The rapid industrial development in the human society has brought about the air pollution, which seriously affects human health. PM2.5 concentration is one of the main factors causing the air pollution. To accurately predict PM2.5 microns, we propose a dendritic neuron model (DNM) trained by an improved state-of-matter heuristic algorithm (DSMS) based on STL-LOESS, namely DS-DNM. Firstly, DS-DNM adopts STL-LOESS for the data preprocessing to obtain three characteristic quantities from original data: seasonal, trend, and residual components. Then, DNM trained by DSMS predicts the residual values. Finally, three sets of feature quantities are summed to obtain the predicted values. In the performance test experiments, five real-world PM2.5 concentration data are used to test DS-DNM. On the other hand, four training algorithms and seven prediction models were selected for comparison to verify the rationality of the training algorithms and the accuracy of the prediction models, respectively. The experimental results show that DS-DNM has the more competitive performance in PM2.5 concentration prediction problem.

For large-scale multiobjective evolutionary algorithms based on the grouping of decision variables, the challenge is to design a stable grouping strategy to balance convergence and population diversity. This paper proposes a large-scale multiobjective optimization algorithm with two alternative optimization methods (LSMOEA-TM). In LSMOEA-TM, two alternative optimization methods, which adopt two grouping strategies to divide decision variables, are introduced to efficiently solve large-scale multiobjective optimization problems. Furthermore, this paper introduces a Bayesian-based parameter-adjusting strategy to reduce computational costs by optimizing the parameters in the proposed two alternative optimization methods. The proposed LSMOEA-TM and four efficient large-scale multiobjective evolutionary algorithms have been tested on a set of benchmark large-scale multiobjective problems, and the statistical results demonstrate the effectiveness of the proposed algorithm.

In a complex agricultural region, determine the appropriate crop for each plot of land to maximize the expected total profit is the key problem in cultivation management. However, many factors such as cost, yield, and selling price are typically uncertain, which causes an exact programming method impractical. In this paper, we present a problem of crop cultivation planning, where the uncertain factors are estimated as fuzzy parameters. We adapt an efficient evolutionary algorithm, water wave optimization (WWO), to solve this problem, where each solution is evaluated based on three metrics including the expected, optimistic and pessimistic values, the combination of which enables the algorithm to search credible solutions under uncertain conditions. Test results on a set of agricultural regions in East China showed that the solutions of our fuzzy optimization approach obtained significantly higher profits than those of non-fuzzy optimization methods based on only the expected values.

The COVID-19 pandemic has caused a global alarm. With the advances in artificial intelligence, the COVID-19 testing capabilities have been greatly expanded, and hospital resources are significantly alleviated. Over the past years, computer vision researches have focused on convolutional neural networks (CNNs), which can significantly improve image analysis ability. However, CNN architectures are usually manually designed with rich expertise that is scarce in practice. Evolutionary algorithms (EAs) can automatically search for the proper CNN architectures and voluntarily optimize the related hyperparameters. The networks searched by EAs can be used to effectively process COVID-19 computed tomography images without expert knowledge and manual setup. In this paper, we propose a novel EA-based algorithm with a dynamic searching space to design the optimal CNN architectures for diagnosing COVID-19 before the pathogenic test. The experiments are performed on the COVID-CT data set against a series of state-of-the-art CNN models. The experiments demonstrate that the architecture searched by the proposed EA-based algorithm achieves the best performance yet without any preprocessing operations. Furthermore, we found through experimentation that the intensive use of batch normalization may deteriorate the performance. This contrasts with the common sense approach of manually designing CNN architectures and will help the related experts in handcrafting CNN models to achieve the best performance without any preprocessing operations.

In this paper, we focus on the bandlimited graph signal sampling problem. To sample graph signals, we need to find small-sized subset of nodes with the minimal optimal reconstruction error. We formulate this problem as a subset selection problem, and propose an efficient Pareto Optimization for Graph Signal Sampling (POGSS) algorithm. Since the evaluation of the objective function is very time-consuming, a novel acceleration algorithm is proposed in this paper as well, which accelerates the evaluation of any solution. Theoretical analysis shows that POGSS finds the desired solution in quadratic time while guaranteeing nearly the best known approximation bound. Empirical studies on both Erdos-Renyi graphs and Gaussian graphs demonstrate that our method outperforms the state-of-the-art greedy algorithms.

There has been substantial growth in research on the robot automation, which aims to make robots capable of directly interacting with the world or human. Robot learning for automation from human demonstration is central to such situation. However, the dependence of demonstration restricts robot to a fixed scenario, without the ability to explore in variant situations to accomplish the same task as in demonstration. Deep reinforcement learning methods may be a good method to make robot learning beyond human demonstration and fulfilling the task in unknown situations. The exploration is the core of such generalization to different environments. While the exploration in reinforcement learning may be ineffective and suffer from the problem of low sample efficiency. In this paper, we present Evolutionary Policy Gradient (EPG) to make robot learn from demonstration and perform goal oriented exploration efficiently. Through goal oriented exploration, our method can generalize robot learned skill to environments with different parameters. Our Evolutionary Policy Gradient combines parameter perturbation with policy gradient method in the framework of Evolutionary Algorithms (EAs) and can fuse the benefits of both, achieving effective and efficient exploration. With demonstration guiding the evolutionary process, robot can accelerate the goal oriented exploration to generalize its capability to variant scenarios. The experiments, carried out in robot control tasks in OpenAI Gym with dense and sparse rewards, show that our EPG is able to provide competitive performance over the original policy gradient methods and EAs. In the manipulator task, our robot can learn to open the door with vision in environments which are different from where the demonstrations are provided.

The quality of solution sets generated by decomposition-based evolutionary multi-objective optimisation (EMO) algorithms depends heavily on the consistency between a given problem\'s Pareto front shape and the specified weights\' distribution. A set of weights distributed uniformly in a simplex often leads to a set of well-distributed solutions on a Pareto front with a simplex-like shape, but may fail on other Pareto front shapes. It is an open problem on how to specify a set of appropriate weights without the information of the problem\'s Pareto front beforehand. In this article, we propose an approach to adapt weights during the evolutionary process (called AdaW). AdaW progressively seeks a suitable distribution of weights for the given problem by elaborating several key parts in weight adaptation-weight generation, weight addition, weight deletion, and weight update frequency. Experimental results have shown the effectiveness of the proposed approach. AdaW works well for Pareto fronts with very different shapes: 1) the simplex-like, 2) the inverted simplex-like, 3) the highly nonlinear, 4) the disconnect, 5) the degenerate, 6) the scaled, and 7) the high-dimensional.

BACKGROUND: There is an urgent need for developing objective, effective and convenient measurements to help clinicians accurately identify bradykinesia. The purpose of this study is to evaluate the accuracy of an objective approach assessing bradykinesia in finger tapping (FT) that uses evolutionary algorithms (EAs) and explore whether it can be used to identify early stage Parkinson\'s disease (PD).
METHODS: One hundred and seven PD, 41 essential tremor (ET) patients and 49 normal controls (NC) were recruited. Participants performed a standard FT task with two electromagnetic tracking sensors attached to the thumb and index finger. Readings from the sensors were transmitted to a tablet computer and subsequently analyzed by using EAs. The output from the device (referred to as \"PD-Monitor\") scaled from - 1 to + 1 (where higher scores indicate greater severity of bradykinesia). Meanwhile, the bradykinesia was rated clinically using the Movement Disorder Society-Sponsored Revision of the Unified Parkinson\'s Disease Rating Scale (MDS-UPDRS) FT item.
RESULTS: With an increasing MDS-UPDRS FT score, the PD-Monitor score from the same hand side increased correspondingly. PD-Monitor score correlated well with MDS-UPDRS FT score (right side: r = 0.819, P = 0.000; left side: r = 0.783, P = 0.000). Moreover, PD-Monitor scores in 97 PD patients with MDS-UPDRS FT bradykinesia and each PD subgroup (FT bradykinesia scored from 1 to 3) were all higher than that in NC. Receiver operating characteristic (ROC) curves revealed that PD-Monitor FT scores could detect different severity of bradykinesia with high accuracy (≥89.7%) in the right dominant hand. Furthermore, PD-Monitor scores could discriminate early stage PD from NC, with area under the ROC curve greater than or equal to 0.899. Additionally, ET without bradykinesia could be differentiated from PD by PD-Monitor scores. A positive correlation of PD-Monitor scores with modified Hoehn and Yahr stage was found in the left hand sides.
CONCLUSIONS: Our study demonstrated that a simple to use device employing classifiers derived from EAs could not only be used to accurately measure different severity of bradykinesia in PD, but also had the potential to differentiate early stage PD from normality.

A wealth of research on resting-state functional MRI (R-fMRI) data has revealed modularity as a fundamental characteristic of the human brain functional network. The modular structure has recently been suggested to be overlapping, meaning that a brain region may engage in multiple modules. However, not only the overlapping modular structure remains inconclusive, the topological features and functional roles of overlapping regions are also poorly understood. To address these issues, the present work utilized the maximal-clique based multiobjective evolutionary algorithm to explore the overlapping modular structure of the R-fMRI data obtained from 57 young healthy adults. Without prior knowledge, brain regions were optimally grouped into eight modules with wide overlap. Based on the topological features captured by graph theory analyses, overlapping regions were classified into an integrated club and a dominant minority club through clustering. Functional flexibility analysis found that overlapping regions in both clubs were significantly more flexible than non-overlapping ones. Lesion simulations revealed that targeted attack at overlapping regions were more damaging than random failure or even targeted attack at hub regions. In particular, overlapping regions in the dominant minority club were more flexible and more crucial for information communication than the others were. Together, our findings demonstrated the highly organized overlapping modular architecture and revealed the importance as well as complexity of overlapping regions from both topological and functional aspects, which provides important implications for their roles in executing multiple tasks and maintaining information communication.

Increased nutrient loads and changed nutrient ratios in estuarine waters have enhanced the occurrence of eutrophication and harmful algae blooms. Most of these consequences are caused by the new proliferation of toxin-producing non-siliceous algae. In this study, we propose a multi-objective reservoir operation model based on 10-day time scale for estuarine eutrophication control to reduce the potential non-siliceous algae outbreak. This model takes the hydropower generation and social economy water requirement in reservoir into consideration, minimizing the ICEP (indicator of estuarine eutrophication potential) as an ecological objective. Three modern multi-objective evolutionary algorithms (MOEAs) are applied to solve the proposed reservoir operation model. The Three Gorges Reservoir and its operation effects on the Yangtze Estuary were chosen as a case study. The performances of these three algorithms were evaluated through a diagnostic assessment framework of modern MOEAs\' abilities. The results showed that the multi-objective evolutionary algorithm based on decomposition with differential evolution operator (MOEA/D-DE) achieved the best performance for the operation model. It indicates that single implementation of hydrological management cannot make effective control of potential estuarine eutrophication, while combined in-estuary TP concentration control and reservoir optimal operation is a more realistic, crucial and effective strategy for controlling eutrophication potential of non-siliceous algae proliferation. Under optimized operation with controlled TP concentration and estuarine water withdrawal of 1470 m3/s, ecological satiety rate for estuarine drinking water source increased to 77.78%, 88.89% and 83.33% for wet, normal and dry years, the corresponding values in practical operation were only 72.22%, 58.33% and 55.56%, respectively. The results suggest that these operations will not negatively affect the economic and social interests. Therefore, the proposed integrated management approaches can provide guidance for water managers to reach a stable trophic control of estuarine waters.