Gaussian Mixture Model Feature Research Articles

Learning feature representations from unlabeled data for volcano-seismic event classification

Accurately identifying and labeling seismic events is essential for understanding the internal dynamics of volcanoes and predicting volcanic eruptions. However, the manual labeling of seismic events is a labor-intensive and resource-demanding process that requires the expertise of highly skilled vulcanologist professionals. Unsupervised learning approaches provide an alternative solution by automatically discovering hidden structures in the data, thereby enabling the characterization of seismic events without requiring manual labeling. We compare two widely recognized unsupervised learning algorithms, k-means and the Gaussian mixture model (GMM), which employ different assignment strategies (i.e., hard assignment for k-means and soft assignment for GMM), to learn a feature representation from an unlabeled dataset collected from the Cotopaxi volcano. The learned feature representations are then evaluated on a supervised task to classify LP and VT events using labeled datasets from the Cotopaxi and Llaima volcanoes. Additionally, we compare our approach to a baseline composed of hand-crafted features engineered by domain experts over the years. Our findings highlight the effectiveness of unsupervised techniques in learning a wide range of relevant features that exhibit a high correlation with the baseline. Furthermore, when assessed in a classification task, our unsupervised approach achieves a statistically similar performance compared to the baseline features. Notably, the GMM feature representation outperforms the baseline features in effectively handling VT and LP noisy signals from the BREF station at Cotopaxi volcano.

3D Holoscopic Image Compression Based on Gaussian Mixture Model

We introduce a Gaussian Mixture Model (GMM) framework for 3D holoscopic image compression in this paper. The elemental-images of the 3D holoscopic image are predicted using GMM and the parameters of GMM are estimated using the common Expectation-Maximization (EM) algorithm. GMM Model Optimization (GMO) is used in this framework to select the optimal number of distributions and avoid local optimum of EM at the same time. A three-dimensional distribution-rotation based decomposition is proposed to change covariance parameters to meaningful features and improve the coding efficiency. The features and the remaining parameters of the GMM are encoded using fixed-length bits. A feature-based dictionary is proposed in this framework to match the similar Gaussian distributions utilizing the similar GMM features. And the offsets of the matched distributions are recorded as motion vectors to replace the similar areas in the elemental-images of the 3D holoscopic image. The residual between the original image and the prediction is encoded using Screen Content Coding Extension of High Efficiency Video Coding (HEVC-SCC). Experimental results show that our method performs better than HEVC-SCC, two coding methods based on pseudo-sequences and a state-of-the-art content-based compression method with Gaussian process regression.

A GMM-DTW-Based Locomotion Mode Recognition Method in Lower Limb Exoskeleton

Exoskeleton robots can provide support and protection to the human body as well as be able to perform a series of tasks under control. Locomotion mode recognition is an essential prerequisite for assisted control of lower limb exoskeleton robots. A system is designed to be applied to a variety of individuals with quick and accurate identification. In this article, we propose a novel real-time locomotion mode recognition algorithm based on Gaussian mixture model (GMM) features aligned by dynamic time warping (DTW). The spatial distribution of the sensor data is represented by the GMM features, which emphasize the coupling between joints. This peculiarity promotes the distinction of similarity judgment and shows superior generalization performance. Furthermore, we expand the study of the warping path. We further validate the reasonableness of the DTW algorithm for feature matching to improve the recognition rate. The data of several inertial measurement units (IMUs) and pressure sensors were collected by 17 subjects in three terrains, including level ground, stairs, and ramp. We define the five locomotion modes as walking on level ground, stair ascent (SA), stair descent, ramp ascent, and ramp descent. Compared with the algorithms in previous papers, the GMM-DTW algorithm can achieve substantial recognition rates and good generalization performance with low latency. This work establishes the groundwork for the soft control of exoskeleton robots in the future.

Stochastic Recognition of Physical Activity and Healthcare Using Tri-Axial Inertial Wearable Sensors

The classification of human activity is becoming one of the most important areas of human health monitoring and physical fitness. With the use of physical activity recognition applications, people suffering from various diseases can be efficiently monitored and medical treatment can be administered in a timely fashion. These applications could improve remote services for health care monitoring and delivery. However, the fixed health monitoring devices provided in hospitals limits the subjects’ movement. In particular, our work reports on wearable sensors that provide remote monitoring that periodically checks human health through different postures and activities to give people timely and effective treatment. In this paper, we propose a novel human activity recognition (HAR) system with multiple combined features to monitor human physical movements from continuous sequences via tri-axial inertial sensors. The proposed HAR system filters 1D signals using a notch filter that examines the lower/upper cutoff frequencies to calculate the optimal wearable sensor data. Then, it calculates multiple combined features, i.e., statistical features, Mel Frequency Cepstral Coefficients, and Gaussian Mixture Model features. For the classification and recognition engine, a Decision Tree classifier optimized by the Binary Grey Wolf Optimization algorithm is proposed. The proposed system is applied and tested on three challenging benchmark datasets to assess the feasibility of the model. The experimental results show that our proposed system attained an exceptional level of performance compared to conventional solutions. We achieved accuracy rates of 88.25%, 93.95%, and 96.83% over MOTIONSENSE, MHEALTH, and the proposed self-annotated IM-AccGyro human-machine dataset, respectively.

Rotation invariant curvelet based image retrieval & classification via Gaussian mixture model and co-occurrence features

Demand for better retrieval methods continue to outstrip the capabilities of available technologies despite the rapid growth of new feature extraction techniques. Extracting discriminatory features that contain texture specific information are of crucial importance in image indexing. This paper presents a novel rotation invariant texture representation model based on the multi-resolution curvelet transform via co-occurrence and Gaussian mixture features for image retrieval and classification. To extract these features, curvelet transform is applied and the coefficients are obtained at each scale and orientation. The Gaussian mixture model (GMM) features are computed from each of the sub bands and co-occurrence features are computed for only specific sub band. Rotation invariance is provided by applying cycle-shift around the GMM features. The proposed method is evaluated on well-known databases such as Brodatz, Outex_TC_00010, Outex_TC_00012, Outex_TC_00012horizon, Outex_TC_00012tl84, Vistex and KTH-TIPS. When the feature vector is analyzed in terms of its size, it is observed that its dimension is smaller than that of the existing rotation-invariant variants and it has a very good performance. Simulation results show a good performance achieved by combining different techniques with the curvelet transform. Proposed method results in high degree of success rate in classification and in precision-recall value for retrieval.

A Novel Online Signature Verification System Based on GMM Features in a DTW Framework

This paper presents a novel online signature verification system based on the extension of the traditional dynamic time warping (DTW) matching scheme. We propose the use of a set of features derived from a Gaussian mixture model (GMM) for the alignment of the signatures using DTW. These features aid in capturing signature-dependent characteristics of a user in the feature space with a probabilistic framework. In addition, we explore the characteristics of the warping path of DTW, by employing the proposed GMM features. We derive a score for the warping path, and fuse it to that of the DTW score for verifying the authenticity of a test signature. To the best of our knowledge, this paper is the first of its kind that uses the features of the GMM, a model-based classifier into the framework of the DTW technique for online signature verification. The experiments are conducted on the publicly available MCYT database for both common and user thresholds. The results obtained are promising over prior works for this database.

Automated Feature Extraction in Brain Tumor by Magnetic Resonance Imaging Using Gaussian Mixture Models.

This paper presents a novel method for Glioblastoma (GBM) feature extraction based on Gaussian mixture model (GMM) features using MRI. We addressed the task of the new features to identify GBM using T1 and T2 weighted images (T1-WI, T2-WI) and Fluid-Attenuated Inversion Recovery (FLAIR) MR images. A pathologic area was detected using multithresholding segmentation with morphological operations of MR images. Multiclassifier techniques were considered to evaluate the performance of the feature based scheme in terms of its capability to discriminate GBM and normal tissue. GMM features demonstrated the best performance by the comparative study using principal component analysis (PCA) and wavelet based features. For the T1-WI, the accuracy performance was 97.05% (AUC = 92.73%) with 0.00% missed detection and 2.95% false alarm. In the T2-WI, the same accuracy (97.05%, AUC = 91.70%) value was achieved with 2.95% missed detection and 0.00% false alarm. In FLAIR mode the accuracy decreased to 94.11% (AUC = 95.85%) with 0.00% missed detection and 5.89% false alarm. These experimental results are promising to enhance the characteristics of heterogeneity and hence early treatment of GBM.

CADrx for GBM Brain Tumors: Predicting Treatment Response from Changes in Diffusion-Weighted MRI

The goal of this study was to develop a computer-aided therapeutic response (CADrx) system for early prediction of drug treatment response for glioblastoma multiforme (GBM) brain tumors with diffusion weighted (DW) MR images. In conventional Macdonald assessment, tumor response is assessed nine weeks or more post-treatment. However, we will investigate the ability of DW-MRI to assess response earlier, at five weeks post treatment. The apparent diffusion coefficient (ADC) map, calculated from DW images, has been shown to reveal changes in the tumor’s microenvironment preceding morphologic tumor changes. ADC values in treated brain tumors could theoretically both increase due to the cell kill (and thus reduced cell density) and decrease due to inhibition of edema. In this study, we investigated the effectiveness of features that quantify changes from pre- and post-treatment tumor ADC histograms to detect treatment response. There are three parts to this study: first, tumor regions were segmented on T1w contrast enhanced images by Otsu’s thresholding method, and mapped from T1w images onto ADC images by a 3D region of interest (ROI) mapping tool using DICOM header information; second, ADC histograms of the tumor region were extracted from both pre- and five weeks post-treatment scans, and fitted by a two-component Gaussian mixture model (GMM). The GMM features as well as standard histogram-based features were extracted. Finally, supervised machine learning techniques were applied for classification of responders or non-responders. The approach was evaluated with a dataset of 85 patients with GBM under chemotherapy, in which 39 responded and 46 did not, based on tumor volume reduction. We compared adaBoost, random forest and support vector machine classification algorithms, using ten-fold cross validation, resulting in the best accuracy of 69.41% and the corresponding area under the curve (Az) of 0.70.