Search

Accurate forecasting of PM2.5 concentrations serves as a critical tool for mitigating air pollution. This study introduces a novel hybrid prediction model, termed MIC-CEEMDAN-CNN-BiGRU, for short-term forecasting of PM2.5 concentrations using a 24-hour historical data window. Utilizing the Maximal Information Coefficient (MIC) for feature selection, the model integrates Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN), Convolutional Neural Network (CNN), and Bidirectional Recurrent Gated Neural Network (BiGRU) to optimize predictive accuracy. We used 2016 PM2.5 monitoring data from Beijing, China as the empirical basis of this study and compared the model with several deep learning frameworks. RNN, LSTM, GRU, and other hybrid models based on GRU, respectively. The experimental results show that the prediction results of the hybrid model proposed in this question are more accurate than those of other models, and the R2 of the hybrid model proposed in this paper improves the R2 by nearly 5 percentage points compared with that of the single model; reduces the MAE by nearly 5 percentage points; and reduces the RMSE by nearly 11 percentage points. The results show that the hybrid prediction model proposed in this study is more accurate than other models in predicting PM2.5. [ABSTRACT FROM AUTHOR]

Understanding air quality requires a comprehensive understanding of its various factors. Most of the association rule techniques focuses on high frequency terms, ignoring the potential importance of low- frequency terms and causing unnecessary storage space waste. Therefore, a dynamic genetic association rule mining algorithm is proposed in this paper, which combines the improved dynamic genetic algorithm with the association rule mining algorithm to realize the importance mining of low- frequency terms. Firstly, in the chromosome coding phase of genetic algorithm, an innovative multi-information coding strategy is proposed, which selectively stores similar values of different levels in one storage unit. It avoids storing all the values at once and facilitates efficient mining of valid rules later. Secondly, by weighting the evaluation indicators such as support, confidence and promotion in association rule mining, a new evaluation index is formed, avoiding the need to set a minimum threshold for high-interest rules. Finally, in order to improve the mining performance of the rules, the dynamic crossover rate and mutation rate are set to improve the search efficiency of the algorithm. In the experimental stage, this paper adopts the 2016 annual air quality data set of Beijing to verify the effectiveness of the unit point multi-information coding strategy in reducing the rule storage air, the effectiveness of mining the rules formed by the low frequency item set, and the effectiveness of combining the rule mining algorithm with the swarm intelligence optimization algorithm in terms of search time and convergence. In the experimental stage, this paper adopts the 2016 annual air quality data set of Beijing to verify the effectiveness of the above three aspects. The unit point multi-information coding strategy reduced the rule space storage consumption by 50%, the new evaluation index can mine more interesting rules whose interest level can be up to 90%, while mining the rules formed by the lower frequency terms, and in terms of search time, we reduced it about 20% compared with some meta-heuristic algorithms, while improving convergence. [ABSTRACT FROM AUTHOR]

Determining accurate PM2.5 pollution concentrations and understanding their dynamic patterns are crucial for scientifically informed air pollution control strategies. Traditional reliance on linear correlation coefficients for ascertaining PM2.5-related factors only uncovers superficial relationships. Moreover, the invariance of conventional prediction models restricts their accuracy. To enhance the precision of PM2.5 concentration prediction, this study introduces a novel integrated model that leverages feature selection and a clustering algorithm. Comprising three components—feature selection, clustering, and integrated prediction—the model first employs the non-dominated sorting genetic algorithm (NSGA-III) to identify the most impactful features affecting PM2.5 concentration within air pollutants and meteorological factors. This step offers more valuable feature data for subsequent modules. The model then adopts a two-layer clustering method (SOM+K-means) to analyze the multifaceted irregularity within the dataset. Finally, the model establishes the Extreme Learning Machine (ELM) weak learner for each classification, integrating multiple weak learners using the AdaBoost algorithm to obtain a comprehensive prediction model. Through feature correlation enhancement, data irregularity exploration, and model adaptability improvement, the proposed model significantly enhances the overall prediction performance. Data sourced from 12 Beijing-based monitoring sites in 2016 were utilized for an empirical study, and the model's results were compared with five other predictive models. The outcomes demonstrate that the proposed model significantly heightens prediction accuracy, offering useful insights and potential for broadened application to multifactor correlation concentration prediction methodologies for other pollutants. [ABSTRACT FROM AUTHOR]

Chinese address element segmentation is a basic and key step in geocoding technology, and the segmentation results directly affect the accuracy and certainty of geocoding. However, due to the lack of obvious word boundaries in Chinese text, the grammatical and semantic features of Chinese text are complicated. Coupled with the diversity and complexity in Chinese address expressions, the segmentation of Chinese address elements is a substantial challenge. Therefore, this paper proposes a method of Chinese address element segmentation based on a bidirectional gated recurrent unit (Bi-GRU) neural network. This method uses the Bi-GRU neural network to generate tag features based on Chinese word segmentation and then uses the Viterbi algorithm to perform tag inference to achieve the segmentation of Chinese address elements. The neural network model is trained and verified based on the point of interest (POI) address data and partial directory data from the Baidu map of Beijing. The results show that the method is superior to previous neural network models in terms of segmentation performance and efficiency. [ABSTRACT FROM AUTHOR]