Search Results (4)

In the recent years, deep learning has been widely used in process monitoring due to its strong ability to extract features. However, with the increasing layers of the deep network, the compression of features by the deep model will lead to the loss of some valuable information and affect the model’s performance. To solve this problem, a fault detection method based on a discriminant enhanced stacked auto-encoder is proposed. An enhanced stacked auto-encoder network structure is designed, and the original data is added to each hidden layer in the model pre-training process to solve the problem of information loss in the feature extraction process. Then the self-encoding network is combined with spectral regression kernel discriminant analysis. The fault category information is introduced into the features to optimize the features and enhance the discrimination of the extracted features. The Euclidean distance is used for fault detection based on the extracted features. From the Tennessee Eastman process experiment, it can be found that the detection accuracy of this method is about 9.4% higher than that of the traditional stacked auto-encoder method. Full article

Pattern recognition is a multidisciplinary area that received more scientific attraction during this period of rapid technological innovation. Today, many real issues and scenarios require pattern recognition to aid in the faster resolution of complicated problems, particularly those that cannot be solved using traditional human heuristics. One common problem in pattern recognition is dealing with multidimensional data, which is prominent in studies involving spectral data such as ultraviolet-visible (UV/Vis), infrared (IR), and Raman spectroscopy data. UV/Vis, IR, and Raman spectroscopy are well-known spectroscopic methods that are used to determine the atomic or molecular structure of a sample in various fields. Typically, pattern recognition consists of two components: exploratory data analysis and classification method. Exploratory data analysis is an approach that involves detecting anomalies in data, extracting essential variables, and revealing the data’s underlying structure. On the other hand, classification methods are techniques or algorithms used to group samples into a predetermined category. This article discusses the fundamental assumptions, benefits, and limitations of some well-known pattern recognition algorithms including Principal Component Analysis (PCA), Kernel PCA, Successive Projection Algorithm (SPA), Genetic Algorithm (GA), Partial Least Square Regression (PLS-R), Linear Discriminant Analysis (LDA), K-Nearest Neighbors (KNN), Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), Partial Least Square-Discriminant Analysis (PLS-DA) and Artificial Neural Network (ANN). The use of UV/Vis, IR, and Raman spectroscopy for disease classification is also highlighted. To conclude, many pattern recognition algorithms have the potential to overcome each of their distinct limits, and there is also the option of combining all of these algorithms to create an ensemble of methods. Full article

The discrimination between earthquakes and artificial explosions is a significant issue in seismic analysis to efficiently prevent and respond to seismic events. However, the discrimination of seismic events is challenging due to the low incidence rate. Moreover, the similarity between earthquakes and artificial explosions with a local magnitude derives a nonlinear data distribution. To improve the discrimination accuracy, this paper proposes machine-learning-based seismic discrimination methods—support vector machine, naive Bayes, and logistic regression. Furthermore, to overcome the nonlinear separation problem, the kernel functions and regularized logistic regression are applied to design seismic classifiers. To efficiently design the classifier, P- and S-wave amplitude ratios on the time domain and spectral ratios on the frequency domain, which is converted by fast Fourier transform and short-time Fourier transform are selected as feature vectors. Furthermore, an adaptive synthetic sampling algorithm is adopted to enhance the classifier performance against the seismic data imbalance issue caused by the non-equivalent number of occurrences. The comparisons among classifiers are evaluated by the binary classification performance analysis methods. Full article

In this paper, we present the supervised multi-view canonical correlation analysis ensemble (SMVCCAE) and its semi-supervised version (SSMVCCAE), which are novel techniques designed to address heterogeneous domain adaptation problems, i.e., situations in which the data to be processed and recognized are collected from different heterogeneous domains. Specifically, the multi-view canonical correlation analysis scheme is utilized to extract multiple correlation subspaces that are useful for joint representations for data association across domains. This scheme makes homogeneous domain adaption algorithms suitable for heterogeneous domain adaptation problems. Additionally, inspired by fusion methods such as Ensemble Learning (EL), this work proposes a weighted voting scheme based on canonical correlation coefficients to combine classification results in multiple correlation subspaces. Finally, the semi-supervised MVCCAE extends the original procedure by incorporating multiple speed-up spectral regression kernel discriminant analysis (SRKDA). To validate the performances of the proposed supervised procedure, a single-view canonical analysis (SVCCA) with the same base classifier (Random Forests) is used. Similarly, to evaluate the performance of the semi-supervised approach, a comparison is made with other techniques such as Logistic label propagation (LLP) and the Laplacian support vector machine (LapSVM). All of the approaches are tested on two real hyperspectral images, which are considered the target domain, with a classifier trained from synthetic low-dimensional multispectral images, which are considered the original source domain. The experimental results confirm that multi-view canonical correlation can overcome the limitations of SVCCA. Both of the proposed procedures outperform the ones used in the comparison with respect to not only the classification accuracy but also the computational efficiency. Moreover, this research shows that canonical correlation weighted voting (CCWV) is a valid option with respect to other ensemble schemes and that because of their ability to balance diversity and accuracy, canonical views extracted using partially joint random view generation are more effective than those obtained by exploiting disjoint random view generation. Full article