Hao Ran Tang¹ and Jonathan Sahagun², ¹USA, ²California State Polytechnic University, USA

This paper addresses the problem of accurate swipe detection and battery life management in wearable devices [1]. We proposed a device that utilizes accelerometers and gyroscopes to detect swipe gestures and analyze user interactions [2]. The system's core technologies include advanced sensor fusion for gesture recognition and real-time data processing. Challenges included ensuring high accuracy in gesture detection and optimizing battery life under continuous use. We conducted experiments to test these aspects, finding an average swipe detection accuracy of 91.6% and battery life extending up to 13 hours under active use. Our approach improved upon existing methodologies by refining gesture recognition algorithms and optimizing power consumption [3]. The results demonstrate that our device effectively balances performance and battery efficiency, making it a viable solution for real-time gesture tracking applications [4]. This innovation has potential applications in user interaction enhancement and energyefficient wearable technology.

IoT (Internet of things), Machine Learning, Could Computing