Real–Time Sign Language Recognition and Multilingual Speech Output Based on Machine Learning

Lavanya N L, H R Sujay, Akash M, Darshan S, Akash G A — Thu, 13 Nov 2025 00:00:00 +0000

For people with hearing and speech disabilities, sign language is an essential means of communication. Yet, a communication gap between signers and non-signers remains large because of limited public knowledge. To overcome this limitation, this work proposes a machine learning–based real-time sign language recognition and translation system. The system captures hand movements using a standard webcam and uses the Mediapipe framework to recognize accurate hand landmarks. These landmarks are subsequently categorized using independently trained Random Forest Classifier models for Indian Sign Language (ISL) and American Sign Language (ASL). The identified gestures are translated into text and then audible speech utilizing the pyttsx3 library, and the Google Translate API provides multilingual translation for cross-linguistic communication. Experimental results show that the system proposed performs accurate real-time recognition performance through regular computing hardware alone.

Predictive Modelling of Student Outcomes Using Ensemble Regression and Classification Methods

Mary Teresa, Sukerthi Sutraya, Y Vijaya Sambhavi, Saritha Dasari, J K Neelima — Thu, 13 Nov 2025 00:00:00 +0000

Accurate prediction of student academic outcomes is vital for developing data-driven interventions in education. This study proposes a robust ensemble learning framework based on the HistGradientBoostingClassifier (HGB) to classify student grades using behavioral and academic features such as self-study hours, attendance, class participation, and total performance scores. Leveraging a large-scale synthetic dataset of 1,000,000 student records, we benchmarked the proposed HGB model against widely used ensemble classifiers including XGBoost, LightGBM, CatBoost, and Random Forest. Comprehensive experiments demonstrated that HGB consistently outperformed all baselines, achieving a testing accuracy of 99.6%, with macro-averaged precision, recall, and F1-score of 0.99. The model also showed strong generalization across both majority and minority grade categories, as confirmed by confusion matrix analysis. These results highlight the effectiveness of histogram-based boosting in educational data mining and support its application in real-time academic performance monitoring and intervention systems.

International Journal of Human Computations and Intelligence

Real–Time Sign Language Recognition and Multilingual Speech Output Based on Machine Learning

Predictive Modelling of Student Outcomes Using Ensemble Regression and Classification Methods