High-dimensional Feature Research Articles

Deep learning based decision-making and outcome prediction for adolescent idiopathic scoliosis patients with posterior surgery

With the emergence of numerous classifications, surgical treatment for adolescent idiopathic scoliosis (AIS) can be guided more effectively. However, surgical decision-making and optimal strategies still lack standardization and personalized customization. Our study aims to devise proper deep learning (DL) models that incorporate key factors influencing surgical outcomes on the coronal plane in AIS patients to facilitate surgical decision-making and predict surgical results for AIS patients. A total of 425 AIS patients who underwent posterior spinal fixation were collected. Variables such as age, gender, preoperative and final follow-up horizontal and vertical coordinate vectors, and screw positioning data were preprocessed by parameterizing image data and transforming various data types into a unified, continuous high-dimensional feature space. Four deep learning models were designed, including Multi-Layer Perceptron model, Encoder-Decoder model, CNN-LSTM Attention model and Deep FM model. For the implementation of deep learning, 70% of the data was adopted for training and 30% for evaluation. The mean square error (MSE), mean absolute error (MAE) and curve fitting between the predicted and corresponding real postoperative spinal coordinates of the test set were adopted to validate and compare the efficacy of the DL models. A total of 425 patients with an average age of 14.60 ± 2.08 years, including 77 males and 348 females, were enrolled in this study. The Lenke type 1 and 5 AIS patients accounted for the majority of the included patients. The results showed that the Multi-Layer Perceptron model achieved the best performance among the four DL models, with a mean square error of 2.77 × 10–5 and an average absolute error of 0.00350 on the validation set. Moreover, the results predicted by the Multi-Layer Perceptron model closely matched the actual coordinate positions on the original postoperative images of patients with Lenke type 1 and AIS patients. Deep learning models can provide alternative and effective decision-making support for AIS patients undergoing surgery. Regarding the learning curve and data volume, the optimal DL models should be adjusted and refined to meet future demands.

Development of a CT radiomics prognostic model for post renal tumor resection overall survival based on transformer enhanced K-means clustering.

Kidney tumors, common in the urinary system, have widely varying survival rates post-surgery. Current prognostic methods rely on invasive biopsies, highlighting the need for non-invasive, accurate prediction models to assist in clinical decision-making. This study aimed to construct a K-means clustering algorithm enhanced by Transformer-based feature transformation to predict the overall survival rate of patients after kidney tumor resection and provide an interpretability analysis of the model to assist in clinical decision-making. This study was based on a publicly available C4KC-KiTS-2019 dataset from the TCIA database, including preoperative computed tomography (CT) images and survival time data of 210 patients. Initially, the radiomics features of the kidney tumor area were extracted using the 3D slicer software. Feature selection was then conducted using ICC, mRMR algorithms, and LASSO regression to calculate radiomics scores. Subsequently, the selected features were input into a pre-trained Transformer model for feature transformation to obtain a higher-dimensional feature set. Then, K-means clustering was performed using this feature set, and the model was evaluated using receiver operating characteristic (ROC) and Kaplan-Meier curves. Finally, the SHAP interpretability algorithm was used for the feature importance analysis of the K-means clustering results. Eleven important features were selected from 851 radiomics features. The K-means clustering model after Transformer feature transformation showed AUCs of 0.889, 0.841, and 0.926 for predicting 1-, 3-, and 5-year overall survival rates, respectively, thereby outperforming both the K-means model with original feature inputs and the radiomics score method. A clustering analysis revealed survival prognosis differences among different patient groups, and a SHAP analysis provided insights into the features that had the most significant impacts on the model predictions. The K-means clustering algorithm enhanced by the Transformer feature transformation proposed in this study demonstrates promising accuracy and interpretability in predicting the overall survival rate after kidney tumor resection. This method provides a valuable tool for clinical decision-making and contributes to improved management and treatment strategies for patients with kidney tumors.

Binary plant rhizome growth-based optimization algorithm: an efficient high-dimensional feature selection approach

Feature selection is a pivotal research area within machine learning, tasked with pinpointing the essential subset of features from a broad array that critically influences a model’s predictive capabilities. This process enhances model precision and drastically lowers the computational demands associated with training and predicting. Consequently, more advanced optimization techniques are employed to address the challenge of feature selection. This paper introduces an innovative intelligent optimization algorithm, the Plant Root Growth Optimization (PRGO) algorithm, inspired by the structure of plant rhizomes and the way they absorb nutrients.In the algorithm, the plant rhizomes are divided into two categories, the taproot and the fibrous root.the growth process of the taproot plants is associated with the global exploration search, and the growth process of the fibrous root plants relates to the local exploitation search.The global asymptotic convergence of the algorithm is proved by applying Markov’s correlation theory, and simulation results using CEC2014 and CEC2017 test sets show that the proposed algorithm has excellent performance.Moreover, a binary variant of this algorithm (BPRGO) has been specifically crafted in this research to tackle the complexities of high-dimensional feature selection issues. The algorithm was compared to eight well-known feature selection methods and its performance was evaluated using a variety of evaluation metrics on 16 high-dimensional datasets from the Arizona State University feature selection library. and the performance of the proposed algorithm was evaluated through feature subset size, classification accuracy, fitness value, and F1-score. The experimental results show that BPRGO achieves the best performance, which has stronger feature reduction ability and achieves better overall performance on most datasets. BPRGO can obtain extremely smaller feature subsets while maintaining much higher classification accuracy, and satisfactory F1-score.

User Profile Construction Based on High-Dimensional Features Extracted by Stacking Ensemble Learning

Online social networks, as platforms for personal expression, have evolved into complex networks integrating political and social dimensions. This evolution has shifted the focus of network governance from addressing hacking activities to mitigating unpredictable social behaviors, such as the malicious manipulation of public opinion, the doxing of ordinary users, and cyberbullying. However, the sparsity of data and the concealed nature of user behavior pose significant challenges to existing network reconnaissance technologies. In this study, we focus on constructing user profiles on online social network platforms by extracting features to build deep user profiles based on behavioral patterns. Drawing inspiration from the 5Cs principle of credit evaluation, we refine it into a 3Cs principle tailored for user profiling on social network platforms and associate it with user behavioral patterns. To further analyze user behavior, a high-dimensional feature extraction method is proposed using an improved stacking ensemble learning model. Based on experimental data analysis, the most suitable base algorithms for high-dimensional feature extraction are identified. Experimental results demonstrate that the integration of high-dimensional features improved the behavior prediction accuracy of the profiling model by 9.26% on balanced datasets and enhanced the AUC (area under the curve) metric by 3.69% on imbalanced datasets. The proposed method effectively increases the depth and generalization performance of user profiling.

Feature selection for high-dimensional data using a multivariate search space reduction strategy based scatter search

In feature selection, the increasing of the dimensionality and the complexity of feature interactions make the problem challenging. Furthermore, searching for an optimal subset of features from a high-dimensional feature space is known to be an NP-hard problem. To improve the efficiency and effectiveness of the search algorithm, feature grouping has emerged as a way to reduce the search space by clustering features according to a measure. In this work we propose to reduce the search space by applying a greedy algorithm, called Multivariate Greedy Predominant Groups Generator (MGPGG). MGPGG extends the idea of the Greedy Predominant Groups Generator (GPGG) algorithm by taking into account feature interaction among three or more features. For this purpose, MGPGG uses the Multivariate Symmetrical Uncertainty (MSU) to group features that share information about the class label. We also propose a Scatter Search strategy that integrates MGPGG to find small subsets of features with high predictive power. The proposed algorithm, called Multivariate Predominant Group-based Scatter Search (MPGSS), is tested on high-dimensional data from biomedical and text-mining fields. The proposal is compared with state-of-the-art feature selection strategies. Results show that MPGSS is competitive since it is capable of finding small subsets of features while keeping high predictive classification models.

Enhancing Blood Cell Diagnosis Using Hybrid Residual and Dual Block Transformer Network

Leukemia is a life-threatening blood cancer that affects a large cross-section of the population, which underscores the great need for timely, accurate, and efficient diagnostic solutions. Traditional methods are time-consuming, subject to human vulnerability, and do not always grasp the subtle morphological differences that form the basic discriminatory features among different leukemia subtypes. The proposed residual vision transformer (ResViT) model breaks these limitations by combining the advantages of ResNet-50 for high dimensional feature extraction and a vision transformer for global attention to the spatial features. ResViT can extract low-level features like texture and edges as well as high-level features like patterns and shapes from the leukemia cell images. Furthermore, we designed a dual-stream ViT with a convolution stream for local details and a transformer stream for capturing the global dependencies, which enables ResViT to pay attention to multiple image regions simultaneously. The evaluation results of the proposed model on the two datasets were more than 99%, which makes it an excellent candidate for clinical diagnostics.

Artificial intelligence and machine learning in cell-free-DNA-based diagnostics.

The discovery of circulating fetal and tumor cell-free DNA (cfDNA) molecules in plasma has opened up tremendous opportunities in noninvasive diagnostics such as the detection of fetal chromosomal aneuploidies and cancers and in posttransplantation monitoring. The advent of high-throughput sequencing technologies makes it possible to scrutinize the characteristics of cfDNA molecules, opening up the fields of cfDNA genetics, epigenetics, transcriptomics, and fragmentomics, providing a plethora of biomarkers. Machine learning (ML) and/or artificial intelligence (AI) technologies that are known for their ability to integrate high-dimensional features have recently been applied to the field of liquid biopsy. In this review, we highlight various AI and ML approaches in cfDNA-based diagnostics. We first introduce the biology of cell-free DNA and basic concepts of ML and AI technologies. We then discuss selected examples of ML- or AI-based applications in noninvasive prenatal testing and cancer liquid biopsy. These applications include the deduction of fetal DNA fraction, plasma DNA tissue mapping, and cancer detection and localization. Finally, we offer perspectives on the future direction of using ML and AI technologies to leverage cfDNA fragmentation patterns in terms of methylomic and transcriptional investigations.

Global sensitivity analysis of high-speed train dynamics system with high-dimensional inputs and multiple outputs

A high-speed train dynamics system involves numerous uncertainty parameters, and there are multiple evaluation indices for its dynamic performance. In this paper, we conduct high-dimensional and multi-output global sensitivity analysis for the dynamic performance of high-speed trains by comprehensively considering these dynamics parameters and indices. Firstly, the dynamics simulation model of the high-speed train is established and six dynamics indices for evaluating the safety and comfort of the train are obtained under operating conditions. Subsequently, considering the multi-output and high-dimensional characteristics of train sensitivity analysis, we propose a multi-output global sensitivity analysis method based on the correlation-analysis-guided Kriging model (CA-K). Finally, global sensitivity analysis of 96 uncertainty parameters on six dynamics indices is conducted under three scenarios utilising the proposed method. The results show that (1) CA-K achieves higher accuracy in approximating high-dimensional train dynamics indices than existing conventional surrogate models. (2) The multi-output global sensitivity analysis method can simultaneously identify all important dynamics parameters and exclude unimportant parameters.

A novel carbon emission monitoring method for power generation enterprises based on hybrid transformer model

Accurate carbon accounting is essential for power generation enterprises to participate in carbon markets and implement carbon reduction strategies. However, due to excessive reliance on detailed energy data and manual calculations, carbon emission accounting in power generation enterprises suffers from low frequency, significant lag, and poor reliability. Some evidences suggest a strong correlation between internal carbon emissions and electricity consumption in power generation enterprises. Inspired by them, this paper proposes a novel model, named ICEEMDAN-Inception-Transformer, to thoroughly explore the relationship between power data and carbon emissions, providing precise hourly carbon emission acquisition for power enterprises. This model first utilizes ICEEMDAN to extract the significant characteristics of power data, then employs advanced Inception and Transformer structures to capture the complex high-dimensional features of the “electricity-carbon” correlation, thereby realizing enterprise carbon emissions monitoring. The model was extensively validated on three datasets from three different types of power enterprises. The average performance on indicators of RMSE, MAE, MAPE, and R2 of the model on the three datasets reached 11.69 tCO2, 9.58 tCO2, 2.44%, and 96.42%, respectively. The results demonstrate that the proposed monitoring model possesses certain advantages in terms of the accuracy and robustness of acquiring enterprise carbon emissions, providing valuable insights for high-frequency accurate carbon monitoring in power generation enterprises.

Multi-strategy fusion pelican optimization algorithm and logic operation ensemble of transfer functions for high-dimensional feature selection problems

Multi-strategy fusion pelican optimization algorithm and logic operation ensemble of transfer functions for high-dimensional feature selection problems

W-Shaped Net: An Inter-Slice Super-Resolution Segmentation Deep Network for CT Scans of Hepatic Ducts

The three-dimensional (3D) reconstruction of the hepatic duct tree is significant for the minimally invasive surgery of hepatobiliary stone disease, which can be influenced by the quantity of the CT scans of hepatic ducts. If insufficient CT scans with low inter-slice resolution are directly utilized for 3D reconstruction, discontinuities and gaps will emerge in the reconstructed hepatic duct tree. In this paper, a novel end-to-end deep learning framework is designed for the inter-slice super-resolution segmentation of the CT slices of hepatic ducts, which can improve the 3D reconstruction performance in the inter-slice dimension. Specifically, the framework cascades into an inter-slice super-resolution subnetwork and a segmentation subnetwork. A deep learning network is introduced as the inter-slice super-resolution subnetwork to generate an intermediate slice between two adjacent CT slices in the simulated CT scans with low inter-slice resolution. To capture the spatiotemporal correlation existing in the CT scans of hepatic ducts, the ConvLSTM is introduced into the U-Net-like segmentation subnetwork in the high-dimensional feature space. To further suppress the problems of discontinuities and gaps, a structure-aware loss function is proposed by incorporating the structural similarity index measure (SSIM) as a regulator to dynamically assign the contribution of the generated CT slice to the total loss of the designed framework. Experimental results demonstrate that our proposed framework performs better segmentations for hepatic ducts than several existing deep learning networks with the performance of 0.7690 DICE and a 0.7712 F1-score, which is beneficial for the 3D reconstruction of the hepatic duct tree.

The Multivariate Fusion Distribution Characteristics in Physician Demand Prediction

Aiming at the optimization of the big data infrastructure in China’s healthcare system, this study proposes a lightweight time series physician demand prediction model, which is especially suitable for the field of telemedicine. The model incorporates multi-head attention mechanisms and generates statistical information, which significantly improves the ability to process nonlinear data, adapt to different data sources, improve the computational efficiency, and process high-dimensional features. By combining variational autoencoders and LSTM units, the model can effectively capture complex nonlinear relationships and long-term dependencies, and the multi-head attention mechanism overcomes the limitations of traditional algorithms. This lightweight architecture design not only improves the computational efficiency but also enhances the stability in high-dimensional data processing and reduces feature redundancy by combining the normalization process with statistics. The experimental results show that the model has wide applicability and excellent performance in a telemedicine consulting service system.

Skin Lesion Classification Through Test Time Augmentation and Explainable Artificial Intelligence.

Despite significant advancements in the automatic classification of skin lesions using artificial intelligence (AI) algorithms, skepticism among physicians persists. This reluctance is primarily due to the lack of transparency and explainability inherent in these models, which hinders their widespread acceptance in clinical settings. The primary objective of this study is to develop a highly accurate AI-based algorithm for skin lesion classification that also provides visual explanations to foster trust and confidence in these novel diagnostic tools. By improving transparency, the study seeks to contribute to earlier and more reliable diagnoses. Additionally, the research investigates the impact of Test Time Augmentation (TTA) on the performance of six Convolutional Neural Network (CNN) architectures, which include models from the EfficientNet, ResNet (Residual Network), and ResNeXt (an enhanced variant of ResNet) families. To improve the interpretability of the models' decision-making processes, techniques such as t-distributed Stochastic Neighbor Embedding (t-SNE) and Gradient-weighted Class Activation Mapping (Grad-CAM) are employed. t-SNE is utilized to visualize the high-dimensional latent features of the CNNs in a two-dimensional space, providing insights into how the models group different skin lesion classes. Grad-CAM is used to generate heatmaps that highlight the regions of input images that influence the model's predictions. Our findings reveal that Test Time Augmentation enhances the balanced multi-class accuracy of CNN models by up to 0.3%, achieving a balanced accuracy rate of 97.58% on the International Skin Imaging Collaboration (ISIC 2019) dataset. This performance is comparable to, or marginally better than, more complex approaches such as Vision Transformers (ViTs), demonstrating the efficacy of our methodology.

Position detection of elements in off-axis three-mirror space optical system based on ResNet50 and LSTM.

Position detection of elements, especially with high-precision and high-efficiency, continue to present challenges in the off-axis three-mirror space optical system to ensure the imaging quality. To test the position of elements in an off-axis three-mirror system, a method based on ResNet50 and Long short-term memory (LSTM) is proposed in this paper. In the proposed method, point spread function (PSF) with different fields of view is extracted as a high dimensional feature vector by the ResNet50 network to achieve high efficiency. The same position information in the high dimensional feature vector from different image plane is obtained by the LSTM module to achieve high precision. To evaluate the performance of the proposed method, three examples of position detection were conducted. The results indicated that the probabilities of achieving detection accuracy better than 10 µm for eccentricity and 10'' for tilt, across single-dimensional variation of components, multi-dimensional random variation, and detector variation, are 100%, 94%, and 100%, respectively. Unlike the other detection method, the positions of elements are obtained with only one calculation and are close to the final results, which saves both time and resources for adjustment. The findings indicate that the method is an accurate and effective method for detecting position of elements in off-axis three-mirror space optical system.

A data-driven modeling framework for mapping genotypes to synthetic microbial community functions.

Microbial communities play a central role in transforming environments across Earth, driving both physical and chemical changes. By harnessing these capabilities, synthetic microbial communities, assembled from the bottom up, offer valuable insights into the mechanisms that govern community functions. These communities can also be tailored to produce desired outcomes, such as the synthesis of health-related metabolites or nitrogen fixation to improve plant productivity. Widely used computational models predict synthetic community functions using species abundances as inputs, making it impossible to predict the effects of species not included in the training data. We bridge this gap using a data-driven community genotype function (dCGF) model. By lifting the representation of each species to a high-dimensional genetic feature space, dCGF learns a mapping from community genetic feature matrices to community functions. We demonstrate that dCGF can accurately predict communities in a fixed environmental context that are composed in part or entirely from new species with known genetic features. In addition, dCGF facilitates the identification of species roles for a community function and hypotheses about how specific genetic features influence community functions. In sum, dCGF provides a new data-driven avenue for modeling synthetic microbial communities using genetic information, which could empower model-driven design of microbial communities.

Identification of hypertension gene expression biomarkers based on the DeepGCFS algorithm.

Hypertension is a critical risk factor and cause of mortality in cardiovascular diseases, and it remains a global public health issue. Therefore, understanding its mechanisms is essential for treating and preventing hypertension. Gene expression data is an important source for obtaining hypertension biomarkers. However, this data has a small sample size and high feature dimensionality, posing challenges to biomarker identification. We propose a novel deep graph clustering feature selection (DeepGCFS) algorithm to identify hypertension gene biomarkers with more biological significance. This algorithm utilizes a graph network to represent the interaction information between genes, builds a GNN model, designs a loss function based on link prediction and self-supervised learning ideas for training, and allows each gene node to obtain a feature vector representing global information. The algorithm then uses hybrid clustering methods for gene module detection. Finally, it combines integrated feature selection methods to determine the gene biomarkers. The experiment revealed that all the ten identified hypertension biomarkers were significantly differentiated, and it was found that the classification performance of AUC can reach 97.50%, which is better than other literature methods. Six genes (PTGS2, TBXA2R, ZNF101, KCNJ2, MSRA, and CMTM5) have been reported to be associated with hypertension. By using GSE113439 as the validation dataset, the AUC value of classification performance was to be 95.45%, and seven of the genes (LYSMD3, TBXA2R, KLC3, GPR171, PTGS2, MSRA, and CMTM5) were to be significantly different. In addition, this algorithm's performance of gene feature vector clustering was better than other comparative methods. Therefore, the proposed algorithm has significant advantages in selecting potential hypertension biomarkers.

Harnessing unlabeled data: Enhanced rare earth component content prediction based on BiLSTM-Deep autoencoder.

Traditional data-driven models for predicting rare earth component content are primarily developed by relying on supervised learning methods, which suffer from limitations such as a lack of labeled data, lagging, and poor usage of a major amount of unlabeled data. This paper proposes a novel prediction approach based on the BiLSTM-Deep autoencoder enhanced traditional LSSVM algorithm, termed BiLSTM-DeepAE-LSSVM. This approach thoroughly exploits the implicit information contained in copious amounts of unlabeled data in the rare earth production process, thereby improving the traditional supervised prediction method and increasing the accuracy of component content predictions. Initially, a BiLSTM autoencoder is established for unsupervised training on the rare earth production process data, enabling the extraction of inherent time series characteristics. Subsequently, boolean vectors are introduced in the Deep autoencoder training process to perform masking operations on the input data, simulating scenarios with noise and missing data. This is facilitated by their adherence to Bernoulli distributions, which allow for the random setting of certain input vector dimensions to zero. Additionally, the Deep autoencoder is capable of extracting high-dimensional implicit features from the data. After that, the conventional supervised prediction technique, least squares support vector machine (LSSVM), is fused with the implicit characteristics derived from the well-constructed BiLSTM-Deep autoencoder, culminating in the creation of a prediction model for rare earth component content. Ultimately, the simulation verification using LaCe/PrNd extraction field data demonstrates the effectiveness of the proposed approach in harnessing substantial quantities of unlabeled data from the rare earth extraction production process, thereby bolstering the accuracy of model predictions.

Dynamic multi-swarm whale optimization algorithm based on elite tuning for high-dimensional feature selection classification problems

Dynamic multi-swarm whale optimization algorithm based on elite tuning for high-dimensional feature selection classification problems

Tongue Image Diagnosis System using Machine Learning with Hand-Crafted Features

Traditional Chinese Medicine theorizes a clear relationship between the visual characteristics of the tongue and the operational condition of the body's organs. The visual characteristics of the tongue can offer important indications for diagnosing diseases. Investigating tongue image processing methods for automated disease identification is a flourishing field of study in the modernization of Traditional Chinese Medicine. Although autonomous extraction of high-dimensional features is inherently more beneficial in deep learning than in conventional methods, its usefulness in medical image analysis, notably in tongue images, is restricted by the need for extensive training data. This limitation arises from the need for more labeled images. This paper demonstrated the automated diagnosis of tongue photos by analyzing digital images utilizing Image Processing techniques and using Machine Learning using major image-based features. The performance simulation and analysis of the suggested system are conducted using MATLAB Software.

Hybrid rice optimization algorithm inspired grey wolf optimizer for high-dimensional feature selection

Feature selection (FS) is a significant dimensionality reduction technique, which can effectively remove redundant features. Metaheuristic algorithms have been widely employed in FS, and have obtained satisfactory performance, among them, grey wolf optimizer (GWO) has received widespread attention. However, the GWO and its variants suffer from limited adaptability, poor diversity, and low accuracy when faced with high-dimensional data. The hybrid rice optimization (HRO) algorithm is an emerging metaheuristic algorithm derived from the hybrid heterosis and breeding mechanism in nature. It possesses a robust capacity to identify and converge towards optimal solutions. Therefore, a novel approach based on multi-strategy collaborative GWO combined with the HRO algorithm (HRO-GWO) for FS is proposed in this paper. The HRO-GWO algorithm is enhanced by four innovative strategies including dynamical regulation strategy and three search strategies. First, to improve the adaptability of GWO, the dynamical regulation strategy is devised for parameter optimization of GWO. Then, a multi-strategy co-evolution model inspired by HRO is designed, which utilizes neighborhood search, dual-crossover, and selfing techniques to bolster population diversity. Finally, the study develops a hybrid filter-wrapper framework incorporating chi-square and the HRO-GWO algorithm to efficiently select pertinent and informative feature subsets, enhancing the classification performance while conserving time. The performance of HRO-GWO has been rigorously assessed across benchmark functions and the effectiveness of the proposed framework has been evaluated on small-sample high-dimensional biomedical datasets. Our experimental findings demonstrate that the approach on the basis of HRO-GWO outperforms state−of-the−art methods.