A vital field of study aiming to overcome communication barriers between those with hearing problems and the rest of the world is gesture sign language recognition. This innovative tool closes the communication gap between those without understanding conventional sign languages and those with hearing problems. Deaf and hard-of-heared people employ rich and sophisticated visual-spatial languages called sign languages to convey thoughts, emotions, and information. For persons with hearing problems, effective communication and social inclusion depend on appropriate recognition and interpretation of these signals. Accurately capturing the subtleties of sign language motions was difficult in traditional sign language recognition systems, which sometimes depended on small datasets and rule-based approaches. These systems lacked the capacity to change with respect to various sign languages and personal signing methods. More flexible and accurate sign language recognition systems may be developed by use of machine learning approaches by integration. This dataset allows one to train machine learning systems to identify a broad spectrum of sign language motions. Particularly with datasets like Nintendo Power Glove Data, machine learning presents a viable path for more accurate and real-time sign language gesture identification. Thus, this work attempts to develop a machine learning-based method using Nintendo Power Glove Data has great possibilities in transforming gesture sign language detection. Leveraging machine learning, the suggested system generates more accurate, flexible, and real-time sign language recognition systems, thereby increasing the quality of life for those living in the deaf and hard-of-hearing groups.

sign language, Nintendo power glove data, machine learning.