HQHui Qi

Hui Qi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Hui Qi has a total of 19 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Short-Term Prediction of Daily O3, NO2, and SO2 Using a Novel Hybrid Model with Additive Correction

    by Hui Qi, Qiurui Song, Yue Qi, Sixian Shu, Enlai Huang, Xuchu Jiang, Chibiao Liu

    Accurate forecasts of O3, NO2, and SO2 from regulatory daily summary records support early warning and environmental management, whereas the inherent nonlinearity, non-stationarity, and multi-scale fluctuations of pollutant sequences severely hinder prediction precision. This paper develops a hybrid CEEMDAN-VMD-GRU-AC model for one-step-ahead concentration prediction of three typical air pollutants. Chronologically ordered valid daily summary records from the Los Angeles–North Main Street monitoring station from 2015 to 2025 were used for evaluation. The original pollutant sequences are first decomposed into multi-scale intrinsic mode functions via complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN). Variational mode decomposition (VMD) is further applied to refine high-frequency IMF1 and IMF2 to decouple irregular short-term oscillations. A gated recurrent unit (GRU) equipped with an additive correction (AC) branch is constructed to predict each decomposed component, and all subseries predictions are aggregated to obtain the final concentration forecasts. The evaluation was conducted under an offline full-series decomposition protocol, in which CEEMDAN and VMD were applied to the complete pollutant sequence before the chronological training–validation–test split; therefore, the reported metrics should not be interpreted as fully prospective rolling-origin forecasting performance. Because the extracted records were not reindexed to a complete daily calendar, the 30-step input represents 30 consecutive valid records rather than 30 uninterrupted calendar days. Compared with benchmark prediction methods, the proposed framework yields the lowest RMSE and MAE, together with the highest R2 values of 0.9646, 0.9516, and 0.9035 for O3, NO2, and SO2, respectively. The ablation results reveal pollutant-dependent effects: VMD refinement provides the largest improvement for O3, whereas the final GRU-AC configuration performs best for NO2 and SO2. These results demonstrate the feasibility of the proposed framework under the stated offline protocol, while calendar-complete rolling-origin and multi-station validation remains necessary before operational deployment.

  • Open Access

    MultiGSA: wind power prediction based on a multi-scale cross-graph network combined with an enhanced simple attention mechanism

    by Xufei Zhang, Zhe Qiu, Yaling Han, Xuchu Jiang, Hui Qi

    Wind power generation datasets are widely encountered in renewable energy systems because of their inherent periodicity, non-stationarity, and substantial noise. Recent advancements in graph neural networks have improved wind power time series forecasting via multi-scale feature extraction. However, a key challenge is effectively capturing multi-scale temporal trends, suppressing intrinsic noise, and leveraging correlations among wind power variables. We propose a novel architecture: Multi-scale coupling graph neural network with enhanced simple attention (MultiGSA). In contrast to traditional approaches that fail to address the instability, high sampling frequency, and intrinsic noise of wind power data, MultiGSA extends feature learning across multi-scale temporal dynamics and cross-variable correlations. It uses a cross-scale Co-GNN module to capture multi-scale trends and suppress time-domain noise, leveraging inter-scale complementary information. The cross-variable Co-GNN capitalizes on variable homogeneity and heterogeneity to strengthen correlation detection, whereas the enhanced simple attention mechanism alleviates frequency-domain noise. We evaluate MultiGSA on four real-world wind farm datasets, and the results show that it consistently outperforms state-of-the-art methods. Specifically, MultiGSA achieves up to 4.8% MAE and 3.2% RMSE improvements over the baselines, demonstrating its effectiveness and robustness in managing wind power data complexity.

  • Open Access

    A Novel Hybrid Approach for Non-Stationary Electricity Price Forecasting

    by Yinwei Li, Ningxuan Li, Hui Qi, Fei Wang, Yiwen Luo, Xuchu Jiang

    With the implementation of market-oriented electricity trading in an increasing number of countries, accurate electricity price forecasting can not only help participants in the electricity market to make more reasonable decisions but also enable regulators to have a more reliable regulatory basis. Therefore, it is necessary to propose an appropriate electricity price forecasting method. In view of the insufficiency of the traditional models in dealing with nonlinear and non-stationary data, to improve the detection ability of the model for hidden information in data and considering the high randomness of electricity price data, this paper proposes an electricity price forecasting method based on singular spectrum analysis (SSA) to decompose the original sequence and combines it with an extreme learning machine (ELM) optimized by the grey wolf optimizer (GWO). First, SSA is used to decompose the original sequence, and then the ELM is used to predict each subsequence and add them, in which the number of neurons in the hidden layer of each ELM is jointly optimized by the GWO. To verify the effectiveness of the SSA–GWO–ELM model, a total of 2106 days of electricity price data in Victoria, Australia, were selected for modeling. The results show that the prediction accuracy of the model proposed in this paper is significantly higher than that of the other comparison models, and the R2 score is as high as 0.989, which is 0.017 higher than that of the suboptimal SSA–ELM. It can also maintain strong robustness and high prediction accuracy for heterogeneous data on power demand. SSA has the potential for real-time prediction, which can provide reliable data support for electricity market participants and supervisors.

  • Open Access

    A method for multi-criteria decision making with probabilistic linguistic term based on cloud TOPSIS

    by Abdulrahman Almandeel, Congjun Rao, Xiaolong Zhang, Hui Qi

    Recent literature has explored various approaches to address the stochasticity and ambiguity inherent in concept terms within the Multi-Criteria Decision Making (MCDM) process. Probabilistic linguistic terms provide a robust means to represent decision makers’ assessment preferences, such as the cloud model, which can describe the relationship between ambiguity and stochasticity using numerical characteristics. To ensure the accuracy and reliability of the decision making process, it is essential to integrate both implicit uncertainty and ambiguity information, which are often present. This study develops an MCDM technique to solve decision problems in which the criterion values are expressed as probabilistic linguistic terms. First, the cloud model is introduced, along with the concept of the probabilistic linguistic cloud. A golden section technique is employed to transform probabilistic linguistic terms into probabilistic linguistic clouds. Next, a novel distance metric between probabilistic linguistic clouds is presented, and a new cloud-weighted averaging operator (PLC-WA) is proposed to aggregate multiple probabilistic linguistic clouds. Subsequently, a new probabilistic linguistic cloud-TOPSIS (PLC-TOPSIS) method is introduced, and an MCDM approach based on PLC-TOPSIS is developed. Finally, a case study on group decision making for public evacuation during nuclear accidents is presented to validate the proposed method. The feasibility of the proposed method is verified through comparative analysis.

  • Open Access

    Time Series Prediction of the AQI in Wuhan City via a Hybrid Prophet–LSTM Model with an Improved PSO Algorithm

    by Duochenxi Liu, Chibiao Liu, Xuchu Jiang, Hui Qi

    The air quality index (AQI) depends on the concentrations of six pollutants (PM2.5, PM10, SO2, NO2, O3, and CO). We propose a hybrid Prophet–LSTM forecasting framework with an improved particle swarm optimization (PSO) algorithm to tune the fusion weight. Prophet captures low–frequency trends and seasonality, while LSTM models residual dynamics; PSO selects weights on a validation subset to avoid test leakage. For the Wuhan PM2.5 test period (1 January 2021 to 3 May 2021), the PSO–enhanced hybrid achieves an MAE = 11.234 and an RMSE = 15.009, corresponding to 35.82%/35.10% reductions in the MAE/RMSE compared with Prophet and 37.69%/40.55% reductions compared with LSTM; it also improves over the unoptimized Prophet–LSTM by 6.70% (MAE) and 4.48% (RMSE). A Diebold–Mariano test indicates a statistically significant improvement over Prophet (p = 0.001), whereas the difference relative to LSTM is not significant at the 0.05 level (p = 0.248). Additional experiments on PM10, SO2, CO, NO2, and O3 show that the proposed framework achieves the lowest or near–lowest errors in most cases.


  • Open Access

    Time Series Prediction of AQI in Wuhan City Using a Hybrid Prophet-LSTM Model with an Improved PSO Algorithm

    by Hui Qi, Chibiao Liu, Xuchu Jiang, Duochenxi Liu

    The air quality index (AQI) depends on the concentrations of six pollutants (PM2.5, PM10, SO2, NO2, O3, and CO). In this paper, a Prophet-LSTM model with improved particle swarm optimization (PSO) is proposed to analyze the time series of six pollutant concentrations in Wuhan city. First, the time series are decomposed by Prophet, and Prophet is used to predict the trend term and periodic term. Then, LSTM is used to predict the error term. Finally, the improved PSO algorithm is used for optimization. These experimental results indicated that (1) Prophet’s decomposition method has good applicability to time series with the multiplication form. The Prophet-LSTM model can overcome the influence of PM series irregularity, large fluctuations and multiple noise on the prediction effect, which improves the prediction ability of the model. (2) The improved PSO algorithm can greatly improve the accuracy of the weight solution space and has the attribute of parallel computing, which makes the solution forms more diversified. (3) The hybrid model has better prediction ability than the comparison model (LSTM, Prophet, Prophet-LSTM). The hybrid model combines the advantages of Prophet and LSTM, which has strong adaptability to the randomness of sample selection and has strong accuracy in predicting pollutant concentrations.