MobiFit: Contactless Fitness Assistant for Freehand Exercises Using Just One Cellular Signal Receiver

Freehand exercises help improve physical fitness without any requirements for devices or places. Existing fitness assistant systems are typically restricted to wearable devices or exercising at specific positions, compromising the ubiquitous availability of freehand exercises. In this paper, we develop MobiFit, a contactless freehand exercise assistant using just one cellular signal receiver placed on the ground. MobiFit passively monitors the ubiquitous cellular signals sent by the base station, which frees users from the space constraints and deployment overheads and provides accurate repetition counting, exercise type recognition and workout quality assessment without any attachments to the human body. The design of MobiFit faces new challenges of the uncertainties not only on cellular signal payloads but also on signal propagations because the sender (base station) is beyond the control of MobiFit and located far away. To tackle these challenges, we conducted experimental studies to observe the received cellular signal sequence during freehand exercises. Based on the observations, we constructed the analytic model of the received signals. Guided by the insights derived from the analytic model, MobiFit segments out every repetition and rest interval from one exercise session through spectrogram analysis and extracts low-frequency features from each repetition for type recognition. Extensive experiments were conducted in both indoor and outdoor environments, which collected 22,960 exercise repetitions performed by ten volunteers over six months. The results confirm that MobiFit achieves high counting accuracy of 98.6%, high recognition accuracy of 94.1% and low repetition duration estimation error within 0.3 s. Besides, the experiments show that MobiFit works both indoors and outdoors and supports multiple users exercising together.

show abstract

AI Gym Buddy Using Mediapipe

Malkar,

Pawar,

Kale

2024

International Journal of Innovative Science and Research Techno

View full text Add to dashboard Cite

The AI Gym Trainer is a system that provides multiple features designed to provide personalized fitness coaching and nutrition tracking. Imposing the advanced pose estimation capabilities of Mediapipe, the system provides real-time responses to exercise performance, focusing on posture, alignment, and technique.This feature is helpful because users will receive accurate guidance in workout sessions, which in turn enhances effectiveness while minimizing the risk of injury. Furthermore, the AI Gym Trainer is implemented using machine learning algorithms, which makes it capable of providing tailor workout routines to individual preferences and abilities, encouraging a personalized training experience. Through a user- friendly interface accessible through a desktop or web application, users can seamlessly interact with the system, track their progress, and receive personalized recommendations. Additionally, the system has a feature of a Flask-based food tracking feature which enhances the capabilities, allowing users to monitor their calorie intake and receive nutritional analysis. This comprehensive approach addresses both physical activity and dietary habits, and provides users with a holistic platform for managing their fitness goals. Evaluation through rigorous testing and user trials demonstrates the effectiveness and potential impact of the AI Gym Trainer in promoting overall health and well-being. With its combination of cutting-edge technology and user-centric design, the AI Gym Trainer represents a significant advancement in personalized fitness coaching and nutrition tracking, catering to the diverse needs of individuals striving to achieve their fitness goals.

show abstract

MobiFit: Contactless Fitness Assistant for Freehand Exercises Using Just One Cellular Signal Receiver

Cited by 3 publications

References 22 publications

A Real-time Posture Recognition System using YOLACT++ and ResNet18

A Real-time Posture Recognition System using YOLACT++ and ResNet18

Recognizing and Counting Freehand Exercises Using Ubiquitous Cellular Signals

AI Gym Buddy Using Mediapipe

Contact Info

Product

Resources

About