Raw Inertial Data Research Articles

An $\omega$-Free Accelerometer Array Method for 2-D Trajectory Reconstruction

A trajectory can be reconstructed by integrating acceleration and angular velocity (i.e. <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\omega$</tex-math></inline-formula> ) sampled by a single inertial measurement unit (IMU) which consists of an accelerometer (ACC) and gyroscope (GYRO). To reduce the system power consumption, a GYRO-free-IMU (GF-IMU) method was proposed which disabled the more power-consuming GYRO and utilized only an ACC array (AA) to obtain acceleration and calculate <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\omega$</tex-math></inline-formula> . To alleviate the error accumulation problem in the GF-IMU method, we previously proposed an <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\omega$</tex-math></inline-formula> -free ACC pair (OFAP) method which doesn't require the calculation of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\omega$</tex-math></inline-formula> and can estimate the trajectory by solving a constrained optimization problem. However, the constrained problem makes it computationally expensive to generalize the proposed approach for different AA setups with more ACCs. To enhance the scalability and robustness of the system, this paper proposes a new <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\omega$</tex-math></inline-formula> -free inertia-based method, namely <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\omega$</tex-math></inline-formula> -free AA (OFAA), which transforms the constrained problem into an unconstrained one, and derives its scalable and computational-efficient closed-form solution. In both physical experiments and simulations, compared with conventional inertial methods, the proposed OFAA method has a lower trajectory-reconstruction error per distance traveled and is more robust to errors in raw inertial data, while still having a low energy consumption.

Deep-Learning-Based Inertial Odometry for Pedestrian Tracking Using Attention Mechanism and Res2Net Module

Pedestrian dead reckoning is a challenging task due to the low-cost inertial sensor error accumulation. Recent research has shown that deep learning methods can achieve impressive performance in handling this issue. In this letter, we propose inertial odometry using a deep-learning-based velocity estimation method. The deep neural network based on Res2Net modules and two convolutional block attention modules is leveraged to restore the potential connection between the horizontal velocity vector and raw inertial data from a smartphone. Our network is trained using only 50% of the public inertial odometry dataset (RoNIN) data. Then, it is validated on the RoNIN testing dataset and another public inertial odometry dataset (OXIOD). Compared with the traditional step-length and heading-system-based algorithm, our approach decreases the absolute translation error (ATE) by 76%–86%. In addition, compared with the state-of-the-art deep learning method (RoNIN), our method improves its ATE by 6%–31.4%.

A Wearable Sensor Network With Embedded Machine Learning for Real-Time Motion Analysis and Complex Posture Detection

This work presents an embedded system driven by a wearable sensor network and machine learning to perform complex posture detection and high-precision <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">human activity recognition</i> (HAR) in real time. The presented prototype performs real-time HAR using raw data collected from three wireless wearable motion sensor nodes in parallel. The sensors communicate the measured inertial data to a Raspberry Pi 3 running a pre-trained classifier, which performs motion detection and classification in real-time. Our approach based on raw data and machine learning provides more efficiency and simplicity by decreasing the computation cost and the latency. Our detection and classification algorithm utilizes a new custom preconditioning method called <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Multi-Mapping Spherical Normalization (MMSN)</i> , in combination with a Support Vector Machine with Radial Basis Function Kernel (RBF-SVM). This new preconditioning algorithm allows to sparse the raw inertial data to increase successful classification results without adding any computational burden. The presented approach achieves a motion classification accuracy of 98.28% for 12 body motions, while allowing for real-time prediction with low latency output (< 20 ms which is 50% less than some studies) for preconditioning and processing thanks to the new MMSN preconditioning method and the use of raw data. We tested our approach with 10 able-bodied subjects.

A Data Driven End-to-End Approach for In-the-Wild Monitoring of Eating Behavior Using Smartwatches

The increased worldwide prevalence of obesity has sparked the interest of the scientific community towards tools that objectively and automatically monitor eating behavior. Despite the study of obesity being in the spotlight, such tools can also be used to study eating disorders (e.g. anorexia nervosa) or provide a personalized monitoring platform for patients or athletes. This paper presents a complete framework towards the automated i) modeling of in-meal eating behavior and ii) temporal localization of meals, from raw inertial data collected in-the-wild using commercially available smartwatches. Initially, we present an end-to-end Neural Network which detects food intake events (i.e. bites). The proposed network uses both convolutional and recurrent layers that are trained simultaneously. Subsequently, we show how the distribution of the detected bites throughout the day can be used to estimate the start and end points of meals, using signal processing algorithms. We perform extensive evaluation on each framework part individually. Leave-one-subject-out (LOSO) evaluation shows that our bite detection approach outperforms four state-of-the-art algorithms towards the detection of bites during the course of a meal (0.923 F1 score). Furthermore, LOSO and held-out set experiments regarding the estimation of meal start/end points reveal that the proposed approach outperforms a relevant approach found in the literature (Jaccard Index of 0.820 and 0.821 for the LOSO and held-out experiments, respectively). Experiments are performed using our publicly available FIC and the newly introduced FreeFIC datasets.

Motion Sensors-Based Machine Learning Approach for the Identification of Anterior Cruciate Ligament Gait Patterns in On-the-Field Activities in Rugby Players.

Anterior cruciate ligament (ACL) injuries are common among athletes. Despite a successful return to sport (RTS) for most of the injured athletes, a significant proportion do not return to competitive levels, and thus RTS post ACL reconstruction still represents a challenge for clinicians. Wearable sensors, owing to their small size and low cost, can represent an opportunity for the management of athletes on-the-field after RTS by providing guidance to associated clinicians. In particular, this study aims to investigate the ability of a set of inertial sensors worn on the lower-limbs by rugby players involved in a change-of-direction (COD) activity to differentiate between healthy and post-ACL groups via the use of machine learning. Twelve male participants (six healthy and six post-ACL athletes who were deemed to have successfully returned to competitive rugby and tested in the 5–10 year period following the injury) were recruited for the study. Time- and frequency-domain features were extracted from the raw inertial data collected. Several machine learning models were tested, such as k-nearest neighbors, naïve Bayes, support vector machine, gradient boosting tree, multi-layer perceptron, and stacking. Feature selection was implemented in the learning model, and leave-one-subject-out cross-validation (LOSO-CV) was adopted to estimate training and test errors. Results obtained show that it is possible to correctly discriminate between healthy and post-ACL injury subjects with an accuracy of 73.07% (multi-layer perceptron) and sensitivity of 81.8% (gradient boosting). The results of this study demonstrate the feasibility of using body-worn motion sensors and machine learning approaches for the identification of post-ACL gait patterns in athletes performing sport tasks on-the-field even a number of years after the injury occurred.

Robust Data-Driven Zero-Velocity Detection for Foot-Mounted Inertial Navigation

We present two novel techniques for detecting zero-velocity events to improve foot-mounted inertial navigation. Our first technique augments a classical zero-velocity detector by incorporating a motion classifier that adaptively updates the detector's threshold parameter. Our second technique uses a long short-term memory (LSTM) recurrent neural network to classify zero-velocity events from raw inertial data, in contrast to the majority of zero-velocity detection methods that rely on basic statistical hypothesis testing. We demonstrate that both of our proposed detectors achieve higher accuracies than existing detectors for trajectories including walking, running, and stair-climbing motions. Additionally, we present a straightforward data augmentation method that is able to extend the LSTM-based model to different inertial sensors without the need to collect new training data.

An End-to-End Multi-Task and Fusion CNN for Inertial-Based Gait Recognition

People identification using gait information (i.e., the way a person walks) obtained from inertial sensors is a robust approach that can be used in multiple situations where vision-based systems are not applicable. Typically, previous methods use hand-crafted features or deep learning approaches with pre-processed features as input. In contrast, we present a new deep learning-based end-to-end approach that employs raw inertial data as input. By this way, our approach is able to automatically learn the best representations without any constraint introduced by the pre-processed features. Moreover, we study the fusion of information from multiple inertial sensors and multi-task learning from multiple labels per sample. Our proposal is experimentally validated on the challenging dataset OU-ISIR, which is the largest available dataset for gait recognition using inertial information. After conducting an extensive set of experiments to obtain the best hyper-parameters, our approach is able to achieve state-of-the-art results. Specifically, we improve both the identification accuracy (from 83.8% to 94.8%) and the authentication equal-error-rate (from 5.6 to 1.1). Our experimental results suggest that: 1) the use of hand-crafted features is not necessary for this task as deep learning approaches using raw data achieve better results; 2) the fusion of information from multiple sensors allows to improve the results; and, 3) multi-task learning is able to produce a single model that obtains similar or even better results in multiple tasks than the corresponding models trained for a single task.

Hankelet-based action classification for motor intention recognition

Powered lower-limb prostheses require a natural, and an easy-to-use, interface for communicating amputee’s motor intention in order to select the appropriate motor program in any given context, or simply to commute from active (powered) to passive mode of functioning. To be widely accepted, such an interface should not put additional cognitive load at the end-user, it should be reliable and minimally invasive.In this paper we present a one such interface based on a robust method for detecting and recognizing motor actions from a low-cost wearable sensor network mounted on a sound leg providing inertial (accelerometer, gyrometer and magnetometer) data in real-time. We assume that the sensor measurement trajectories – in a given temporal window – can be represented as the output of a linear time invariant system. We describe such set of trajectories via a Hankel matrix, which embeds the observability matrix of the LTI system generating the set of trajectories. The use of Hankel matrices (known as Hankelets) avoids the burden of performing system identification while providing a computationally convenient descriptor for the dynamics of a time-series.For the recognition of actions, we use two off-the-shelf classifiers, nearest neighbor (NN) and support vector machines (SVM), in cross-subject validation. We present results using either the joint angles or the raw sensor data showing a net improvement of the Hankelet-based approach against a baseline method. In addition, we compare results on action recognition using joint angles provided by trakSTAR, a high-accuracy motion tracking unit, demonstrating – somewhat surprisingly – that best results (in terms of average recognition accuracy over different actions) are provided by raw inertial data, paving the way towards a wider usage of our method in the field of active prosthetics, in particular, and motor intention recognition, in general.

A Waist-Worn Inertial Measurement Unit for Long-Term Monitoring of Parkinson's Disease Patients.

Inertial measurement units (IMUs) are devices used, among other fields, in health applications, since they are light, small and effective. More concretely, IMUs have been demonstrated to be useful in the monitoring of motor symptoms of Parkinson’s disease (PD). In this sense, most of previous works have attempted to assess PD symptoms in controlled environments or short tests. This paper presents the design of an IMU, called 9 × 3, that aims to assess PD symptoms, enabling the possibility to perform a map of patients’ symptoms at their homes during long periods. The device is able to acquire and store raw inertial data for artificial intelligence algorithmic training purposes. Furthermore, the presented IMU enables the real-time execution of the developed and embedded learning models. Results show the great flexibility of the 9 × 3, storing inertial information and algorithm outputs, sending messages to external devices and being able to detect freezing of gait and bradykinetic gait. Results obtained in 12 patients exhibit a sensitivity and specificity over 80%. Additionally, the system enables working 23 days (at waking hours) with a 1200 mAh battery and a sampling rate of 50 Hz, opening up the possibility to be used for other applications like wellbeing and sports.

Dead Reckoning in a Dynamic Quadruped Robot Based on Multimodal Proprioceptive Sensory Information

It is an important ability for any mobile robot to be able to estimate its posture and to gauge the distance it traveled. In this paper, we have addressed this problem in a dynamic quadruped robot by combining traditional state estimation methods with machine learning. We have designed and implemented a navigation algorithm for full body state (position, velocity, and attitude) estimation that uses no external reference but relies on multimodal proprioceptive sensory information only. The extended Kalman filter (EKF) was used to provide error estimation and data fusion from two independent sources of information: 1) strapdown mechanization algorithm processing raw inertial data and 2) legged odometry. We have devised a novel legged odometer that combines information from a multimodal combination of sensors (joint and pressure). We have shown our method to work for a dynamic turning gait, and we have also successfully demonstrated how it generalizes to different velocities and terrains. Furthermore, our solution proved to be immune to substantial slippage of the robot's feet.