Recognizing human physical activities from streaming smartphone sensor readings is essential for the successful realization of a smart environment. Physical activity recognition is one of the active ...research topics to provide users the adaptive services using smart devices. Existing physical activity recognition methods lack in providing fast and accurate recognition of activities. This paper proposes an approach to recognize physical activities using only2-axes of the smartphone accelerometer sensor. It also investigates the effectiveness and contribution of each axis of the accelerometer in the recognition of physical activities. To implement our approach, data of daily life activities are collected labeled using the accelerometer from 12 participants. Furthermore, three machine learning classifiers are implemented to train the model on the collected dataset and in predicting the activities. Our proposed approach provides more promising results compared to the existing techniques and presents a strong rationale behind the effectiveness and contribution of each axis of an accelerometer for activity recognition. To ensure the reliability of the model, we evaluate the proposed approach and observations on standard publicly available dataset WISDM also and provide a comparative analysis with state-of-the-art studies. The proposed approach achieved 93% weighted accuracy with Multilayer Perceptron (MLP) classifier, which is almost 13% higher than the existing methods.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
To evaluate the reliability and validity of the commercially available Fitbit Ultra (2012) accelerometer compared to polysomnography (PSG) and two different actigraphs in a pediatric sample.
All ...subjects wore the Fitbit Ultra while undergoing overnight clinical polysomnography in a sleep laboratory; a randomly selected subset of participants also wore either the Ambulatory Monitoring Inc. Motionlogger Sleep Watch (AMI) or Phillips-Respironics Mini-Mitter Spectrum (PRMM).
63 youth (32 females, 31 males), ages 3-17 years (mean 9.7 years, SD 4.6 years).
Both "Normal" and "Sensitive" sleep-recording Fitbit Ultra modes were examined. Outcome variables included total sleep time (TST), wake after sleep onset (WASO), and sleep efficiency (SE). Primary analyses examined the differences between Fitbit Ultra and PSG using repeated-measures ANCOVA, with epoch-by-epoch comparisons between Fitbit Ultra and PSG used to determine sensitivity, specificity, and accuracy. Intra-device reliability, differences between Fitbit Ultra and actigraphy, and differences by both developmental age group and sleep disordered breathing (SDB) status were also examined.
Compared to PSG, the Normal Fitbit Ultra mode demonstrated good sensitivity (0.86) and accuracy (0.84), but poor specificity (0.52); conversely, the Sensitive Fitbit Ultra mode demonstrated adequate specificity (0.79), but inadequate sensitivity (0.70) and accuracy (0.71). Compared to PSG, the Fitbit Ultra significantly overestimated TST (41 min) and SE (8%) in Normal mode, and underestimated TST (105 min) and SE (21%) in Sensitive mode. Similar differences were found between Fitbit Ultra (both modes) and both brands of actigraphs.
Despite its low cost and ease of use for consumers, neither sleep-recording mode of the Fitbit Ultra accelerometer provided clinically comparable results to PSG. Further, pediatric sleep researchers and clinicians should be cautious about substituting these devices for validated actigraphs, with a significant risk of either overestimating or underestimating outcome data including total sleep time and sleep efficiency.
In this article, we review optical MEMS accelerometers with a particular focus on sensing techniques and interrogation methods. Optical accelerometers find use in various application domains ranging ...from microgravity to inertial navigation to vibration sensing. The performance of an accelerometer is quantified in terms of its range, bandwidth, sensitivity, and resolution. The combination of sensing technique and interrogation method determines the optical accelerometer's performance. This article presents a classification in terms of guided-wave and free-space based optical sensing techniques used in acceleration measurement and their review. In free-space based sensing techniques, light propagating in free-space interacts with the mechanical structure resulting in modification of light properties at the receiver. In guided-wave based sensing techniques, light interaction with the mechanical structure is confined to the waveguide. Also, the different interrogation methods used in optical MEMS accelerometers are reviewed. The interrogation methods are classified as based on intensity modulation or frequency modulation of the optical signal received from sensor. In intensity-modulation based interrogation, light intensity at output is the measurand and, the cost and complexity of this class of methods is lower. In frequency-modulation based interrogation, the frequency or phase of the optical signal at the output is the measurand. Further, a high-resolution optical MEMS accelerometer based on waveguide Bragg gratings is described. A combination of free-space based sensing and intensity-modulation based interrogation methods will be suitable for consumer-grade accelerometer applications. For high-resolution applications like tactical and navigation grades, a combination of guided-wave sensing and frequency-modulation based interrogation methods would be appropriate.
Vibrating beam accelerometers (VBAs) have significant application potential in navigation guidance. This paper proposed a novel high-precision frequency readout method and integrated CMOS circuit ...implementation for VBAs. And technologies including sigma-delta modulation, up-sample and split, data synchronization and nonlinearity correction are employed in the method which is analyzed in detail in this paper. The method offers the advantages of low quantization noise, enough range, fixed output rate, and high linearity. Other force-frequency sensors could also benefit from this method but note that its noise suppression is most effective when the output rate is much smaller than the frequency under test. The method is implemented by a CMOS circuit and integrated with an oscillator circuit, which makes a full-function single-package VBA possible. Static, shock, random vibration, and centrifugal tests of the frequency readout circuit and VBA were performed. Test results show that the frequency quantization noise is less than 10 μHz/√Hz at 1 Hz, and can support 0.1 μg noise output. They also show that the vibration rectification error is lower than 0.5 mg at 8 grms, and that the 20 g full range nonlinearity is 16 ppm.
An integrated self‐powered dynamic displacement monitoring system by utilizing a novel triboelectric accelerometer for structural health monitoring is proposed and implemented in this study, which ...can show the dynamic displacement and transmit the alarming signal by accurately sensing the vibration acceleration. The fabricated triboelectric accelerometer based on the noncontact freestanding triboelectric nanogenerator consists of an outer transparent sleeve tube and an inner cylindrical inertial mass that is suspended by a highly stretchable silicone fiber. One pair of copper film electrodes is deposited by physical vapor deposition on nylon film and adhered on the inner wall of the outer tube, while a fluorinated ethylene propylene film with nanowire structures is adhered on the surface of the inner cylindrical inertial mass. The experimental results show that proposed triboelectric accelerometer can accurately sense the vibration acceleration with a high sensitivity of 0.391 V s2 m−1. In particular, the developed accelerometer has superior performance within the low‐frequency range. One of the most striking features is that the commercial accelerometer using piezoelectric material is strongly dominated by high‐order harmonics, which can cause confusion in computer data analysis. In contrast, the triboelectric accelerometer is only dominated by the base resonance mode.
Based on the noncontact freestanding triboelectric nanogenerator (TENG), a novel self‐powered accelerometer sensor with the sleeve‐tube structure for vibration detection is proposed and fabricated, which has more superior performance applying in lower vibration frequency compared with the traditional piezoelectric accelerometer. Moreover, an integrated self‐powered dynamic displacement monitoring system by utilizing a novel triboelectric accelerometer for structural health monitoring is developed.
Full text
Available for:
FZAB, GIS, IJS, KILJ, NLZOH, NUK, OILJ, SBCE, SBMB, UL, UM, UPUK
For physical activity recognition, smartphone sensors, such as an accelerometer and a gyroscope, are being utilized in many research studies. So far, particularly, the accelerometer has been ...extensively studied. In a few recent studies, a combination of a gyroscope, a magnetometer (in a supporting role) and an accelerometer (in a lead role) has been used with the aim to improve the recognition performance. How and when are various motion sensors, which are available on a smartphone, best used for better recognition performance, either individually or in combination? This is yet to be explored. In order to investigate this question, in this paper, we explore how these various motion sensors behave in different situations in the activity recognition process. For this purpose, we designed a data collection experiment where ten participants performed seven different activities carrying smart phones at different positions. Based on the analysis of this data set, we show that these sensors, except the magnetometer, are each capable of taking the lead roles individually, depending on the type of activity being recognized, the body position, the used data features and the classification method employed (personalized or generalized). We also show that their combination only improves the overall recognition performance when their individual performances are not very high, so that there is room for performance improvement. We have made our data set and our data collection application publicly available, thereby making our experiments reproducible.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
Differences in running gait between treadmill and overground running has been subject of study, while consistency of group differences between running surfaces has not been previously analysed. This ...study examined both the differences between running surfaces and the consistency of sex-based differences between surfaces in some spatiotemporal and kinematic variables measured by an inertial measurement unit fastened over the lumbar spine. Thirty-two (sixteen females) endurance runners firstly performed overground and then treadmill (1 % inclination) runs at speeds between 9–21 km∙h−1. Males showed lower flight time (FT) moderate effect size (ES) during treadmill running compared to overground, while females showed greater stride frequency (SF) (moderate ES), lower stride length (SL) (moderate ES), FT (moderate ES), and vertical (VT) trunk displacement (moderate ES), as well as greater medio-lateral (ML) trunk displacement (moderate ES). No differences in CT between surfaces were found (trivial to small). Furthermore, all the sex-differences were consistent between treadmill and overground running: Males showed lower SF (large and moderate ES, respectively), greater SL (large and moderate ES) and CT (moderate and large ES), lower FT (large ES), greater VT displacement (moderate to large ES), and lower ML displacement (moderate ES) than females. These results may be of interest to carefully transfer the running gait analyses between surfaces depending on sex.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Kidney stone disease (KSD), a significant health care problem within both developed and developing countries, has been associated with genetic risk factors. An association between physical activity ...and KSD risk also has been hypothesized, but studies have yielded inconsistent findings. This study investigated the association between the intensity of physical activity and the incidence of KSD accounting for genetic risk.
Prospective cohort study.
A total of 80,473 participants from the UK Biobank Study.
Physical activity levels, including total physical activity (TPA), moderate-to-vigorous intensity physical activity (MVPA), and light-intensity physical activity (LPA), were measured using accelerometers and quantified using a machine learning model. A polygenic risk score (PRS) for KSD was also constructed.
Individuals with KSD were identified using the International Classification of Diseases, Tenth Revision (ICD-10), and procedure codes for KSD surgery.
A Fine and Gray survival model was used to estimate the associations of incident KSD with TPA, MVPA, LPA, and PRS (as categorical variables). Restricted cubic splines were used to examine potential nonlinear associations within the fully adjusted models.
During an average follow-up of 6.19 years, 421 participants developed KSD. Participants in the highest quartiles of TPA, MVPA, and LPA had lower adjusted rates of KSD compared with those in the lowest quartiles: HR, 0.50 (95% CI, 0.44-0.56), 0.57 (95% CI, 0.51-0.64), and 0.66 (95% CI, 0.59-0.74), respectively. TPA, MVPA, and LPA were associated with a lower risk of KSD in participants with low and high genetic predisposition for KSD.
Selection bias as participants who provided accelerometry data may have been more adherent to health care.
Physical activity was negatively associated with the risk of KSD, regardless of the genetic risk. Future large studies are warranted to confirm and explain the mechanisms underlying these associations.
The association between the intensity of physical activity (PA) and the incidence of kidney stone disease (KSD) after accounting for genetic risk is unclear. We conducted a comprehensive prospective cohort study utilizing participants from the UK Biobank to assess the intensity of PA using accelerometers. Our study findings indicated that greater total PA, moderate-to-vigorous-intensity PA, and light-intensity PA were each associated with a lower risk of KSD irrespective of an individual’s genetic risk. Our study informs the understanding of risk factors for KSD.
Display omitted
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Microelectromechanical system (MEMS) capacitive accelerometer for the Internet of Things applications is designed with open-loop structure rather than closed-loop structure to achieve low power ...consumption. In the open-loop structure, voltage control readout structure instead of charge control readout structure is preferred for low cost. However, the voltage control readout structure suffers from low power efficiency in terms of figure of merit (FoM) due to significant parasitic-capacitance-induced noise. In this article, the correlated double amplifying (CDA) technique is proposed to reduce the noise of the voltage control readout circuit with high power efficiency. Although traditional correlated double sampling (CDS) technique can also be used in readout circuit to reduce the parasitic-capacitance-induced noise, it sacrifices driving ability and bandwidth of the readout circuit, while CDA does not. The CDA technique adopts correlated amplifying to reduced noise without significant increase of power consumption. Thus, CDA technique leads to higher power efficiency. The CDA technique is demonstrated in a fully differential readout circuit fabricated in a 0.18-um CMOS process and tested with a sensing element from a commercial MEMS accelerometer. The measurement results show that noise floor of the readout circuit is <inline-formula> <tex-math notation="LaTeX">0.5~ \mathrm {aF}/\!\surd {\mathrm {Hz}} </tex-math></inline-formula> and the noise floor of the whole system is <inline-formula> <tex-math notation="LaTeX">112 ~\mathrm {ug}/\!\surd {\mathrm {Hz}} </tex-math></inline-formula>, with a power consumption of <inline-formula> <tex-math notation="LaTeX">139~ \mu \text{W} </tex-math></inline-formula> and a bandwidth of 12.5 kHz. The full input range of ±4 g, an FoM 1 of 80 pJ, and an FoM 2 of <inline-formula> <tex-math notation="LaTeX">254 ~\mathrm {uW}{\cdot }{\mathrm {ug/Hz}} </tex-math></inline-formula> are achieved.
ABSTRACTFox, JL, Scanlan, AT, and Stanton, R. A review of player monitoring approaches in basketballcurrent trends and future directions. J Strength Cond Res 31(7)2021–2029, 2017—Effective monitoring ...of players in team sports such as basketball requires an understanding of the external demands and internal responses, as they relate to training phases and competition. Monitoring of external demands and internal responses allows coaching staff to determine the dose-response associated with the imposed training load (TL), and subsequently, if players are adequately prepared for competition. This review discusses measures reported in the literature for monitoring the external demands and internal responses of basketball players during training and competition. The external demands of training and competition were primarily monitored using time-motion analysis, with limited use of microtechnology being reported. Internal responses during training were typically measured using hematological markers, heart rate, various TL models, and perceptual responses such as rating of perceived exertion (RPE). Heart rate was the most commonly reported indicator of internal responses during competition with limited reporting of hematological markers or RPE. These findings show a large discrepancy between the reporting of external and internal measures and training and competition demands. Microsensors, however, may be a practical and convenient method of player monitoring in basketball to overcome the limitations associated with current approaches while allowing for external demands and internal responses to be recorded simultaneously. The triaxial accelerometers of microsensors seem well suited for basketball and warrant validation to definitively determine their place in the monitoring of basketball players. Coaching staff should make use of this technology by tracking individual player responses across the annual plan and using real-time monitoring to minimize factors such as fatigue and injury risk.