Panigrahi, S.Seal, S.Lal, S.Naik, G.2026-02-062025Communications in Computer and Information Science, 2025, Vol.2491 CCIS, , p. 438-44918650929https://doi.org/10.1007/978-3-031-90577-3_37https://idr.nitk.ac.in/handle/123456789/28624Gesture prediction plays a crucial role in enhancing human-computer interaction by enabling intuitive and natural control methods, thereby reducing reliance on traditional input devices. It significantly improves accessibility for individuals with physical disabilities by providing alternative means of communication and control. Moreover, gesture prediction has broad applications in fields such as robotics, virtual reality, and prosthetics, enhancing both the functionality and user experience of these technologies. This study presents the design and development of an Electromyogram (EMG) signal-based gesture recognition system utilizing recent Deep Learning (DL) techniques. The Hyser EMG dataset was used for experimentation, and its data was pre-processed and analyzed using both sliding window and a combination of sliding window and Fourier transform methods. The performance of the EMG signal-based gesture recognition system was evaluated and compared across different DL models. The results demonstrate that RCCGNet-based gesture prediction outperforms other models. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.AlexNetFourier TransformGesture IdentificationRCCGNetResNetSliding Window MethodVGGNet