Research activity in the field of air pollution forecasting using artificial neural networks (ANNs) has increased dramatically in recent years. However, the development of ANN models entails levels ...of uncertainty given the black-box nature of ANNs. In this paper, a protocol by Maier et al. (2010) for ANN model development is presented and applied to assess journal papers dealing with air pollution forecasting using ANN models. The majority of the reviewed works are aimed at the long-term forecasting of outdoor PM10, PM2.5, and oxides of nitrogen, and ozone. The vast majority of the identified works utilised meteorological and source emissions predictors almost exclusively. Furthermore, ad-hoc approaches are found to be predominantly used for determining optimal model predictors, appropriate data subsets and the optimal model structure. Multilayer perceptron and ensemble-type models are predominantly implemented. Overall, the findings highlight the need for developing systematic protocols for developing powerful ANN models.
•Research activity in ambient air pollution forecasting with ANNs continues to grow .•Forecasting of outdoor PM10, PM2.5, nitrogen oxides and ozone levels was widely done .•Feedforward and hybrid ANN model types were predominantly used .•Most of the identified model building steps were done in an ad-hoc manner .
In this brief, the output reachable estimation and safety verification problems for multilayer perceptron (MLP) neural networks are addressed. First, a conception called maximum sensitivity is ...introduced, and for a class of MLPs whose activation functions are monotonic functions, the maximum sensitivity can be computed via solving convex optimization problems. Then, using a simulation-based method, the output reachable set estimation problem for neural networks is formulated into a chain of optimization problems. Finally, an automated safety verification is developed based on the output reachable set estimation result. An application to the safety verification for a robotic arm model with two joints is presented to show the effectiveness of the proposed approaches.
Land cover (LC) and land use (LU) have commonly been classified separately from remotely sensed imagery, without considering the intrinsically hierarchical and nested relationships between them. In ...this paper, for the first time, a highly novel Joint Deep Learning framework is proposed and demonstrated for LC and LU classification. The proposed Joint Deep Learning (JDL) model incorporates a multilayer perceptron (MLP) and convolutional neural network (CNN), and is implemented via a Markov process involving iterative updating. In the JDL, LU classification conducted by the CNN is made conditional upon the LC probabilities predicted by the MLP. In turn, those LU probabilities together with the original imagery are re-used as inputs to the MLP to strengthen the spatial and spectral feature representations. This process of updating the MLP and CNN forms a joint distribution, where both LC and LU are classified simultaneously through iteration. The proposed JDL method provides a general framework within which the pixel-based MLP and the patch-based CNN provide mutually complementary information to each other, such that both are refined in the classification process through iteration. Given the well-known complexities associated with the classification of very fine spatial resolution (VFSR) imagery, the effectiveness of the proposed JDL was tested on aerial photography of two large urban and suburban areas in Great Britain (Southampton and Manchester). The JDL consistently demonstrated greatly increased accuracies with increasing iteration, not only for the LU classification, but for both the LC and LU classifications, achieving by far the greatest accuracies for each at around 10 iterations. The average overall classification accuracies were 90.18% for LC and 87.92% for LU for the two study sites, far higher than the initial accuracies and consistently outperforming benchmark comparators (three each for LC and LU classification). This research, thus, represents the first attempt to unify the remote sensing classification of LC (state; what is there?) and LU (function; what is going on there?), where previously each had been considered separately only. It, thus, has the potential to transform the way that LC and LU classification is undertaken in future. Moreover, it paves the way to address effectively the complex tasks of classifying LC and LU from VFSR remotely sensed imagery via joint reinforcement, and in an automatic manner.
•Joint Deep Learning (JDL) was first proposed for land cover and land use classification.•JDL incorporated patch-based CNN and pixel-based MLP with joint reinforcement and mutual complementarity.•The joint distributions between LC and LU were formulated into a Markov process through iterative updating.•Increased accuracies were achieved for both LC and LU in an automatic fashion with iteration.•The JDL framework is readily generalisable to hierarchical representations at multiple levels and scales.
Data-driven methods open up unprecedented possibilities for maritime surveillance using automatic identification system (AIS) data. In this work, we explore deep learning strategies using historical ...AIS observations to address the problem of predicting future vessel trajectories with a prediction horizon of several hours. We propose novel sequence-to-sequence vessel trajectory prediction models based on encoder–decoder recurrent neural networks (RNNs) that are trained on historical trajectory data to predict future trajectory samples given previous observations. The proposed architecture combines long short-term memory RNNs for sequence modeling to encode the observed data and generate future predictions with different intermediate aggregation layers to capture space-time dependencies in sequential data. Experimental results on vessel trajectories from an AIS dataset made freely available by the Danish Maritime Authority (DMA) show the effectiveness of deep learning methods for trajectory prediction based on sequence-to-sequence neural networks, which achieve better performance than baseline approaches based on linear regression or on the multilayer perceptron architecture. The comparative evaluation of results shows: first, the superiority of attention pooling over static pooling for the specific application, and second, the remarkable performance improvement that can be obtained with labeled trajectories, i.e., when predictions are conditioned on a low-level context representation encoded from the sequence of past observations, as well as on additional inputs (e.g., port of departure or arrival) about the vessel's high-level intention, which may be available from AIS.
Biomass gasification is a promising power generation process due to its ability to utilize waste materials and similar renewable energy sources. Predicting the outcomes of this process is a critical ...step to efficiently obtain the optimal amount of products. For this purpose, various kinetic and equilibrium models are proposed, but the assumptions made in these models significantly reduced their practical usability and consistency. More recently, machine learning methods have started been employed, but the limited selection of methods and lack of implementation of cross-validation techniques caused insufficiency to obtain unbiased performance evaluations. In this study, we employed four regression techniques, i.e., polynomial regression, support vector regression, decision tree regression and multilayer perceptron to predict CO, CO2, CH4, H2 and HHV outputs of the biomass gasification process. The data set is experimentally collected via downdraft fixed-bed gasifier. PCA technique is applied to the extracted features to prevent multicollinearity and to increase computational efficiency. Performances of the proposed regression methods are evaluated with k-fold cross validation. Multilayer perceptron and decision tree regression performed the best among other methods by achieving R2> 0.9 for the majority of outputs and were able to outperform other modeling approaches.
•Machine learning methods are used to predict the outcomes of biomass gasification.•Data set with 5237 samples is experimentally collected via downdraft gasifier.•PCA dimension reduction technique is applied to extracted features.•K-fold cross validation technique is utilized for performance evaluation.•DTR and MLP were able to outperform conventional modeling approaches.
Coronavirus disease (COVID-19) is an inflammation disease from a new virus. The disease causes respiratory ailment (like influenza) with manifestations, for example, cold, cough and fever, and in ...progressively serious cases, the problem in breathing. COVID-2019 has been perceived as a worldwide pandemic and a few examinations are being led utilizing different numerical models to anticipate the likely advancement of this pestilence. These numerical models dependent on different factors and investigations are dependent upon potential inclination. Here, we presented a model that could be useful to predict the spread of COVID-2019. We have performed linear regression, Multilayer perceptron and Vector autoregression method for desire on the COVID-19 Kaggle data to anticipate the epidemiological example of the ailment and pace of COVID-2019 cases in India. Anticipated the potential patterns of COVID-19 effects in India dependent on data gathered from Kaggle. With the common data about confirmed, death and recovered cases across India for over the time length helps in anticipating and estimating the not so distant future. For extra assessment or future perspective, case definition and data combination must be kept up persistently.
Summary
Different solar tracking variables have been employed to build intelligent solar tracking systems without considering the dominant and optimum ones. Thus, several low performance intelligent ...solar tracking systems have been designed and implemented due to the inappropriate combination of solar tracking variables and intelligent predictors to drive the solar trackers. This research aims to investigate and evaluate the most effective and dominant variables on dual‐ and single‐axis solar trackers and to find the appropriate combination of solar variables and intelligent predictors. The optimum variables will be found by using correlation results between different variables and both orientation and tilt angles. Then, to use the selected variables to develop different intelligent solar trackers. The results revealed that month, day, and time are the most effective variables for horizontal single‐axis and dual‐axis solar tracking systems. Using these variables in cascade multilayer perceptron (CMLP) and multilayer perceptron (MLP) produced high performance. These predictors could predict both orientation and tilt angles efficiently. It is found that day variable is very effective to increase the performance of solar trackers although day variable is neither correlated nor significant with both orientation and tilt angles. Linear regression predicted less than 70% of the given data in most cases, whereas nonlinear models could predict the optimum orientation and tilt angles. In single‐axis tracker, month, day, and time variables achieved prediction rates of 96.85% and 96.83% for three hidden layers of MLP and CMLP, respectively, whereas the MSE are 0.0025 and 0.0008, respectively. In dual‐axis solar tracker, MLP and CMLP predicted 96.68% and 97.98% respectively, with MSE of 0.0007 for both.
This research aims to investigate and evaluate the most effective and dominant variables on dual and horizontal single‐axis solar trackers and to find the appropriate combination of solar variables and intelligent predictors. The optimum variables will be found by using correlation results between different variables and both orientation and tilt angles. In single‐axis tracker, month, day, and time variables achieved predictions rates of 96.85% and 96.83% for three hidden layers of MLP and CMLP, respectively. In dual‐axis solar trackers, MLP and CMLP predicted 96.68% and 97.98% respectively.
Diabetes, also known as chronic illness, is a group of metabolic diseases due to a high level of sugar in the blood over a long period. The risk factor and severity of diabetes can be reduced ...significantly if the precise early prediction is possible. The robust and accurate prediction of diabetes is highly challenging due to the limited number of labeled data and also the presence of outliers (or missing values) in the diabetes datasets. In this literature, we are proposing a robust framework for diabetes prediction where the outlier rejection, filling the missing values, data standardization, feature selection, K-fold cross-validation, and different Machine Learning (ML) classifiers (k-nearest Neighbour, Decision Trees, Random Forest, AdaBoost, Naive Bayes, and XGBoost) and Multilayer Perceptron (MLP) were employed. The weighted ensembling of different ML models is also proposed, in this literature, to improve the prediction of diabetes where the weights are estimated from the corresponding Area Under ROC Curve (AUC) of the ML model. AUC is chosen as the performance metric, which is then maximized during hyperparameter tuning using the grid search technique. All the experiments, in this literature, were conducted under the same experimental conditions using the Pima Indian Diabetes Dataset. From all the extensive experiments, our proposed ensembling classifier is the best performing classifier with the sensitivity, specificity, false omission rate, diagnostic odds ratio, and AUC as 0.789, 0.934, 0.092, 66.234, and 0.950 respectively which outperforms the state-of-the-art results by 2.00 % in AUC. Our proposed framework for the diabetes prediction outperforms the other methods discussed in the article. It can also provide better results on the same dataset which can lead to better performance in diabetes prediction. Our source code for diabetes prediction is made publicly available.
•A new method has been proposed, known as MSCA, for global optimization.•The MSCA improves the SCA using a novel transition parameter and mutation operator.•A set of 33 benchmark problems is used to ...examine the MSCA.•The MSCA is also used to solve real-engineering problems and to train multilayer perceptron.•Comparisons illustrate the improvement in the performance of the MSCA.
Inspired by the mathematical characteristics of sine and cosine trigonometric functions, the Sine Cosine Algorithm (SCA) has shown competitive performance among other meta-heuristic algorithms. However, despite its sufficient global search ability, its low exploitation ability and immature balance between exploitation and exploration remain weaknesses. In order to improve Sine Cosine Algorithm (SCA), this paper presents a modified version of the SCA called MSCA. Firstly, a non-linear transition rule is introduced instead of a linear transition to provide comparatively better transition from the exploration to exploitation. Secondly, the classical search equation of the SCA is modified by introducing the leading guidance based on the elite candidate solution. When the above proposed modified search mechanism fails to provide a better solution, in addition, a mutation operator is used to generate a new position to avoid the situation of getting trapped in locally optimal solutions during the search. Thus, the MSCA effectively maximizes the advantages of proposed strategies in maintaining a comparatively better balance of exploration and exploitation as compared to the classical SCA. The validity of the MSCA is tested on a set of 33 benchmark optimization problems and employed for training multilayer perceptrons. The numerical results and comparisons among several algorithms show the enhanced search efficiency of the MSCA.
Most existing evolutionary search strategies are not so efficient when directly handling the decision space of large-scale multiobjective optimization problems (LMOPs). To enhance the efficiency of ...tackling LMOPs, this article proposes an accelerated evolutionary search (AES) strategy. Its main idea is to learn a gradient-descent-like direction vector (GDV) for each solution via the specially trained feedforward neural network, which may be the learnt possibly fastest convergent direction to reproduce new solutions efficiently. To be specific, a multilayer perceptron (MLP) with only one hidden layer is constructed, in which the number of neurons in the input and output layers is equal to the dimension of the decision space. Then, to get appropriate training data for the model, the current population is divided into two subsets based on the nondominated sorting, and each poor solution in one subset with worse convergence will be paired to an elitist solution in another subset with the minimum angle to it, which is considered most likely to guide it with rapid convergence. Next, this MLP is updated via backpropagation with gradient descent by using the above elaborately prepared dataset. Finally, an accelerated large-scale multiobjective evolutionary algorithm (ALMOEA) is designed by using AES as a reproduction operator. Experimental studies validate the effectiveness of the proposed AES when handling the search space of LMOPs with dimensionality ranging from 1000 to 10000. When compared with six state-of-the-art evolutionary algorithms, the experimental results also show the better efficiency and performance of the proposed optimizer in solving various LMOPs.