Kimia Shirini

Dr. Kimia Shirini

orcid

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

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

Representative Publications

View All Publications
28 January 2026 in Scientific Reports
Verified
Journal Article
Open access
PDF file
AHAmirhosein Hayati
Amirhosein Hayati
SGSina Samadi Gharehveran
Sina Samadi Gharehveran
KSKimia Shirini
Kimia Shirini
Accurate electricity price forecasting is essential for optimizing market operations, enhancing resource allocation, and ensuring sustainable energy management in volatile and complex markets. This research introduces a comprehensive ensemble meta-modeling framework that integrates machine learning techniques with SHAP (SHapley Additive exPlanations) for enhanced interpretability and PCA (Principal Component Analysis) for effective dimensionality reduction. The methodology capitalizes on the complementary strengths of predictive models such as XGBoost, LSTM, and CNN to address the non-linear and temporal intricacies of electricity price datasets. Two ensemble approaches were implemented: (1) Weighted Averaging, assigning weights inversely proportional to model RMSE, achieving an RMSE of 2.126761, and (2) Meta-Model Ensemble, employing Linear Regression, achieving superior accuracy with an RMSE of 1.939032. SHAP analysis provided actionable insights into model contributions, highlighting XGBoost and LSTM as key components. Furthermore, error trajectory analysis demonstrated the robustness of the ensembles in minimizing cumulative forecasting errors over time. This study contributes to the field by combining advanced machine learning models, ensemble strategies, and explainability frameworks to deliver an interpretable, high-performing electricity price forecasting system. The results inform policy-making and lay the foundation for scalable, data-driven energy market solutions.

18 April 2026 in Scientific Reports
Verified
Journal Article
Open access
DBDeniz Baharvand
Deniz Baharvand
NSNima Saeedi
Nima Saeedi
SGSina Samadi Gharehveran
Sina Samadi Gharehveran
KSKimia Shirini
Kimia Shirini
Designing game levels that appropriately match a player’s skill level remains a fundamental challenge in procedural content generation, as mismatches in difficulty can lead to player boredom, frustration, and reduced engagement. While deep generative models enable automatic level synthesis at scale, the comparative effectiveness of different GAN architectures for skill-conditioned and personalized level generation remains insufficiently explored. In this work, we investigate the use of generative adversarial networks (GANs) for skill-conditioned procedural content generation by evaluating five architectures: U-Net GAN, StyleGAN, Deep Convolutional GAN (DCGAN), ResNet-GAN, and Spectral Normalization GAN (SN-GAN). Player behavior is clustered into discrete skill groups using Spectral Clustering, and the resulting labels are employed as conditioning signals for level generation. The selected architectures span different convolutional depths, normalization strategies, and regularization mechanisms, enabling a broad and systematic comparison. All models are evaluated using consistent quantitative metrics, including tile distribution entropy, diversity score, discriminator accuracy, generation speed, and pairwise Hamming distance. Quantitative analysis demonstrates that as player skill increases, generated levels exhibit fewer deaths and shorter completion times, while encouraging more complex interactions such as higher jumps and coin collection. Experimental results indicate that ResNet-based and U-Net-style GAN architectures achieve the most favorable balance between level diversity, playability, and training stability, corroborating both qualitative and quantitative assessments. The spectral clustering-based skill-conditioning approach successfully produced personalized levels aligned with each player’s abilities, supporting adaptive procedural content generation across different skill groups.

9 June 2026 in Scientific Reports
Verified
Journal Article
Open access
DBDeniz Baharvand
Deniz Baharvand
FJFatemeh Jodati
Fatemeh Jodati
KSKimia Shirini
Kimia Shirini
SGSina Samadi Gharehveran
Sina Samadi Gharehveran
Facial emotion recognition (FER) is one of the main fields of research in image processing and artificial intelligence with applications in human-machine interaction, behavior analysis, and intelligent vision. The RAF DB dataset, a widely used benchmark dataset for emotion recognition, is used for the training and testing of deep learning models. In real application conditions, the facial image may be subjected to visual noise. Large glasses that occlude the eye region of the face are one example of environmental or artificial noise which distorts the visual information. If frames covering a large area of an expressive part of the face, like the eyes, are recognized as noise by the emotion recognition network this may lead to noticeable performance degradation. Artificial occlusion noise, similar to large glasses, was applied to the eye region of the facial images from the RAF DB dataset. The impact of this type of structural noise on the performance of deep-learning-based facial emotion recognition models is analyzed. Three state-of-the-art architectures (ResNet-50, Vision Transformer (ViT-Base/16) and Swin Transformer Tiny (Swin T)) are tested to determine their robustness to the noisy application conditions. The objective of the study is to determine and suggest possible methods to counter the decrease in recognition performance caused by the occlusion noise. Experimental results indicate that, within our evaluation setup, transformer-based architectures, especially Swin-T, tend to be more robust to the simulated visual noise, which may be useful for the design of facial emotion recognition models intended for more complex conditions.

29 May 2026
Verified
Book Chapter
Closed access
NSNima Saeedi
Nima Saeedi
KSKimia Shirini
Kimia Shirini
SGSina Samadi Gharehveran
Sina Samadi Gharehveran
SRSaman Rajebi
Saman Rajebi
Siamak PedrammehrSiamak Pedrammehr
Siamak Pedrammehr
JSJuan Manuel Gorriz Saez
Juan Manuel Gorriz Saez

30 May 2026
Verified
Book Chapter
Closed access
KSKimia Shirini
Kimia Shirini
SGSina Samadi Gharehveran
Sina Samadi Gharehveran
SRSaman Rajebi
Saman Rajebi
Siamak PedrammehrSiamak Pedrammehr
Siamak Pedrammehr
RARoohallah Alizadehsani
Roohallah Alizadehsani
JSJuan Manuel Gorriz Saez
Juan Manuel Gorriz Saez

10 August 2026 in Algorithms
Verified
Journal Article
Open access
PDF file
SFSina Mohammadpour Farshbaf
Sina Mohammadpour Farshbaf
KSKimia Shirini
Kimia Shirini
SGSina Samadi Gharehveran
Sina Samadi Gharehveran
Arya AbdollahiArya Abdollahi
Arya Abdollahi
Residential short-term load forecasting (STLF) plays a critical role in maintaining grid stability and enabling effective demand response in smart grid environments. However, residential electricity consumption exhibits strong stochastic variability, non-linear patterns, and abrupt changes caused by occupant behavior and environmental factors, making direct forecasting of raw power signals highly susceptible to high-frequency noise and temporal prediction lag. To address these challenges, this study proposes a Robust Residual Attention Network (Robust-RAN) for trend-oriented residential STLF. The proposed framework integrates localized causal denoising, residual multi-head attention mechanisms, and cyclic temporal encoding to mitigate observable phase lag and stabilize predictions against stochastic fluctuations, capture both short- and long-term temporal dependencies, and preserve daily periodicity. The proposed model was evaluated on the public UCI Appliances Energy Prediction dataset using comprehensive regression, classification, and residual analysis metrics. The experimental results demonstrate that Robust-RAN achieves a Coefficient of Determination (R2) of 0.9063 and a Mean Absolute Error (MAE) of 13.00 W. Under high-load conditions, the proposed approach further attains a peak detection accuracy of 96.63% with an F1-score of 0.8529, indicating reliable prediction of critical demand events. The results demonstrate that the proposed framework provides a stable and accurate estimation of the underlying residential load trend, offering a stable forecasting framework evaluated on the UCI benchmark dataset for demand response, peak- load management, and advanced residential energy management applications.