Inertial Measurement Unit Sensor Research Articles

State-of-the-art in human activity recognition based on inertial measurement unit sensors: survey and applications

State-of-the-art in human activity recognition based on inertial measurement unit sensors: survey and applications

Construct Validity of a Wearable Inertial Measurement Unit (IMU) in Measuring Postural Sway and the Effect of Visual Deprivation in Healthy Older Adults

Inertial Motor sensors (IMUs) are valid instruments for measuring postural sway but their ability to detect changes derived from visual deprivation in healthy older adults requires further investigations. We examined the validity and relationship of IMU sensor-derived postural sway measures compared to force plates for different eye conditions in healthy older adults (32 females, 33 males). We compared the relationship of the center of mass and center of pressure (CoM and CoP)-derived total length, root means square (RMS) distance, mean velocity, and 95% confidence interval ellipse area (95% CI ellipse area). In addition, we examined the relationship of the IMU sensor in discriminating between open- (EO) and closed-eye (EC) conditions compared to the force plate. A significant effect of the instruments and eye conditions was found for almost all the variables. Overall, EO and EC variables within (force plate r, from 0.38 to 0.78; IMU sensor r, from 0.36 to 0.69) as well as between (r from 0.50 to 0.88) instruments were moderately to strongly correlated. The EC:EO ratios of RMS distance and 95% CI ellipse area were not different between instruments, while there were significant differences between total length (p = 0.973) and mean velocity (p = 0.703). The ratios’ correlation coefficients between instruments ranged from moderate (r = 0.65) to strong (r = 0.87). The IMU sensor offers an affordable, valid alternative to a force plate for objective, postural sway assessment.

Comparing feature usage in IMU-based gesture control for omnidirectional robot via wearable glove

<span>To improve the intuitiveness of maneuver control on omniwheeled mobile robot, many hand gesture-based robot controls have been developed. The focus of this research is to develop a wearable system for data acquisition from inertial measurement unit (IMU) sensors and compare its features to be used as gesture recognition using the random forest algorithm. With the need of resource constrained device for wearable system based on microcontrollers, we compared the use of Euler and quaternion-based orientation data as input features. As additional comparison, dimension reduction was also carried out using the principal component analysis (PCA) method. Hand gestures are recognized using data obtained by the IMU sensor embedded in the wearable glove. This study compared the accuracy and size of library files embedded in microcontrollers in several feature usage scenarios. The test evaluation results of all scenarios show that the use of all features provides a balance between high accuracy but small file sizes, respectively 99% and 9.2 KB. However, the use of other fewer features, such as by only using 3 Euler data, 4 quaternion data, or by using PCA algorithm (PC=3) can also be used since the accuracy is still above 90%, with a relatively larger file size.</span>

RingGesture: A Ring-Based Mid-Air Gesture Typing System Powered by a Deep-Learning Word Prediction Framework.

Text entry is a critical capability for any modern computing experience, with lightweight augmented reality (AR) glasses being no exception. Designed for all-day wearability, a limitation of lightweight AR glass is the restriction to the inclusion of multiple cameras for extensive field of view in hand tracking. This constraint underscores the need for an additional input device. We propose a system to address this gap: a ring-based mid-air gesture typing technique, RingGesture, utilizing electrodes to mark the start and end of gesture trajectories and inertial measurement units (IMU) sensors for hand tracking. This method offers an intuitive experience similar to raycast-based mid-air gesture typing found in VR headsets, allowing for a seamless translation of hand movements into cursor navigation. To enhance both accuracy and input speed, we propose a novel deep-learning word prediction framework, Score Fusion, comprised of three key components: a) a word-gesture decoding model, b) a spatial spelling correction model, and c) a lightweight contextual language model. In contrast, this framework fuses the scores from the three models to predict the most likely words with higher precision. We conduct comparative and longitudinal studies to demonstrate two key findings: firstly, the overall effectiveness of RingGesture, which achieves an average text entry speed of 27.3 words per minute (WPM) and a peak performance of 47.9 WPM. Secondly, we highlight the superior performance of the Score Fusion framework, which offers a 28.2% improvement in uncorrected Character Error Rate over a conventional word prediction framework, Naive Correction, leading to a 55.2% improvement in text entry speed for RingGesture. Additionally, RingGesture received a System Usability Score of 83 signifying its excellent usability.

Utilizing Inertial Measurement Units for Detecting Dynamic Stability Variations in a Multi-Condition Gait Experiment.

This study proposes a wearable gait assessment method using inertial measurement units (IMUs) to evaluate gait ability in daily environments. By focusing on the estimation of the margin of stability (MoS), a key kinematic stability parameter, a method using a convolutional neural network, was developed to estimate the MoS from IMU acceleration time-series data. The relationship between MoS and other stability indices, such as the Lyapunov exponent and the multi-site time-series (MSTS) index, using data from five IMU sensors placed on various body parts was also examined. To simulate diverse gait conditions, treadmill speed was varied, and a knee-ankle-foot orthosis was used to restrict left knee extension, inducing gait asymmetry. The model achieved over 90% accuracy in classifying MoS in both forward and lateral directions using three-axis acceleration data from the IMUs. However, the correlation between MoS and the Lyapunov exponent or MSTS index was weak, suggesting that these indices may capture different aspects of gait stability.

A Novel Nonlinear Stochastic-Resonance-Enhanced Acceleration Data Processing Approach

Abstract. Smartphones are indispensable tools in modern social life, and they can be used for online shopping, electronic payment, gaming, and navigation. In particular, low-cost inertial measurement unit (IMU) sensors are widely integrated into smartphones, so pedestrian dead reckoning (PDR) positioning techniques based on smartphone IMU sensors have been applied and developed. PDR positioning techniques require acceleration data for step detection, step length estimation, and step heading estimation. However, due to the cost limitations of the built-in IMU sensor in smartphones, acceleration data contains measurement noise and interference, resulting in poor consistency in acceleration peak detection and the generation of false peaks, which is not conducive to step detection and accurate step length estimation. Therefore, this paper proposes a stochastic resonance (SR) enhancement method for smartphone IMU acceleration data. The SR-enhanced acceleration data has better peak consistency and is conducive to step detection. Finally, the algorithm is evaluated using actual measurement data collected from a smartphone. The results show that the SR-enhanced acceleration data has excellent peak consistency and higher step detection accuracy.

Quantifying Hand Motion Complexity in Simulated Sailing Using Inertial Sensors.

The control of hand movement during sailing is important for performance. To quantify the amount of regularity and the unpredictability of hand fluctuations during the task, the mathematical algorithm Approximate Entropy (ApEn) of the hand acceleration can be used. Approximate Entropy is a mathematical algorithm that depends on the combination of two input parameters including (1) the length of the sequences to be compared (m), and (2) the tolerance threshold for accepting similar patterns between two segments (r). The aim of this study is to identify the proper combinations of 'm' and 'r' parameter values for ApEn measurement in the hand movement acceleration data during sailing. Inertial Measurement Units (IMUs) recorded acceleration data for both the mainsail (non-dominant) and tiller (dominant) hands across the X-, Y-, and Z-axes, as well as vector magnitude. ApEn values were computed for 24 parameter combinations, with 'm' ranging from 2 to 5 and 'r' from 0.10 to 0.50. The analysis revealed significant differences in acceleration ApEn regularity between the two hands, particularly along the Z-axis, where the mainsail hand exhibited higher entropy values (p = 0.000673), indicating greater acceleration complexity and unpredictability. In contrast, the tiller hand displayed more stable and predictable acceleration patterns, with lower ApEn values. ANOVA results confirmed that parameter 'm' had a significant effect on acceleration complexity for both hands, highlighting differing motor control demands between the mainsail and tiller hands. These findings demonstrate the utility of IMU sensors and ApEn in detecting nuanced variations in acceleration dynamics during sailing tasks. This research contributes to the understanding of hand-specific acceleration patterns in sailing and provides a foundation for further studies on adaptive sailing techniques and motor control strategies for both novice and expert sailors.

Modified tai chi movement training based on sEMG and movement analysis on improving upper extremities motor function: a protocol for a clinical randomised controlled trial

IntroductionStroke survivors often face motor dysfunction, increasing fall risk. Lower extremity muscle weakness is a key factor affecting walking ability. Tai chi (TC) has been shown to improve muscle strength...

Simple and efficient step detection algorithm for foot-mounted IMU

Abstract This paper presents a concise, efficient, and adaptive step detection algorithm based on foot-mounted inertial measurement unit sensors. The proposed method maps the temporal values of pedestrian motion and gait diversity into two variables: the distance between peaks and valleys, and the slope. Compared to traditional sliding window methods, this approach amplifies the differences between normal and abnormal steps, allowing it to adapt to various indoor activities such as fast walking, slow walking, running, jogging, standing still, and turning. By incorporating adaptive factors, it addresses the challenge of detecting steps while going up and down stairs. The proposed algorithm overcomes the limitations of traditional adaptive threshold methods that require different temporal and peak thresholds for various gait conditions. By utilizing the significant differences in distance and slope, it effectively resolves the issue of detecting steps during stationary periods. Unlike neural network-based gait classifiers, this algorithm does not need to account for multiple gait conditions, thereby simplifying the training process. Experimental results demonstrate that the algorithm achieves an average accuracy of over 99% under mixed indoor walking conditions and over 98% accuracy in long-term outdoor walking conditions.

UWB/IMU integrated indoor positioning algorithm based on robust extended Kalman filter

Abstract As a fundamental method for integrated indoor positioning, Ultra wideband (UWB)/ Inertial Measurement Unit (IMU) offers more stable performance compared to separate UWB sensor and IMU sensor positioning and uses the least squares (LS) and extended Kalman filter (EKF) for positioning processing, however, the performance of conventional LS and EKF will be seriously affected when the contamination rate of measurement noise is high. To address this problem, this paper proposes a robust extended Kalman filter (REKF) based algorithm for robot-integrated indoor positioning, which combines UWB and IMU positioning methods to obtain a more robust system performance and optimal positioning accuracy. In this paper, a vehicle equipped with a UWB/IMU sensor and four anchor points is set up to perform linear, circular, and trajectory motions in an experimental environment with visible obstacles. The experimental results show that compared with EKF, REKF improves the localization precision and accuracy in the three motions by 20.98%, 35.51%, and 47.06%, respectively. REKF effectively improves the accuracy and robustness of the robot’s indoor positioning, and provides an improved and practical method for integrated indoor positioning algorithms to make indoor positioning more accurate and reliable.

Real-Time Forward Head Posture Detection and Correction System Utilizing an Inertial Measurement Unit Sensor

Forward head posture (FHP) has become a prevailing health issue in modern society as people spend more time on computers and smartphones. FHP is a posture where the head is forward and the anterior and posterior curvatures of the lower cervical and upper thoracic spines are both, respectively, exaggerated. FHP is often associated with neck pain, bad static balance, and hunched shoulders or back. To prevent this, consciously maintaining good posture is important. Therefore, in this study, we propose a system that gives users real-time, accurate information about their neck posture, and it also encourages them to maintain a good posture. This inexpensive system utilizes a single inertial measurement unit sensor and a Raspberry Pi system to detect the changes in state that can progress to an FHP. It retrieves data from the sensor attached to the user’s cervical spine to indicate their real-time posture. In a real-world office environment experiment with ten male participants, the system accurately detected the transition to the FHP state for more than 10 s, with a delay of less than 0.5 s, and it also provided personalized feedback to encourage them to maintain good posture. All ten participants recognized that their average craniovertebral angle had to be increased after receiving visual alerts regarding their poor postures in real time. The results indicate that the system has potential for widespread applications.

Enabling Technologies and Techniques for Floor Identification

Location information has initiated a multitude of applications such as location-based services, health care, emergency response and rescue operations, and assets tracking. A plethora of techniques and technologies have been presented to ensure enhanced location accuracy, both horizontal and vertical. Despite many surveys covering horizontal localization technologies, the literature lacks a comprehensive survey incorporating up-to-date vertical localization approaches. This article provides a detailed survey of different vertical localization techniques such as path loss models, time of arrival, received signal strength, reference signal received power, fingerprinting utilized by WiFi, radio-frequency identification (RFID), global system for mobile communications (GSM), long-term evolution (LTE), barometer, inertial measurement unit (IMU) sensors, and geomagnetic field. The article primarily aims at human localization in indoor environments using smartphones in essence. Besides the localization accuracy, the presented approaches are evaluated in terms of cost, infrastructure dependence, deployment complexity, and sensitivity. We highlight the pros and cons of these approaches and outline future research directions to enhance the accuracy to meet the future needs of floor identification standards set by the Federal Communications Commission.

Older Adult Fall Risk Prediction with Deep Learning and Timed Up and Go (TUG) Test Data.

Falls are a major health hazard for older adults; therefore, in the context of an aging population, predicting the risk of a patient suffering falls in the near future is of great impact for health care systems. Currently, the standard prospective fall risk assessment instrument relies on a set of clinical and functional mobility assessment tools, one of them being the Timed Up and Go (TUG) test. Recently, wearable inertial measurement units (IMUs) have been proposed to capture motion data that would allow for the building of estimates of fall risk. The hypothesis of this study is that the data gathered from IMU readings while the patient is performing the TUG test can be used to build a predictive model that would provide an estimate of the probability of suffering a fall in the near future, i.e., assessing prospective fall risk. This study applies deep learning convolutional neural networks (CNN) and recurrent neural networks (RNN) to build such predictive models based on features extracted from IMU data acquired during TUG test realizations. Data were obtained from a cohort of 106 older adults wearing wireless IMU sensors with sampling frequencies of 100 Hz while performing the TUG test. The dependent variable is a binary variable that is true if the patient suffered a fall in the six-month follow-up period. This variable was used as the output variable for the supervised training and validations of the deep learning architectures and competing machine learning approaches. A hold-out validation process using 75 subjects for training and 31 subjects for testing was repeated one hundred times to obtain robust estimations of model performances At each repetition, 5-fold cross-validation was carried out to select the best model over the training subset. Best results were achieved by a bidirectional long short-term memory (BLSTM), obtaining an accuracy of 0.83 and AUC of 0.73 with good sensitivity and specificity values.

Estimation of aboveground biomass of Alfalfa using field robotics

Alfalfa is a high-yielding forage crop that is widely grown in the United States for grazing, hay and silage making. A proper maintenance of these grasslands is necessary to ensure optimum productivity and profits. The pre-harvest estimation of biomass yield helps in quantifying the profits and optimizing the forage allocation in advance. Most traditional methods of forage estimation are relatively laborious and time-consuming. Recent developments in contact and remote sensing technologies opened numerous paths for performing aboveground biomass estimation tasks with flexibility and easiness. This study focused on the development of crop height measurement systems for estimating the aboveground biomass yield of Alfalfa (Medicago sativa L.). Five different systems for measuring crop height were evaluated on their ability to estimate aboveground wet and dry biomass. The crop height measurement systems used in this study were Structure-from-Motion, Ultrasound Sensor and Ski, Inertial Measurement Unit and Ski, Inertial Measurement Units and Roller, and a Depth Camera. The results indicated that the system using the Inertial Measurement Unit sensor and ski (IMU-Ski) performed the best among ground-based methods (R2= 0.79; SeY= 3166 kg-wet/ha). The Structure-from-Motion (SfM) method using UAV also provided satisfactory results for biomass predictions (R2= 0.74; SeY= 2543 kg-wet/ha). The models based on IMU-Ski and UAV-based SfM methods were facilitated with vegetation coverage as an additional independent variable to evaluate their effect on biomass predictions. The results indicated that the vegetation coverage did not improve the predictions in any of these systems. Thus, the models based on only the crop height (IMU-Ski and UAV-SfM) were the recommended approaches for Alfalfa biomass estimations. The addition of data points for wide ranges of crop height and vegetation coverage is recommended for future studies to improve the results and ensure the adaptability of these systems in varying environmental conditions.

Analyzing Optimal Wearable Motion Sensor Placement for Accurate Classification of Fall Directions.

Falls represent a significant risk factor, necessitating accurate classification methods. This study aims to identify the optimal placement of wearable sensors-specifically accelerometers, gyroscopes, and magnetometers-for effective fall-direction classification. Although previous research identified optimal sensor locations for distinguishing falls from non-falls, limited attention has been given to the classification of fall direction across different body regions. This study assesses inertial measurement unit (IMU) sensors placed at 12 distinct body locations to determine the most effective positions for capturing fall-related data. The research was conducted in three phases: first, comparing classifiers across all sensor locations to identify the most effective; second, evaluating performance differences between sensors placed on the left and right sides of the body; and third, exploring the efficacy of combining sensors from the upper and lower body regions. Statistical analyses of the results for the most effective classifier model demonstrate that the support vector machine (SVM) is more effective than other classifiers across all sensor locations, with statistically significant differences in performance. At the same time, the comparison between the left and right sensor locations shows no significant performance differences within the same anatomical areas. Regarding optimal sensor placement, the findings indicate that sensors positioned on the pelvis and upper legs in the lower body, as well as on the shoulder and head in the upper body, were the most effective results for accurate fall-direction classification. The study concludes that the optimal sensor configuration for fall-direction classification involves strategically combining sensors placed on the pelvis, upper legs, and lower legs.

UWB distance estimation errors in (non-)line of sight situations within the context of 3D analysis of human movement

Abstract Integrated Ultrawideband (UWB) and Magnetic Inertial Measurement Unit (MIMU) sensors are becoming popular for indoor localization applications, as a higher accuracy can be achieved than with just MIMU sensors. These integrated sensors could extend stability and accuracy in the field of 3D analysis of human movement (3D AHM) if they can deliver position estimates with an accuracy close to 1 cm. Achieving this high accuracy of 1 cm remains challenging, with most studies reporting position estimation errors around 5 cm, often due to Non-Line of Sight (NLOS) conditions and systematic UWB sensor distance estimation errors. Studying the distance error characteristic of UWB in situations of 3D AHM is essential to deal with these errors. While research on UWB distance errors in Line of Sight (LOS) and NLOS situations exists, few studies focus on the NLOS errors caused by the human body and were not in the relevant scenarios of 3D AHM. Therefore, this article examines UWB sensor performance and distance error characteristics in LOS and NLOS situations typical for the 3D AHM. Both the LOS and NLOS situations were studied in the typical 3D AHM distance range of 0.2 m to 2 m. The NLOS situations were studied first with a human subject as NLOS causing object and then with simulated human body segments (PVC pipes filled with water) of varying diameters. In LOS situations, consistent systematic bias errors were observed, along with incidental errors at specific positions in the room. In NLOS scenarios caused by the human and simulated body segments, a consistent and reproducible overestimation of distances was found. The reproducibility of these errors based on relative node and object positions suggests that systematic mitigation methods could significantly reduce errors, enabling more accurate and reproducible 3D human movement analysis.

Evaluation of Autonomous Navigation and Path Accuracy for Unmanned Surface Vehicles Using IMU Sensor and GPS Data

The development of autonomous systems for environmental monitoring is becoming increasingly important. This project focuses on creating a robotic marine vessel, Aqua Sense, for efficient water quality monitoring. Existing methods are often labour-intensive, time-consuming, and lack real-time data capability. The objective is to develop a robotic vessel with autonomous navigation for water quality applications. A comprehensive design approach, including a literature review and careful component selection, was employed. Key components include the Arduino Mega, Blue Robotics T200 thruster, GlobalSat BU-353N5 GPS sensor, BNO055 Inertial Measurement Unit (IMU), and a Li-po 11.1v battery. In this paper, several field trials data collection is presented to evaluate the navigation algorithm. These findings validate the feasibility of Aqua Sense for real-world applications. The varying distance errors at points B and C demonstrate an error range, with a maximum error of approximately 1.130m at point B (about 0.11% of the target location) and a significant variation at point C, reaching up to 1.660m (approximately 0.15%).

Effects of wearable device training on upper limb motor function in patients with stroke: a systematic review and meta-analysis.

To evaluate the effect of wearable device training on improving upper limb motor function in patients who experienced strokes. The PubMed, Embase, Cochrane Library, Web of Science, MEDLINE, SCOPUS, China National Knowledge Infrastructure, WanFang, and VIP databases were searched for randomized controlled trials (RCTs) that assessed the effectiveness of wearable device training in improving upper limb motor function in patients with stroke. Two investigators independently screened studies by their titles and abstracts and cross-checked, downloaded, and evaluated the results. Disagreements were resolved by a third highly experienced researcher. Risk of bias was evaluated using the Cochrane risk-of-bias tool. This meta-analysis was registered in PROSPERO (registration No. CRD42023421633). This study comprised 508 patients from 14 RCTs. The experimental group assessed various wearable devices, including 3D-printed dynamic orthoses, inertial measurement unit (IMU) sensors, electrical stimulation devices, and virtual reality (VR) devices for virtual interactive training. The control group received traditional rehabilitation therapies, including physical and conventional rehabilitation. The experimental group scored better on the Fugl-Meyer Assessment (FMA-UE) scale (standardized mean difference [SMD] 0.26, 95% confidence interval [CI] 0.07, 0.45) and Box and Block Test (BBT) (SMD 0.43, 95% CI 0.17, 0.69) versus controls. No significant intergroup differences were observed in the Action Research Arm Test (SMD 0.20, 95% CI -0.15, 0.55), motor activity log (mean difference [MD] 0.32, 95% CI -0.54, 0.33), and modified Ashworth scale (MD -0.08, 95% CI -0.81, 0.64). The probability rankings of wearable devices that improved FMA-UE scores in patients with stroke were: orthotic devices, with the highest probability ranking of 0.45, followed by sensor devices at 0.23, electrical stimulation devices at 0.21, and VR devices at 0.11. Wearable device training was found to significantly improve upper limb motor function in patients with stroke, particularly for large-range movements. Improvements in FMA-UE and BBT scores reflected reduced impairment and enhanced manual dexterity, respectively. However, the training had no significant effect on hand movement frequency, fine motor skills, or spasticity. Among the different wearable devices tested, orthoses produced the most effective results.

Personalized food consumption detection with deep learning and Inertial Measurement Unit sensor

For individuals diagnosed with diabetes mellitus, it is crucial to keep a record of the carbohydrates consumed during meals, as this should be done at least three times daily, amounting to an average of six meals. Unfortunately, many individuals tend to overlook this essential task. For those who use an artificial pancreas, carbohydrate intake proves to be a critical factor, as it can activate the insulin pump in the artificial pancreas to deliver insulin to the body. To address this need, we have developed personalized deep learning model that can accurately detect carbohydrate intake with a high degree of accuracy. Our study employed a publicly available dataset gathered by an Inertial Measurement Unit (IMU), which included accelerometer and gyroscope data. The data was sampled at a rate of 15 Hz, necessitating preprocessing. For our tailored to the patient model, we utilized a recurrent network comprising Long short-term memory (LSTM) layers. Our findings revealed a median F1 score of 0.99, indicating a high level of accuracy. Additionally, the confusion matrix displayed a difference of only 6 s, further validating the model’s accuracy. Therefore, we can confidently assert that our model architecture exhibits a high degree of accuracy. Our model performed well above 90% on the dataset, with most results between 98%–99%. The recurrent networks improved the problem-solving capabilities significantly, though some outliers remained. The model’s average prediction latency was 5.5 s, suggesting that later meal predictions result in extended meal progress predictions. The dataset’s limitation of mostly single-day data points raises questions about multi-day performance, which could be explored by collecting multi-day data, including night periods. Future enhancements might involve transformer networks and shorter time windows to improve model responsiveness and accuracy. Therefore, we can confidently assert that our model exhibits a high degree of accuracy.

Machine Learning-Based Gesture Recognition Glove: Design and Implementation.

In the evolving field of human-computer interaction (HCI), gesture recognition has emerged as a critical focus, with smart gloves equipped with sensors playing one of the most important roles. Despite the significance of dynamic gesture recognition, most research on data gloves has concentrated on static gestures, with only a small percentage addressing dynamic gestures or both. This study explores the development of a low-cost smart glove prototype designed to capture and classify dynamic hand gestures for game control and presents a prototype of data gloves equipped with five flex sensors, five force sensors, and one inertial measurement unit (IMU) sensor. To classify dynamic gestures, we developed a neural network-based classifier, utilizing a convolutional neural network (CNN) with three two-dimensional convolutional layers and rectified linear unit (ReLU) activation where its accuracy was 90%. The developed glove effectively captures dynamic gestures for game control, achieving high classification accuracy, precision, and recall, as evidenced by the confusion matrix and training metrics. Despite limitations in the number of gestures and participants, the solution offers a cost-effective and accurate approach to gesture recognition, with potential applications in VR/AR environments.