Ruchi Patel

Nanofluid-assisted machining is a promising sustainable alternative to the conventional cutting fluids; however, the correct prediction and optimization of the latter process is still difficult due to nonlinearities inherent to it and the lack of experimental data. Hence, the current study presents an innovative hybrid generative deep-learning model that synergistically integrates Response Surface Methodology (RSM), Artificial Neural Networks (ANN), and a Generative Adversarial Network (GAN) to predict intelligently and optimize multi-fold in the nanofluid-assisted turning of EN31 steel. It has been experimentally shown that MWCNT based gravity fed nanofluid decreases the surface roughness by 12.83% and cutting force components by up to 23.4% when compared to traditional coolant. The RSM model has a moderate predictive power (R ² ≈ 0.82–0.88) and ANN model outperforms the RSM model (R ² ≈ 0.95–0.97). Under the limited data condition, the GAN-ANN hybrid has higher predictive robustness with R ² ≈ 0.97–0.99 and lowest mean squared error (1.49 for roughness and 7.89 for cutting forces) than any of the other models tested. Using a hybrid ANN-RSM strategy based on desirability, best machining parameters predict a cutting force of about 205 N, a surface roughness of 0.45 μm and a maximum rate of material removal of 16.6 m ³ /min, which are later confirmed in follow-up experiments with an error of less than 5%. Therefore, the suggested framework will provide a scalable, interpretable and environmentally friendly decision support system to intelligent machining applications.

The goal of emotion detection is to find and recognise emotions in text, speech, gestures, facial expressions, and more. This paper proposes an effective multimodal emotion recognition system based on facial expressions, sentence-level text, and voice. Using public datasets, we examine face expression image classification and feature extraction. The Tri-modal fusion is used to integrate the findings and to provide the final emotion. The proposed method has been verified in classroom students, and the feelings correlate with their performance. This method categorizes students' expressions into seven emotions: happy, surprise, sad, fear, disgust, anger, and contempt. Compared to the unimodal models, the suggested multimodal network design may reach up to 65% accuracy. The proposed method can detect negative feelings such as boredom or loss of interest in the learning environment.