Dimensionality Reduction Model Research Articles

Sequential Active Learning of Low-Dimensional Model Representations for Reliability Analysis

To date, the analysis of high-dimensional, computationally expensive engineering models remains a difficult challenge in risk and reliability engineering. We use a combination of dimensionality reduction and surrogate modeling termed partial least squares--driven polynomial chaos expansion (PLS-PCE) to render such problems feasible. Standalone surrogate models typically perform poorly for reliability analysis. Therefore, in a previous work, we have used PLS-PCEs to reconstruct the intermediate densities of a sequential importance sampling approach to reliability analysis. Here, we extend this approach with an active learning procedure that allows for improved error control at each importance sampling level. To this end, we formulate an estimate of the combined estimation error for both the subspace identified in the dimension reduction step and the surrogate model constructed therein. With this, it is possible to adapt the training set so as to optimally learn the subspace representation and the surrogate model constructed therein. The approach is gradient-free and thus can be directly applied to black box--type models. We demonstrate the performance of this approach with a series of low- (2 dimensions) to high- (869 dimensions) dimensional example problems featuring a number of well-known caveats for reliability methods besides high dimensions and expensive computational models: strongly nonlinear limit-state functions, multiple relevant failure regions, and small probabilities of failure.

Internal quality assessment of mango fruit: an automated grading system with ensemble classifier

ABSTRACT In this work, a non-destructive and automated mango grading system model is developed for grading the mangoes into three categories depending on their internal features like Soluble Solid Content (SSC) as well as Total Acid Content (TAC). Initially, the prepared database is de-noised with the proposed adaptive Gaussian noise removal approach. Then, the Gray Level Co Occurrence Matrix (GLCM), Gray Level Run-Length Matrix (GLRM) features, and Near Infrared (NIR) spectroscopy features were extracted. As the curse of dimensionality persists, a patch-based Principal Component Analysis (PCA) model for dimensionality reduction is introduced. Subsequently, the dimensional reduced features are subjected to aproposed ensemble classifier that encompasses: ‘Support Vector Machine (SVM), Random Forest (RF), three Artificial Neural Network (ANN), and K-Nearest Neighbor (KNN)’. The weight of the third ANN is optimally-tuned by a novel improved meta-heuristic model depicting the Lion-Binary crossover mask base Whale Optimization (LBWO) Algorithm.

NGS data vectorization, clustering, and finding key codons in SARS-CoV-2 variations

The rapid global spread and dissemination of SARS-CoV-2 has provided the virus with numerous opportunities to develop several variants. Thus, it is critical to determine the degree of the variations and in which part of the virus those variations occurred. Therefore, in this study, methods that could be used to vectorize the sequence data, perform clustering analysis, and visualize the results were proposed using machine learning methods. To conduct this study, a total of 224,073 cases of SARS-CoV-2 sequence data were collected through NCBI and GISAID, and the data were visualized using dimensionality reduction and clustering analysis models such as T-SNE and DBSCAN. The SARS-CoV-2 virus, which was first detected, was distinguished from different variations, including Omicron and Delta, in the cluster results. Furthermore, it was possible to examine which codon changes in the spike protein caused the variants to be distinguished using feature importance extraction models such as Random Forest or Shapely Value. The proposed method has the advantage of being able to analyse and visualize a large amount of data at once compared to the existing tree-based sequence data analysis. The proposed method was able to identify and visualize significant changes between the SARS-CoV-2 virus, which was first detected in Wuhan, China, in December 2019, and the newly formed mutant virus group. As a result of clustering analysis using sequence data, it was possible to confirm the formation of clusters among various variants in a two-dimensional graph, and by extracting the importance of variables, it was possible to confirm which codon changes played a major role in distinguishing variants. Furthermore, since the proposed method can handle a variety of data sequences, it can be used for all kinds of diseases, including influenza and SARS-CoV-2. Therefore, the proposed method has the potential to become widely used for the effective analysis of disease variations.

Specific dopaminergic genetic variants influence impulsivity, cognitive deficit, and disease severity of Indian ADHD probands.

Impulsivity (Imp), being one of the cardinal symptoms of Attention Deficit Hyperactivity Disorder (ADHD), often leads to inappropriate responses to stimuli. Since the dopaminergic system is the primary target for pharmaceutical intervention in ADHD, we investigated the association between ADHD-related Imp and functional gene variants of the dopamine transporter (SLC6A3) and catechol-O-methyltransferase involved in dopamine clearance. Indo-Caucasoid families with ADHD probands (N = 217) were recruited based on the Diagnostic and Statistical Manual of Mental Disorders (DSM). Imp of the probands was assessed using the Domain Specific Imp Scale for Children and DSM. Peripheral blood was collected after obtaining informed written consent for participation, genomic DNA was isolated, and target sites were genotyped by DNA sequencing. The association of genetic variants with Imp was examined by the Quantitative trait analysis (QTA) and Analysis of variance (ANOVA). Post-Hoc analysis following QTA and ANOVA showed significant associations of rs2254408, rs2981359, and rs2239393 with different domains of Imp (P < 0.05). Various haplotypic combinations also showed statistically significant associations with Imp (P < 0.05). Multifactor dimensionality reduction models revealed strong effects of the variants on Imp. ADHD probands harboring the risk alleles exhibited a deficit in performance during cognitive assessment. Longitudinal follow-up revealed a significant association of rs2254408 with trait persistence. The present study indicates the influence of the studied genetic variants on ADHD-associated imp, executive deficit, and disease persistence. Thus, these variants may be helpful as predictors for the success of individual therapeutic sessions during cognitive training.

DAE-TPGM: A deep autoencoder network based on a two-part-gamma model for analyzing single-cell RNA-seq data

Single-cell RNA sequencing (scRNA-seq) can reveal differences in genetic material at the single-cell level and is widely used in biomedical studies. However, the minute RNA content within individual cells often results in a high number of dropouts and introduces random noise of scRNA-seq data, concealing the original gene expression pattern. Therefore, data normalization is critical in the analysis pipeline to adjust for unexpected biological and technical effects, leading to a particular bimodal expression pattern exhibited in the semi-continuous normalized data. We further find the positive continuous expression presents a right-skewed distribution, which is still under-explored by mainstream dimensionality reduction and imputation methods. We introduced a deep autoencoder network based on a two-part-gamma model (DAE-TPGM) for joint dimensionality reduction and imputation of scRNA-seq data. DAE-TPGM uses a two-part-gamma model to capture the statistical characteristics of semi-continuous normalized data and adaptively explores the potential relationships between genes for promoting data imputation by deep autoencoder. Just as the classic application scenarios that use an autoencoder in dimensionality reduction, our personalized autoendoer can capture phenotypic information on the peripheral blood mononuclear cells (PBMC) better and clearly infer continuous phenotype information for hematopoiesis in mice. Compared with that of mainstream imputation methods such as MAGIC, SAVER, scImpute and DCA, the new model achieved substantial improvement on the recognition of cellular phenotypes in two real datasets, and the comprehensive analyses on synthetic “ground truth” data demonstrated that our method obtains competitive advantages over other imputation methods in discovering underlying gene expression patterns in time-course data.

Fault detection and quantitative assessment method for process industry based on feature fusion

As the premise of ensuring safe production and improving economic benefits, process monitoring and fault diagnosis technology plays a vital role in process industry. Traditional industrial process monitoring and fault diagnosis mostly focus on fault detection and identification, and seldom involve quantitative assessment of faults. Considering that different dimensionality reduction methods may affect the monitoring effect, this paper proposes a fault detection and quantitative assessment method based on global and local information features to reduce the influence of data preference for dimensionality reduction model. Firstly, kernel principal component analysis and sparse locally linear embedding are used to reduce the dimension of the data, and the features preserving global and local structural information are obtained respectively. Secondly, finding the projection matrices through canonical correlation analysis makes the correlation between global features and global featured maximum, and the features transformed by the projection matrices are fused. Fusion features not only retain the difference between single features, but also eliminate the redundant information. Then, support vector data description is utilized to monitor the fused data to complete fault detection and quantitative assessment. Finally, a fault detection and quantitative assessment experiment on Tennessee Eastman process is conducted to demonstrate the effectiveness of the proposed method.

Prediction Method of Biological Fermentation Data Based on Deep Neural Network

This paper proposes a (Takagi-Sugeno-Kang) TSK fuzzy regression model that based on self-supervised learning and deep autoencoder to predict and monitor the real-time concentration of each ingredient in the fermentation process. The entire model consists of the following steps: obtaining and preprocessing sample spectral data to obtain a training set; using the training set to train a self-supervised feature extraction network model to optimize the parameters of the feature extraction network model; training the autoencoder network model to establish a dimensionality reduction model by using the feature-extracted data; performing TSK fuzzy regression on the data selected by the dimensionality reduction model to establish a concentration prediction model; inputting the spectral data of the solution to be tested to predict the concentration of the solution. Combined with the deep autoencoder feature extraction method of self-supervised learning, our model can not only construct a more complex nonlinear map than the traditional principal component analysis (PCA), but also ensure that the extracted features have semantic information that is beneficial to the subsequent regression prediction method. Combined with TSK regression prediction, our model can avoid the problem of excessive spectral data dimension and redundant information, and can give accurate and interpretable results.

Free and forced vibration analysis of pyramid lattice sandwich plate based on the dimensional reduction model

Due to the high porosity and periodicity of a pyramid lattice core, the dynamic behaviors of a pyramid lattice sandwich plate (PLSP) show new characteristics. In this work, the equivalent stiffness of a PLSP was obtained by homogenizing over the unit cell, and input to an equivalent two-dimensional (2D) reduced-order model constructed from the framework of a variational asymptotic method, based on which the calculation of natural frequencies and the frequency domain analysis of forced vibration were carried out. The accuracy and efficiency of the proposed model were verified by numerical examples of free and forced vibration under different boundary conditions, including frequency domain analysis, steady-state time domain analysis, and analysis of the local field recovered from the maximum resonance response at the peak and trough times. We also investigated the influence of the pyramid lattice core’s structural parameters on the first three natural frequencies and the maximum resonance response, which can provide a useful reference for the fatigue life expectation of a PLSP under a periodic load.

Correlation Imputation for Single-Cell RNA-seq.

Recent advances in single-cell RNA sequencing (scRNA-seq) technologies have yielded a powerful tool to measure gene expression of individual cells. One major challenge of the scRNA-seq data is that it usually contains a large amount of zero expression values, which often impairs the effectiveness of downstream analyses. Numerous data imputation methods have been proposed to deal with these "dropout" events, but this is a difficult task for such high-dimensional and sparse data. Furthermore, there have been debates on the nature of the sparsity, about whether the zeros are due to technological limitations or represent actual biology. To address these challenges, we propose Single-cell RNA-seq Correlation completion by ENsemble learning and Auxiliary information (SCENA), a novel approach that imputes the correlation matrix of the data of interest instead of the data itself. SCENA obtains a gene-by-gene correlation estimate by ensembling various individual estimates, some of which are based on known auxiliary information about gene expression networks. Our approach is a reliable method that makes no assumptions on the nature of sparsity in scRNA-seq data or the data distribution. By extensive simulation studies and real data applications, we demonstrate that SCENA is not only superior in gene correlation estimation, but also improves the accuracy and reliability of downstream analyses, including cell clustering, dimension reduction, and graphical model estimation to learn the gene expression network.

Emotional Calculation Method of Rural Tourist Based on Improved SPCA-LSTM Algorithm

New technologies such as big data and cloud computing provide new means and tools for rural development. The big rural tourism, with its convenience, quickness, and low threshold, presents great convenience for tourists’ emotional calculation and has become one of the main sources of tourism big data. Under the guidance of big data theory and emotion theory, this paper proposes an emotional calculation method of rural tourists based on improved SPCA-LSTM algorithm, taking big text data as data source. Firstly, the improved TF-IDF algorithm is designed to highlight the importance of feature items, and the word vector trained by word2vec model is applied to represent the rural tourism data text. Then, a weighted sparse PCA (RSPCA) is constructed to reduce the dimension of massive word vector features. RSPCA introduces the weighted l 1 optimization framework and LASSO regression model into the mathematical model of PCA algorithm and establishes a new data dimension reduction model. Thereupon, the long-term and short-term memory convolution network with attention mechanism is employed to extract text features. Finally, the feature vector is utilized to calculate the rural tourist’s emotion by softmax function. The experimental results indicate that the improved SPCA-LSTM algorithm, whose performance index is better than other existing algorithms, is effective in calculating tourists’ emotions. Also, it is more suitable for the research of tourist sentiment calculation in the era of big data.

Modelling Holling type II functional response in deterministic and stochastic food chain models with mass conservation

The Rosenzweig-MacArthur predator-prey model is the building block in modeling food chain, food webs and ecosystems. There are a number of hidden assumptions involved in the derivation. For instance the prey population growth is logistic without predation but also with predation. In order to reveal these we will start with modelling a resource-predator-prey system in a closed spatially homogeneous environment. This allows us to keep track of the nutrient flow. With an instantaneous remineralisation of the products excreted in the environment by the populations and dead body mass there is conservation of mass. This allows for a model dimension reduction and yields the mass balance predator-prey model. When furthermore the searching and handling processes are much faster that the population changing rates, the trophic interaction is described by a Holling type II functional response, also assumed in the Rosenzweig-MacArthur model. The derivation uses an extended deterministic model with number of searching and handling predators as model variables where the ratio of the predator/prey body masses is used as a mechanistic time-scale parameter. This extended model is also used as a starting point for the derivation of a stochastic model. We will investigate the stochastic effects of random switching between searching and handling of the predators and predator dying. Prey growth by consumption of ambient resources is still deterministic and therefore the stochastic model is hybrid. The transient dynamics is studied by numerical Monte Carlo simulations and also the quasi-equilibrium distribution for the population quantities is calculated. The body mass of the prey individual is the scaling parameter in the stochastic model formulation. This allows for a quantification of the mean-field approximation criterion for the justification of replacement of the stochastic by a deterministic model.

Dimensionality Reduction and Louvain Agglomerative Hierarchical Clustering for Cluster-Specified Frequent Biomarker Discovery in Single-Cell Sequencing Data.

The major interest domains of single-cell RNA sequential analysis are identification of existing and novel types of cells, depiction of cells, cell fate prediction, classification of several types of tumor, and investigation of heterogeneity in different cells. Single-cell clustering plays an important role to solve the aforementioned questions of interest. Cluster identification in high dimensional single-cell sequencing data faces some challenges due to its nature. Dimensionality reduction models can solve the problem. Here, we introduce a potential cluster specified frequent biomarkers discovery framework using dimensionality reduction and hierarchical agglomerative clustering Louvain for single-cell RNA sequencing data analysis. First, we pre-filtered the features with fewer number of cells and the cells with fewer number of features. Then we created a Seurat object to store data and analysis together and used quality control metrics to discard low quality or dying cells. Afterwards we applied global-scaling normalization method “LogNormalize” for data normalization. Next, we computed cell-to-cell highly variable features from our dataset. Then, we applied a linear transformation and linear dimensionality reduction technique, Principal Component Analysis (PCA) to project high dimensional data to an optimal low-dimensional space. After identifying fifty “significant”principal components (PCs) based on strong enrichment of low p-value features, we implemented a graph-based clustering algorithm Louvain for the cell clustering of 10 top significant PCs. We applied our model to a single-cell RNA sequential dataset for a rare intestinal cell type in mice (NCBI accession ID:GSE62270, 23,630 features and 1872 samples (cells)). We obtained 10 cell clusters with a maximum modularity of 0.885 1. After detecting the cell clusters, we found 3871 cluster-specific biomarkers using an expression feature extraction statistical tool for single-cell sequencing data, Model-based Analysis of Single-cell Transcriptomics (MAST) with a log 2 FC threshold of 0.25 and a minimum feature detection of 25%. From these cluster-specific biomarkers, we found 1892 most frequent markers, i.e., overlapping biomarkers. We performed degree hub gene network analysis using Cytoscape and reported the five highest degree genes (Rps4x, Rps18, Rpl13a, Rps12 and Rpl18a). Subsequently, we performed KEGG pathway and Gene Ontology enrichment analysis of cluster markers using David 6.8 software tool. In summary, our proposed framework that integrated dimensionality reduction and agglomerative hierarchical clustering provides a robust approach to efficiently discover cluster-specific frequent biomarkers, i.e., overlapping biomarkers from single-cell RNA sequencing data.

The Gender-Specific Interaction of DVL3 and GSK3β Polymorphisms on Major Depressive Disorder Susceptibility in a Chinese Han Population: A Case-Control Study.

Based on the “oxidative stress hypothesis” of major depressive disorder (MDD), cells regulate their structure through the Wnt pathway. Little is known regarding the interactions of dishevelled 3 (DVL3) and glycogen synthase kinase 3 beta (GSK3β) polymorphisms with MDD. The aim of the current study was to verify the relationship between DVL3 and GSK3β genetic variants in a Chinese Han population and further to evaluate whether these interactions exhibit gender-specificity. A total of 1136 participants, consisting of 541 MDD patients and 595 healthy subjects, were recruited. Five single-nucleotide polymorphisms (SNPs) of DVL3/GSK3β were selected to assess their interaction by use of a generalized multifactor dimensionality reduction method. The genotype and haplotype frequencies of DVL3/GSK3β polymorphisms were significantly different between patients and controls for DVL3 rs1709642 (P < 0.01) and GSK3β rs334558, rs6438552, and rs2199503 (P < 0.01). In addition, our results also showed that there were significant interaction effects between DVL3 and GSK3β polymorphisms and the risk of developing MDD, particularly in women. The interaction between DVL3 (rs1709642) and GSK3β (rs334558, rs6438552) showed a cross-validation (CV) consistency of 10/10, a P value of 0.001, and a testing accuracy of 59.22%, which was considered as the best generalized multifactor dimensionality reduction (GMDR) model. This study reveals the interaction between DVL3 and GSK3β polymorphisms on MDD susceptibility in a female Chinese Han population. The effect of gender should be taken into account in future studies that seek to explore the genetic predisposition to MDD relative to the DVL3 and GSK3β genes.

Dynamic manifold Boltzmann optimization based on self‐supervised learning for human motion estimation

It is a challenge work to estimate the 3D human motion from image sequence. There are some problems, such as unsatisfactory estimation error, ambiguous matching and transient occlusion. Although the prior information of learning large-scale samples exists, these problems are still difficult to be solved. How to extract the feature of the high-dimensional (HD) sample of 3D human motion and find the desired one will become the key to solve these problems above. Some dimension reduction methods can extract the sample features and build the low-dimensional (LD) space to view their LD features, but how to search the relevant valid and desired LD samples remains the bottleneck problem, which can be used to reconstruct the 3D human motions denoted by the corresponding high-dimensional samples. Thus, a new method called dynamic manifold Boltzmann optimization (DMBO) is proposed to estimate the 3D human motion from multi-view images. DMBO can find the best matching 3D human motion model by the help of the self-supervised learning from Gaussian incremental dimension reduction model (GIDRM). DMBO can avoid the local optimum during searching and solve the problems above, so that the generation of the accurate 3D human motion corresponding to multi-view images can be achieved.

SAR Image Compression Using Integer to Integer Transformations, Dimensionality Reduction, and High Correlation Modeling

In this document, we present new techniques for near-lossless and lossy compression of SAR imagery saved in PNG and binary formats of magnitude and phase data based on the application of transforms, dimensionality reduction methods, and lossless compression. In particular, we discuss the use of blockwise integer to integer transforms, subsequent application of a dimensionality reduction method, and Burrows-Wheeler based lossless compression for the PNG data and the use of high correlation based modeling of sorted transform coefficients for the raw floating point magnitude and phase data. The gains exhibited are substantial over the application of different lossless methods directly on the data and competitive with existing lossy approaches. The methods presented are effective for large scale processing of similar data formats as they are heavily based on techniques which scale well on parallel architectures.

A parallel strategy for predicting the quality of welded joints in automotive bodies based on machine learning

Due to the complexity of the resistance spot welding process, it is still a challenge to accurately know the operating status of the welding robot under the current parameter settings and to assess the welding quality of electrode caps under different types of plates in real time with large data sizes. To solve this problem, this paper classifies the overall data set and proposes a parallel strategy method for predicting the quality of weld joints using machine learning for subsets of the data with different distribution patterns. Firstly, the PCA dimensionality reduction model was used to set the number of principal components to reduce the dimensionality of the welding process feature value dataset and reduce the difficulty of classifying the data subgroups, and the elbow method was used to set the number of clustering centers to complete the classification of the sub-datasets by applying the k-means model on the basis of the dimensionality reduction data. Finally, the feature parameters of each sub-dataset are used as input for machine learning, and a parallel prediction strategy for weld joint quality is developed based on the data distribution characteristics of each sub-dataset. The test results show that the model in this paper outperforms the static BP neural network in predicting the quality of all types of welded joints, the machine learning parallel strategy tailored to the characteristics of the data population works well with more complexly distributed welded big data. This paper provides accurate and effective estimation of body resistance welding condition, which can provide some guidance for online inspection of body resistance spot welding quality in automotive production lines.

Incremental Linear Discriminant Analysis Dimensionality Reduction and 3D Dynamic Hierarchical Clustering WSNs

Optimizing the sensor energy is one of the most important concern in Three-Dimensional (3D) Wireless Sensor Networks (WSNs). An improved dynamic hierarchical clustering has been used in previous works that computes optimum clusters count and thus, the total consumption of energy is optimal. However, the computational complexity will be increased due to data dimension, and this leads to increase in delay in network data transmission and reception. For solving the above-mentioned issues, an efficient dimensionality reduction model based on Incremental Linear Discriminant Analysis (ILDA) is proposed for 3D hierarchical clustering WSNs. The major objective of the proposed work is to design an efficient dimensionality reduction and energy efficient clustering algorithm in 3D hierarchical clustering WSNs. This ILDA approach consists of four major steps such as data dimension reduction, distance similarity index introduction, double cluster head technique and node dormancy approach. This protocol differs from normal hierarchical routing protocols in formulating the Cluster Head (CH) selection technique. According to node’s position and residual energy, optimal cluster-head function is generated, and every CH is elected by this formulation. For a 3D spherical structure, under the same network condition, the performance of the proposed ILDA with Improved Dynamic Hierarchical Clustering (IDHC) is compared with Distributed Energy-Efficient Clustering (DEEC), Hybrid Energy Efficient Distributed (HEED) and Stable Election Protocol (SEP) techniques. It is observed that the proposed ILDA based IDHC approach provides better results with respect to Throughput, network residual energy, network lifetime and first node death round.

A Full Tensor Network for Hyperspectral Image Classification

Hyperspectral image (HSI) is widely used in real-world classification tasks since it contains rich spatial and spectral features consisting of hundreds of continuous bands. However, the rich spectral features always result in “dimension disaster” for HSI classification. Some traditional methods adopt the strategy of dimensionality reduction in advance to alleviate the influences of high spectral feature dimension, which usually results in degraded classification accuracy due to the hard coupling of the dimensionality reduction model and the classifier. In this letter, we propose a full tensor network for HSI classification based on Tucker decomposition-based hidden layer and CP decomposition-based classification layer. The proposed network can efficiently extract the high-level structural features directly from the original data and classify HSI in a single network without dimension reduction procedure in advance. Moreover, the proposed model has a simple structure and holds less parameters than the state-of-art classification methods. The experimental results on Pavia University and Salinas datasets show that for training ratio of 5%, the overall accuracy of our model are averaged 3.41% higher than CNN models while the network parameters are averaged 80.44% less, which validate the merits of the proposed method.

Modeling of discrete questionnaire data with dimension reduction

The paper deals with the task of modeling discrete questionnaire data with a reduced dimension of the model. The discrete model dimension is reduced using the construction of local models based on independent binomial mixtures estimated with the help of recursive Bayesian algorithms in the combination with the naive Bayes technique. The main contribution of the paper is a three-phase algorithm of the discrete model dimension reduction, which allows to model high-dimensional questionnaire data with high number of explanatory variables and their possible realizations. The proposed general solution is applied to the traffic accident questionnaire analysis, where it takes the form of the classification of the accident circumstances and prediction of the traffic accident severity using the currently measured discrete data. Results of testing the obtained model on real data and comparison with theoretical counterparts are demonstrated.

The Effects of Variable Selection and Dimension Reduction Methods on the Classification Model in the Small Round Blue Cell Tumor Dataset

Objective: The purpose of this study is to investigate and compare the effects of different dimension reduction methods (PCA, ICA, PCA + Forward Selection, ICA + Forward Selection) on the K-NN classifier using open access gene expression data of small round blue cell tumor types.Methods: In this study, open access gene expression data of small round blue cell tumor types was used for investigate and compare the effects of different dimension reduction methods. In the study, PCA, ICA, PCA + Forward Selection, ICA + Forward Selection were used as different dimension reduction methods together with K-NN classification method.Results: Accuracy values obtained from the dimension reduction model made with PCA on K-NN model; for EWS, BL, NB, and RMS type tumors with 93.51%, 91.14%, 92.31%, and 94.74% respectively. Accuracy values obtained from the dimension reduction model made with PCA + Forward Selection on K-NN model; for EWS, BL, NB, and RMS type tumors with 96.25%, 96.25%, 95.06% and 95.47%, respectively. Accuracy values obtained from the dimension reduction model made with ICA on K-NN model; for EWS, BL, NB, and RMS type tumors with 91.89%, 90.67%, 88.31% and 89.47% respectively. Accuracy values obtained from the dimension reduction model made with ICA+ Forward Selection on K-NN model; for EWS, BL, NB, and RMS type tumors with 93.51%, 91.14%, 92.31% and 94.74% respectively.Conclusion: In this study, the model created with PCA gives higher results than the model created with ICA. In addition, according to the results of the models obtained by applying the Forward selection method on these 2 models, the forward selection method has increased the classification performance.