Step Cycle Detection of Human Gait Based on Inertial Sensor Signal

The most significant barrier to success in human activity recognition is extracting and selecting the right features. In traditional methods, the features are chosen by humans, which requires the user to have expert knowledge or to do a large amount of empirical study. Newly developed deep learning technology can automatically extract and select features. Among the various deep learning methods, convolutional neural networks (CNNs) have the advantages of local dependency and scale invariance and are suitable for temporal data such as accelerometer (ACC) signals. In this paper, we propose an efficient human activity recognition method, namely Iss2Image (Inertial sensor signal to Image), a novel encoding technique for transforming an inertial sensor signal into an image with minimum distortion and a CNN model for image-based activity classification. Iss2Image converts real number values from the X, Y, and Z axes into three color channels to precisely infer correlations among successive sensor signal values in three different dimensions. We experimentally evaluated our method using several well-known datasets and our own dataset collected from a smartphone and smartwatch. The proposed method shows higher accuracy than other state-of-the-art approaches on the tested datasets.

Download Full-text

Recognition of Gait Activities Using Acceleration Data from A Smartphone and A Wearable Device

Proceedings ◽

10.3390/proceedings2019031060 ◽

2019 ◽

Vol 31 (1) ◽

pp. 60 ◽

Cited By ~ 1

Author(s):

Irvin Hussein Lopez-Nava ◽

Matias Garcia-Constantino ◽

Jesus Favela

Keyword(s):

Assisted Living ◽

Inertial Sensor ◽

Ambient Assisted Living ◽

Human Gait ◽

Support Vector ◽

K Nearest Neighbors ◽

Acceleration Data ◽

Vector Machines ◽

Young Subjects ◽

Physical Spaces

Activity recognition is an important task in many fields, such as ambient intelligence, pervasive healthcare, and surveillance. In particular, the recognition of human gait can be useful to identify the characteristics of the places or physical spaces, such as whether the person is walking on level ground or walking down stairs in which people move. For example, ascending or descending stairs can be a risky activity for older adults because of a possible fall, which can have more severe consequences than if it occurred on a flat surface. While portable and wearable devices have been widely used to detect Activities of Daily Living (ADLs), few research works in the literature have focused on characterizing only actions of human gait. In the present study, a method for recognizing gait activities using acceleration data obtained from a smartphone and a wearable inertial sensor placed on the ankle of people is introduced. The acceleration signals were segmented based on the automatic detection of strides, also called gait cycles. Subsequently, a feature vector of the segmented signals was extracted, which was used to train four classifiers using the Naive Bayes, C4.5, Support Vector Machines, and K-Nearest Neighbors algorithms. Data was collected from seven young subjects who performed five gait activities: (i) going down an incline, (ii) going up an incline, (iii) walking on level ground, (iv) going down stairs, and (v) going up stairs. The results demonstrate the viability of using the proposed method and technologies in ambient assisted living contexts.

Download Full-text

A Method of Lower Limb Joint Points Extraction Based on Pendulum Model under Arbitrary Gesture Walk

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.556-562.4347 ◽

2014 ◽

Vol 556-562 ◽

pp. 4347-4351

Author(s):

Ning Yang ◽

Jin Tao Li ◽

Rong Wang

Keyword(s):

Human Body ◽

Lower Limb ◽

Extraction Method ◽

Gait Recognition ◽

Human Gait ◽

Step Cycle ◽

Joint Point ◽

Pendulum Model ◽

Real Time Tracking ◽

Body Joints

The position extraction of lower limb joint points is important for gait recognition because the feature data is always based on the position of lower limb joint points. Since the detection of motion information of human body can affect the gait recognition directly, we propose a position extraction method of lower limb joint points in this paper. Through the study on the human body centroid tracking, and positioning of human lower limb joint point, we can obtain the step cycle information. It has been demonstrated via plenty experiments that the proposed method is feasible and easy for implement, since it can achieve real-time tracking and improve positioning accuracy of the human body joints, and can provide feature data for human gait recognition.

Download Full-text

Sensor Type, Axis, and Position-Based Fusion and Feature Selection for Multimodal Human Daily Activity Recognition in Wearable Body Sensor Networks

Journal of Healthcare Engineering ◽

10.1155/2020/7914649 ◽

2020 ◽

Vol 2020 ◽

pp. 1-14

Author(s):

Abeer A. Badawi ◽

Ahmad Al-Kabbany ◽

Heba A. Shaban

Keyword(s):

Feature Selection ◽

Inertial Sensors ◽

Inertial Sensor ◽

Real Life ◽

Human Gait ◽

Body Sensor Networks ◽

Sequential Feature Selection ◽

Wearable Inertial Sensors ◽

Robust Systems ◽

Remote Health

This research addresses the challenge of recognizing human daily activities using surface electromyography (sEMG) and wearable inertial sensors. Effective and efficient recognition in this context has emerged as a cornerstone in robust remote health monitoring systems, among other applications. We propose a novel pipeline that can attain state-of-the-art recognition accuracies on a recent-and-standard dataset—the Human Gait Database (HuGaDB). Using wearable gyroscopes, accelerometers, and electromyography sensors placed on the thigh, shin, and foot, we developed an approach that jointly performs sensor fusion and feature selection. Being done jointly, the proposed pipeline empowers the learned model to benefit from the interaction of features that might have been dropped otherwise. Using statistical and time-based features from heterogeneous signals of the aforementioned sensor types, our approach attains a mean accuracy of 99.8%, which is the highest accuracy on HuGaDB in the literature. This research underlines the potential of incorporating EMG signals especially when fusion and selection are done simultaneously. Meanwhile, it is valid even with simple off-the-shelf feature selection methods such the Sequential Feature Selection family of algorithms. Moreover, through extensive simulations, we show that the left thigh is a key placement for attaining high accuracies. With one inertial sensor on that single placement alone, we were able to achieve a mean accuracy of 98.4%. The presented in-depth comparative analysis shows the influence that every sensor type, position, and placement can have on the attained recognition accuracies—a tool that can facilitate the development of robust systems, customized to specific scenarios and real-life applications.

Download Full-text

Stride segmentation of inertial sensor data using statistical methods for different walking activities

Robotica ◽

10.1017/s026357472100179x ◽

2021 ◽

pp. 1-14

Author(s):

Rahul Jain ◽

Vijay Bhaskar Semwal ◽

Praveen Kaushik

Keyword(s):

Autocorrelation Function ◽

Electronic Device ◽

Inertial Sensor ◽

Linear Acceleration ◽

Sensor Data ◽

Human Gait ◽

Tuning Parameter ◽

Measurement Unit ◽

Specific Information ◽

Inertial Measurement

Abstract Human gait data can be collected using inertial measurement units (IMUs). An IMU is an electronic device that uses an accelerometer and gyroscope to capture three-axial linear acceleration and three-axial angular velocity. The data so collected are time series in nature. The major challenge associated with these data is the segmentation of signal samples into stride-specific information, that is, individual gait cycles. One empirical approach for stride segmentation is based on timestamps. However, timestamping is a manual technique, and it requires a timing device and a fixed laboratory set-up which usually restricts its applicability outside of the laboratory. In this study, we have proposed an automatic technique for stride segmentation of accelerometry data for three different walking activities. The autocorrelation function (ACF) is utilized for the identification of stride boundaries. Identification and extraction of stride-specific data are done by devising a concept of tuning parameter ( $t_{p}$ ) which is based on minimum standard deviation ( $\sigma$ ). Rigorous experimentation is done on human activities and postural transition and Osaka University – Institute of Scientific and Industrial Research gait inertial sensor datasets. Obtained mean stride duration for level walking, walking upstairs, and walking downstairs is 1.1, 1.19, and 1.02 s with 95% confidence interval [1.08, 1.12], [1.15, 1.22], and [0.97, 1.07], respectively, which is on par with standard findings reported in the literature. Limitations of accelerometry and ACF are also discussed. stride segmentation; human activity recognition; accelerometry; gait parameter estimation; gait cycle; inertial measurement unit; autocorrelation function; wearable sensors; IoT; edge computing; tinyML.

Download Full-text

Person Re-Identification Using Deep Modeling of Temporally Correlated Inertial Motion Patterns

Sensors ◽

10.3390/s20030949 ◽

2020 ◽

Vol 20 (3) ◽

pp. 949 ◽

Cited By ~ 6

Author(s):

Imad Gohar ◽

Qaiser Riaz ◽

Muhammad Shahzad ◽

Muhammad Zeeshan Ul Hasnain Hashmi ◽

Hasan Tahir ◽

...

Keyword(s):

Visual Cues ◽

Inertial Sensor ◽

Strong Dependence ◽

Identification Problem ◽

Sensor Data ◽

Human Gait ◽

Motion Patterns ◽

Deep Recurrent Neural Network ◽

Essential Components ◽

Using Data

Person re-identification (re-ID) is among the essential components that play an integral role in constituting an automated surveillance environment. Majorly, the problem is tackled using data acquired from vision sensors using appearance-based features, which are strongly dependent on visual cues such as color, texture, etc., consequently limiting the precise re-identification of an individual. To overcome such strong dependence on visual features, many researchers have tackled the re-identification problem using human gait, which is believed to be unique and provide a distinctive biometric signature that is particularly suitable for re-ID in uncontrolled environments. However, image-based gait analysis often fails to extract quality measurements of an individual’s motion patterns owing to problems related to variations in viewpoint, illumination (daylight), clothing, worn accessories, etc. To this end, in contrast to relying on image-based motion measurement, this paper demonstrates the potential to re-identify an individual using inertial measurements units (IMU) based on two common sensors, namely gyroscope and accelerometer. The experiment was carried out over data acquired using smartphones and wearable IMUs from a total of 86 randomly selected individuals including 49 males and 37 females between the ages of 17 and 72 years. The data signals were first segmented into single steps and strides, which were separately fed to train a sequential deep recurrent neural network to capture implicit arbitrary long-term temporal dependencies. The experimental setup was devised in a fashion to train the network on all the subjects using data related to half of the step and stride sequences only while the inference was performed on the remaining half for the purpose of re-identification. The obtained experimental results demonstrate the potential to reliably and accurately re-identify an individual based on one’s inertial sensor data.

Download Full-text

Gait acts as a gate for reflexes from the foot

Canadian Journal of Physiology and Pharmacology ◽

10.1139/y04-071 ◽

2004 ◽

Vol 82 (8-9) ◽

pp. 715-722 ◽

Cited By ~ 46

Author(s):

J Duysens ◽

C M Bastiaanse ◽

B C.M Smits-Engelsman ◽

V Dietz

Keyword(s):

Electrical Stimulation ◽

Tibialis Anterior ◽

Stance Phase ◽

Background Activity ◽

Swing Phase ◽

The Body ◽

Human Gait ◽

Step Cycle ◽

Reflex Reversal ◽

Stimulation Of

During human gait, electrical stimulation of the foot elicits facilitatory P2 (medium latency) responses in TA (tibialis anterior) at the onset of the swing phase, while the same stimuli cause suppressive responses at the end of swing phase, along with facilitatory responses in antagonists. This phenomenon is called phase-dependent reflex reversal. The suppressive responses can be evoked from a variety of skin sites in the leg and from stimulation of some muscles such as rectus femoris (RF). This paper reviews the data on reflex reversal and adds new data on this topic, using a split-belt paradigm. So far, the reflex reversal in TA could only be studied for the onset and end phases of the step cycle, simply because suppression can only be demonstrated when there is background activity. Normally there are only 2 TA bursts in the step cycle, whereas TA is normally silent during most of the stance phase. To know what happens in the stance phase, one needs to have a means to evoke some background activity during the stance phase. For this purpose, new experiments were carried out in which subjects were asked to walk on a treadmill with a split-belt. When the subject was walking with unequal leg speeds, the walking pattern was adapted to a gait pattern resembling limping. The TA then remained active throughout most of the stance phase of the slow-moving leg, which was used as the primary support. This activity was a result of coactivation of agonistic and antagonistic leg muscles in the supporting leg, and represented one of the ways to stabilize the body. Electrical stimulation was given to a cutaneous nerve (sural) at the ankle at twice the perception threshold. Nine of the 12 subjects showed increased TA activity during stance phase while walking on split-belts, and 5 of them showed pronounced suppressions during the first part of stance when stimuli were given on the slow side. It was concluded that a TA suppressive pathway remains open throughout most of the stance phase in the majority of subjects. The suggestion was made that the TA suppression increases loading of the ankle plantar flexors during the loading phase of stance.Key words: human gait, cutaneous reflexes, sural nerve, tibialis anterior, split belt, reflex reversal.

Download Full-text

Aβ Fibers Mediate Cutaneous Reflexes During Human Walking

Journal of Neurophysiology ◽

10.1152/jn.2000.83.5.2980 ◽

2000 ◽

Vol 83 (5) ◽

pp. 2980-2986 ◽

Cited By ~ 27

Author(s):

B.M.H. van Wezel ◽

B.G.M. van Engelen ◽

F.J.M. Gabreëls ◽

A.A.W.M. Gabreëls-Festen ◽

J. Duysens

Keyword(s):

Healthy Subjects ◽

Biceps Femoris ◽

Human Gait ◽

Emg Activity ◽

Cutaneous Reflexes ◽

Step Cycle ◽

Reflex Responses ◽

Low Threshold ◽

Two Phases ◽

Aβ Fibers

During human gait, transmission of cutaneous reflexes from the foot is controlled specifically according to the phase of the step cycle. These reflex responses can be evoked by nonnociceptive stimuli, and therefore it is thought that the large-myelinated and low-threshold Aβ afferent fibers mediate these reflexes. At present, this hypothesis is not yet verified. To test whether Aβ fibers are involved the reflex responses were studied in patients with a sensory polyneuropathy who suffer from a predominant loss of large-myelinated Aβ fibers. The sural nerve of both patients and healthy control subjects was stimulated electrically at a nonnociceptive intensity during the early and late swing phases while they walked on a treadmill. The responses were studied by recording electromyographic (EMG) activity of the biceps femoris (BF) and tibialis anterior (TA) of the stimulated leg. In both phases, large facilitatory responses were observed in the BF of the healthy subjects. These facilitations were reduced significantly in the BF of the patients, indicating that Aβ fibers mediate these reflexes. In TA similar results were obtained. The absolute response magnitude across the two phases was significantly smaller for the patients than for the healthy subjects. The TA responses for the healthy subjects were on average facilitatory during early swing and suppressive during end swing. Both facilitations and suppressions were considerably smaller for the patients, indicating that both types of responses are mediated by Aβ fibers. It is concluded that low-threshold Aβ sensory fibers mediate these reflexes during human gait. The low threshold and the precise phase-dependent control of these responses suggest that these responses are important in the regulation of gait. The loss of such reflex activity may be related to the gait impairments of these patients.

Download Full-text

An evaluation of inertial sensor technology in the discrimination of human gait

Journal of Sports Sciences ◽

10.1080/02640414.2013.779739 ◽

2013 ◽

Vol 31 (12) ◽

pp. 1312-1318 ◽

Cited By ~ 15

Author(s):

Chris Little ◽

James Bruce Lee ◽

Daniel A. James ◽

Kade Davison

Keyword(s):

Inertial Sensor ◽

Human Gait ◽

Sensor Technology

Download Full-text

Towards Wearable-Inertial-Sensor-Based Gait Posture Evaluation for Subjects with Unbalanced Gaits

Sensors ◽

10.3390/s20041193 ◽

2020 ◽

Vol 20 (4) ◽

pp. 1193 ◽

Cited By ~ 8

Author(s):

SEN QIU ◽

Huihui Wang ◽

Jie Li ◽

Hongyu Zhao ◽

Zhelong Wang ◽

...

Keyword(s):

Gait Analysis ◽

Inertial Sensor ◽

Strong Support ◽

3D Models ◽

Health Condition ◽

Lower Limbs ◽

Sensor Nodes ◽

Human Gait ◽

Gait Parameters ◽

Analysis System

Human gait reflects health condition and is widely adopted as a diagnostic basisin clinical practice. This research adopts compact inertial sensor nodes to monitor the functionof human lower limbs, which implies the most fundamental locomotion ability. The proposedwearable gait analysis system captures limb motion and reconstructs 3D models with high accuracy.It can output the kinematic parameters of joint flexion and extension, as well as the displacementdata of human limbs. The experimental results provide strong support for quick access to accuratehuman gait data. This paper aims to provide a clue for how to learn more about gait postureand how wearable gait analysis can enhance clinical outcomes. With an ever-expanding gait database,it is possible to help physiotherapists to quickly discover the causes of abnormal gaits, sports injuryrisks, and chronic pain, and provides guidance for arranging personalized rehabilitation programsfor patients. The proposed framework may eventually become a useful tool for continually monitoringspatio-temporal gait parameters and decision-making in an ambulatory environment.

Download Full-text