Atmospheric PM2.5 Prediction Using DeepAR Optimized by Sparrow Search Algorithm with Opposition-Based and Fitness-Based Learning

There is an important significance for human health in predicting atmospheric concentration precisely. However, due to the complexity and influence of contingency, atmospheric concentration prediction is a challenging topic. In this paper, we propose a novel hybrid learning method to make point and interval predictions of PM2.5 concentration simultaneously. Firstly, we optimize Sparrow Search Algorithm (SSA) by opposition-based learning, fitness-based learning, and Lévy flight. The experiments show that the improved Sparrow Search Algorithm (FOSSA) outperforms SSA-based algorithms. In addition, the improved Sparrow Search Algorithm (FOSSA) is employed to optimize the initial weights of probabilistic forecasting model with autoregressive recurrent network (DeepAR). Then, the FOSSA–DeepAR learning method is utilized to achieve the point prediction and interval prediction of PM2.5 concentration in Beijing, China. The performance of FOSSA–DeepAR is compared with other hybrid models and a single DeepAR model. Furthermore, hourly data of PM2.5 and O3 concentration in Taian of China, O3 concentration in Beijing, China are used to verify the effectiveness and robustness of the proposed FOSSA–DeepAR learning method. Finally, the empirical results illustrate that the proposed FOSSA–DeepAR learning model can achieve more efficient and accurate predictions in both interval and point prediction.

Download Full-text

Enhanced Reinforcement Learning Method Combining One-Hot Encoding-Based Vectors for CNN-Based Alternative High-Level Decisions

Applied Sciences ◽

10.3390/app11031291 ◽

2021 ◽

Vol 11 (3) ◽

pp. 1291

Author(s):

Bonwoo Gu ◽

Yunsick Sung

Keyword(s):

Reinforcement Learning ◽

Search Algorithm ◽

Classification Criteria ◽

Tree Search ◽

Learning Method ◽

Board Game ◽

Ancient China ◽

Monte Carlo Tree Search ◽

High Level ◽

Tree Search Algorithm

Gomoku is a two-player board game that originated in ancient China. There are various cases of developing Gomoku using artificial intelligence, such as a genetic algorithm and a tree search algorithm. Alpha-Gomoku, Gomoku AI built with Alpha-Go’s algorithm, defines all possible situations in the Gomoku board using Monte-Carlo tree search (MCTS), and minimizes the probability of learning other correct answers in the duplicated Gomoku board situation. However, in the tree search algorithm, the accuracy drops, because the classification criteria are manually set. In this paper, we propose an improved reinforcement learning-based high-level decision approach using convolutional neural networks (CNN). The proposed algorithm expresses each state as One-Hot Encoding based vectors and determines the state of the Gomoku board by combining the similar state of One-Hot Encoding based vectors. Thus, in a case where a stone that is determined by CNN has already been placed or cannot be placed, we suggest a method for selecting an alternative. We verify the proposed method of Gomoku AI in GuPyEngine, a Python-based 3D simulation platform.

Download Full-text

Trends in PM2.5 Concentration in Nagoya, Japan, from 2003 to 2018 and Impacts of PM2.5 Countermeasures

Atmosphere ◽

10.3390/atmos12050590 ◽

2021 ◽

Vol 12 (5) ◽

pp. 590

Author(s):

Makiko Yamagami ◽

Fumikazu Ikemori ◽

Hironori Nakashima ◽

Kunihiro Hisatsune ◽

Kayo Ueda ◽

...

Keyword(s):

Fine Particulate Matter ◽

Control Measures ◽

Source Control ◽

Atmospheric Concentration ◽

Construction Machinery ◽

Emission Regulations ◽

Volatile Organic ◽

Stationary Sources ◽

Pm2.5 Concentration

In Japan, various countermeasures have been undertaken to reduce the atmospheric concentration of fine particulate matter (PM2.5). We evaluated the extent to which these countermeasures were effective in reducing PM2.5 concentrations by analyzing the long-term concentration trends of the major components of PM2.5 and their emissions in Nagoya City. PM2.5 concentrations decreased by 53% over the 16-year period from fiscal years 2003 to 2018 in Nagoya City. Elemental carbon (EC) was the component of PM2.5 with the greatest decrease in concentration over the 16 years, decreasing by 4.3 μg/m3, followed by SO42− (3.0 μg/m3), organic carbon (OC) (2.0 μg/m3), NH4+ (1.6 μg/m3), and NO3− (1.3 μg/m3). The decrease in EC concentration was found to be caused largely by the effect of diesel emission control. OC concentrations decreased because of the effects of volatile organic compound (VOC) emission regulations for stationary sources and reductions in VOCs emitted by vehicles and construction machinery. NO3− concentrations decreased alongside decreased contributions from vehicles, construction machinery, and stationary sources, in descending order of the magnitude of decrease. Although these findings identify some source control measures that have been effective in reducing PM2.5, they also reveal the ineffectiveness of some recent countermeasures for various components, such as those targeting OC concentrations.

Download Full-text

An improved sparrow search algorithm based on levy flight and opposition-based learning

Assembly Automation ◽

10.1108/aa-09-2020-0134 ◽

2021 ◽

Vol ahead-of-print (ahead-of-print) ◽

Author(s):

Danni Chen ◽

JianDong Zhao ◽

Peng Huang ◽

Xiongna Deng ◽

Tingting Lu

Keyword(s):

Parameter Optimization ◽

Optimization Problem ◽

Heuristic Algorithms ◽

Search Algorithm ◽

Convergence Speed ◽

Support Vector ◽

Lévy Flight ◽

Levy Flight ◽

Content Type ◽

Opposition Based Learning

Purpose Sparrow search algorithm (SSA) is a novel global optimization method, but it is easy to fall into local optimization, which leads to its poor search accuracy and stability. The purpose of this study is to propose an improved SSA algorithm, called levy flight and opposition-based learning (LOSSA), based on LOSSA strategy. The LOSSA shows better search accuracy, faster convergence speed and stronger stability. Design/methodology/approach To further enhance the optimization performance of the algorithm, The Levy flight operation is introduced into the producers search process of the original SSA to enhance the ability of the algorithm to jump out of the local optimum. The opposition-based learning strategy generates better solutions for SSA, which is beneficial to accelerate the convergence speed of the algorithm. On the one hand, the performance of the LOSSA is evaluated by a set of numerical experiments based on classical benchmark functions. On the other hand, the hyper-parameter optimization problem of the Support Vector Machine (SVM) is also used to test the ability of LOSSA to solve practical problems. Findings First of all, the effectiveness of the two improved methods is verified by Wilcoxon signed rank test. Second, the statistical results of the numerical experiment show the significant improvement of the LOSSA compared with the original algorithm and other natural heuristic algorithms. Finally, the feasibility and effectiveness of the LOSSA in solving the hyper-parameter optimization problem of machine learning algorithms are demonstrated. Originality/value An improved SSA based on LOSSA is proposed in this paper. The experimental results show that the overall performance of the LOSSA is satisfactory. Compared with the SSA and other natural heuristic algorithms, the LOSSA shows better search accuracy, faster convergence speed and stronger stability. Moreover, the LOSSA also showed great optimization performance in the hyper-parameter optimization of the SVM model.

Download Full-text

Spatiotemporal Distribution of PM2.5 and O3 and Their Interaction During the Summer and Winter Seasons in Beijing, China

Sustainability ◽

10.3390/su10124519 ◽

2018 ◽

Vol 10 (12) ◽

pp. 4519 ◽

Cited By ~ 5

Author(s):

Hui Zhao ◽

Youfei Zheng ◽

Chen Li

Keyword(s):

Traffic Monitoring ◽

Diurnal Variations ◽

Quality Monitoring ◽

Air Quality Monitoring ◽

Spatiotemporal Variations ◽

Spatial Trend ◽

The North ◽

Northern Areas ◽

Beijing China ◽

Pm2.5 Concentration

This study analyzed the spatiotemporal variations in PM2.5 and O3, and explored their interaction in the summer and winter seasons in Beijing. To this aim, hourly PM2.5 and O3 data for 35 air quality monitoring sites were analyzed during the summer and winter of 2016. Results suggested that the highest PM2.5 concentration and the lowest O3 concentration were observed at traffic monitoring sites during the two seasons. A statistically significant (p < 0.05) different diurnal variation of PM2.5 was observed between the summer and winter seasons, with higher concentrations during daytime summer and nighttime winter. Diurnal variations of O3 concentrations during the two seasons showed a single peak, occurring at 16:00 and 15:00 in summer and winter, respectively. PM2.5 presented a spatial pattern with higher concentrations in southern Beijing than in northern areas, particularly evident during wintertime. On the contrary, O3 concentrations presented a decreasing spatial trend from the north to the south, particularly evident during summer. In addition, we found that PM2.5 concentrations were positively correlated (p < 0.01, r = 0.57) with O3 concentrations in summer, but negatively correlated (p < 0.01, r = −0.72) with O3 concentrations in winter.

Download Full-text

A Multi-Objective Optimization Dispatch Method for Microgrid Energy Management Considering the Power Loss of Converters

Energies ◽

10.3390/en12112160 ◽

2019 ◽

Vol 12 (11) ◽

pp. 2160 ◽

Cited By ~ 5

Author(s):

Xiaomin Wu ◽

Weihua Cao ◽

Dianhong Wang ◽

Min Ding

Keyword(s):

Power Loss ◽

Search Algorithm ◽

Gravitational Search Algorithm ◽

Inertial Mass ◽

Real Time Scheduling ◽

Opposition Based Learning ◽

Hybrid Particle Swarm Optimization ◽

Time Scheduling ◽

Benchmark Test Functions ◽

Energy Conversion Devices

With the spreading and applying of microgrids, the economic and environment friendly microgrid operations are required eagerly. For the dispatch of practical microgrids, power loss from energy conversion devices should be considered to improve the efficiency. This paper presents a two-stage dispatch (TSD) model based on the day-ahead scheduling and the real-time scheduling to optimize dispatch of microgrids. The power loss cost of conversion devices is considered as one of the optimization objectives in order to reduce the total cost of microgrid operations and improve the utility efficiency of renewable energy. A hybrid particle swarm optimization and opposition-based learning gravitational search algorithm (PSO-OGSA) is proposed to solve the optimization problem considering various constraints. Some improvements of PSO-OGSA, such as the distribution optimization of initial populations, the improved inertial mass update rule, and the acceleration mechanism combining the memory and community of PSO, have been integrated into the proposed approach to obtain the best solution for the optimization dispatch problem. The simulation results for several benchmark test functions and an actual test microgrid are employed to show the effectiveness and validity of the proposed model and algorithm.

Download Full-text