Human Gait Analysis Based on Decision Tree, Random Forest and KNN Algorithms
01 Jan 2020-pp 283-289
TL;DR: The results show that the Random Forest algorithm performs better in classifying normal and abnormal gait, and the comparison of these classification models based on various parameters using the RapidMiner Studio tool shows this.
Abstract: Human Gait refers to motion accomplished through the movement of hand limbs. Gait analysis is a precise investigation of the human walking pattern using sensors attached to the body for recording body movements during activities like walking on a flat surface, treadmill and running. This paper addresses the analysis of human gait based on performance using various classification techniques involving Decision Tree, Random Forest and KNN algorithms. The paper highlights the comparison of these classification models based on various parameters using the RapidMiner Studio tool. The comparison is based on performance metrics and Receiver Operating Characteristic (ROC). The results show that the Random Forest algorithm performs better in classifying normal and abnormal gait.
Citations
More filters
TL;DR: In this article, a decision tree model and a long short-term memory (LSTM) model were used to detect foot strike in lower limb amputees using accelerometer and gyroscope signals collected from a smartphone positioned at the posterior pelvis.
Abstract: Foot strike detection is important when evaluating a person’s gait characteristics. Accelerometer and gyroscope signals from smartphones have been used to train artificial intelligence (AI) models for automated foot strike detection in able-bodied and elderly populations. However, there is limited research on foot strike detection in lower limb amputees, who have a more variable and asymmetric gait. A novel method for automated foot strike detection in lower limb amputees was developed using raw accelerometer and gyroscope signals collected from a smartphone positioned at the posterior pelvis. Raw signals were used to train a decision tree model and long short-term memory (LSTM) model for automated foot strike detection. These models were developed using retrospective data (n = 72) collected with the TOHRC Walk Test app during a 6-min walk test (6MWT). An Android smartphone was placed on a posterior belt for each participant during the 6MWT to collect accelerometer and gyroscope signals at 50 Hz. The best model for foot strike identification was the LSTM with 100 hidden nodes in the LSTM layer, 50 hidden nodes in the dense layer, and a batch size of 64 (99.0% accuracy, 86.4% sensitivity, 99.4% specificity, and 83.7% precision). This research created a novel method for automated foot strike identification in lower extremity amputee populations that is equivalent to manual labelling and accessible for clinical use. Automated foot strike detection is required for stride analysis and to enable other AI applications, such as fall detection.
4 citations
01 Jan 2022
TL;DR: In this article , three feature descriptor algorithms that are Scale Invariant Feature Transform (SIFT), Speeded Up Robust Feature (SURF) and Shi-Tomasi edge corner detector are used for extracting the unique features of the gait images.
Abstract: Human Gait Recognition has become a burning research area because of its promising application in security enhancement. There are numerous state-of-the-art feature detectors and classifiers available for gait recognition. In this article, three popular feature descriptor algorithms that are Scale Invariant Feature Transform (SIFT), Speeded Up Robust Feature (SURF) and Shi-Tomasi edge corner detector are used for extracting the unique features of the gait images. At first, the experiment is done by using a single feature descriptor then a combination of these three is applied. Various classifiers like Decision Tree, Random Forest, MLP are used to make the class membership based on features. Maximum accuracy of 76.12%, by applying the Decision Tree classifier, 80.11% by Random Forest, and 74.25% by applying MLP has been achieved for the CASIA-A dataset. In this article authors have computed recognition rate, false-positive rate (FPR) and root mean squared error (RMSE) in all cases to compare the performance of features and classifiers considered in this article. The experimental results depict that a combination of these three feature descriptors is performing better than other existing state-of-the art-work.
1 citations
TL;DR: It is suggested that children under the age of five should be supervised by an adult rather than a stranger, as is the case with children aged under five in the United States.
Abstract: ......................................................................................................................................... ii Table of
TL;DR: Wang et al. as discussed by the authors proposed a two-stream framework, with one stream learning from the joint position and the other from the relative joint displacement, and further developed a mid-layer fusion module to combine the discovered patterns in these two streams for diagnosis.
Abstract: Musculoskeletal and neurological disorders are the most common causes of walking problems among older people, and they often lead to diminished quality of life. Analyzing walking motion data manually requires trained professionals and the evaluations may not always be objective. To facilitate early diagnosis, recent deep learning-based methods have shown promising results for automated analysis, which can discover patterns that have not been found in traditional machine learning methods. We observe that existing work mostly applies deep learning on individual joint features such as the time series of joint positions. Due to the challenge of discovering inter-joint features such as the distance between feet (i.e. the stride width) from generally smaller-scale medical datasets, these methods usually perform sub-optimally. As a result, we propose a solution that explicitly takes both individual joint features and inter-joint features as input, relieving the system from the need of discovering more complicated features from small data. Due to the distinctive nature of the two types of features, we introduce a two-stream framework, with one stream learning from the time series of joint position and the other from the time series of relative joint displacement. We further develop a mid-layer fusion module to combine the discovered patterns in these two streams for diagnosis, which results in a complementary representation of the data for better prediction performance. We validate our system with a benchmark dataset of 3D skeleton motion that involves 45 patients with musculoskeletal and neurological disorders, and achieve a prediction accuracy of 95.56%, outperforming state-of-the-art methods.
TL;DR: By analyzing a large cohort database, this study systematically identified four major types of anomalies that occur during gait analysis using OpenPose in uncontrolled environments: anatomical, biomechanical, and physical anomalies and errors due to estimation.
Abstract: Two-dimensional video-based pose estimation is a technique that can estimate human skeletal coordinates from video data alone. It is also being applied to gait analysis and, particularly, due to its simplicity of measurement, it has the potential to be applied to the gait analysis of large populations. In contrast, it is considered difficult to completely homogenize the environment and settings during the measurement of large populations. Therefore, it is necessary to appropriately deal with technical errors that are not related to the biological factors of interest. In this study, by analyzing a large cohort database, we have identified four major types of anomalies that occur during gait analysis using OpenPose in uncontrolled environments: anatomical, biomechanical, and physical anomalies and errors due to estimation. We have also developed a workflow for identifying and correcting those anomalies and confirmed that the workflow is reproducible through simulation experiments. Our results will help obtain a comprehensive understanding of the anomalies to be addressed in a pre-processing for 2D video-based gait analysis of large populations. Author summary Gait is one of the important biomarkers of health conditions. With developing mobile health technologies, it is becoming easier to measure our health. However, to realize preventive medicine, establishing evidence is a critical issue, and we need to collect data from a large population. Two-dimensional video-based pose estimation can be a solution for the gait analysis of such a population. However, the technical accuracy and limitations of this analysis have not yet been sufficiently discussed. In this study, by analyzing the largest database currently available, we systematically identified four types of technical anomalies that occur during gait measurement: anatomical, biomechanical, and physical anomalies and errors dues to estimation. We have also shown how to deal with these issues and made solutions available as software so that researchers can reproduce them. In the future, increasing number of studies will use 2D video-based pose estimation to research health-related gait among large populations. We believe that our work will provide a guideline for researchers and clinicians involved in these studies to discuss design and algorithms.
References
More filters
[...]
TL;DR: Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the forest, and are also applicable to regression.
Abstract: Random forests are a combination of tree predictors such that each tree depends on the values of a random vector sampled independently and with the same distribution for all trees in the forest. The generalization error for forests converges a.s. to a limit as the number of trees in the forest becomes large. The generalization error of a forest of tree classifiers depends on the strength of the individual trees in the forest and the correlation between them. Using a random selection of features to split each node yields error rates that compare favorably to Adaboost (Y. Freund & R. Schapire, Machine Learning: Proceedings of the Thirteenth International conference, aaa, 148–156), but are more robust with respect to noise. Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the splitting. Internal estimates are also used to measure variable importance. These ideas are also applicable to regression.
79,257 citations
[...]
01 Aug 1996
TL;DR: Tests on real and simulated data sets using classification and regression trees and subset selection in linear regression show that bagging can give substantial gains in accuracy.
Abstract: Bagging predictors is a method for generating multiple versions of a predictor and using these to get an aggregated predictor. The aggregation averages over the versions when predicting a numerical outcome and does a plurality vote when predicting a class. The multiple versions are formed by making bootstrap replicates of the learning set and using these as new learning sets. Tests on real and simulated data sets using classification and regression trees and subset selection in linear regression show that bagging can give substantial gains in accuracy. The vital element is the instability of the prediction method. If perturbing the learning set can cause significant changes in the predictor constructed, then bagging can improve accuracy.
16,118 citations
TL;DR: A new approach to shape recognition based on a virtually infinite family of binary features (queries) of the image data, designed to accommodate prior information about shape invariance and regularity, and a comparison with artificial neural networks methods is presented.
Abstract: We explore a new approach to shape recognition based on a virtually infinite family of binary features (queries) of the image data, designed to accommodate prior information about shape invariance and regularity. Each query corresponds to a spatial arrangement of several local topographic codes (or tags), which are in themselves too primitive and common to be informative about shape. All the discriminating power derives from relative angles and distances among the tags. The important attributes of the queries are a natural partial ordering corresponding to increasing structure and complexity; semi-invariance, meaning that most shapes of a given class will answer the same way to two queries that are successive in the ordering; and stability, since the queries are not based on distinguished points and substructures. No classifier based on the full feature set can be evaluated, and it is impossible to determine a priori which arrangements are informative. Our approach is to select informative features and build tree classifiers at the same time by inductive learning. In effect, each tree provides an approximation to the full posterior where the features chosen depend on the branch that is traversed. Due to the number and nature of the queries, standard decision tree construction based on a fixed-length feature vector is not feasible. Instead we entertain only a small random sample of queries at each node, constrain their complexity to increase with tree depth, and grow multiple trees. The terminal nodes are labeled by estimates of the corresponding posterior distribution over shape classes. An image is classified by sending it down every tree and aggregating the resulting distributions. The method is applied to classifying handwritten digits and synthetic linear and nonlinear deformations of three hundred L AT E X symbols. Stateof-the-art error rates are achieved on the National Institute of Standards and Technology database of digits. The principal goal of the experiments on L AT E X symbols is to analyze invariance, generalization error and related issues, and a comparison with artificial neural networks methods is presented in this context.
1,214 citations
01 Mar 2008
TL;DR: This paper analyzes the effectiveness of the seven human gait components for ID and gender recognition under a wide range of circumstances.
Abstract: Human gait is a promising biometrics resource. In this paper, the information about gait is obtained from the motions of the different parts of the silhouette. The human silhouette is segmented into seven components, namely head, arm, trunk, thigh, front-leg, back-leg, and feet. The leg silhouettes for the front-leg and the back-leg are considered separately because, during walking, the left leg and the right leg are in front or at the back by turns. Each of the seven components and a number of combinations of the components are then studied with regard to two useful applications: human identification (ID) recognition and gender recognition. More than 500 different experiments on human ID and gender recognition are carried out under a wide range of circumstances. The effectiveness of the seven human gait components for ID and gender recognition is analyzed.
295 citations
TL;DR: A sparse reconstruction based metric learning method is proposed to learn a distance metric to minimize the intra-class sparse reconstruction errors and maximize the inter-class dense reconstruction errors simultaneously, so that discriminative information can be exploited for recognition.
Abstract: We investigate the problem of human identity and gender recognition from gait sequences with arbitrary walking directions. Most current approaches make the unrealistic assumption that persons walk along a fixed direction or a pre-defined path. Given a gait sequence collected from arbitrary walking directions, we first obtain human silhouettes by background subtraction and cluster them into several clusters. For each cluster, we compute the cluster-based averaged gait image as features. Then, we propose a sparse reconstruction based metric learning method to learn a distance metric to minimize the intra-class sparse reconstruction errors and maximize the inter-class sparse reconstruction errors simultaneously, so that discriminative information can be exploited for recognition. The experimental results show the efficacy of our approach.
195 citations