scholarly journals Pre-Impact Detection Algorithm to Identify Tripping Events Using Wearable Sensors

Sensors ◽  
2019 ◽  
Vol 19 (17) ◽  
pp. 3713
Author(s):  
Federica Aprigliano ◽  
Silvestro Micera ◽  
Vito Monaco
Keyword(s):  
Wearable Sensors ◽  
Detection Algorithm ◽  
Lower Limbs ◽  
False Alarms ◽  
Daily Life Activities ◽  
Impact Detection ◽  
Wearable Robots ◽  
Adaptive Oscillators ◽  
Young Subjects ◽  
Smart Garments

This study aimed to investigate the performance of an updated version of our pre-impact detection algorithm parsing out the output of a set of Inertial Measurement Units (IMUs) placed on lower limbs and designed to recognize signs of lack of balance due to tripping. Eight young subjects were asked to manage tripping events while walking on a treadmill. An adaptive threshold-based algorithm, relying on a pool of adaptive oscillators, was tuned to identify abrupt kinematics modifications during tripping. Inputs of the algorithm were the elevation angles of lower limb segments, as estimated by IMUs located on thighs, shanks and feet. The results showed that the proposed algorithm can identify a lack of balance in about 0.37 ± 0.11 s after the onset of the perturbation, with a low percentage of false alarms (<10%), by using only data related to the perturbed shank. The proposed algorithm can hence be considered a multi-purpose tool to identify different perturbations (i.e., slippage and tripping). In this respect, it can be implemented for different wearable applications (e.g., smart garments or wearable robots) and adopted during daily life activities to enable on-demand injury prevention systems prior to fall impacts.

scholarly journals Optimization and Technical Validation of the AIDE-MOI Fall Detection Algorithm in a Real-Life Setting with Older Adults

Sensors ◽  
2019 ◽  
Vol 19 (6) ◽  
pp. 1357
Author(s):  
Simon Scheurer ◽  
Janina Koch ◽  
Martin Kucera ◽  
Hȧkon Bryn ◽  
Marcel Bärtschi ◽  
...  
Keyword(s):  
Real Life ◽  
Fall Detection ◽  
Detection Algorithm ◽  
False Alarms ◽  
Second Phase ◽  
Two Phase ◽  
Motion Data ◽  
Technical Validation ◽  
Young Subjects ◽  
Risk Of Fall

Falls are the primary contributors of accidents in elderly people. An important factor of fall severity is the amount of time that people lie on the ground. To minimize consequences through a short reaction time, the motion sensor “AIDE-MOI” was developed. “AIDE-MOI” senses acceleration data and analyzes if an event is a fall. The threshold-based fall detection algorithm was developed using motion data of young subjects collected in a lab setup. The aim of this study was to improve and validate the existing fall detection algorithm. In the two-phase study, twenty subjects (age 86.25 ± 6.66 years) with a high risk of fall (Morse > 65 points) were recruited to record motion data in real-time using the AIDE-MOI sensor. The data collected in the first phase (59 days) was used to optimize the existing algorithm. The optimized second-generation algorithm was evaluated in a second phase (66 days). The data collected in the two phases, which recorded 31 real falls, was split-up into one-minute chunks for labelling as “fall” or “non-fall”. The sensitivity and specificity of the threshold-based algorithm improved significantly from 27.3% to 80.0% and 99.9957% (0.43) to 99.9978% (0.17 false alarms per week and subject), respectively.

scholarly journals A new open-access platform for measuring and sharing mTBI data

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
August G. Domel ◽  
Samuel J. Raymond ◽  
Chiara Giordano ◽  
Yuzhe Liu ◽  
Seyed Abdolmajid Yousefsani ◽  
...  
Keyword(s):  
Brain Injury ◽  
Open Access ◽  
Injury Risk ◽  
Wearable Sensors ◽  
Detection Algorithm ◽  
Diagnostic Tools ◽  
Support Vector ◽  
Head Impacts ◽  
Impact Detection ◽  
Out Of Sample

AbstractDespite numerous research efforts, the precise mechanisms of concussion have yet to be fully uncovered. Clinical studies on high-risk populations, such as contact sports athletes, have become more common and give insight on the link between impact severity and brain injury risk through the use of wearable sensors and neurological testing. However, as the number of institutions operating these studies grows, there is a growing need for a platform to share these data to facilitate our understanding of concussion mechanisms and aid in the development of suitable diagnostic tools. To that end, this paper puts forth two contributions: (1) a centralized, open-access platform for storing and sharing head impact data, in collaboration with the Federal Interagency Traumatic Brain Injury Research informatics system (FITBIR), and (2) a deep learning impact detection algorithm (MiGNet) to differentiate between true head impacts and false positives for the previously biomechanically validated instrumented mouthguard sensor (MiG2.0), all of which easily interfaces with FITBIR. We report 96% accuracy using MiGNet, based on a neural network model, improving on previous work based on Support Vector Machines achieving 91% accuracy, on an out of sample dataset of high school and collegiate football head impacts. The integrated MiG2.0 and FITBIR system serve as a collaborative research tool to be disseminated across multiple institutions towards creating a standardized dataset for furthering the knowledge of concussion biomechanics.

scholarly journals Analysis of 3-D Kinematics Using H-Gait System during Walking on a Lower Body Positive Pressure Treadmill

Sensors ◽  
2021 ◽  
Vol 21 (8) ◽  
pp. 2619
Author(s):  
Yoshiaki Kataoka ◽  
Ryo Takeda ◽  
Shigeru Tadano ◽  
Tomoya Ishida ◽  
Yuki Saito ◽  
...  
Keyword(s):  
Motion Analysis ◽  
Wearable Sensors ◽  
Three Dimensional ◽  
Lower Limbs ◽  
Positive Pressure ◽  
Lower Body ◽  
Lower Body Positive Pressure ◽  
Gait Kinematics ◽  
Peak Knee ◽  
Body Positive

Recently, treadmills equipped with a lower-body positive-pressure (LBPP) device have been developed to provide precise body weight support (BWS) during walking. Since lower limbs are covered in a waist-high chamber of an LBPP treadmill, a conventional motion analysis using an optical method is impossible to evaluate gait kinematics on LBPP. We have developed a wearable-sensor-based three-dimensional motion analysis system, H-Gait. The purpose of the present study was to investigate the effects of BWS by a LBPP treadmill on gait kinematics using an H-Gait system. Twenty-five healthy subjects walked at 2.5 km/h on a LBPP treadmill under the following three conditions: (1) 0%BWS, (2) 25%BWS and (3) 50%BWS conditions. Acceleration and angular velocity from seven wearable sensors were used to analyze lower limb kinematics during walking. BWS significantly decreased peak angles of hip adduction, knee adduction and ankle dorsiflexion. In particular, the peak knee adduction angle at the 50%BWS significantly decreased compared to at the 25%BWS (p = 0.012) or 0%BWS (p < 0.001). The present study showed that H-Gait system can detect the changes in gait kinematics in response to BWS by a LBPP treadmill and provided a useful clinical application of the H-Gait system to walking exercises.

Algorithms for detecting broadband signals with a constant level of false alarms

2021 ◽  
Author(s):  
I.F. Lozovskiy
Keyword(s):  
Detection Threshold ◽  
Signal Amplitude ◽  
Rayleigh Distribution ◽  
Training Sample ◽  
Detection Algorithm ◽  
Constant Level ◽  
False Alarms ◽  
Interference Power ◽  
Number Of False Alarms ◽  
Distribution Type

The use of broadband souding signals in radars, which has become real in recent years, leads to a significant reduction in the size of resolution elements in range and, accordingly, in the size of the window in which the training sample is formed, which is used to adapt the detection threshold in signal detection algorithms with a constant level of false alarms. In existing radars, such a window would lead to huge losses. The purpose of the work was to study the most rational options for constructing detectors with a constant level of false alarms in radars with broadband sounding signals. The problem was solved for the Rayleigh distribution of the envelope of the noise and a number of non-Rayleigh laws — Weibull and the lognormal, the appearance of which is associated with a decrease in the number of reflecting elements in the resolution volume. For Rayleigh interference, an algorithm is proposed with a multi-channel in range incoherent signal amplitude storage and normalization to the larger of the two estimates of the interference power in the range segments. The detection threshold in it adapts not only to the interference power, but also to the magnitude of the «power jump» in range, which allows reducing the number of false alarms during sudden changes in the interference power – the increase in the probability of false alarms did not exceed one order of magnitude. In this algorithm, there is a certain increase in losses associated with incoherent accumulation of signals reflected from target elements, and losses can be reduced by certain increasing the size of the distance segments that make up the window. Algorithms for detecting broadband signals against interference with non-Rayleigh laws of distribution of the envelope – Weibull and lognormal, based on the addition of the algorithm for detecting signals by non-linear transformation of sample counts into counts with a Rayleigh distribution, are studied. The structure of the detection algorithm remains unchanged in practice. The options for detectors of narrowband and broadband signals are considered. It was found that, in contrast to algorithms designed for the Rayleigh distribution, these algorithms provide a stable level of false alarms regardless of the values of the parameters of non-Rayleigh interference. To reduce losses due to interference with the distribution of amplitudes according to the Rayleigh law, detectors consisting of two channels are used, in which one of the channels is tuned for interference with the Rayleigh distribution, and the other for lognormal or Weibull interference. Channels are switched according to special distribution type recognition algorithms. In such detectors, however, there is a certain increase in the probability of false alarms in a rather narrow range of non-Rayleigh interference parameters, where their distribution approaches the Rayleigh distribution. It is shown that when using broadband signals, there is a noticeable decrease in detection losses in non-Rayleigh noise due to lower detection thresholds for in range signal amplitudes incoherent storage.

scholarly journals Atrial Fibrillation Detection from Wrist Photoplethysmography Signals Using Smartwatches

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Syed Khairul Bashar ◽  
Dong Han ◽  
Shirin Hajeb-Mohammadalipour ◽  
Eric Ding ◽  
Cody Whitcomb ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Detection Algorithm ◽  
Motion Artifacts ◽  
False Alarms ◽  
Time Frequency ◽  
Non Invasive ◽  
Accelerometer Signal ◽  
Atrial Contraction ◽  
Premature Atrial Contraction ◽  
Sensitivity Specificity

Abstract Detection of atrial fibrillation (AF) from a wrist watch photoplethysmogram (PPG) signal is important because the wrist watch form factor enables long term continuous monitoring of arrhythmia in an easy and non-invasive manner. We have developed a novel method not only to detect AF from a smart wrist watch PPG signal, but also to determine whether the recorded PPG signal is corrupted by motion artifacts or not. We detect motion and noise artifacts based on the accelerometer signal and variable frequency complex demodulation based time-frequency analysis of the PPG signal. After that, we use the root mean square of successive differences and sample entropy, calculated from the beat-to-beat intervals of the PPG signal, to distinguish AF from normal rhythm. We then use a premature atrial contraction detection algorithm to have more accurate AF identification and to reduce false alarms. Two separate datasets have been used in this study to test the efficacy of the proposed method, which shows a combined sensitivity, specificity and accuracy of 98.18%, 97.43% and 97.54% across the datasets.

scholarly journals Time-Frequency Characteristics of In-Home Radio Channels Influenced by Activities of the Home Occupant

Sensors ◽  
2019 ◽  
Vol 19 (16) ◽  
pp. 3557
Author(s):  
Alireza Borhani ◽  
Matthias Pätzold ◽  
Kun Yang
Keyword(s):  
Radio Channel ◽  
Wearable Sensors ◽  
Fall Detection ◽  
The Body ◽  
Home Healthcare ◽  
Radio Waves ◽  
Time Frequency ◽  
Daily Life Activities ◽  
Data Files ◽  
The Impact

While aging is a serious global concern, in-home healthcare monitoring solutions are limited to context-aware systems and wearable sensors, which may easily be forgotten or ignored for privacy and comfort reasons. An emerging non-wearable fall detection approach is based on processing radio waves reflected off the body, who has no active interaction with the system. This paper reports on an indoor radio channel measurement campaign at 5.9 GHz, which has been conducted to study the impact of fall incidents and some daily life activities on the temporal and spectral properties of the indoor channel under both line-of-sight (LOS) and obstructed-LOS (OLOS) propagation conditions. The time-frequency characteristic of the channel has been thoroughly investigated by spectrogram analysis. Studying the instantaneous Doppler characteristics shows that the Doppler spread ignores small variations of the channel (especially under OLOS conditions), but highlights coarse ones caused by falls. The channel properties studied in this paper can be considered to be new useful metrics for the design of reliable fall detection algorithms. We share all measured data files with the community through Code Ocean. The data can be used for validating a new class of channel models aiming at the design of smart activity recognition systems via a software-based approach.

Postural Control in Young and Elderly Adults When Stance is Challenged: Clinical versus Laboratory Measurements

1993 ◽  
Vol 102 (7) ◽  
pp. 508-517 ◽  
Author(s):  
Neil T. Shepard ◽  
Albert Schultz ◽  
Mian Ju Gu ◽  
Neil B. Alexander ◽  
Thomas Boismier
Keyword(s):  
Postural Control ◽  
Laboratory Study ◽  
Lower Limbs ◽  
Measuring System ◽  
Elderly Subjects ◽  
Dynamic Posturography ◽  
Clinical Interpretation ◽  
Healthy Elderly ◽  
Young Subjects

The use of dynamic posturography (EquiTest) for the characterization of postural control biomechanics would be aided by specific knowledge of what the measured data imply about body segment movements. To investigate this issue, the biomechanics of a group of 15 healthy elderly subjects were compared to those of healthy young subjects by using both dynamic posturography and a laboratory movement and force measuring system. The results from EquiTest were analyzed by 1) routine clinical interpretation of data and 2) a clinical research interpretation by subjecting the EquiTest parameters to additional statistical comparison of mean performance of the young and elderly groups. The young-elderly differences from the 2 EquiTest analyses were then compared to the young-elderly differences derived from the laboratory protocol. The routine clinical interpretation of EquiTest data identified the same increases in sway shown by the laboratory study, but did not reveal the more subtle differences indicated by the laboratory study. When the EquiTest data were subjected to additional statistical analysis, the characterization of difference between young and elderly subjects was the same as that of the laboratory study, with the exception of issues of head versus trunk movement, a measure not made by EquiTest. This essential similarity in the characterization of elderly compared to young subjects by both systems suggests 1) that EquiTest is able to detect subtle differences in biomechanics of postural control between young and elderly healthy adult groups and 2) that implied movements of center of gravity, trunk versus lower limbs, and strength of reaction measures are consistently detected by both EquiTest and the laboratory kinematics and dynamics measurement systems.

scholarly journals Muscle mechanoreflex activation via passive calf stretch causes renal vasoconstriction in healthy humans

2017 ◽  
Vol 312 (6) ◽  
pp. R956-R964 ◽  
Author(s):  
Rachel C. Drew ◽  
Cheryl A. Blaha ◽  
Michael D. Herr ◽  
Ruda Cui ◽  
Lawrence I. Sinoway
Keyword(s):  
Voluntary Contraction ◽  
Lower Limbs ◽  
Renal Vasoconstriction ◽  
Healthy Humans ◽  
Arterial Blood ◽  
Vasoconstrictor Response ◽  
Muscle Mechanoreflex ◽  
Metabolite Accumulation ◽  
Young Subjects ◽  
Renal Vascular

Reflex renal vasoconstriction occurs during exercise, and renal vasoconstriction in response to upper-limb muscle mechanoreflex activation has been documented. However, the renal vasoconstrictor response to muscle mechanoreflex activation originating from lower limbs, with and without local metabolite accumulation, has not been assessed. Eleven healthy young subjects (26 ± 1 yr; 5 men) underwent two trials involving 3-min passive calf muscle stretch (mechanoreflex) during 7.5-min lower-limb circulatory occlusion (CO). In one trial, 1.5-min 70% maximal voluntary contraction isometric calf exercise preceded CO to accumulate metabolites during CO and stretch (mechanoreflex and metaboreflex; 70% trial). A control trial involved no exercise before CO (mechanoreflex alone; 0% trial). Beat-to-beat renal blood flow velocity (RBFV; Doppler ultrasound), mean arterial blood pressure (MAP; photoplethysmographic finger cuff), and heart rate (electrocardiogram) were recorded. Renal vascular resistance (RVR), an index of renal vasoconstriction, was calculated as MAP/RBFV. All baseline cardiovascular variables were similar between trials. Stretch increased RVR and decreased RBFV in both trials (change from CO with stretch: RVR – 0% trial = Δ 10 ± 2%, 70% trial = Δ 7 ± 3%; RBFV – 0% trial = Δ −3.8 ± 1.1 cm/s, 70% trial = Δ −2.7 ± 1.5 cm/s; P < 0.05 for RVR and RBFV). These stretch-induced changes were of similar magnitudes in both trials, e.g., with and without local metabolite accumulation, as well as when thromboxane production was inhibited. These findings suggest that muscle mechanoreflex activation via passive calf stretch causes renal vasoconstriction, with and without muscle metaboreflex activation, in healthy humans.

Development of a Torsional Behavior Powertrain Model for Multiple Misfire Detection

2005 ◽  
Author(s):  
Fabrizio Ponti
Keyword(s):  
Torsional Vibration ◽  
Engine Speed ◽  
Experimental Tests ◽  
Detection Algorithm ◽  
Operating Conditions ◽  
False Alarms ◽  
Time Interval ◽  
Short Time Interval ◽  
Torsional Behavior ◽  
Misfire Detection

Many methodologies have been developed in the past for misfire detection purposes based on the analysis of the instantaneous engine speed. The missing combustion is usually detected thanks to the sudden engine speed decrease that takes place after a misfire event. Misfire detection and in particular cylinder isolation is anyhow still a challenging issue for engines with a high number of cylinders, for engine operating conditions at low load or high engine speed and for multiple misfire events. When a misfire event takes place in fact a torsional vibration is excited and shows up in the instantaneous engine speed waveform. If a multiple misfire occurs this torsional vibration is excited more than once in a very short time interval. The interaction among these successive vibrations can generate false alarms or misdetection, and an increased complexity when dealing with cylinder isolation. The paper presents the development of a powertrain torsional behavior model in order to identify the effects of a misfire event on the instantaneous engine speed signal. The identified waveform has then been used to filter out the torsional vibration effects in order to enlighten the missing combustions even in the case of multiple misfire events. The model response is also used to quicken the setup process for the detection algorithm employed, evaluating before running specific experimental tests on a test bench facility, the values for the threshold and the optimal setup of the procedure. The proposed algorithm is developed in this paper for an SI L4 engine; Its application to other engine configurations is possible, as it is also discussed in the paper.

Sign in / Sign up

Export Citation Format

Share Document