Gait recognition: Highly unique dynamic plantar pressure patterns among 104 individuals

Department of Bioengineering, Shinshu University, Tokida 3-15-1 Ueda, Nagano 386-8567, Japan.
Journal of The Royal Society Interface (Impact Factor: 3.92). 09/2011; 9(69):790-800. DOI: 10.1098/rsif.2011.0430
Source: PubMed


Everyone's walking style is unique, and it has been shown that both humans and computers are very good at recognizing known gait patterns. It is therefore unsurprising that dynamic foot pressure patterns, which indirectly reflect the accelerations of all body parts, are also unique, and that previous studies have achieved moderate-to-high classification rates (CRs) using foot pressure variables. However, these studies are limited by small sample sizes (n < 30), moderate CRs (CR ≃ 90%), or both. Here we show, using relatively simple image processing and feature extraction, that dynamic foot pressures can be used to identify n = 104 subjects with a CR of 99.6 per cent. Our key innovation was improved and automated spatial alignment which, by itself, improved CR to over 98 per cent, a finding that pointedly emphasizes inter-subject pressure pattern uniqueness. We also found that automated dimensionality reduction invariably improved CRs. As dynamic pressure data are immediately usable, with little or no pre-processing required, and as they may be collected discreetly during uninterrupted gait using in-floor systems, foot pressure-based identification appears to have wide potential for both the security and health industries.

Download full-text


Available from: Todd C Pataky,
147 Reads
  • Source
    • "In gait and posture research, plantar pressure measurement is important to determine the condition of foot and ankle. Such measurement is used in footwear design [7,8], gait identification [9], gait alteration recognition [10], etc. It is also used to investigate the loading characteristics and classification of foot types. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Motion characteristics of CoP (Centre of Pressure, the point of application of the resultant ground reaction force acting on the plate) are useful for foot type characteristics detection. To date, only few studies have investigated the nonlinear characteristics of CoP velocity and acceleration during the stance phase. The aim of this study is to investigate whether CoP regularity is different among four foot types (normal foot, pes valgus, hallux valgus and pes cavus); this might be useful for classification and diagnosis of foot injuries and diseases. To meet this goal, sample entropy, a measure of time-series regularity, was used to quantify the CoP regularity of four foot types. One hundred and sixty five subjects that had the same foot type bilaterally (48 subjects with healthy feet, 22 with pes valgus, 47 with hallux valgus, and 48 with pes cavus) were recruited for this study. A Footscan(R) system was used to collect CoP data when each subject walked at normal and steady speed. The velocity and acceleration in medial-lateral (ML) and anterior-posterior (AP) directions, and resultant velocity and acceleration were derived from CoP. The sample entropy is the negative natural logarithm of the conditional probability that a subseries of length m that matches pointwise within a tolerance r also matches at the next point. This was used to quantify variables of CoP velocity and acceleration of four foot types. The parameters r (the tolerance) and m (the matching length) for sample entropy calculation have been determined by an optimal method. It has been found that in order to analyze all CoP parameters of velocity and acceleration during the stance phase of walking gait, for each variable there is a different optimal r value. On the contrary, the value m=4 is optimal for all variables.Sample entropies of both velocity and acceleration in AP direction were highly correlated with their corresponding resultant variables for r>0.91. The sample entropy of the velocity in AP direction was moderately correlated with the one of the acceleration in the same direction (r>=0.673), as well as with the resultant acceleration (r>=0.660). The sample entropy of resultant velocity was moderately correlated with the one of the acceleration in AP direction, as well as with the resultant acceleration (for the both r>=0.689). Moderate correlations were found between variables for the left foot and their corresponding variables for the right foot.Sample entropies of AP velocity, resultant velocity, AP acceleration, and resultant acceleration of the right foot as well as AP velocity and resultant velocity of the left foot were, respectively, significantly different among the four foot types. It can be concluded that the sample entropy of AP velocity (or the resultant velocity) of the left foot, ML velocity, resultant velocity, ML acceleration and resultant acceleration could serve for evaluation of foot types or selection of appropriate footwear.
    BioMedical Engineering OnLine 10/2013; 12(1):101. DOI:10.1186/1475-925X-12-101 · 1.43 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: A new method for performing a nonlinear form of principal component analysis is proposed. By the use of integral operator kernel functions, one can efficiently compute principal components in high-dimensional feature spaces, related to input space by some nonlinear mapfor instance, the space of all possible five-pixel products in 16 16 images. We give the derivation of the method and present experimental results on polynomial feature extraction for pattern recognition.
    Neural Computation 07/1998; 10(5):1299-1319. DOI:10.1162/089976698300017467 · 2.21 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we study travel time and energy cost prediction at any future departure time for a targeted road segment and vehicle. These two prediction tasks play an important part in the design of advanced driver-assistance systems (ADAS) that can automatically manage battery charging, energy saving, and route planning for fully electric vehicles. Compared with the fundamental problem of travel time prediction, which usually learns from the historical and current data of travel time itself, energy cost prediction is a more complex problem that involves multiple context conditions and vehicle status measured by various time-invariant and time-variant data. We define a general learning problem based on multiple time-invariant and time-variant inputs to unify these two prediction tasks. To solve the defined learning problem, we propose heterogeneous delay embedding (HDE), which extracts an informative feature space for regression analysis and aims at achieving satisfactory prediction for any future departure time. The proposed HDE first categorizes the historical and current data of a time-variant measurement into different types, then incorporates different delay settings for embedding multiple types of time-series data, and finally removes redundant information and noise from the generated features using orthogonal locality preserving projection. Experimental results demonstrate the effectiveness of the proposed method for both short- and long-term predictions of travel time and energy cost.
    IEEE Transactions on Intelligent Transportation Systems 03/2013; 14(1):214-224. DOI:10.1109/TITS.2012.2210419 · 2.38 Impact Factor
Show more