Inertial Sensors Research Articles

RaDro: Indoor Drone Tracking Using Millimeter Wave Radar

Core to drone design is its ability to ascertain its location by utilizing onboard inertial sensors combined with GPS data. However, GPS is not always reachable, especially in challenging environments such as indoors. This paper proposes RaDro; a system that leverages millimeter-waves (mmWave) to precisely localize and track drones in indoor environments. Unlike commonly used alternative technologies, RaDro is cost-effective and can penetrate obstacles, a bonus in non-line-of-sight (NLoS) scenarios, which enhances its reliability for tracking objects in complex environments. It does this without the need for tags or anchors to be attached to the drone, achieving 3D tracking with just a single radar point, significantly streamlining the deployment process. Comprehensive experiments are conducted in different scenarios to evaluate RaDro's performance. These include employing different drone models with different sizes to execute a range of aerial manoeuvres across different flight arenas, each with its own settings and clutter, and encountering various LoS and NLoS scenarios in dynamic environments. The experiments aimed to assess the capabilities of the system to extract coarse-grained and fine-grained information for drone detection, motion recognition, and localization. The results showcase precise localization, achieving a 50% reduction in localization error compared to the conventional baseline. This localization accuracy remains resilient even when confronted with interference from other moving sources. The results also demonstrate the system's ability to accurately localize drones in NLoS scenarios where existing state-of-the-art optical technologies cannot work.

Load increases IMU signal attenuation per step but reduces IMU signal attenuation per kilometre

BackgroundDespite deleterious biomechanics associated with injury, particularly as it pertains to load carriage, there is limited research on the association between physical demands and variables captured with wearable sensors. While inertial measurement units (IMUs) can be used as surrogate measures of ground reaction force (GRF) variables, it is unclear if these data are sensitive to military-specific task demands. Research questionCan wearable sensors characterise physical load and demands placed on individuals in different load, speed and grade conditions? MethodsData were collected on 20 individuals who were self-reportedly free from current injury, recreationally active, and capable of donning 23 kg in the form of a weighted vest. Each participant walked and ran on flat, uphill (+6 %) and downhill (-6 %) without and with load (23 kg). Data were collected synchronously from optical motion capture (OMC) and IMUs placed on the distal limb and the pelvis. Data from an 8-second window was used to generate a participant-based mean of OMC and IMU variables of interest. Repeated Measures ANOVA was used to measure main and interaction effects of load, speed, and grade. Simple linear regression was used to elucidate a relationship between OMC measures and estimated metabolic cost (EMC) to IMU measures. ResultsLoad reduces foot and pelvic accelerations (p<0.001) but elevate signal attenuation per step (p=0.044). Conversely, attenuation per kilometre is lowered with the addition of load (p=0.017). Uphill had the lowest attenuation per step (p=0.003) and kilometre (p≤0.033) in walking, while downhill had the greatest attenuation per step (p≤0.002) and per kilometre (p≤0.004). Attenuation measures are inconsistently moderately related to limb negative work (R≤0.57). EMC is moderately positively related to unloaded running (R≥0.39), and moderately negatively related to walking with and without load (R≤-0.52). SignificanceWhile load reduces peak accelerations at both the pelvis and foot. However, it may increase demand on the lower extremity to attenuate the signal between the two sensors with each step, while attenuation over time reduces with load.

LDVI-SLAM: A Lightweight Monocular Visual-Inertial SLAM System for Dynamic Environments Based on Motion Constraints

Abstract Traditional Simultaneous Localization and Mapping (SLAM) systems are typically based on the assumption of a static environment. However, in practical applications, the presence of moving objects significantly reduces localization accuracy, limiting the system's versatility. To address the challenges of SLAM systems in dynamic environments, the academic community often employs computationally intensive methods such as deep learning, and some algorithms rely on expensive sensors (e.g., LiDAR or RGBD cameras) to obtain depth information. These factors increase computational complexity or hardware costs, complicating practical deployment. To improve localization accuracy and adaptability of SLAM systems in dynamic scenarios while maintaining low deployment costs, this paper proposes a dynamic environment robust monocular inertial SLAM system named LDVI-SLAM. The system uses more cost-effective sensors—monocular cameras and Inertial Measurement Unit (IMU)—along with lightweight computational methods. In LDVI-SLAM, first, the reliability of IMU data is verified. Then, using the ego-motion information provided by the IMU, along with epipolar constraint and an improved Rotation-aware Flow Vector Bound (R-FVB) constraint, dynamic feature points are eliminated. Additionally, this paper proposes a continuous tracking across interval frames method to enhance the distinction between static and dynamic feature points. Experimental results demonstrate that LDVI-SLAM performs effectively in dynamic environments and is easy to deploy. On the VIODE dataset, experimental results show that compared to the deep learning-based DynaSLAM, this method reduces the RMSE (Root Mean Square Error) of absolute trajectory error by 10.3%. Moreover, in terms of speed, under the same computing power, the single-frame processing speed of this method is comparable to ORB-SLAM3 and is two orders of magnitude faster than DynaSLAM, significantly outperforming deep learning-based SLAM algorithms. Experiments on the OMD dataset further prove that this method effectively avoids the risk of semantic classification errors, demonstrating better robustness and generality.

Measuring the Effect of an Ergonomic Lecture on the Rapid Upper Limb Assessment Scores of Dental Assistant Students Using Inertial Sensor-Based Motion Capture-A Randomized Controlled Study.

Individuals working in the field of dentistry have a high prevalence of musculoskeletal disorders (MSDs) owing to monotonous and one-sided physical exertion. Inertial measurement units (IMU) are increasingly shifting into focus for assessing postural risk at work. Therefore, the present study aimed to evaluate the effects of an ergonomic lecture and training intervention on postural risk and MSDs in dental assistant students using inertial sensor-based motion capture (MoCap). Eighteen female dental assistant students (age: 19.44 ± 6.83 years; height: 164.59 ± 5.32 cm; weight: 64.88 ± 16.52 kg; BMI: 19.70 ± 4.89 kg/m2), randomly divided into intervention (n = 9) and control (n = 9) groups, participated in the present study. The participants completed the Nordic Questionnaire on MSD prevalence, after which a 90 s MoCap with Xsens IMU was performed. A lecture on ergonomics was provided, followed by a five-week intervention for the intervention group. Follow-up assessments were performed, and 5- and 18-week follow-up MSD questionnaires were administered. Mixed analysis of variance (MANOVA) showed a significant difference in the Rapid Upper Limb Assessment (RULA) and part-scores of the upper arm and wrist. Despite a reduction in MSDs, no significant differences in the time of measurement and groups were detected after the five-week training intervention and the 18-week follow-up questionnaire. A targeted ergonomics lecture was effective for dental assistant students, and technologies such as IMU improved workplace ergonomics in dentists. Further studies with a longer measurement periods, follow-up, and larger sample sizes are recommended.

Validity and Reliability of a Commercially Available Inertial Sensor for Measuring Barbell Mechanics during Weightlifting

This study aimed to assess the validity and reliability of a commercially available inertial measurement unit (Enode) for measuring barbell kinematics and kinetics during a snatch. In order to assess validity and within- and between-session reliability, thirteen competitive weightlifters conducted two snatches on two separate occasions at 85% of their one-repetition maximum. The Enode sensor was attached to the barbell, with each lift recorded via the device’s native application concurrently with an 11-camera motion capture system. Passing–Bablok regression indicated fixed and proportional bias in some horizontal measures of barbell mechanics but showed no bias in all but one vertical variable. Collectively, this suggests that the Enode is a valid tool in the measurement of vertically derived, but not horizontally derived, variables from barbell kinematics. Within- and between-session reliability showed moderate to excellent ICCs, with trivial to small differences between repetitions and between sessions. However, between-session reliability showed lower levels of variability and, thus, may help coaches identify changes in technique over time (between sessions) with good accuracy. Overall the Enode offers a practical and affordable option for coaches seeking to monitor weightlifting technique in training environments.

A multi-sensor fusion SLAM algorithm for indoor aerial robots

Nowdays, existing Light Detection and Ranging (LiDAR) based unknown-space-exploration Simultaneous Localization and Mapping (SLAM) methods have the problems of unstable mapping in feature-degraded environments and poor estimation accuracy in the vertical direction. To solve these problems, this study presents a multi-sensor fusion SLAM algorithm for indoor aerial robots as well as Unmanned Aerial Vehicles (UAVs). The sensors used in the multi-sensor fusion algorithm include optical flow sensor, barometer, Inertial Measurement Unit (IMU), and LiDAR. The proposed algorithm is named LiDAR-IMU-optical flow odometry fusion algorithm (Lioo). We derived and established a tightly coupled multi-sensor fusion framework based on factor graph optimisation. The IMU-optical flow pre-integration factor is proposed, and the barometer factor to the algorithm is added innovatively. Engineering applications are also realised in this paper. Flight experiments demonstrated that the proposed algorithm achieves more precise mapping and localisation of UAVs in indoor environments.

An experimental analysis of outdoor UAV localisation through diverse estimators and crowd-sensed data fusion

Motivated by the challenge of achieving precise 3D outdoor localisation for unmanned aerial vehicles (UAVs) in global navigation satellite system (GNSS)-denied environments, this paper introduces an innovative technique. Integrating crowd-sensed data fusion to counter inertial navigation system (INS) drift during GNSS signal outages, the proposed method exploits diverse estimators to enhance its efficacy. A micro lightweight frequency modulated continuous wave (FMCW) radar mounted on the UAV captures ground scatterer reflections, processed via fast Fourier transform (FFT) to generate a range-Doppler map. This map facilitates forward velocity estimation during GNSS signal loss. This approach employs adaptive thresholding, image binarisation, and connected components-based techniques for target detection from a computer vision standpoint. The derived radar-based velocity fuses with magnetometer, barometer, and inertial measurement unit (IMU) data using diverse estimators like extended Kalman filter (EKF) and particle filter (PF). Real-time flight data evaluation and simulated outage periods using EKF and PF validate the outdoor localisation system. Experimental analyses demonstrate substantial improvements, enhancing 3D positioning accuracy by 99.89% and 99.83% for the initial and subsequent flights, respectively, leveraging PF to fortify the standalone INS mode during GNSS signal loss. This approach significantly enhances UAV localisation precision, particularly in challenging GNSS-denied scenarios, showcasing the potential for real-world applications.

Design and Characterization of a Wearable Inertial Measurement Unit.

The utilization of inertial measurement units as wearable sensors is proliferating across various domains, such as health care, sports, and rehabilitation. This expansion has produced a market of devices tailored to accommodate very specific ranges of operational demands. Simultaneously, this growth is creating opportunities for the development of a new class of devices more oriented towards general-purpose use and capable of capturing both high-frequency signals for short-term, event-driven motion analysis and low-frequency signals for extended monitoring. For such a design, which combines flexibility and low cost, a rigorous evaluation of the device in terms of deviation, noise levels, and precision is essential. This evaluation is crucial for identifying potential improvements and refining the design accordingly, yet it is rarely addressed in the literature. This paper presents the development process of such a device. The results of the design process demonstrate acceptable performance in optimizing energy consumption and storage capacity while highlighting the most critical optimizations needed to advance the device towards the goal of a smart, general-purpose unit for human motion monitoring.

Online Handwriting Recognition Method with a Non-Inertial Reference Frame Based on the Measurement of Linear Accelerations and Differential Geometry: An Alternative to Quaternions.

This work describes a mathematical model for handwriting devices without a specific reference surface (SRS). The research was carried out on two hypotheses: the first considers possible circular segments that could be made during execution for the reconstruction of the trace, and the second is the combination of lines and circles. The proposed system has no flat reference surface, since the sensor is inside the pencil that describes the trace, not on the surface as in tablets or cell phones. An inertial sensor was used for the measurements, in this case, a commercial Micro-Electro Mechanical sensor of linear acceleration. The tracking device is an IMU sensor and a processing card that allows inertial measurements of the pen during on-the-fly tracing. It is essential to highlight that the system has a non-inertial reference frame. Comparing the two proposed models shows that it is possible to construct shapes from curved lines and that the patterns obtained are similar to what is recognized; this method provides an alternative to quaternion calculus for poorly specified orientation problems.

Revolutionizing Urban Pest Management with Sensor Fusion and Precision Fumigation Robotics

Effective pest management in urban areas is critically challenged by the rapid proliferation of mosquito breeding sites. Traditional fumigation methods expose human operators to harmful chemicals, posing significant health risks ranging from respiratory problems to long-term chronic conditions. To address these issues, a novel fumigation robot equipped with sensor fusion technology for optimal pest control in urban landscapes is proposed. The proposed robot utilizes light detection and ranging data, depth camera inputs processed through the You Only Look Once version 8 (YOLOv8) algorithm for precise object recognition, and inertial measurement unit data. These technologies allow the robot to accurately identify and localize mosquito breeding hotspots using YOLOv8, achieving a precision of 0.81 and a mean average precision of 0.74. The integration of these advanced sensor technologies allows for detailed and reliable mapping, enhancing the robot’s navigation through complex urban terrains and ensuring precise targeting of fumigation efforts. In a test case, the robot demonstrated a 62.5% increase in efficiency by significantly reducing chemical usage through targeted hotspot fumigation. By automating the detection and treatment of breeding sites, the proposed method boosts the efficiency and effectiveness of pest management operations and significantly diminishes the health risks associated with chemical exposure for human workers. This approach, featuring real-time object recognition and dynamic adaptation to environmental changes, represents a substantial advancement in urban pest management, offering a safer and more effective solution to a persistent public health issue.

Assessing the clinical utility of inertial sensors for home monitoring in Parkinson’s disease: a comprehensive review

This review screened 296 articles on wearable sensors for home monitoring of people with Parkinson’s Disease within the PubMed Database, from January 2017 to May 2023. A three-level maturity framework was applied for classifying the aims of 59 studies included: demonstrating technical efficacy, diagnostic sensitivity, or clinical utility. As secondary analysis, user experience (usability and patient adherence) was evaluated. The evidences provided by the studies were categorized and stratified according to the level of maturity. Our results indicate that approximately 75% of articles investigated diagnostic sensitivity, i.e. correlation of sensor-data with clinical parameters. Evidence of clinical utility, defined as improvement on health outcomes or clinical decisions after the use of the wearables, was found only in nine papers. A third of the articles included reported evidence of user experience. Future research should focus more on clinical utility, to facilitate the translation of research results within the management of Parkinson’s Disease.

The Dual Task Ball Balancing Test and Its Association With Cognitive Function: Algorithm Development and Validation.

Dual task paradigms are thought to offer a quantitative means to assess cognitive reserve and the brain's capacity to allocate resources in the face of competing cognitive demands. The most common dual task paradigms examine the interplay between gait or balance control and cognitive function. However, gait and balance tasks can be physically challenging for older adults and may pose a risk of falls. We introduce a novel, digital dual-task assessment that combines a motor-control task (the "ball balancing" test), which challenges an individual to maintain a virtual ball within a designated zone, with a concurrent cognitive task (the backward digit span task [BDST]). The task was administered on a touchscreen tablet, performance was measured using the inertial sensors embedded in the tablet, conducted under both single- and dual-task conditions. The clinical use of the task was evaluated on a sample of 375 older adult participants (n=210 female; aged 73.0, SD 6.5 years). All older adults, including those with mild cognitive impairment (MCI) and Alzheimer disease-related dementia (ADRD), and those with poor balance and gait problems due to diabetes, osteoarthritis, peripheral neuropathy, and other causes, were able to complete the task comfortably and safely while seated. As expected, task performance significantly decreased under dual task conditions compared to single task conditions. We show that performance was significantly associated with cognitive impairment; significant differences were found among healthy participants, those with MCI, and those with ADRD. Task results were significantly associated with functional impairment, independent of diagnosis, degree of cognitive impairment (as indicated by the Mini Mental State Examination [MMSE] score), and age. Finally, we found that cognitive status could be classified with >70% accuracy using a range of classifier models trained on 3 different cognitive function outcome variables (consensus clinical judgment, Rey Auditory Verbal Learning Test [RAVLT], and MMSE). Our results suggest that the dual task ball balancing test could be used as a digital cognitive assessment of cognitive reserve. The portability, simplicity, and intuitiveness of the task suggest that it may be suitable for unsupervised home assessment of cognitive function.

Walking performance differs between people with multiple sclerosis who perform distinct types of exercise.

Aim: To determine whether walking performance differed between people with multiple sclerosis (MS) who performed distinct types, volumesand intensities of exercise.Materials& methods: Forty-five people with relapsing-remitting MS performed two trials of the 2-minwalk test, one at a preferred speed and another at a fast speed. Gait metrics were measured by wireless inertial sensors. Participants reported the type (aerobic, resistance), volumeand intensity of exercise performed.Results: Walking speed reserve and gait variability were better in participants who performed combined aerobic and resistance exercises compared with those who performed aerobic-only exercise.Conclusion: Walking performance differs in people with mild MS disability based on the type and volume of exercise performed.

An IMU-based machine learning approach for daily behavior pattern recognition in dairy cows

Technological advancements have revolutionized livestock farming, notably in health monitoring. Traditional methods, which have been criticized for subjectivity and treatment delays, can be replaced with efficient health monitoring systems, thereby reducing costs and workload. Implementing cow behavior recognition allows for effective dairy cow health monitoring. In this research, we propose an integrated system using inertial measurement unit (IMU) devices and machine learning techniques for dairy cow behavior recognition. Six main dairy cow behaviors were studied: lying, standing, walking, drinking, feeding, and ruminating. All behavior types were manually labeled into the IMU data by reviewing the recorded footage. The labeled IMU data underwent four processing steps: selecting different window sizes, feature extraction, feature selection, and normalization. These processed data were then used to build the behavior recognition model. Various model structures, including SVM, Random Forest, and XGBoost, were tested. The top-performing model, XGBoost, with its proposed 58 features achieved an F1-score of 0.87, with specific scores of 0.93 for lying, 0.85 for walking, 0.94 for ruminating, 0.89 for feeding, 0.86 for standing, 0.93 for drinking, and 0.59 for other activities. During our online testing, we observed similar patterns for each healthy cow. The cumulative time spent on each behavior also matched the statistics from previous surveys. Additionally, our backend optimization approach resulted in a final overall percentage error of 1.55 % per day during online testing. In conclusion, our study presents an IMU-based system capable of accurately recognizing dairy cow behavior. Feature design and appropriate models are proposed herein. A functional optimization method was introduced indicating that our system has the potential with applications for estrus detection and other reproductive management practices in the dairy industry.

Kinematic Responses to Water Treadmill Exercise When Used Regularly within a Sport Horse Training Programme: A Longitudinal, Observational Study.

Repeated exposure to water treadmill (WT) exercise could elicit kinematic responses reflecting adaptation to WT exercise. The study's aim was to compare the responses of a group of sport horses to a standardised WT exercise test (WTSET) carried out at three time points, week 0 (n = 48), week 20 (n = 38), and week 40 (n = 29), throughout a normal training programme incorporating WT exercise. Horses were recruited from the existing client populations of two commercial water treadmill venues for the purpose of this longitudinal, observational study. Limb, back, poll, wither, and pelvic kinematics were measured during the WTSET using videography, optical motion capture, and inertial motion sensors. Forelimb and hindlimb protraction increased (p < 0.001 for both), and forelimb and hindlimb retraction decreased (p < 0.001 for both) at week 40 compared to week 0. Caudal thoracic flexion-extension and lateral bend ranges of movement were greater at week 40 compared to week 0 (p < 0.001 and p = 0.009, respectively). Increased training speed was associated with increased craniocaudal poll movement (p = 0.021), decreased forelimb protraction (p = 0.008), and increased forelimb retraction (p = 0.021). In addition to characteristic changes in kinematics due to increasing water depth, regular WT exercise resulted in kinematic adaptation to movement in water. Factors such as the frequency of WT sessions and the type of session used with respect to depth and speed were seen to influence the nature of the adaptation. The results suggest that WT exercise sessions could be designed in accordance with specific training goals when used within a normal sport horse training programme.

GNSS/IMU/map-matching feedback integration with adaptive GNSS accuracy estimation by using low-quality sensors for vehicle localization in urban canyon

In urban canyons, the performance of vehicle navigation systems based on Global Navigation Satellite System (GNSS) and Inertial Measurement Unit (IMU) is notably compromised due to satellite signal obstructions and severe multipath effects. This article proposes a GNSS/IMU/Map-Matching feedback (MMF) integration with the adaptive GNSS accuracy estimation to provide accurate and robust positions for vehicles in urban canyons. This system integrates self-constraints and MMF to control the drift of low- quality IMU. To avoid fatal positioning errors caused by incorrect MMF, motion states are categorized into straight-line driving and corner turning, with different criteria set based on their characteristics to validate MMF. Furthermore, GNSS accuracy is estimated adaptively with MMF. Extensive experiments in Hong Kong’s dense urban canyons demonstrated significantly improved positioning accuracy of 37% and 51% in the north and east directions, respectively, outperforming traditional GNSS/IMU/Map configurations. The results demonstrate the proposed approach’s marked enhancement in urban vehicular navigation.

Sensing and Control Strategies Used in FES Systems Aimed at Assistance and Rehabilitation of Foot Drop: A Systematic Literature Review.

Functional electrical stimulation (FES) is a rehabilitation and assistive technique used for stroke survivors. FES systems mainly consist of sensors, a control algorithm, and a stimulation unit. However, there is a critical need to reassess sensing and control techniques in FES systems to enhance their efficiency. This SLR was carried out following the PRISMA 2020 statement. Four databases (PubMed, Scopus, Web of Science, Wiley Online Library) from 2010 to 2024 were searched using terms related to sensing and control strategies in FES systems. A total of 322 articles were chosen in the first stage, while only 60 of them remained after the final filtering stage. This systematic review mainly focused on sensor techniques and control strategies to deliver FES. The most commonly used sensors reported were inertial measurement units (IMUs), 45% (27); biopotential electrodes, 36.7% (22); vision-based systems, 18.3% (11); and switches, 18.3% (11). The control strategy most reported is closed-loop; however, most of the current commercial FES systems employ open-loop strategies due to their simplicity. Three main factors were identified that should be considered when choosing a sensor for gait-oriented FES systems: wearability, accuracy, and affordability. We believe that the combination of computer vision systems with artificial intelligence-based control algorithms can contribute to the development of minimally invasive and personalized FES systems for the gait rehabilitation of patients with FDS.

Dynamic Soft Tissue Artifacts during Impulsive Loads: Measurement Errors Vary With Wearable Inertial Measurement Unit Sensor Design.

Characterize and model Inertial Measurement Unit (IMU) errors due to transient dynamic soft tissue artifacts excited by impulsive loads, such as foot strikes during running and jumping. We instrumented 10 participants (5 female, 5 male) with IMUs on the dominant leg. An ankle IMU measured reference vertical accelerations during impulsive loads and was cross-validated against vertical force measures. Two IMUs on the posterior shank and anterior shank were used to characterize errors caused by dynamic soft tissue artifacts with respect to the reference. Shank sensors' masses were varied to explore their effect on dynamic soft tissue artifacts. Both the posterior IMU and anterior IMU overestimated peak vertical accelerations during the impulsive load (gain of 2.18 ± 0.63 and 1.55 ± 0.35 respectively). The post- impulsive load oscillation duration and natural frequency varied with sensor mass according to an underdamped second-order system, with posterior IMU and anterior IMU durations of 326 ± 75ms and 151 ± 50ms respectively and natural frequencies of 9.79 ± 2.68Hz and 18.22 ± 12.10Hz respectively. Low-pass filtering reduced overestimation of peak vertical accelerations, but also attenuated the reference measure. Our study suggests dynamic soft tissue artifacts result in transient, but substantial measurement errors that may not be appropriately mitigated through low-pass filtering. However, these dynamic soft tissue artifacts can be modeled using an underdamped second-order system and used to estimate material properties of underlying soft tissue. We demonstrate that dynamic soft tissue artifacts can be modeled and potentially mitigated to improve accuracy in applications necessitating measurement of impulsive loads such as foot strikes.

A Smart Ski Pole for Skiing Pattern Recognition and Quantification Application.

In cross-country skiing, ski poles play a crucial role in technique, propulsion, and overall performance. The kinematic parameters of ski poles can provide valuable information about the skier's technique, which is of great significance for coaches and athletes seeking to improve their skiing performance. In this work, a new smart ski pole is proposed, which combines the uniaxial load cell and the inertial measurement unit (IMU), aiming to provide comprehensive data measurement functions more easily and to play an auxiliary role in training. The ski pole can collect data directly related to skiing technical actions, such as the skier's pole force, pole angle, inertia data, etc., and the system's design, based on wireless transmission, makes the system more convenient to provide comprehensive data acquisition functions, in order to achieve a more simple and efficient use experience. In this experiment, the characteristic data obtained from the ski poles during the Double Poling of three skiers were extracted and the sample t-test was conducted. The results showed that the three skiers had significant differences in pole force, pole angle, and pole time. Spearman correlation analysis was used to analyze the sports data of the people with good performance, and the results showed that the pole force and speed (r = 0.71) and pole support angle (r = 0.76) were significantly correlated. In addition, this study adopted the commonly used inertial sensor data for action recognition, combined with the load cell data as the input of the ski technical action recognition algorithm, and the recognition accuracy of five kinds of cross-country skiing technical actions (Diagonal Stride (DS), Double Poling (DP), Kick Double Poling (KDP), Two-stroke Glide (G2) and Five-stroke Glide (G5)) reached 99.5%, and the accuracy was significantly improved compared with similar recognition systems. Therefore, the equipment is expected to be a valuable training tool for coaches and athletes, helping them to better understand and improve their ski maneuver technique.

Kinematics-Based Predictions of External Loads during Handcycling.

The increased risk of cardiovascular disease in people with spinal cord injuries motivates work to identify exercise options that improve health outcomes without causing risk of musculoskeletal injury. Handcycling is an exercise mode that may be beneficial for wheelchair users, but further work is needed to establish appropriate guidelines and requires assessment of the external loads. The goal of this research was to predict the six-degree-of-freedom external loads during handcycling from data similar to those which can be measured from inertial measurement units (segment accelerations and velocities) using machine learning. Five neural network models and two ensemble models were compared against a statistical model. A temporal convolutional network (TCN) yielded the best predictions. Predictions of forces and moments in-plane with the crank were the most accurate (r = 0.95-0.97). The TCN model could predict external loads during activities of different intensities, making it viable for different exercise protocols. The ability to predict the loads associated with forward propulsion using wearable-type data enables the development of informed exercise guidelines.