Search

Emerging contaminants (ECs), which are present in water bodies, could cause global environmental and human health problems. These contaminants originate from various sources such as hospitals, clinics, households, and industries. Additionally, they can also indirectly enter the water supply through runoff from agriculture and leachate from landfills. ECs, specifically Pharmaceutical and personal care products (PPCPs), are causing widespread concern due to their contribution to persistent water pollution. Traditional approaches often involve expensive chemicals and energy or result in the creation of by-products. This study developed a practical and environmentally-friendly method for removing PPCPs, which involved combining and integrating various techniques. To implement this method, it was necessary to establish and used a field simulator based on the real-life scenario. Based on the data analysis, the average removal rates of COD, TP, TN, and NH 4 +-N were 57%, 59%, 63%, and 73%, respectively. the removal rate of PPCPs by CCWs was found to be 82.7% after comparing samples that were not treated by constructed wetlands and those that were treated. Combined constructed wetlands (CCWs) were found to effectively remove PPCPs from water. This is due to the combined action of plant absorption, absorption, and biodegradation by microorganisms living in the wetlands. Interestingly, the wetland plant reed had been shown to play an important role in removing these pollutants. Microbial degradation was the most important pathway for PPCPs removal in CCWs. Carbamazepine was selected as a typical PPCP for analysis. In addition, the microbial community structure of the composite filler was also investigated. High-throughput sequencing confirmed that the dominant bacteria had good adaptability to PPCPs. This technique not only reduced the potential environmental impact but also served as a foundation for further research on the use of constructed wetlands for the treatment of PPCPs contaminated water bodies and its large-scale implementation. [Display omitted] • CWs were a promising method for PPCPs removal. • Integrated/combined technologies could effectively remove PPCPs from wastewater. • CCWs demonstrated medium-high efficiency in removing various PPCPs. • Mechanism of PPCPs degradation by CCWs. • Reeds played an active role in eliminating PPCPs. [ABSTRACT FROM AUTHOR]

• Three variants of Ensemble Deep Random Vector Functional Link network are proposed. • Batch normalization is introduced to the edRVFL network to re-normalize the hidden features. • Weighting and pruning methods are employed to improve the classification ability. • No re-training of previous layers is required for these networks when adding one more hidden layer. • Our best method outperforms other 13 classifiers on 24 datasets. In this paper, we first integrate normalization to the Ensemble Deep Random Vector Functional Link network (edRVFL). This re-normalization step can help the network avoid divergence of the hidden features. Then, we propose novel variants of the edRVFL network. Weighted edRVFL (WedRVFL) uses weighting methods to give training samples different weights in different layers according to how the samples were classified confidently in the previous layer thereby increasing the ensemble's diversity and accuracy. Furthermore, a pruning-based edRVFL (PedRVFL) has also been proposed. We prune some inferior neurons based on their importance for classification before generating the next hidden layer. Through this method, we ensure that the randomly generated inferior features will not propagate to deeper layers. Subsequently, the combination of weighting and pruning, called Weighting and Pruning based Ensemble Deep Random Vector Functional Link Network (WPedRVFL), is proposed. We compare their performances with other state-of-the-art classification methods on 24 tabular UCI classification datasets. The experimental results illustrate the superior performance of our proposed methods. [ABSTRACT FROM AUTHOR]

Randomized neural networks have become more and more attractive recently since they use closed-form solutions for parameter training instead of gradient-based approaches. Among them, the random vector functional link network (RVFL) and its deeper version ensemble deep random vector functional link network (edRVFL) show great performance on both classification and regression tasks. However, the previous research on these two models mainly focuses on the supervised learning area. Although there have been efforts to extend the RVFL network to solve semi-supervised learning problems, the potential of the edRVFL network has not been fully investigated. Therefore, we propose a jointly optimized learning strategy for the edRVFL network (JOSedRVFL) for semi-supervised learning tasks in this paper. The JOSedRVFL network uses an iterative procedure to compute the output weights and consequently predicts the class labels of the unlabeled training data during the training process. In addition, we propose another semi-supervised edRVFL network (SS-edRVFL) using manifold regularization in this work. We then do a brief comparison between these two methods to illustrate their similarities and differences. In the experimental part, we conduct the first set of experiments using the UCI datasets to compare the performance of our proposed semi-supervised algorithms against 11 other classifiers to demonstrate the superior performance of the SS-edRVFL and JOSedRVFL networks. JOSedRVFL achieves the highest accuracy on all 4 datasets while SS-edRVFL takes the second place 3 times which is only worse than JOSedRVFL. Moreover, we apply the proposed methods to real-world applications using the electroencephalography-based emotion recognition dataset to compare the performance of RVFL-based methods (RVFL, SS-RVFL, and JOSRVFL) and their edRVFL counterparts (edRVFL, SS-edRVFL, and JOSedRVFL). Results from this test revealed that the edRVFL-based models (edRVFL, SS-edRVFL, and JOSedRVFL) can obtain higher accuracy than the RVFL-based versions (RVFL, SS-RVFL, and JOSRVFL) with the same learning framework on 45 real-world semi-supervised benchmarks. We then perform the Wilcoxon signed-rank test to show that JOSedRVFL is significantly better than 5 other competitors, which supports our claim that JOSedRVFL can be treated as a superior classifier for semi-supervised classification on both benchmark datasets and real-world applications. • We extend the shallow semi-supervised RVFL network to its deep version. • A joint optimization framework for semi-supervised learning using ensemble deep RVFL is proposed. • We perform experiments on both UCI and real-world EEG datasets. • Our proposed JOSedRVFL and SS-edRVFL outperform JOSRVFL and JOSELM. [ABSTRACT FROM AUTHOR]

• Inspired by the principles of Random Vector Functional Link (RVFL) network, we propose a deep RVFL network (dRVFL) with rich feature extraction capabilities through several hidden layers. • We also propose an ensemble deep network (edRVFL) based on a single dRVFL network. • We demonstrate the generic nature of the proposed methods by integrating them with a recent RVFL variant called sparse-pretrained RVFL (SP-RVFL). • Experiments on 46 tabular UCI classification datasets demonstrate that the proposed ensemble deep RVFL networks outperform state-of-the-art deep feed-forward neural networks. • Experiments on 12 sparse classification datasets demonstrate that the proposed ensemble deep SP-RVFL networks outperform the best. In this paper, we propose deep learning frameworks based on the randomized neural network. Inspired by the principles of Random Vector Functional Link (RVFL) network, we present a deep RVFL network (dRVFL) with stacked layers. The parameters of the hidden layers of the dRVFL are randomly generated within a suitable range and kept fixed while the output weights are computed using the closed-form solution as in a standard RVFL network. We also propose an ensemble deep network (edRVFL) that can be regarded as a marriage of ensemble learning with deep learning. Unlike traditional ensembling approaches that require training several models independently from scratch, edRVFL is obtained by training a single dRVFL network once. Both dRVFL and edRVFL frameworks are generic and can be used with any RVFL variant. To illustrate this, we integrate the deep learning RVFL networks with a recently proposed sparse pre-trained RVFL (SP-RVFL). Experiments on 46 tabular UCI classification datasets and 12 sparse datasets demonstrate that the proposed deep RVFL networks outperform state-of-the-art deep feed-forward neural networks (FNNs). [ABSTRACT FROM AUTHOR]

A constructed wetland (CW)-coupled microbial fuel cell (MFC) system was constructed to treat wastewater and generate electricity. The total phosphorus in the simulated domestic sewage was used as the treatment target, and the optimal phosphorus removal effect and electricity generation were determined by comparing the changes in substrates, hydraulic retention times, and microorganisms. The mechanism underlying phosphorus removal was also analyzed. By using magnesia and garnet as substrates, the best removal efficiencies of two CW-MFC systems reached 80.3% and 92.4%. Phosphorus removal by the garnet matrix mainly depends on a complex adsorption process, whereas the magnesia system relies on ion exchange reactions. The maximum output voltage and stabilization voltage of the garnet system were higher than those of the magnesia system. Microorganisms in the wetland sediments and electrode also changed considerably. It indicates that the mechanism of phosphorus removal by the substrate in the CW-MFC system is adsorption and chemical reaction between ions to generate precipitation. The population structure of proteobacteria and other microorganisms has an impact on both power generation and phosphorus removal. Combining the advantages of constructed wetlands and microbial fuel cells also improved phosphorus removal in coupled system. Therefore, when studying a CW-MFC system, the selection of electrode materials, matrix, and system structure should be taken into account to find a method that will improve the power generation capacity of the system and remove phosphorus. [ABSTRACT FROM AUTHOR]