Linear Dimensionality Reduction Methods Research Articles

Exploring visual quality of multidimensional time series projections

Dimensionality reduction is often used to project time series data from multidimensional to two-dimensional space to generate visual representations of the temporal evolution. In this context, we address the problem of multidimensional time series visualization by presenting a new method to show and handle projection errors introduced by dimensionality reduction techniques on multidimensional temporal data. For visualization, subsequent time instances are rendered as dots that are connected by lines or curves to indicate the temporal dependencies. However, inevitable projection artifacts may lead to poor visualization quality and misinterpretation of the temporal information. Wrongly projected data points, inaccurate variations in the distances between projected time instances, and intersections of connecting lines could lead to wrong assumptions about the original data. We adapt local and global quality metrics to measure the visual quality along the projected time series, and we introduce a model to assess the projection error at intersecting lines. These serve as a basis for our new uncertainty visualization techniques that use different visual encodings and interactions to indicate, communicate, and work with the visualization uncertainty from projection errors and artifacts along the timeline of data points, their connections, and intersections. Our approach is agnostic to the projection method and works for linear and non-linear dimensionality reduction methods alike.

Identification of control equations using low-dimensional flow representations of pitching airfoil

This study investigates the application of data-driven modeling techniques for understanding the complex dynamics of pitching airfoils at low Reynolds numbers and high angles of attack. Linear and nonlinear dimensionality reduction methods, namely principal component analysis (PCA) and isometric mapping (ISOMAP), are employed to obtain low-dimensional representations of the flow field. Subsequently, sparse identification of nonlinear dynamics (SINDy) is utilized to model the governing equations. The key findings are as follows: PCA primarily captures linear information, with the first two to three dimensions maintaining relatively low reconstruction errors. In contrast, ISOMAP excels in capturing nonlinear features, exhibiting noticeably smaller reconstruction errors. The main information is concentrated in the two-dimensional plane constructed by PCA1 and PCA2 (or ISOMAP1 and ISOMAP2). Differences in trajectory planes formed by combinations of other axes reflect flow field disparities. ISOMAP provides a nonlinear low-dimensional representation, advantageous for capturing nonlinear relationships between flow field characteristics and governing equations. The combination of ISOMAP and SINDy yields virtually no errors in identifying governing equations. Conversely, PCA and SINDy result in significantly different linear trajectories, leading to higher reconstruction errors. The identified governing equations using ISOMAP and SINDy remain consistent across different datasets, demonstrating the method's stability and robustness in accurately characterizing flow field properties under similar conditions.

Geometric space construction method combined of a spline-skinning based geometric variation method and PCA dimensionality reduction for ship hull form optimization

In the construction stage of ship hull geometric space, the representation and variation of hull forms pose challenges due to the complex nature of the geometry and the necessity for enhanced flexibility in space. In this study, we utilize T-spline technology for the representation of ship hulls, enabling a unified parameter domain with a reduced number of control points to effectively depict the entire hull surface. Furthermore, we introduce a method for geometric variation based on the T-spline parameter domain, which permits both local and global alterations, thus offering greater flexibility in modifying the geometry. By leveraging the T-spline representation and the geometric variation method, we developed a hybrid geometric approach for constructing the geometric space, which significantly increased the geometric flexibility in ship hull optimization. A geometric space characterized by a high degree of geometric freedom typically requires the use of numerous optimization variables and incurs considerable computational resource consumption. In this research, we apply a linear dimensionality reduction method, principal component analysis, to decrease the dimensionality of the geometric space. This method effectively preserves the original geometric design space, thereby eliminating the need for performance analyses. The numerical optimization results clearly indicate that the proposed method significantly enhances optimization efficiency.

A hybrid model for data visualization using linear algebra methods and machine learning algorithm

The t-distributed stochastic neighbor embedding (t-SNE) is a powerful technique for visualizing high-dimensional datasets. By reducing the dimensionality of the data, t-SNE transforms it into a format that can be more easily understood and analyzed. The existing approach is to visualize high-dimensional data but not deeply visualize. This paper proposes a model that enhances visualization and improves the accuracy. The proposed model combines the non-linear embedding technique t-SNE, the linear dimensionality reduction method principal component analysis (PCA), and the QR decomposition algorithm for discovering eigenvalues and eigenvectors. In Addition, we quantitatively compare the proposed model QRPCA-t-SNE with PCA-t-SNE using the following criteria: data visualization with different perplexity and different principal components, confusion matrix, model score, mean square error (MSE), training, testing accuracy, receiver operating characteristic curve (ROC) score, and AUC score.

Factorized discriminant analysis for genetic signatures of neuronal phenotypes.

Navigating the complex landscape of single-cell transcriptomic data presents significant challenges. Central to this challenge is the identification of a meaningful representation of high-dimensional gene expression patterns that sheds light on the structural and functional properties of cell types. Pursuing model interpretability and computational simplicity, we often look for a linear transformation of the original data that aligns with key phenotypic features of cells. In response to this need, we introduce factorized linear discriminant analysis (FLDA), a novel method for linear dimensionality reduction. The crux of FLDA lies in identifying a linear function of gene expression levels that is highly correlated with one phenotypic feature while minimizing the influence of others. To augment this method, we integrate it with a sparsity-based regularization algorithm. This integration is crucial as it selects a subset of genes pivotal to a specific phenotypic feature or a combination thereof. To illustrate the effectiveness of FLDA, we apply it to transcriptomic datasets from neurons in the Drosophila optic lobe. We demonstrate that FLDA not only captures the inherent structural patterns aligned with phenotypic features but also uncovers key genes associated with each phenotype.

Model-based evaluation of spatiotemporal data reduction methods with unknown ground truth through optimal visualization and interpretability metrics.

Optimizing and benchmarking data reduction methods for dynamic or spatial visualization and interpretation (DSVI) face challenges due to many factors, including data complexity, lack of ground truth, time-dependent metrics, dimensionality bias and different visual mappings of the same data. Current studies often focus on independent static visualization or interpretability metrics that require ground truth. To overcome this limitation, we propose the MIBCOVIS framework, a comprehensive and interpretable benchmarking and computational approach. MIBCOVIS enhances the visualization and interpretability of high-dimensional data without relying on ground truth by integrating five robust metrics, including a novel time-ordered Markov-based structural metric, into a semi-supervised hierarchical Bayesian model. The framework assesses method accuracy and considers interaction effects among metric features. We apply MIBCOVIS using linear and nonlinear dimensionality reduction methods to evaluate optimal DSVI for four distinct dynamic and spatial biological processes captured by three single-cell data modalities: CyTOF, scRNA-seq and CODEX. These data vary in complexity based on feature dimensionality, unknown cell types and dynamic or spatial differences. Unlike traditional single-summary score approaches, MIBCOVIS compares accuracy distributions across methods. Our findings underscore the joint evaluation of visualization and interpretability, rather than relying on separate metrics. We reveal that prioritizing average performance can obscure method feature performance. Additionally, we explore the impact of data complexity on visualization and interpretability. Specifically, we provide optimal parameters and features and recommend methods, like the optimized variational contractive autoencoder, for targeted DSVI for various data complexities. MIBCOVIS shows promise for evaluating dynamic single-cell atlases and spatiotemporal data reduction models.

Trade-offs in the latent representation of microstructure evolution

Characterizing and quantifying microstructure evolution is critical to forming quantitative relationships between material processing conditions, resulting microstructure, and observed properties. Machine-learning methods are increasingly accelerating the development of these relationships by treating microstructure evolution as a pattern recognition problem, discovering relationships explicitly or implicitly. These methods often rely on identifying low-dimensional microstructural fingerprints as latent variables. However, using inappropriate latent variables can lead to challenges in learning meaningful relationships. In this work, we survey and discuss the ability of various linear and nonlinear dimensionality reduction methods including principal component analysis, autoencoders, and diffusion maps to quantify and characterize the learned latent space microstructural representations and their time evolution. We characterize latent spaces by their ability to represent high-dimensional microstructural data in terms of compression achieved as a function of the number of latent dimensions required to represent the data accurately, their accuracy based on their reconstruction performance, and the smoothness of the microstructural trajectories in latent dimension. We quantify these metrics for common microstructure evolution problems in material science including spinodal decomposition of a binary metallic alloy, thin film deposition of a binary metallic alloy, dendritic growth, and grain growth in a polycrystal. This study provides considerations and guidelines for choosing dimensionality reduction methods when considering materials problems that involve high dimensional data and a variety of features over a range of lengths and time scales.

High-Dimensional Feature Space for Diabetes Diagnosis and Identification of Diabetic-Sensitive Features in Ayurvedic Nadi Signals

Nadi-based disease diagnosis is a traditional art in Ayurvedic medicine that is an inquisitive yet not widely comprehended subject. A collection of higher dimensional features from a preprocessed Nadi dataset was extracted and analyzed to diagnose diabetes. The t-distributed Stochastic Neighbor Embedding was used to visualize the higher dimensional feature space in 2-D. The linear dimensionality reduction method of Principal Component Analysis and several linear and nonlinear classifiers were tested on the reduced feature space in identifying diabetes. The key outcomes of this paper are the ability to reduce the feature space by 73.33% while retaining a classification accuracy of 95.4%, identifying age as a compounding factor in diagnosis, and extracting the diabetes-sensitive features with eigenvalue loading.

BEENE: deep learning-based nonlinear embedding improves batch effect estimation.

Analyzing large-scale single-cell transcriptomic datasets generated using different technologies is challenging due to the presence of batch-specific systematic variations known as batch effects. Since biological and technological differences are often interspersed, detecting and accounting for batch effects in RNA-seq datasets are critical for effective data integration and interpretation. Low-dimensional embeddings, such as principal component analysis (PCA) are widely used in visual inspection and estimation of batch effects. Linear dimensionality reduction methods like PCA are effective in assessing the presence of batch effects, especially when batch effects exhibit linear patterns. However, batch effects are inherently complex and existing linear dimensionality reduction methods could be inadequate and imprecise in the presence of sophisticated nonlinear batch effects. We present Batch Effect Estimation using Nonlinear Embedding (BEENE), a deep nonlinear auto-encoder network which is specially tailored to generate an alternative lower dimensional embedding suitable for both linear and nonlinear batch effects. BEENE simultaneously learns the batch and biological variables from RNA-seq data, resulting in an embedding that is more robust and sensitive than PCA embedding in terms of detecting and quantifying batch effects. BEENE was assessed on a collection of carefully controlled simulated datasets as well as biological datasets, including two technical replicates of mouse embryogenesis cells, peripheral blood mononuclear cells from three largely different experiments and five studies of pancreatic islet cells. BEENE is freely available as an open source project at https://github.com/ashiq24/BEENE.

A normalized differential sequence feature encoding method based on amino acid sequences.

Protein interactions are the foundation of all metabolic activities of cells, such as apoptosis, the immune response, and metabolic pathways. In order to optimize the performance of protein interaction prediction, a coding method based on normalized difference sequence characteristics (NDSF) of amino acid sequences is proposed. By using the positional relationships between amino acids in the sequences and the correlation characteristics between sequence pairs, NDSF is jointly encoded. Using principal component analysis (PCA) and local linear embedding (LLE) dimensionality reduction methods, the coded 174-dimensional human protein sequence vector is extracted using sequence features. This study compares the classification performance of four ensemble learning methods (AdaBoost, Extra trees, LightGBM, XGBoost) applied to PCA and LLE features. Cross-validation and grid search methods are used to find the best combination of parameters. The results show that the accuracy of NDSF is generally higher than that of the sequence matrix-based coding method (MOS) coding method, and the loss and coding time can be greatly reduced. The bar chart of feature extraction shows that the classification accuracy is significantly higher when using the linear dimensionality reduction method, PCA, compared to the nonlinear dimensionality reduction method, LLE. After classification with XGBoost, the model accuracy reaches 99.2%, which provides the best performance among all models. This study suggests that NDSF combined with PCA and XGBoost may be an effective strategy for classifying different human protein interactions.

Rapid detection of lignin content in corn straw based on Laplacian Eigenmaps

Lignin is an essential components of corn stalk and has a wide range of application. To realize the rapid detection of lignin content in corn straw and increase the detection accuracy, we initially preprocess the gathered corn straw near-infrared spectral data with Standard Normal Variable transformation (SNV). After that, the nonlinear dimensionality reduction method Laplacian Eigenmaps (LE) and Local Tangent Space Alignment (LTSA) are applied independently to reduce the dimension of spectral data. principal component analysis (PCA), a linear dimensionality reduction method, is also utilized for spectral data dimensionality reduction. Finally, models for Partial Least Squares Regression (PLSR) and Support Vector Regression (SVR) are constructed. According to the model findings, LE-SVR model offers the best prediction accuracy and stability. The determination coefficient and root mean square error of the training and tests sets are 97.17%, 0.1875 and 96.25%, 0.2718 respectively. Furthermore, the relative analytical error is 5.0776. In addition, the study findings show that the number of neighbor points k has no discernible effect on the model performance. According to the findings, nonlinear modeling using LE-SVR for NIR spectral data of corn stover can lower model complexity, while improving model prediction accuracy and stability. NIR spectroscopy may be used to determine lignin content in corn straw. At the same time, the technique in this work offers a novel approach for the rapidly detecting lignin content in other crops straw.

Abnormal Status Detection of Catenary Based on TSNE Dimensionality Reduction Method and IGWO-LSSVM Model

Background: Catenary is a crucial component of an electrified railroad's traction power supply system. There is a considerable incidence of abnormal status and failures due to prolonged outside exposure. Driving safety will be directly impacted if an abnormal status or failure occurs. Currently, catenary detection vehicles are the most often utilized technique for gathering data and identifying faults based on manual experience. However, this technology cannot meet the demands of prompt detection and correction of faults in railways engineering due to its extremely low work efficiency. Objective: Based on the above, an abnormal status detection method of catenary based on the improved gray wolf (IGWO) algorithm optimized the least squares support vector machine (LSSVM) with the t-distributed stochastic neighbor embedding (TSNE) is proposed in this paper. In order to improve the accuracy of catenary abnormal status detection and shorten the detection time. Methods: Firstly, the TSNE dimensionality reduction technology is used to reduce the original catenary data to three-dimensional space. Then, in order to address the issue that the parameters of the LSSVM detection model are hard to determine, the improved GWO algorithm is used to optimize the penalty factor and kernel parameter in the LSSVM and establish the TSNE-IGWO-LSSVM catenary abnormal status detection model. Finally, contrasting experimental results of different detection models. The T-distributed Stochastic Domain Embedding (TSNE) is an improved nonlinear dimensionality reduction method based on the Stochastic Neighbor Embedding (SNE). TSNE no longer adopts the distance invariance in linear dimensionality reduction methods such as ISOMAP. TSNE is much better than the linear dimensionality reduction method in the reduction degree of the original dimension. The GWO algorithm, which is frequently used in engineering research, has the advantages of a simple model, great generalization capability, and good optimization performance. The premature convergence is one of the remaining flaws. By applying a good point set to initialize the gray wolf population and the nonlinear control parameters, the gray wolf algorithm is improved in this research. The IGWO algorithm effectively makes up for the problem of balancing the local exploitation and global search capabilities of GWO. Additionally, this IGWO algorithm performs the Cauchy variation operation on the current generation optimal solution to improve population diversity, enlarge the search space, and increase the likelihood of the algorithm escaping the local optimal solution in order to prevent the algorithm from failing the local optimum. The Least Squares Support Vector Machine (LSSVM) is an improved version of the Support Vector Machine (SVM), which replaces the original inequality constraint with a linear least squares criterion for the loss function. The kernel parameters of the RBF function and the penalty factor, these two parameters directly determine the detection effect of LSSVM. In this paper, the IGWO is utilized to adjust and determine the LSSVM parameters in order to enhance the detection capacity of the LSSVM model. Results:: In this paper, in order to minimize the experiment's bias, the training data and the test data are allocated in a ratio of 4:1, the training data are set to 400 groups, and the test data are set to 100 groups. After training the five models, the test data is used to validate and compare the detection capacity of the models. After each of the five detection models was tested ten times, the TSNE-IGWO-LSSVM model is compared with the IGWO-LSSVM model, the TSNE-FA-LSSVM model, the GWO-LSSVM model, and the GWO-ELM model, the results show that the TSNE-IGWO-LSSVM model has the highest average detection accuracy of 97.1% and the shortest running time of 26.9s. For the root mean squared error (RMSE) and the root mean squared error (RMSE), the TSNE-IGWO-LSSVM model is 0.17320 and 2.51% respectively, which is the best among the five models, indicating that it not only has higher detection accuracy but also better convergence of detection accuracy than the other models. Conclusions: With the thousands of miles of catenary and the complexity of the data, it is crucial to shorten the running time in order to improve the efficiency and ease the burden of the processors. The experiments demonstrate that the TSNE-IGWO-LSSVM detection model can detect the abnormal status of catenary more accurately and quickly, providing a new method for the abnormal status detection of catenary, which has certain application value and engineering significance in the era of fully electrified railways.

Combination of Manifold Learning and Deep Learning Algorithms for Mid-Term Electrical Load Forecasting.

Mid-term load forecasting (MTLF) is of great significance for power system planning, operation, and power trading. However, the mid-term electrical load is affected by the coupling of multiple factors and demonstrates complex characteristics, which leads to low prediction accuracy in MTLF. Furthermore, MTLF is faced with the "curse of dimensionality" problem due to a large number of variables. This article proposes an MTLF method based on manifold learning, which can extract the underlying factors of load variations to help improve the accuracy of MTLF and significantly reduce the calculation. Unlike linear dimensionality reduction methods, manifold learning has better nonlinear feature extraction ability and is more suitable for load data with nonlinear characteristics. Furthermore, long short-term memory (LSTM) neural networks are used to establish forecasting models in the low-dimensional space obtained by manifold learning. The proposed MTLF method is tested on independent system operator (ISO) New England datasets, and load forecasting in 24, 168, and 720 h ahead is carried out. The numerical results validate that the proposed method has higher prediction accuracy than many mature methods in the mid-term time scale.

Neural networks with dimensionality reduction for efficient springback prediction in deep drawing of multi-material cylindrical cups

ABSTRACT Deep drawing involves the use of a punch to plastically deform a workpiece to create sheet metal parts such as cups and channels. Upon release of the punch, the workpiece undergoes elastic recovery and results in a change in geometry known as the springback effect. The process is highly non-linear and involves many parameters, leading to large computation times to fully simulate the process or train a regression model on the high dimensionality of the data. In this paper, dimension-reduced neural networks (DR-NNs) for efficient springback prediction in the process of deep drawing a cylindrical cup are presented with consideration for different materials. The DR-NNs are trained on FEM data from a deep drawing simulation performed on ABAQUS/CAE. Features such as the workpiece’s initial coordinates, material properties, and thickness are introduced as inputs for the dimensionality reduction. Linear and non-linear dimensionality reduction methods reduce the input to a smaller set of principal components, which are fed as inputs to the neural networks for predicting the springback after punch release. The DR-NNs are compared against a deep neural network (DNN) and show improvements in lower computation time for training, prediction uncertainty, and less storage space required while retaining prediction accuracy.

Novel Hybrid Calibration Transfer Method Based on Nonlinear Dimensionality Reduction for Robust Standardization in Near-Infrared Spectroscopy

To correct the spectral changes measured on different instruments in near-infrared (NIR) spectroscopy, a novel hybrid calibration transfer method with nonlinear dimensionality reduction based on direct standardization (DS) and autoencoder (AE), named DS-AE, is reported. First, DS was employed to preliminarily eliminate the spectral difference from the master and slave instruments. Next, the spectral features were extracted by AE to construct the partial least squares (PLS) calibration model. Compared with the linear dimensionality reduction methods, AE learns more latent features of the input spectra that are beneficial to reflect the chemical information of samples. Two NIR experiment datasets, including wheat and corn samples measured on different spectrometers, were employed to evaluate the performance of the DS-AE method. DS, piecewise direct standardization (PDS), canonical correlation analysis (CCA), principal components canonical correlation analysis (PC-CCA), and transfer via an extreme learning machine auto-encoder (TEAM) were introduced for comparative analysis with the proposed method. The results showed that DS-AE provided the lowest root mean squared error of prediction (RMSEP) for the wheat dataset; For the corn dataset, DS-AE provided lower RMSEP than DS, PDS, and CCA, and comparable with PC-CCA and TEAM. The score of the PLS principal components (PCs) describes the spectral differences of different instruments. The results indicated that the hybrid DS-AE method effectively corrected for the spectral variations. In summary, the proposed hybrid DS-AE method provided an alternative for robust standardization of near-infrared spectra measured on different instruments.

Decomposition and Classification of Carbon Star Spectra

Automatic classification of stellar spectra is an important research component of astronomical data processing and is the basis for studying stellar evolution and parameter measurements. As a rare kind of stellar spectra, carbon star spectra put forward more efficient and accurate requirements for classification methods. The traditional manual classification methods have the disadvantages of slow speed and low accuracy, which can no longer meet the practical needs of automatic classification of massive stellar spectra, especially low signal-to-noise ratio stellar spectra, and machine learning algorithms have been widely applied to stellar spectral classification. A distinctive feature of stellar spectra is high data dimensionality, and dimensionality reduction can not only realize feature extraction, but also reduce the computational effort, which is the first task of spectral classification. Traditional linear dimensionality reduction methods such as principal component analysis reduce the spectra only based on the variance, and different types of spectra will appear crossover after projection into the low-dimensional feature space, while streamwise learning can produce excellent classification boundaries, which will avoid overlap and facilitate subsequent classification. In view of the high dimensionality of spectral data, we investigate the distribution of spectral data in high-dimensional space and the principle of dimensionality reduction of high-dimensional linear data by stream shape learning, compare the effect of two-dimensionality reduction methods, t - SNE and principal component analysis, on spectral data, and finally analyze the experimental results and compare and validate them using various machine learning classifiers. The algorithm is implemented using Python language and Scikit - learn third-party library to perform experiments on 1000 low signal-to-noise carbon star spectra from LAMOST, and finally achieve high accuracy automatic processing and classification of the spectral data. The experimental results show that for the dimensionality reduction processing of spectral data, the t - SNE method based on stream shape learning can recover the low-dimensional stream shape structure in the high-dimensional spectral data, and after feature extraction, satisfactory classification accuracy can be achieved on the test dataset using a machine learning classifier.

Protein folding pathway and intermediates on the dimensionality reduced landscape with UMAP and native contact likelihood.

To understand protein folding mechanisms from molecular dynamics (MD) simulations, it is important to explore not only folded/unfolded states but also representative intermediate structures on the conformational landscape. Generally, such a conformational landscape is obtained by linear dimensionality reduction methods, principal component analysis (PCA) or time-lagged independent component analysis (tICA), for instance. However, it is often difficult to apply these linear methods to large-scale, nonlinear conformational changes such as protein folding. Here, we propose a novel approach to construct the landscape using the uniform manifold approximation and projection (UMAP) method, which nonlinearly reduces the dimensionality without losing data-point proximity. In the approach, native contact likelihood, a measure for native contact formation, is used as feature variables rather than the conventional Cartesian coordinates or dihedral angles of protein structures. We tested the performance of UMAP for coarse-grained MD simulation trajectories of B1 domain in protein G and observed on-pathway transient structures and other metastable states on the UMAP conformational landscape. In contrast, these structures were not clearly distinguished on the dimensionality reduced landscape using PCA or tICA. This approach is also useful to obtain dynamical information through Markov State Modeling and would be applicable to large-scale conformational changes in many other biomacromolecules.

Linear dimensionality reduction method based on topological properties

Dimensionality reduction is an important data preprocessing technique that has been extensively studied in machine learning and data mining. Locality Preserving Projection (LPP) is a widely used linear unsupervised dimensionality reduction method, which maps high-dimensional data into low-dimensional subspace through linear transformation. Although various variants of LPP have been proposed to tackle different drawbacks of LPP, it is identified in this article that LPP does not possess the important topological property of translation invariance, that is, the linear transformation given by LPP is strongly related to the relative position between the data and the origin of the coordinate system. In this article, we theoretically analyze the reason why this drawback exists in LPP and propose to resolve it by introducing a kind of centralization to the model. Moreover, as topological properties are prominent information to characterize the structure of the data, this article proposes a further improvement of LPP to maintain topological connectivity of data after dimensionality reduction. Experiments on multiple synthetic and real-world datasets show that the new model incorporating topological properties outperforms not only the original LPP model but also several other classic linear or non-linear dimensionality reduction methods.

Neural networks with dimensionality reduction for predicting temperature change due to plastic deformation in a cold rolling simulation

Abstract Cold rolling involves large deformation of the workpiece leading to temperature increase due to plastic deformation. This process is highly nonlinear and leads to large computation times to fully model the process. This paper describes the use of dimension-reduced neural networks (DR-NNs) for predicting temperature changes due to plastic deformation in a two-stage cold rolling process. The main objective of these models is to reduce computational demand, error, and uncertainty in predictions. Material properties, feed velocity, sheet dimensions, and friction models are introduced as inputs for the dimensionality reduction. Different linear and nonlinear dimensionality reduction methods reduce the input space to a smaller set of principal components. The principal components are fed as inputs to the neural networks for predicting the output temperature change. The DR-NNs are compared against a standalone neural network and show improvements in terms of lower computational time and prediction uncertainty.

Protein Interaction Prediction Method Based on Feature Engineering and XGBoost

Human protein interaction prediction studies occupy an important place in systems biology. The understanding of human protein interaction networks and interactome will provide important insights into the regulation of developmental, physiological and pathological processes. In this study, we propose a method based on feature engineering and integrated learning algorithms to construct protein interaction prediction models. Principal Component Analysis (PCA) and Locally Linear Embedding (LLE) dimensionality reduction methods were used to extract sequence features from the 174-dimensional human protein sequence vector after Normalized Difference Sequence Feature (NDSF) encoding, respectively. The classification performance of three integrated learning methods (AdaBoost, Extratrees, XGBoost) applied to PCA and LLE features was compared, and the best combination of parameters was found using cross-validation and grid search methods. The results show that the classification accuracy is significantly higher when using the linear dimensionality reduction method PCA than the nonlinear dimensionality reduction method LLE. the classification with XGBoost achieves a model accuracy of 99.2%, which is the best performance among all models. This study suggests that NDSF combined with PCA and XGBoost may be an effective strategy for classifying different human protein interactions.