A survey of datasets, applications, and models for IMU sensor signals

Aparajita Saraf, Seungwhan Moon, Andrea Madotto

Abstract:

Inertial Measurement Units (IMUs) are small, low-cost
sensors that can measure accelerations and angular velocities, making them valuable tools for a variety of applications,
including robotics, virtual reality, and healthcare. With the
advent of deep learning, there has been a surge of interest
in using IMU data to train DNN models for various applications. In this paper, we survey the state-of-the-art ML models
including deep neural network models and applications for
IMU sensors. We first provide an overview of IMU sensors
and the types of data they generate. We then review the most
popular models for IMU data, including convolutional neural networks, recurrent neural networks, and attention-based
models. We also discuss the challenges associated with training deep neural networks on IMU data, such as data scarcity,
noise, and sensor drift. Finally, we present a comprehensive
review of the most prominent applications of deep neural networks for IMU data, including human activity recognition,
gesture recognition, gait analysis, and fall detection. Overall,
this survey provides a comprehensive overview of the stateof-the-art deep neural network models and applications for
IMU sensors and highlights the challenges and opportunities
in this rapidly evolving field.