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.
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 .
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.
•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.
Accurate carbon price forecasting is of great significance for policy-makers and market participants. However, previous studies only focus on point-valued forecasting and ignore the importance of ...interval carbon price forecasting. In fact, interval-valued forecasting contains more information and can measure the uncertainty and variability of carbon price. Thus, to predict interval carbon price accurately, we propose a novel interval decomposition ensemble model based on multivariate variational mode decomposition (MVMD) and interval multilayer perceptron (iMLP) optimized by Jaya algorithm. Firstly, MVMD is used to decompose the original interval carbon price series into several sub-series. Secondly, iMLP optimized by Jaya algorithm is constructed to predict each sub-series of the above step. Finally, forecasting results of each sub-series are aggerated into the ultimate predictions of interval carbon price by linear addition. The interval carbon price data from two carbon markets in China are utilized to validate the effectiveness of the proposed model. Experimental results reveal that the proposed model outperforms all the benchmark models and the average values of the interval U of Theil statistics (UI) and the interval average relative variance (ARVI) in two datasets are 0.3003 and 0.0569, respectively. Overall, the proposed model can be used as an effective tool for future interval carbon price forecasting.
•Propose a novel model to predict interval carbon price: MVMD-Jaya-iMLP.•MVMD is applied to decompose the original interval carbon price.•Jaya algorithm is employed to optimize the initial weights and biases of iMLP.•MVMD improves the forecasting accuracy.•The proposed model outperforms other benchmark models.
Detection and isolation of single and mixed faults in a gearbox are very important to enhance the system reliability, lifetime, and service availability. This paper proposes a hybrid learning ...algorithm, consisting of multilayer perceptron (MLP)- and convolutional neural network (CNN)-based classifiers, for diagnosis of gearbox mixed faults. Domain knowledge features are required to train the MLP classifier, while the CNN classifier can learn features itself, allowing to reduce the required knowledge features for the counterpart. Vibration data from an experimental setup with gearbox mixed faults is used to validate the effectiveness of the algorithms and compare them with conventional methods. The comparative study shows that accuracies and robustness of the individual MLP and CNN algorithms are better than those of the compared methods and can be significantly improved using data fusion at the feature level. Furthermore, the robustness of the algorithm is secured under noises by combining the results of individual classifiers.
This paper proposes a new hybrid stochastic training algorithm using the recently proposed grasshopper optimization algorithm (GOA) for multilayer perceptrons (MLPs) neural networks. The GOA ...algorithm is an emerging technique with a high potential in tackling optimization problems based on its flexible and adaptive searching mechanisms. It can demonstrate a satisfactory performance by escaping from local optima and balancing the exploration and exploitation trends. The proposed GOAMLP model is then applied to five important datasets: breast cancer, parkinson, diabetes, coronary heart disease, and orthopedic patients. The results are deeply validated in comparison with eight recent and well-regarded algorithms qualitatively and quantitatively. It is shown and proved that the proposed stochastic training algorithm GOAMLP is substantially beneficial in improving the classification rate of MLPs.
PDF
