RESUMEN
Human gait is a unique behavioral characteristic that can be used to recognize individuals. Collecting gait information widely by the means of wearable devices and recognizing people by the data has become a topic of research. While most prior studies collected gait information using inertial measurement units, we gather the data from 40 people using insoles, including pressure sensors, and precisely identify the gait phases from the long time series using the pressure data. In terms of recognizing people, there have been a few recent studies on neural network-based approaches for solving the open set gait recognition problem using wearable devices. Typically, these approaches determine decision boundaries in the latent space with a limited number of samples. Motivated by the fact that such methods are sensitive to the values of hyper-parameters, as our first contribution, we propose a new network model that is less sensitive to changes in the values using a new prototyping encoder-decoder network architecture. As our second contribution, to overcome the inherent limitations due to the lack of transparency and interpretability of neural networks, we propose a new module that enables us to analyze which part of the input is relevant to the overall recognition performance using explainable tools such as sensitivity analysis (SA) and layer-wise relevance propagation (LRP).
Asunto(s)
Apatía , Dispositivos Electrónicos Vestibles , Marcha , Humanos , Redes Neurales de la Computación , Reconocimiento en PsicologíaRESUMEN
Gait is a characteristic that has been utilized for identifying individuals. As human gait information is now able to be captured by several types of devices, many studies have proposed biometric identification methods using gait information. As research continues, the performance of this technology in terms of identification accuracy has been improved by gathering information from multi-modal sensors. However, in past studies, gait information was collected using ancillary devices while the identification accuracy was not high enough for biometric identification. In this study, we propose a deep learning-based biometric model to identify people by their gait information collected through a wearable device, namely an insole. The identification accuracy of the proposed model when utilizing multi-modal sensing is over 99%.
Asunto(s)
Identificación Biométrica , Aprendizaje Profundo , Análisis de la Marcha , Zapatos , Dispositivos Electrónicos Vestibles , Biometría , HumanosRESUMEN
Recent studies indicate that individuals can be identified by their gait pattern. A number of sensors including vision, acceleration, and pressure have been used to capture humans' gait patterns, and a number of methods have been developed to recognize individuals from their gait pattern data. This study proposes a novel method of identifying individuals using null-space linear discriminant analysis on humans' gait pattern data. The gait pattern data consists of time series pressure and acceleration data measured from multi-modal sensors in a smart insole used while walking. We compare the identification accuracies from three sensing modalities, which are acceleration, pressure, and both in combination. Experimental results show that the proposed multi-modal features identify 14 participants with high accuracy over 95% from their gait pattern data of walking.
Asunto(s)
Marcha/fisiología , Dispositivos Electrónicos Vestibles , Acelerometría , Adulto , Algoritmos , Análisis Discriminante , Femenino , Análisis de la Marcha , Humanos , Masculino , Zapatos , Adulto JovenRESUMEN
Supertree problems are a standard tool for synthesizing large-scale species trees from a given collection of gene trees under some problem-specific objective. Unfortunately, these problems are typically NP-hard, and often remain so when their instances are restricted to rooted gene trees sampled from the same species. While a class of restricted supertree problems has been effectively addressed by the parameterized strict consensus approach, in practice, most gene trees are unrooted and sampled from different species. Here, we overcome this stringent limitation by describing efficient algorithms that are adopting the strict consensus approach to also handle unrestricted supertree problems. Finally, we demonstrate the performance of our algorithms in a comparative study with classic supertree heuristics using simulated and empirical data sets.
Asunto(s)
Algoritmos , Filogenia , Biología Computacional/métodos , Simulación por Computador , Duplicación de GenRESUMEN
Solving the gene duplication problem is a classical approach for species tree inference from gene trees that are confounded by gene duplications. This problem takes a collection of gene trees and seeks a species tree that implies the minimum number of gene duplications. Wilkinson et al. posed the conjecture that the gene duplication problem satisfies the desirable Pareto property for clusters. That is, for every instance of the problem, all clusters that are commonly present in the input gene trees of this instance, called strict consensus, will also be found in every solution to this instance. We prove that this conjecture does not generally hold. Despite this negative result we show that the gene duplication problem satisfies a weaker version of the Pareto property where the strict consensus is found in at least one solution (rather than all solutions). This weaker property contributes to our design of an efficient scalable algorithm for the gene duplication problem. We demonstrate the performance of our algorithm in analyzing large-scale empirical datasets. Finally, we utilize the algorithm to evaluate the accuracy of standard heuristics for the gene duplication problem using simulated datasets.