large number of samples, but in the case of a smaller data set, the MLR showed a better performance. [ABSTRACT FROM AUTHOR]

Assessing wine taste quality is a key factor for successful sales in the wine industry, where the aim is to meet consumer's demands. This is obtained by the analytic method of wine vinification. Evaluation of the wine's quality as determined by wine experts, according to sensor properties, plays an important role. This study introduces an alternative method for wine quality prediction by using machine learning techniques, such as linear regression and neural networks. The purpose is to make the evaluation process less expensive and less time-consuming at various stages of the production process. Our data analysis is based on a real wine dataset provided by an established winery in Greece. First of all, we study the correlation of quality with physicochemical features of wine considered at the winery. Statistical analysis indicates a significant interaction between the variables involved. We handle this problem by using Artificial Neural Networks(ANN). It is shown that ANN improves the accuracy of predicting wine quality based on the features selected. [ABSTRACT FROM AUTHOR]

• A model for estimating Life Cycle Cost of road tunnels. • A homogeneous database of 32 road tunnels, with a total length of 55 km. • Artificial Neural Networks are employed to estimate final costs. • Rapid cost pre-estimation of alternatives at early stages. • Development of tunnel operation & maintenance strategy. The estimation of road tunnel costs is crucial for motorway operators and transport infrastructure project managers. This paper presents a life cycle model for estimating costs in road tunnels. The research is based on a data set of 32 dual bore road tunnels, with a total length of 55 km, which are part of the Egnatia Odos Motorway in Northern Greece. The factors affecting civil engineering construction works and electromechanical installations are analyzed in great detail. Energy consumption and operation and maintenance costs are examined. Additionally, replacement costs are studied for an operation period of 75 years. Overall, Artificial Neural Networks are employed to estimate final costs in relation to tunnel design input parameters. The life cycle cost model uses depreciation and price escalation on all costs. It is concluded that the proposed framework can assist tunnel operators and asset managers in reliable costing of alternatives as well as developing operation and maintenance strategies. [ABSTRACT FROM AUTHOR]

The aim of this paper is the generation of a time-series based statistical data-driven procedure in order to track an outbreak. At first are used univariate time series models in order to predict the evolution of the reported cases. Moreover, are considered combinations of the models in order to provide more accurate and robust results. Additionally, statistical probability distributions are considered in order to generate future scenarios. Final step is the build and use of an epidemiological model (tSIR) and the calculation of an epidemiological ratio (R 0) for estimating the termination of the outbreak. The time series models include Exponential Smoothing and ARIMA approaches from the classical models, also Feed-Forward Artificial Neural Networks and Multivariate Adaptive Regression Splines from the machine learning toolbox. Combinations include simple mean, Newbolt-Granger and Bates-Granger approaches. Finally, the tSIR model and the R 0 ratio are used for estimating the spread and the reversion of the pandemic. The suggested procedure is used to track the COVID-19 epidemic in Greece. This epidemic has appeared in China in December 2019 and has been widespread since then to all over the world. Greece is the center of this empirical study as is considered an early successful paradigm of resistance against the virus. [ABSTRACT FROM AUTHOR]

This article presents information related to organization of the sixth international symposium on applied stochastic models and data analysis in Chania, Crete, Greece, during May 3-6, 1993. The symposium will include three kinds of contributions, invited papers, classical communications and problems relative to any confrontation of real life problems on the two mentioned topics and a number of proposed solutions. The symposium will be focused on the following fields, real life problems and theoretical results in data analysis and stochastic modelling, interactions between data analysis, applied stochastic models and artificial intelligence including neural networks, probabilistic and statistical computation, and forecasting.

The excavation of rock masses has a crucial importance for the safety and cost of construction of engineering projects. In this study, a flexible excavation assessment (EXCASS) system was developed with two components, the geological strength index (GSI) and the point load strength index (Is50). In order to develop the system, artificial neural network (ANN) analysis were performed using datasets from surface excavations (12 sites in Turkey and 61 sites in Greece reported by Tsiambaos and Saroglou (2010)). The EXCASS system in this study includes two parameters, namely the excavation power index (EPI) and the excavation performance rating (EPR) ranging between the value of 0 and 100. The optimum excavation power index (EPIopt) can be determined theoretically by using ( GSI 2 × Is 50 ) as an input when EPR is equal to 0, for the selection of the optimum excavation method. EPR is a rating which provides relative information on the ease or difficulty of the excavation method. Although the value of EPR varies between 0 and ± 100 in the EXCASS system, the use of the excavation method for "normally classes" is recommended in order to achieve costly and efficient excavation. The EXCASS system, on the other hand, has an ability to respond to possible technological developments by associating the excavation method with the EPI rating. [ABSTRACT FROM AUTHOR]

Water quality monitoring is an important component of water resources management. In order to predict two water quality variables, namely dissolved oxygen (DO; mg/L) and chlorophyll-a (Chl-a; µg/L) in the Small Prespa Lake in Greece, two standalone deep learning (DL) models, the long short-term memory (LSTM) and convolutional neural network (CNN) models, along with their hybrid, the CNN–LSTM model, were developed. The main novelty of this study was to build a coupled CNN–LSTM model to predict water quality variables. Two traditional machine learning models, support-vector regression (SVR) and decision tree (DT), were also developed to compare with the DL models. Time series of the physicochemical water quality variables, specifically pH, oxidation–reduction potential (ORP; mV), water temperature (°C), electrical conductivity (EC; µS/cm), DO and Chl-a, were obtained using a sensor at 15-min intervals from June 1, 2012 to May 31, 2013 for model development. Lag times of up to one (t − 1) and two (t − 2) for input variables pH, ORP, water temperature, and EC were used to predict DO and Chl-a concentrations, respectively. Each model's performance in both training and testing phases was assessed using statistical metrics including the correlation coefficient (r), root mean square error (RMSE), mean absolute error (MAE), their normalized equivalents (RRMSE, RMAE; %), percentage of bias (PBIAS), Nash–Sutcliffe coefficient ( E NS ), Willmott's Index, and graphical plots (Taylor diagram, box plot and spider diagram). Results showed that LSTM outperformed the CNN model for DO prediction, but the standalone DL models yielded similar performances for Chl-a prediction. Generally, the hybrid CNN–LSTM models outperformed the standalone models (LSTM, CNN, SVR and DT models) in predicting both DO and Chl-a. By integrating the LSTM and CNN models, the hybrid model successfully captured both the low and high levels of the water quality variables, particularly for the DO concentrations. [ABSTRACT FROM AUTHOR]

The on-demand content enrichment of an exhibition center visit is an active applied research domain. This work focuses on the exploitation of mobile devices as an efficient medium to deliver information related to an exhibit or an area within the exhibition center by utilizing machine learning approaches. We present YPOPSEI, an integrated system that formulates the information retrieval task as an image recognition mechanism, enabling visitors to simply capture an entity of interest in order to acquire information similar to a tour-guidance experience via their personal mobile devices. This scheme not only minimizes the additional infrastructure requirements, but additionally enhances the versatility in cases of exhibits topology alterations while still providing high accuracy in terms of image content recognition. Two hybrid approaches are developed that set Convolutional Neural Networks (CNNs) and Bags of VisualWords (BOVWs) to operate in a synergistic and cooperative manner. They are evaluated under real-world conditions on a client-server Web architecture system that experimentally operates within the premises of the Folklore Museum of Xanthi, Greece. [ABSTRACT FROM AUTHOR]

The main purpose of this study is to compare the performance of two statistical analysis models like weight of evidence and logistic regression (LR) with a soft computing model like artificial neural networks for landslide susceptibility assessment. These models were applied for the Selinous River drainage basin (northern Peloponnese, Greece) in order to map landslide susceptibility and rate the importance of landslide causal factors. A landslide inventory was prepared using satellite imagery interpretation and field surveys. Eight causal factors including altitude, slope angle, slope aspect, distance to road network, distance to drainage network, distance to tectonic elements, land cover, and lithology were considered. Model performance was tested with receiver operator characteristic analysis. The validation findings revealed that the three models show promising results since they give good accuracy values. However, the LR model proved to be relatively superior in estimating landslide susceptibility throughout the study area. [ABSTRACT FROM AUTHOR]

The main scope of this study is to compare the performance of a conventional statistical method like the landslide susceptibility index (LSI) and a soft computing method like artificial neural networks (ANNs). These models were applied in order to realistically map landslide susceptibility (LS) in the Krathis and Krios drainage basins in northern Peloponnesus. The relationship between landslides and various conditioning factors contributing to their occurrence was investigated through geographic information system-based analysis. A landslide inventory was realised using aerial-photos, satellite images and field surveys. Eight conditioning factors, including land cover, geology, elevation, slope, aspect, distance to road network, distance to drainage network, distance to structural elements, were considered. Subsequently, LS maps were produced using LSI and ANNs, and they were then compared and validated accordingly. Model performance was checked by an independent validation set of landslide events. For the validation process, the receiver operating curve was drawn and the area-under-the-curve (AUC) values were calculated. The calculated AUC values were 0.852 for the LSI model, and 0.842 for the ANNs; thus, both methods seem to lead to quite similar results. Based on these results, with an average percentage of correctly predicting landslides of about 84 %, model validation confirms that extrapolation results are very good, and that both models can be used to mitigate hazards related to landslides, and to aid in generalised land-use planning assessment purposes. [ABSTRACT FROM AUTHOR]

Lake Koronia is located in the North part of Greece and is protected by the Ramsar Convention of wetlands. A deficit in the water balance has been presented at the last twenty years due to the excessive water consumption for agricultural uses. This research is an attempt to simulate water flow with MIKE SHE model in order to observe how the water is allocated in the study area. The results of water flow module used for the estimation of Lake's water balance for 4 hydrological years (2008-2012). Furthermore the Artificial Neural Networks (ANNs) was used for the prediction of water flow in two sub-catchments. The coefficient correlation (R) was found for Bogdanas (0.9) and Kolxikos (0.86). The Root Mean Square Error (RMSE) and the Mean Absolute Percentages Error (MAPE) were also calculated in order to evaluate the quality of the ANNs results. [ABSTRACT FROM AUTHOR]

A landslide susceptibility analysis is performed through an artificial neural network (ANN) algorithm, in order to model the nonlinear relationship between landslide manifestation and geological and geomorphological parameters. The proposed methodology can be divided into two distinctive phases. In the first phase, the methodology introduces a specific distance metric, the Mahalanobis distance metric, to improve the selection of non-landslide records that 'enriches' the training database and provides the model with the necessary data during the training phase. In the second phase, the methodology develops a ANN model that was capable of minimizing the effect of over-fitting by monitoring in parallel the testing data during the training phase and terminating the process of learning when a certain acceptable criteria are achieved. The model was capable in identifying unstable areas, expressed by a landslide susceptibility index. The proposed methodology has been applied in the County of Xanthi, in the northern part of Greece, an area where a well-established landslide database existed. The landslide-related parameters that had been taken in account in the analysis were the following: lithology, distance from geological boundaries, distance from tectonic features, elevation, slope inclination, slope orientation, distance from hydrographic network and distance from road network. These parameters have been normalized and reclassified and used as input variables, while the description of a given area as landslide/non-landslide was assumed to be the output variable. The final outcome of the model was a geospatial product, which expressed the landslide susceptibility index and when compared with an up-to-date landslide inventory database showed satisfactory results. [ABSTRACT FROM AUTHOR]

In this work, artificial neural networks (ANNs) were developed and applied in order to forecast the discomfort levels due to the combination of high temperature and air humidity, during the hot season of the year, in eight different regions within the Greater Athens area (GAA), Greece. For the selection of the best type and architecture of ANNs-forecasting models, the multiple criteria analysis (MCA) technique was applied. Three different types of ANNs were developed and tested with the MCA method. Concretely, the multilayer perceptron, the generalized feed forward networks (GFFN), and the time-lag recurrent networks were developed and tested. Results showed that the best ANNs type performance was achieved by using the GFFN model for the prediction of discomfort levels due to high temperature and air humidity within GAA. For the evaluation of the constructed ANNs, appropriate statistical indices were used. The analysis proved that the forecasting ability of the developed ANNs models is very satisfactory at a significant statistical level of p < 0.01. [ABSTRACT FROM AUTHOR]

Artificial neural networks (ANNs) are addressed in order to assess the electric and magnetic field radiating by electrostatic discharges (ESDs). Actual input and output data collected from hundreds of measurements carried out in the High Voltage Laboratory of the National Technical University of Athens are used in the training, validation and testing process. The developed ANN method is coded in a comprehensive software tool to be used by laboratories involved in ESD tests, which either face a lack of suitable measuring equipment or want to compare their own measurements. The electromagnetic field produced by radiating ESDs, can be assessed very easily and accurately by simply measuring and providing to the tool the discharge current. The authors strongly believe that the proposed ANN software tool can be extremely useful for laboratories involved in ESD tests according to the current IEC Standard, as the forthcoming revised version of this standard will almost certainly include measurements of the radiating electromagnetic field during the verification of ESD generators. [ABSTRACT FROM AUTHOR]

Three layer cascade correlation artificial neural network (CCANN) models have been developed for the prediction of monthly values of some water quality parameters in rivers by using monthly values of other existing water quality parameters as input variables. The monthly data of some water quality parameters and discharge, for the time period 1980-1994, of Axios river, at a station near the Greek - FYROM borders and for the time period 1980-1990, of Strymon river, at a station near the Greek - Bulgarian borders, were selected for this study. The training of CCANN models was achieved by the cascade correlation algorithm which is a feed-forward and supervised algorithm. Kalman's learning rule was used to modify the artificial neural network weights. The choice of the input variables introduced to the input layer was based on the stepwise approach. The number of nodes in the hidden layer was determined based on the maximum value of the correlation coefficient. The final network architecture and geometry were tested to avoid over-fitting. The selected CCANN models gave very good results for both rivers and seem promising to be applicable for the estimation of missing monthly values of water quality parameters in rivers. [ABSTRACT FROM AUTHOR]

Normal lung function values are conventionally calculated according to prediction equations. The primary objective of this study is the development of a different method for the prediction of FVC and FEV 1 parameters, in order to achieve better correlation of the predicted values to the real ones. Using a sample from the Greek elderly population that was separated into two groups (a training and a testing one), a number of artificial neural networks were trained. Considering that men and women were studied separately and that two parameters (FVC, FEV 1 ) were the target of the study, four cases came up. In each case two neural networks were trained using different transfer functions, number of neurons and number of layers. When passing the inputs of the testing data set to the trained networks it was found that the outputs were well correlated with the corresponding measures of the sample. Furthermore, the match with the sample, for a number of neural networks developed, was better compared to the matches of Baltopoulos et al . study that used the same sample for developing prediction equations. This high match allows the potential use of neural networks for predicting not only FVC and FEV 1 but also other spirometric parameters. [ABSTRACT FROM AUTHOR]

The main objective of the present study is to introduce a novel predictive model that combines evolutionary algorithms and machine learning (ML) models, so as to construct a landslide susceptibility map. Genetic algorithms (GA) are used as a feature selection method, whereas the particle swarm optimization (PSO) method is used to optimize the structural parameters of two ML models, support vector machines (SVM) and artificial neural network (ANN). A well-defined spatial database, which included 335 landslides and twelve landslide-related variables (elevation, slope angle, slope aspect, curvature, plan curvature, profile curvature, topographic wetness index, stream power index, distance to faults, distance to river, lithology, and hydrological cover) are considered for the analysis, in the Achaia Regional Unit located in Northern Peloponnese, Greece. The outcome of the study illustrates that both ML models have an excellent performance, with the SVM model achieving the highest learning accuracy (0.977 area under the receiver operating characteristic curve value (AUC)), followed by the ANN model (0.969). However, the ANN model shows the highest prediction accuracy (0.800 AUC), followed by the SVM (0.750 AUC) model. Overall, the proposed ML models highlights the necessity of feature selection and tuning procedures via evolutionary optimization algorithms and that such approaches could be successfully used for landslide susceptibility mapping as an alternative investigation tool. [ABSTRACT FROM AUTHOR]

Land cover type classification still remains an active research topic while new sensors and methods become available. Applications such as environmental monitoring, natural resource management, and change detection require more accurate, detailed, and constantly updated land-cover type mapping. These needs are fulfilled by newer sensors with high spatial and spectral resolution along with modern data processing algorithms. Sentinel-2 sensor provides data with high spatial, spectral, and temporal resolution for the in classification of highly fragmented landscape. This study applies six traditional data classifiers and nine ensemble methods on multitemporal Sentinel-2 image datasets for identifying land cover types in the heterogeneous Mediterranean landscape of Lesvos Island, Greece. Support vector machine, random forest, artificial neural network, decision tree, linear discriminant analysis, and k-nearest neighbor classifiers are applied and compared with nine ensemble classifiers on the basis of different voting methods. kappa statistic, F1-score, and Matthews correlation coefficient metrics were used in the assembly of the voting methods. Support vector machine outperformed the base classifiers with kappa of 0.91. Support vector machine also outperformed the ensemble classifiers in an unseen dataset. Five voting methods performed better than the rest of the classifiers. A diversity study based on four different metrics revealed that an ensemble can be avoided if a base classifier shows an identifiable superiority. Therefore, ensemble approaches should include a careful selection of base-classifiers based on a diversity analysis. [ABSTRACT FROM AUTHOR]