Fault Detection Method Based on Global-Local Marginal Discriminant Preserving Projection for Chemical Process

Feature extraction plays a key role in fault detection methods. Most existing methods focus on comprehensive and accurate feature extraction of normal operation data to achieve better detection performance. However, discriminative features based on historical fault data are usually ignored. Aiming at this point, a global-local marginal discriminant preserving projection (GLMDPP) method is proposed for feature extraction. Considering its comprehensive consideration of global and local features, global-local preserving projection (GLPP) is used to extract the inherent feature of the data. Then, multiple marginal fisher analysis (MMFA) is introduced to extract the discriminative feature, which can better separate normal data from fault data. On the basis of fisher framework, GLPP and MMFA are integrated to extract inherent and discriminative features of the data simultaneously. Furthermore, fault detection methods based on GLMDPP are constructed and applied to the Tennessee Eastman (TE) process. Compared with the PCA and GLPP method, the effectiveness of the proposed method in fault detection is validated with the result of TE process.

Image Segmentation Using PSO-Enhanced K-Means Clustering and Region Growing Algorithms

Image segmentation is a basic image processing technique that is primarily used for finding segments that form the entire image. These segments can be then utilized in discriminative feature extraction, image retrieval, and pattern recognition. Clustering and region growing techniques are the commonly used image segmentation methods. K-Means is a heavily used clustering technique due to its simplicity and low computational cost. However, K-Means results depend on the initial centres’ values which are selected randomly, which leads to inconsistency in the image segmentation results. In addition, the quality of the isolated regions depends on the homogeneity of the resulted segments. In this paper, an improved K-Means clustering algorithm is proposed for image segmentation. The presented method uses Particle Swarm Intelligence (PSO) for determining the initial centres based on Li’s method. These initial centroids are then fed to the K-Means algorithm to assign each pixel into the appropriate cluster. The segmented image is then given to a region growing algorithm for regions isolation and edge map generation. The experimental results show that the proposed method gives high quality segments in a short processing time.

Multistage Polymerization Network for Multiperson Pose Estimation

Multiperson pose estimation is an important and complex problem in computer vision. It is regarded as the problem of human skeleton joint detection and solved by the joint heat map regression network in recent years. The key of achieving accurate pose estimation is to learn robust and discriminative feature maps. Although the current methods have made significant progress through interlayer fusion and intralevel fusion of feature maps, few works pay attention to the combination of the two methods. In this paper, we propose a multistage polymerization network (MPN) for multiperson pose estimation. The MPN continuously learns rich underlying spatial information by fusing features within the layers. The MPN also adds hierarchical connections between feature maps at the same resolution for interlayer fusion, so as to reuse low-level spatial information and refine high-level semantic information to obtain accurate keypoint representation. In addition, we observe a lack of connection between the output low-level information and the high-level information. To solve this problem, an effective shuffled attention mechanism (SAM) is proposed. The shuffle aims to promote the cross-channel information exchange between pyramid feature maps, while attention makes a trade-off between the low-level and high-level representations of the output features. As a result, the relationship between the space and the channel of the feature map is further enhanced. Evaluation of the proposed method is carried out on public datasets, and experimental results show that our method has better performance than current methods.

A Machine Learning Method for Detection of Surface Defects on Ceramic Tiles Using Convolutional Neural Networks

We propose a simple but effective convolutional neural network to learn the similarities between closely related raw pixel images for feature representation extraction and classification through the initialization of convolutional kernels from learned filter kernels of the network. The binary-class classification of sigmoid and discriminative feature vectors are simultaneously learned together contrasting the handcrafted traditional method of feature extractions, which split feature-extraction and classification tasks into two different processes during training. Relying on the high-quality feature representation learned by the network, the classification tasks can be efficiently conducted. We evaluated the classification performance of our proposed method using a collection of tile surface images consisting of cracked surfaces and no-cracked surfaces. We tried to classify the tiny-cracked surfaces from non-crack normal tile demarcations, which could be useful for automated visual inspections that are labor intensive, risky in high altitudes, and time consuming with manual inspection methods. We performed a series of comparisons on the results obtained by varying the optimization, activation functions, and deployment of different data augmentation methods in our network architecture. By doing this, the effectiveness of the presented model for smooth surface defect classification was explored and determined. Through extensive experimentation, we obtained a promising validation accuracy and minimal loss.

TP-MV: Therapeutic protein prediction by multi-view learning

Background: Therapeutic peptide prediction is critical for drug development and therapy. Researchers have been studying this essential task, developing several computational methods to identify different therapeutic peptide types. Objective: Most predictors are the specific methods for certain peptides. Currently, developing methods to predict the presence of multiple peptides remains a challenging problem. Moreover, it is still challenging to combine different features to make the therapeutic prediction. Method: In this paper, we proposed a new ensemble method TP-MV for general therapeutic peptide recognition. TP-MV is developed using the stacking framework in conjunction with the KNN, SVM, ET, RF, and XGB. Then TP-MV constructs a multi-view learning model as meta-classifiers to extract the discriminative feature for different peptides. Results: In the experiment, the proposed method outperforms the other existing methods on the benchmark datasets, indicating that the proposed method has the ability to predict multiple therapeutic peptides simultaneously. Conclusion: The TP-MV is a useful tool for predicting therapeutic peptides.

Hypergraph-Supervised Deep Subspace Clustering

Auto-encoder (AE)-based deep subspace clustering (DSC) methods aim to partition high-dimensional data into underlying clusters, where each cluster corresponds to a subspace. As a standard module in current AE-based DSC, the self-reconstruction cost plays an essential role in regularizing the feature learning. However, the self-reconstruction adversely affects the discriminative feature learning of AE, thereby hampering the downstream subspace clustering. To address this issue, we propose a hypergraph-supervised reconstruction to replace the self-reconstruction. Specifically, instead of enforcing the decoder in the AE to merely reconstruct samples themselves, the hypergraph-supervised reconstruction encourages reconstructing samples according to their high-order neighborhood relations. By the back-propagation training, the hypergraph-supervised reconstruction cost enables the deep AE to capture the high-order structure information among samples, facilitating the discriminative feature learning and, thus, alleviating the adverse effect of the self-reconstruction cost. Compared to current DSC methods, relying on the self-reconstruction, our method has achieved consistent performance improvement on benchmark high-dimensional datasets.

A dual-branch balance saliency model based on discriminative feature for fabric defect detection

PurposeThe purpose of this paper is to focus on the design of a dual-branch balance saliency model based on fully convolutional network (FCN) for automatic fabric defect detection, and improve quality control in textile manufacturing.Design/methodology/approachThis paper proposed a dual-branch balance saliency model based on discriminative feature for fabric defect detection. A saliency branch is firstly designed to address the problems of scale variation and contextual information integration, which is realized through the cooperation of a multi-scale discriminative feature extraction module (MDFEM) and a bidirectional stage-wise integration module (BSIM). These modules are respectively adopted to extract multi-scale discriminative context information and enrich the contextual information of features at each stage. In addition, another branch is proposed to balance the network, in which a bootstrap refinement module (BRM) is trained to guide the restoration of feature details.FindingsTo evaluate the performance of the proposed network, we conduct extensive experiments, and the experimental results demonstrate that the proposed method outperforms state-of-the-art (SOTA) approaches on seven evaluation metrics. We also conduct adequate ablation analyses that provide a full understanding of the design principles of the proposed method.Originality/valueThe dual-branch balance saliency model was proposed and applied into the fabric defect detection. The qualitative and quantitative experimental results show the effectiveness of the detection method. Therefore, the proposed method can be used for accurate fabric defect detection and even surface defect detection of other industrial products.

Discriminative feature of cells characterizes cell populations of interest by a small subset of genes

Organisms are composed of various cell types with specific states. To obtain a comprehensive understanding of the functions of organs and tissues, cell types have been classified and defined by identifying specific marker genes. Statistical tests are critical for identifying marker genes, which often involve evaluating differences in the mean expression levels of genes. Differentially expressed gene (DEG)-based analysis has been the most frequently used method of this kind. However, in association with increases in sample size such as in single-cell analysis, DEG-based analysis has faced difficulties associated with the inflation of P-values. Here, we propose the concept of discriminative feature of cells (DFC), an alternative to using DEG-based approaches. We implemented DFC using logistic regression with an adaptive LASSO penalty to perform binary classification for discriminating a population of interest and variable selection to obtain a small subset of defining genes. We demonstrated that DFC prioritized gene pairs with non-independent expression using artificial data and that DFC enabled characterization of the muscle satellite/progenitor cell population. The results revealed that DFC well captured cell-type-specific markers, specific gene expression patterns, and subcategories of this cell population. DFC may complement DEG-based methods for interpreting large data sets. DEG-based analysis uses lists of genes with differences in expression between groups, while DFC, which can be termed a discriminative approach, has potential applications in the task of cell characterization. Upon recent advances in the high-throughput analysis of single cells, methods of cell characterization such as scRNA-seq can be effectively subjected to the discriminative methods.