Mostafa Merras

Wind energy conversion systems driven by the doubly fed induction generator (DFIG) are commonly used in variable-speed wind turbines due to their high efficiency and reduced converter rating. This paper investigates a control strategy integrating a maximum power point tracking (MPPT) algorithm based on a tip-speed-ratio with field-oriented control (FOC) for the DFIG. The main contribution lies in a comparative evaluation between conventional proportional–integral (PI) control and sliding mode control (SMC) employed for both the MPPT speed loop and the rotor current regulation within the FOC structure. The proposed approach aims to improve transient response and robustness under variable wind conditions while maintaining separate regulation of active and reactive stator powers. The mathematical model of the system is developed using the aerodynamic turbine model and the dq dynamic model of the DFIG. Control laws for both the SMC and PI control are derived for the mechanical speed loop and the rotor current loops. Simulation studies are carried out using a realistic wind profile with an average velocity of approximately 7.5 m s ^–1 . The results show that the SMC-based MPPT achieves a response time of about 1.5 ms with no overshoot and a speed tracking error below 0.0025 rad s ^–1 , whereas the PI controller exhibits 21% overshoot, a 0.1 s settling time and a speed tracking error of about 0.05 rad s ^–1 . In the power control stage, the SMC approach ensures a convergence time of approximately 1.5 ms for the regulation of both stator powers, with no overshoot and negligible power tracking error, whereas the PI controller exhibits a convergence time of about 0.01 s and an overshoot of approximately 12.5%, while also maintaining a negligible steady-state tracking error. These results demonstrate that SMC significantly improves the transient performance and robustness of a DFIG-based wind turbine systems.

SMS spam detection remains a critical challenge in mobile communication security, particularly when addressing the inherent class imbalance present in real-world datasets, where spam messages constitute only 13–15% of total communications. This study presents a comprehensive framework integrating advanced word embeddings, deep learning architectures, and Generative Adversarial Networks (GANs) for synthetic data augmentation to enhance SMS spam classification performance. A systematic evaluation is conducted across six machine learning algorithms (Support Vector Machine (SVM), Logistic Regression (LR), K-Nearest Neighbors (KNN), Decision Tree (DT), Stochastic Gradient Descent (SGD), Random Forest (RF)) and two deep learning models (Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM)), combined with five embedding techniques (Term Frequency–Inverse Document Frequency (TF-IDF), Bag of Words (BoW), Word2Vec, GloVe, Bidirectional Encoder Representations from Transformers (BERT)), resulting in 120 experimental configurations tested both with and without data augmentation. A novel GAN-based approach is employed to generate synthetic word embeddings rather than raw text, preserving semantic coherence while addressing dataset imbalance more effectively than traditional oversampling methods (Synthetic Minority Over-sampling Technique (SMOTE), Adaptive Synthetic Sampling (ADASYN)). Experimental validation on both the monolingual UCI SMS Spam Collection and multilingual datasets demonstrates that the optimal BERT+Bi-LSTM+GAN configuration achieves exceptional performance, with F1-scores of 97.61% (monolingual) and 94.44% (multilingual), surpassing existing state-of-the-art approaches. The comprehensive evaluation framework, incorporating Matthews Correlation Coefficient (MCC) and Cohen’s Kappa (CK), provides robust assessment for imbalanced classification scenarios. Results reveal that contextual embeddings consistently outperform traditional frequency-based methods, with BERT achieving perfect precision of 100% in baseline configurations. The study establishes strategic deployment guidelines: BERT configurations for maximum accuracy scenarios, Word2Vec approaches for balanced performance–efficiency requirements, and traditional methods for resource-constrained environments. Cross-linguistic validation confirms the universality of the approach, demonstrating only a 3.25% performance degradation in multilingual contexts. This research advances both theoretical understanding of imbalanced text classification and practical implementation of robust SMS spam detection systems, providing a methodological foundation applicable to broader cybersecurity and natural language processing challenges.