Deep forest regression based on cross-layer full connection

Polychlorinated dibenzo-p-dioxins and polychlorinated dibenzofurans (PCDD/Fs) prediction model based on limited peat samples using an evolved artificial neural network

Polychlorinated dibenzo-p-dioxins and polychlorinated dibenzofurans (PCDD/Fs) are involuntary by-products of incomplete combustion and are highly toxic to humans and the environment. The Malaysian peat is often acidic or extremely acidic having high levels of chlorine and/or other organic acids that act as catalysts or precursors in PCDD/Fs formation. This study aims to predict PCDD/Fs emissions in peat soil using an artificial neural network (ANN) approach based on limited emission data and selected physico-chemical properties. The ANN's prediction performance is affected by uncertainties in its initial connection weights. To improve prediction performance, an optimisation algorithm, termed differential evolution (DE), is used to optimise the ANN's initial connection weights and bias. The study adopts several ANNs with fixed architecture to predict PCDD/Fs emissions, each consisting of a multilayer perceptron (MLP) with a backpropagation algorithm. Eight input variables and one output variable were adopted to train and test various neural network architectures using real-world datasets. The model optimisation procedure was conducted to ascertain the network architecture with the best predictive accuracy. The evolved ANN based on 5 hidden neurons, with the assistance of self-adaptive ensemble-based differential evolution with enhanced population sizing (SAEDE-EP), successfully produced the lowest MSEtest (6.1790 × 10-3) and highest R2 (0.97447) based on the mean among the other HNs. An evolutionary-optimised ANN-based methodology is a viable solution to predict PCDD/Fs in peat soil. It is cost-effective for pollution control, environmental monitoring and capable of aiding authorities prevent PCDD/Fs exposure, e.g., during a fire.

Dioxin emission modeling using feature selection and simplified DFR with residual error fitting for the grate-based MSWI process

Municipal solid waste incineration (MSWI) with grate technology is a widely applied waste-to-energy process in various cities in China. Meanwhile, dioxins (DXN) are emitted at the stack and are the critical environmental indicator for operation optimization control in the MSWI process. However, constructing a high-precision and fast emission model for DXN emission operation optimization control becomes an immediate difficulty. To address the above problem, this research utilizes a novel DXN emission measurement method using simplified deep forest regression (DFR) with residual error fitting (SDFR-ref). First, the high-dimensional process variables are optimally reduced following the mutual information and significance test. Then, a simplified DFR algorithm is established to infer or predict the nonlinearity between the selected process variables and the DXN emission concentration. Moreover, a gradient enhancement strategy in terms of residual error fitting with a step factor is designed to improve the measurement performance in the layer-by-layer learning process. Finally, an actual DXN dataset from 2009 to 2020 of the MSWI plant in Beijing is utilized to verify the SDFR-ref method. Comparison experiments demonstrate the superiority of the proposed method over other methods in terms of measurement accuracy and time consumption.

Deflection Prediction of Rehabilitation Asphalt Pavements through Deep Forest

The deep forest is a powerful deep-learning algorithm that has been applied in certain fields. In this study, a deep forest (DF) model was developed to predict the central deflection measured by a falling weight deflectometer (FWD). In total, 11,075 samples containing information related to pavement structure, traffic conditions, and weather conditions were extracted from the LTPP dataset. The performance of the DF model with custom backend settings was compared with that of models random forest (RF), multilayer perceptron (MLP), and DF built on the sklearn backend. All four deep-learning algorithms could identify the complex relationship between central deflection and relevant feature variables with high accuracy and stability. The learning and generalization abilities of DF was stronger than those of MLP and RF. The predictive performance and computation time of DF (custom) were better than those of DF (sklearn), indicating that the custom model was superior to the highly encapsulated model with sklearn as the backend. Feature importance analysis indicated that the drop load of FWD was the key factor influencing deflection. In addition, structural number, annual precipitation, and annual kilo equivalent standard axle load (kESAL) are very important features related with deflection. The feature importance of rehabilitation improvement thickness was less than the drop load, climatic factors, kESAL, structural number, and layer thickness.

Application of Deep Learning Model in the Avoidance of Investment Risk of Multinational Enterprises

With the continuous improvement and development of the socialist market economic system, China's economic development has full momentum, but the domestic market is no longer sufficient to meet the needs of enterprise development. China has always focused on peaceful diplomacy, and the world market has a strong demand for Chinese products. This work aims to improve the accuracy of exchange rate forecasting. The risk factors that may be encountered in the investment process of multinational enterprises can be effectively avoided. Combining the advantages of Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN), the LSTM-CNN (Long Short-Term Memory-Convolutional Neural Network) model is proposed to predict the volatility trend of stocks. Firstly, the investment risk of multinational enterprises is analyzed, and, secondly, the principles of the used CNN and LSTM are expounded. Finally, the performance of the proposed model is verified by setting experiments. The experimental results demonstrate that when predicting the 10 selected stocks, the proposed LSTM-CNN model has the highest accuracy in predicting the volatility of stocks, with an average accuracy of 60.1%, while the average accuracy of the rest of the models is all below 60%. It can be found that the stock category does not have a great impact on the prediction accuracy of the model. The average prediction accuracy of the CNN model is 0.578, which is lower than that of the Convolutional Neural Network-Relevance model, and the prediction accuracy of the LSTM model is 0.592, which is better than that of the Long Short-Term Memory-Relevance model. The designed model can be used to predict the stock market to guide investors to make effective investments and reduce investment risks based on relevant cases. The research makes a certain contribution to improving the company's income and stabilizing the national economic development.

Dioxin emission prediction based on improved deep forest regression for municipal solid waste incineration process

Dioxin (DXN) emission concentration is an important environmental indicator in the municipal solid waste incineration (MSWI) process. The prediction model of DXN emission can be used for pollution control to realize actual requirements of operation optimization. Therefore, a DXN emission concentration prediction model based on improved deep forest regression (ImDFR) is proposed in this study. A feature reduction layer based on out-of-bagging error is first introduced into the ImDFR to eliminate redundant variables and feed all confidence information on DXN emission into the feature enhancement layer of the MSWI process. A deep ensemble stacking model is subsequently built to depict deep features and increase diversity and accuracy using random forests, completely random forests, GBDT, and XGBoost as subforests. Finally, the predicted value of the DXN prediction model is determined in the decision layer. The DXN emission prediction model is verified using actual historical data of two incinerators operated with a daily processing capacity of 800 tons. The experimental results showed that the proposed prediction model presents higher accuracy and better generalization ability than state-of-the-art models.