Online Decoding of Hidden Markov Models for Gait Event Detection Using Foot-Mounted Gyroscopes

Mannini, Andrea; Genovese, V.; Sabatini, A.M.

doi:10.1109/jbhi.2013.2293887

Cited by 104 publications

(97 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example, the approach in [18] uses adaptive thresholds while [13], [19] use peak detection to identify HS and TO from angular velocity signals. Other approaches include [20], where the gait cycle is divided into four gait phases represented in the form of a state machine and the transitions are governed by a knowledgebased algorithm, and [21], where an online Hidden Markov Model based method is presented. In [12], a wavelet based method is used to search for peaks associated with HS and TO which is modified in [22], such that the method can be used with minimal time delay.…”

Section: Introductionmentioning

confidence: 99%

Gait Event Detection in Real-World Environment for Long-Term Applications: Incorporating Domain Knowledge Into Time-Frequency Analysis

Khandelwal

Wickström

2016

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

PostprintThis is the accepted version of a paper published in IEEE transactions on neural systems and rehabilitation engineering. This paper has been peer-reviewed but does not include the final publisher proof-corrections or journal pagination. This article has been accepted for publication in a future issue of this journal, but has not been fully edited. Content may change prior to final publication. Abstract-Detecting gait events is the key to many gait analysis applications that would benefit from continuous monitoring or long-term analysis. Most gait event detection algorithms using wearable sensors that offer a potential for use in daily living have been developed from data collected in controlled indoor experiments. However, for real-word applications, it is essential that the analysis is carried out in humans' natural environment; that involves different gait speeds, changing walking terrains, varying surface inclinations and regular turns among other factors. Existing domain knowledge in the form of principles or underlying fundamental gait relationships can be utilized to drive and support the data analysis in order to develop robust algorithms that can tackle real-world challenges in gait analysis. This paper presents a novel approach that exhibits how domain knowledge about human gait can be incorporated into time-frequency analysis to detect gait events from longterm accelerometer signals. The accuracy and robustness of the proposed algorithm are validated by experiments done in indoor and outdoor environments with approximately 93,600 gait events in total. The proposed algorithm exhibits consistently high performance scores across all datasets in both, indoor and outdoor environments.

show abstract

Section: Introductionmentioning

confidence: 99%

Gait Event Detection in Real-World Environment for Long-Term Applications: Incorporating Domain Knowledge Into Time-Frequency Analysis

Khandelwal

Wickström

2016

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

show abstract

“…FF and HO were detected with greater difficulty [31] (Table 3). The algorithm was capable of generalizing well across different tested subjects and walking conditions, although overground walking is known to be different from treadmill walking [32,33]; moreover, the participants recruited for constructing the two datasets were different people, and even the experimental setups were different in the two cases (Table 1 and Table 2).…”

Section: Discussionmentioning

confidence: 99%

Ambulatory Assessment of Instantaneous Velocity during Walking Using Inertial Sensor Measurements

Sabatini

Mannini

2016

Sensors

Self Cite

View full text Add to dashboard Cite

A novel approach for estimating the instantaneous velocity of the pelvis during walking was developed based on Inertial Measurement Units (IMUs). The instantaneous velocity was modeled by the sum of a cyclical component, decomposed in the Medio-Lateral (ML), VerTical (VT) and Antero-Posterior (AP) directions, and the Average Progression Velocity (APV) over each gait cycle. The proposed method required the availability of two IMUs, attached to the pelvis and one shank. Gait cycles were identified from the shank angular velocity; for each cycle, the Fourier series coefficients of the pelvis and shank acceleration signals were computed. The cyclical component was estimated by Fourier-based time-integration of the pelvis acceleration. A Bayesian Linear Regression (BLR) with Automatic Relevance Determination (ARD) predicted the APV from the stride time, the stance duration, and the Fourier series coefficients of the shank acceleration. Healthy subjects performed tasks of Treadmill Walking (TW) and Overground Walking (OW), and an optical motion capture system (OMCS) was used as reference for algorithm performance assessment. The widths of the limits of agreements (±1.96 standard deviation) were computed between the proposed method and the reference OMCS, yielding, for the cyclical component in the different directions: ML: ±0.07 m/s (±0.10 m/s); VT: ±0.03 m/s (±0.05 m/s); AP: ±0.06 m/s (±0.10 m/s), in TW (OW) conditions. The ARD-BLR achieved an APV root mean square error of 0.06 m/s (0.07 m/s) in the same conditions.

show abstract

“…Most current gait feedback systems focused on precise gait phase recognition [12], [36], [16], [15], [37] while the detected gait event was used as a reliable trigger to start the stimulation. Seel et al [1] measured foot pitch angle and four gait phases by placing a 6D IMU on the foot, and based on which an iterative learning control scheme was developed.…”

Section: Accuracy Of Ankle Angle Measurementmentioning

confidence: 99%

A Practical Gait Feedback Method Based on Wearable Inertial Sensors for a Drop Foot Assistance Device

et al. 2019

View full text Add to dashboard Cite

To maximise the efficiency of gait interventions, gait phase and joint kinematics are important for closing the system loop of adaptive robotic control. However, few studies have applied an inertial sensor system including both gait phase detection and joint kinematic measurement. Many algorithms for joint measurement require careful alignment of the inertial measurement unit (IMU) to the body segment. In this paper, we propose a practical gait feedback method, which provides sufficient feedback without requiring precise alignment of the IMUs. The method incorporates a two-layer model to realise simultaneous gait stance and swing phase detection and ankle joint angle measurement. Recognition of gait phases is performed by a high-level probabilistic method using angular rate from the sensor attached to the shank while the ankle angle is calculated using a data fusion algorithm based on the complementary filter and sensor-to-segment calibration. The online performance of the algorithm was experimentally validated when 10 able-bodied participants walked on the treadmill with three different speeds. The outputs were compared to the ones measured by an optical motion analysis system. The results showed that the IMU-based algorithm achieved a good accuracy of the gait phase recognition (above 95%) with a short delay response below 20 ms and accurate angle measurements with root mean square errors below 3.5 • compared to the optical reference. It demonstrates that our method can be used to provide gait feedback for the correction of drop foot.

show abstract

Online Decoding of Hidden Markov Models for Gait Event Detection Using Foot-Mounted Gyroscopes

Cited by 104 publications

References 32 publications

Gait Event Detection in Real-World Environment for Long-Term Applications: Incorporating Domain Knowledge Into Time-Frequency Analysis

Gait Event Detection in Real-World Environment for Long-Term Applications: Incorporating Domain Knowledge Into Time-Frequency Analysis

Ambulatory Assessment of Instantaneous Velocity during Walking Using Inertial Sensor Measurements

A Practical Gait Feedback Method Based on Wearable Inertial Sensors for a Drop Foot Assistance Device

Contact Info

Product

Resources

About