Faezeh Amirteimoury

Ms. Faezeh Amirteimoury

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 March 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
FAFaezeh Amirteimoury
Faezeh Amirteimoury
FKFarshid Keynia
Farshid Keynia
EAElaheh Amirteimoury
Elaheh Amirteimoury
GMGholamreza Memarzadeh
Gholamreza Memarzadeh
HSHanieh Shabanian
Hanieh Shabanian
Wind is a renewable, sustainable, and clean source of energy. This has led to wind gaining a lot of attention in recent decades as a reliable alternative to fossil fuels. However, wind speed fluctuations complicate its integration with power grids. To tackle this issue, this paper proposes a new wind speed prediction model that combines four techniques: Discrete Wavelet Transform, which smooths the wind speed signal; Mutual Information, which selects the most informative part of the wind speed time series; Coot Optimization Algorithm for optimal feature selection; and Bidirectional Long Short-Term Memory for capturing complex patterns. To evaluate the efficiency of the proposed model, its performance was measured using error metrics such as mean squared error, mean absolute error, mean absolute percentage error, coefficient of determination (\(R^2\)), and median absolute error. The proposed model was examined using two different wind speed datasets and achieved high prediction accuracy. Additionally, 14 different benchmark models were created, and their prediction results were compared with those of the proposed model. A comparison between the results of the proposed model and benchmark models demonstrated the superiority of the proposed model.

5 June 2024 in Sustainability
Verified
Journal Article
Open access
PDF file
HJHossein Jalali
Hossein Jalali
FKFarshid Keynia
Farshid Keynia
FAFaezeh Amirteimoury
Faezeh Amirteimoury
AHAzim Heydari
Azim Heydari
In the contemporary era, global air quality has been adversely affected by technological progress, urban development, population expansion, and the proliferation of industries and power plants. Recognizing the urgency of addressing air pollution consequences, the prediction of the concentration levels of air pollutants has become crucial. This study focuses on the short-term prediction of nitrogen dioxide (NO2) and sulfur dioxide (SO2), prominent air pollutants emitted by the Kerman Combined Cycle Power Plant, from May to September 2019. The proposed method utilizes a new two-step feature selection (FS) process, a hybrid neural network (HNN), and the Coot optimization algorithm (COOT). This combination of FS and COOT selects the most relevant input features while eliminating redundant ones, leading to improved prediction accuracy. The application of HNN for training further enhances the accuracy significantly. To assess the model’s performance, two datasets, including real data from two different parts of Combined Cycle Power Plant in Kerman, Iran, from 1 May 2019 to 30 September 2019 (namely dataset A and B), are utilized. Subsequently, mean square error (MSE), mean absolute error (MAE), root mean square deviation (RMSE), and mean absolute percentage error (MAPE) were employed to obtain the accuracy of FS-HNN-COOT. Experimental results showed MSE of FS-HNN-COOT for NO2 ranged from 0.002 to 0.005, MAE from 0.016 to 0.0492, RMSE from 0.0142 to 0.0736, and MAEP from 4.21% to 8.69%. Also, MSE, MAE, RMSE, and MAPE ranged from 0.0001 to 0.0137, 0.0108 to 0.0908, 0.0137 to 0.1173, and 9.03% to 15.93%, respectively, for SO2.

17 September 2025 in IEEE Access
Verified
Journal Article
Open access
FAFaezeh Amirteimoury
Faezeh Amirteimoury
GMGholamreza Memarzadeh
Gholamreza Memarzadeh
HNHossein Noori
Hossein Noori
FKFarshid Keynia
Farshid Keynia
AHAzim Heydari
Azim Heydari
Afef FekihAfef Fekih
Afef Fekih
The global rise in energy demand has driven the large-scale integration of photovoltaic (PV) systems into the power grids, increasing the need for accurate forecasting models to manage solar energy variability and uncertainty. This study proposes a novel 24-hour-ahead PV power generation prediction model based on the Multi-Scale Feature Attention Network (MSFAN), which integrates convolutional neural networks (CNNs), attention mechanisms, and gated recurrent units within a non-sequential architecture to enhance prediction accuracy. The model also incorporates a two-step feature selection technique, Mutual Information-Interaction Gain (MI-IG), to extract the most relevant input features whilst minimizing redundancies. The proposed model was validated using real-world PV power generation data from the Arvand power plant in Mahan, Iran. The results indicate that the the model outperformed traditional methods, including LSTM, MLP, and Elman networks. It achieved a mean squared error (MSE) of 0.001, mean absolute error (MAE) of 0.02, mean absolute percentage error (MAPE) of 2.5%, and a coefficient of determination (R²) of 0.991—substantially surpassing the performance of the comparison models. These results underscore the model's potential to improve PV forecasting accuracy and support more stable and efficient power grid operations.

23 December 2025 in Results in Engineering
Verified
Journal Article
Open access
GMGholamreza Memarzadeh
Gholamreza Memarzadeh
FKFarshid Keynia
Farshid Keynia
RMRasoul Memarzadeh
Rasoul Memarzadeh
FAFaezeh Amirteimoury
Faezeh Amirteimoury

11 March 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
GMGholamreza Memarzadeh
Gholamreza Memarzadeh
FKFarshid Keynia
Farshid Keynia
FAFaezeh Amirteimoury
Faezeh Amirteimoury
AHAzim Heydari
Azim Heydari
Afef FekihAfef Fekih
Afef Fekih
Electricity price forecasting plays a vital role in daily trading operations, enabling market participants to make informed bidding and operational decisions. However, this task remains highly challenging due to the volatility of electricity markets, the influence of renewable energy integration, and the significant economic impact of pricing decisions on producers and consumers. This study proposes a Hybrid Cascaded Forecaster Network (HCaFN) for day-ahead electricity price forecasting. The proposed framework first applies a Wavelet Transform (WT)–based decomposition to enhance forecasting performance under renewable generation uncertainty. It then employs the Mutual Information–Interaction Gain (MI-IG) technique for feature selection, ensuring that the most relevant and least redundant input variables, particularly those associated with price spikes, are retained. The preprocessed data are used to train multiple forecasting models, including the Multi-Layer Perceptron (MLP), Cascade Neural Network (CaNN), and Extreme Learning Machine (ELM). Finally, a stacking ensemble learning strategy is implemented to further reduce price uncertainty and improve overall prediction accuracy in the day-ahead electricity market. Experimental results demonstrate that the proposed HCaFN model consistently outperforms several state-of-the-art electricity price forecasting approaches.

21 May 2024 in SSRN Electronic Journal
Verified
Preprint
Open access
PDF file
FAFaezeh Amirteimoury
Faezeh Amirteimoury
GMGholamreza Memarzadeh
Gholamreza Memarzadeh
FKFarshid Keynia
Farshid Keynia
Wind energy is gaining attention in power sector. However, the instability of wind speed (WS) negatively affects the incorporation of wind energy into the power grid. Reducing wind power issues requires precise WS forecasting. The current paper introduces an ensemble approach for multi-steps WS forecasting including discrete wavelet transform (DWT) to denoise WS signal and mutual information-interaction gain (MI-IG) to identify the most relevant input features. Moreover, multi-layer perceptron (MLP), bidirectional long short-term memory (BiLSTM), gated recurrent unit (GRU), and convolutional neural network (CNN) are employed to build individual forecasting modules. Finally, stacking ensemble learning combines the outputs from these modules. For the first dataset, the proposed model achieved MSE between 0.05 to 0.59, MAE from 0.19 to 0.6, MAPE from 5.97% to 21.94% and R2 from 0.985 to 0.852 for one-hour ahead to five-hours ahead.