A Novel Three-stage Feature Fusion Methodology and its Application in Degradation State Identification for Hydraulic Pumps

The performance of feature is essential to the degradation state identification for hydraulic pumps. The initial feature set extracted from the vibration signal of the hydraulic pump is often high-dimensional and contains redundant information, which undermines the effectiveness of the feature set. The novel three-stage feature fusion scheme proposed in this paper aims to enhance the performance of the original features extracted from the vibration signal. First, sparse local Fisher discriminant analysis (SLFDA) performs intra-set fusion within the two original feature sets, respectively. SLFDA has a good effect on samples with intra-class multimodality, and the feature set fused by it has obvious multivariate normal distribution characteristics, which is conducive to the next fusion. Second, our modified intra-class correlation analysis (MICA) is used to fuse two feature sets in the second stage. MICA is a CCA (Canonical correlation analysis) -based method. A new class matrix is used to modify the covariance matrix between two feature sets, which allows MICA to conveniently inherit the discriminating structure while fusing features. Finally, we propose a feature selection algorithm based on kernel local Fisher discriminant analysis (KLFDA) and kernel canonical correlation analysis (KCCA) to select the desired features. This algorithm based on Max-Relevance and Min-Redundancy (mRMR) framework solves the problem that CCA cannot properly evaluate the correlation between features and the class variable, as well as accurately evaluates the correlation among features. Based on the experimental data, the proposed method is compared with several popular methods, and the feature fusion methods used in some previous studies related to the fault diagnosis of rotating machinery are compared with it as well. The results show that the fusion effectiveness of our method is better than other methods, which obtains higher recognition accuracy.

Revisiting the performance of PCA versus FDA versus Simple Projection for image recognition

In this paper, our main aim is to show a better dimension reduction process of high dimensional image data sets from several existing techniques. To verify it we start with most useful singular value decomposition to reduce the dimensionality of data to incorporate principal components. On the other hand, we classify data in advance to work out Fisher’s discriminant. From many real-world examples, we set a very well-known paradigm of analysis using Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA) or Fisher Discriminant Analysis (FDA) and Simple Projection (SP) to recognize people from their facial images. We consider that we have some images of known people that can be used to compare and recognize new images (of the same set of face images). Moreover, we show graphical and tabular representation for average performance of correct recognition as well as analyze the effectiveness of three different machine learning techniques.

Texture Analysis of Myometrium-Derived T2WI in the Evaluation of Placenta Increta: An Observational Retrospective Study

Background: To develop an objective and quantitative measurement based on texture analysis of myometrium-derived T2WI to differentiate placenta accreta from increta.Methods: Participants with MRI and clinical or histopathological diagnosis of placenta increta were included. Texture analysis of T2WI was implemented on normal myometrium and placenta increta by MaZda software. Parameter selection and reduction was automatically done with Fisher discriminant method. Multivariate analysis was used for the comparison of response variables between two groups. Profile analysis was used to compare the contours of multivariable average vectors. Two-step clustering was performed to evaluate the importance of parameters.Results: Multivariate analysis showed that nine second-order parameters between normal myometrium and placenta increta were statistically significant(P﹤0.05). The t-test showed that there were two parameters (Skew and Kurtosis) that had no statistical significance. Profile analysis showed that the profiles of seven parameters were neither parallel(P﹤0.05) nor coincident(P﹤0.05). The results of two-step cluster indicated that Mean, Percentile 90% and Percentile 99% were important (predictor importance﹥0.8).Conclusion: The study showed statistically significant differences for Mean, Percentile 90% and Percentile 99% between normal myometrium and placenta increta. Texture analysis of myometrium-derived T2WI may be a useful add-on to MRI in diagnosing placenta increta.Trial registration: Registration number: ChiCTR2000038604 and name of registry: Evaluation of diagnostic accuracy of MRI multi-parameter imaging combined with texture analysis for placenta accreta spectrum disorders (PAD).