A Novel HMM Distributed Classifier for the Detection of Gait Phases by Means of a Wearable Inertial Sensor Network

Taborri, Juri; Rossi, Stefano; Palermo, Eduardo; Patanè, Fabrizio; Cappa, Paolo

doi:10.3390/s140916212

Cited by 113 publications

(112 citation statements)

References 57 publications

(72 reference statements)

Supporting

Mentioning

101

Contrasting

Unclassified

Order By: Relevance

“…In a clinical environment, faster and easier algorithms and protocols should be employed, for example as in Palermo et al (2014a,b) and Taborri et al (2014).…”

Section: Figure 7 | Coefficients Of Determination Rmentioning

confidence: 99%

“…Standard wearable kinematic sensors are inertial measurement units (IMUs), consisting of accelerometers, gyroscopes, and potentially magnetometers. Such IMUs are commonly used in several fields, not only for real-time fall detection (Kangas et al, 2008), teNyan2008 but also for clinical gait analysis (Goršič et al, 2014;Taborri et al, 2014) or in sport coaching (Exell et al, 2012). IMUs are advantageous in terms of weight, size, energy consumption, and cost.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Observing the State of Balance with a Single Upper-Body Sensor

2016

View full text Add to dashboard Cite

The occurrence of falls is an urgent challenge in our aging society. For wearable devices that actively prevent falls or mitigate their consequences, a critical prerequisite is knowledge on the user's current state of balance. To keep such wearable systems practical and to achieve high acceptance, only very limited sensor instrumentation is possible, often restricted to inertial measurement units at waist level. We propose to augment this limited sensor information by combining it with additional knowledge on human gait, in the form of an observer concept. The observer contains a combination of validated concepts to model human gait: a spring-loaded inverted pendulum model with articulated upper body, where foot placement and stance leg are controlled via the extrapolated center of mass (XCoM) and the virtual pivot point (VPP), respectively. State estimation is performed via an Additive Unscented Kalman Filter (Additive UKF). We investigated sensitivity of the proposed concept to model uncertainties, and we evaluated observer performance with real data from human subjects walking on a treadmill. Data were collected from an Inertial Measurement Unit (IMU) placed near the subject's center of mass (CoM), and observer estimates were compared to the ground truth as obtained via infrared motion capture. We found that the root mean squared deviation did not exceed 13 cm on position, 22 cm/s on velocity (0.56-1.35 m/s), 1.2°on orientation, and 17°/s on angular velocity.Keywords: human gait and balance, wearable sensors, state estimation, virtual pivot point, extrapolated center of mass, capture point, additive unscented kalman filter, fall detection

show abstract

“…In a clinical environment, faster and easier algorithms and protocols should be employed, for example as in Palermo et al (2014a,b) and Taborri et al (2014).…”

Section: Figure 7 | Coefficients Of Determination Rmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Observing the State of Balance with a Single Upper-Body Sensor

2016

View full text Add to dashboard Cite

show abstract

“…The expectation maximization (EM) algorithm and hidden Markov model (HMM) model are used for dividing one gait cycle into six sub-phases. The work in [29,30] focused on the gait partitioning by means of gyroscope data in order to implement a control system for a pediatric exoskeleton. They introduced a novel algorithm based on a hierarchical weighted decision on the output of two or more scalar HMMs to estimate the most likely sequence of four gait phases.…”

Section: Introductionmentioning

confidence: 99%

Gait Phase Recognition for Lower-Limb Exoskeleton with Only Joint Angular Sensors

Liu

Wang

et al. 2016

Sensors

View full text Add to dashboard Cite

Gait phase is widely used for gait trajectory generation, gait control and gait evaluation on lower-limb exoskeletons. So far, a variety of methods have been developed to identify the gait phase for lower-limb exoskeletons. Angular sensors on lower-limb exoskeletons are essential for joint closed-loop controlling; however, other types of sensors, such as plantar pressure, attitude or inertial measurement unit, are not indispensable.Therefore, to make full use of existing sensors, we propose a novel gait phase recognition method for lower-limb exoskeletons using only joint angular sensors. The method consists of two procedures. Firstly, the gait deviation distances during walking are calculated and classified by Fisher’s linear discriminant method, and one gait cycle is divided into eight gait phases. The validity of the classification results is also verified based on large gait samples. Secondly, we build a gait phase recognition model based on multilayer perceptron and train it with the phase-labeled gait data. The experimental result of cross-validation shows that the model has a 94.45% average correct rate of set (CRS) and an 87.22% average correct rate of phase (CRP) on the testing set, and it can predict the gait phase accurately. The novel method avoids installing additional sensors on the exoskeleton or human body and simplifies the sensory system of the lower-limb exoskeleton.

show abstract

“…The results obtained are used in the second stage to classify the process based on the Viterbi Algorithm [34] or its modification, called Forward-Only [35,36], which improves the quality of data processing in real time.…”

Section: B Intellectual Subsystemmentioning

confidence: 99%

Transfemoral Prostheses Control in a Frame of Intellectual-Synergetic Concept

Poliakov¹,

Pakhaliuk²,

Kolesova³

et al. 2017

Proceedings of the 2017 2nd International Conference on Automation, Mechanical and Electrical Engineering (AMEE 2017)

View full text Add to dashboard Cite

Abstract-In the control process of transfemoral prostheses in real time, the need to solve a number of non-trivial tasks there arises. The most difficult of them: recognizing the intentions of the disabled person to carry out any movement in the short term and choosing the optimal strategy for moving to the target, taking into account excessive number degrees of freedom of the prosthetic system. At the same time, the optimal should be considered the strategy of movement, which ensures the safety and most comfortable walking of a disabled person from its subjective point of view. Such a strategy can be implemented in a frame of the intellectual-synergistic concept of control. Herewith, the prosthesis control system is designed based on two basic subsystems: the intellectual subsystem -designed to assess the current state and recognize the intentions of the disabled person and the synergetic subsystem -designed to select the optimal strategy for limb movement toward the goal. In this work, the structure of the transfemoral prosthesis control system, realized within the framework of the intellectual-synergistic concept with regard to synergistic quality criteria, is substantiated. It is shown that the use of reasonable synergetic quality criteria allows successfully solving the pseudo-Bernstein problem when planning the movements of controlled transfemoral prostheses and using these movements as reference for the prostheses control system.

show abstract

A Novel HMM Distributed Classifier for the Detection of Gait Phases by Means of a Wearable Inertial Sensor Network

Cited by 113 publications

References 57 publications

Observing the State of Balance with a Single Upper-Body Sensor

Observing the State of Balance with a Single Upper-Body Sensor

Gait Phase Recognition for Lower-Limb Exoskeleton with Only Joint Angular Sensors

Transfemoral Prostheses Control in a Frame of Intellectual-Synergetic Concept

Contact Info

Product

Resources

About