Candidate Features Research Articles

Feature Selection and Classification for Anomaly Detection in IoT Networks using Multi-layer Perceptron - Chaotic Ant Lion Optimization (MLP-CALO) Algorithm

As the number of devices in Internet of Things (IoT) increases exponentially, the risks of unknown vulnerabilities and threats also increases resulting in degradation of performance. Traditional anomaly detection systems are ineffective within IoT ecosystems, since the range of possible normal behaviours of devices is significantly larger and more dynamic. The main objective of this work is to develop a machine learning (ML) algorithm to classify the selected features of IoT traffic and detect the malicious behaviour of users and unauthorised devices dynamically. In this paper feature Selection and classification for anomaly detection in IoT using Multi Layer Perception (MLP) and Chaotic Ant Lion Optimization (CALO) algorithm is proposed. In this algorithm, Filtering method using Fisher’ score and correlation coefficient is applied to select the candidate feature set. Then hybrid MLP-CALO algorithm is proposed to classify the selected features and detects the anomalies from the IoT traffic. The objective function of the CALO algorithm minimizes the average MSE of MLP output. Experimental results have shown that MLP-CALO has higher classification accuracy and lesser computation cost when compared to traditional ALO and ANN algorithms

Computer-aided diagnosis for China-Japan Friendship Hospital classification of necrotic femurs using statistical shape and appearance model based on CT scans.

The purpose of this study is to quantify the three-dimensional (3D) structural morphology, bone mineral density (BMD) distribution, and mechanical properties of different China-Japan Friendship Hospital (CJFH) classification types and assist clinicians in classifying necrotic femurs accurately. In this study, 41 cases were classified as types L2 and L3 based on CT images. Then, 3D Statistical Shape and Appearance Models (SSM and SAM) were established, and 80 principal component (PC) modes were extracted from the SSM and SAM as the candidate features. The bone strength of each case was also calculated as the candidate feature using finite element analysis (FEA). Support vector machine (SVM) and Extreme Gradient Boosting (XGBoost) were used to establish 10 machine learning models. Feature selection methods were used to screen the candidate features. The performance of each model was evaluated based on sensitivity, specificity, accuracy, and the area under the receiver operating characteristic (ROC) curve. This resulted in a SVM model for CJFH classification with the performance: accuracy of 87.5%, sensitivity of 85.0%, specificity of 76.0%, and AUC of 94.2%. This study provided effective machine learning models for assisting in diagnosing CJFH types, increasing the objectivity of the diagnosis. They may have great potential for application in clinical assessments of CJFH classification.

A Similar Feature Point Matching Method for Aerial Electric Power Tower Images Based on a One-Ring Neighborhood of Vertices

Due to the susceptibility of images to various factors such as scale changes, imaging conditions, and image noise, traditional feature point matching methods are difficult to achieve ideal matching accuracy, leading to many challenges in the automatic analysis and processing of power tower images. To improve the matching accuracy of similar feature points in aerial images of electric power tower, this study proposes a method for matching similar feature points in aerial images of electric power tower based on a vertex ring neighborhood, addressing the problem of large matching errors caused by factors such as scale and imaging conditions. This method first adopts the feature point extraction technique of electric power tower image based on decomposition and filtering, and constructs the Laplacian pyramid of the original image. Subsequently, filter banks are used to decompose the pyramid image in different directions, extract local extremum points as candidate feature point sets, and merge them to obtain the final feature point set. On this basis, taking into account the spatial relationships and geometric characteristics around the feature points, a texture mapping algorithm based on vertex ring neighborhood and patch classification is applied to construct a vertex ring neighborhood structure and extract geometrically representative electric power tower features. Finally, by using a texture feature point matching method based on the principle of similarity, the similarity between the real-time image and the reference image features is calculated for matching, and combined with the Babbitt coefficient to remove mismatched feature points, accurate matching of similar feature points in aerial electric power tower images is achieved. The experimental results show that this method has a mean square error of less than 0.1Pixel in matching similar texture feature points of aerial power tower images under various working conditions, significantly improving the matching accuracy and providing an effective tool for automatic analysis and processing of power tower images.

Chain hybrid feature selection algorithm based on improved Grey Wolf Optimization algorithm.

Hybrid feature selection algorithm is a strategy that combines different feature selection methods aiming to overcome the limitations of a single feature selection method and improve the effectiveness and performance of feature selection. In this paper, we propose a new hybrid feature selection algorithm, to be named as Tandem Maximum Kendall Minimum Chi-Square and ReliefF Improved Grey Wolf Optimization algorithm (TMKMCRIGWO). The algorithm consists of two stages: First, the original features are filtered and ranked using the bivariate filter algorithm Maximum Kendall Minimum Chi-Square (MKMC) to form a subset of candidate features S1; Subsequently, S1 features are filtered and sorted to form a candidate feature subset S2 by using ReliefF in tandem, and finally S2 is used in the wrapper algorithm to select the optimal subset. In particular, the wrapper algorithm is an improved Grey Wolf Optimization (IGWO) algorithm based on random disturbance factors, while the parameters are adjusted to vary randomly to make the population variations rich in diversity. Hybrid algorithms formed by combining filter algorithms with wrapper algorithms in tandem show better performance and results than single algorithms in solving complex problems. Three sets of comparison experiments were conducted to demonstrate the superiority of this algorithm over the others. The experimental results show that the average classification accuracy of the TMKMCRIGWO algorithm is at least 0.1% higher than the other algorithms on 20 datasets, and the average value of the dimension reduction rate (DRR) reaches 24.76%. The DRR reached 41.04% for 12 low-dimensional datasets and 0.33% for 8 high-dimensional datasets. It also shows that the algorithm improves the generalization ability and performance of the model.

High-dimensional Biomarker Identification for Scalable and Interpretable Disease Prediction via Machine Learning Models.

Omics data generated from high-throughput technologies and clinical features jointly impact many complex human diseases. Identifying key biomarkers and clinical risk factors is essential for understanding disease mechanisms and advancing early disease diagnosis and precision medicine. However, the high-dimensionality and intricate associations between disease outcomes and omics profiles present significant analytical challenges. To address these, we propose an ensemble data-driven biomarker identification tool, Hybrid Feature Screening (HFS), to construct a candidate feature set for downstream advanced machine learning models. The pre-screened candidate features from HFS are further refined using a computationally efficient permutation-based feature importance test, forming the comprehensive High-dimensional Feature Importance Test (HiFIT) framework. Through extensive numerical simulations and real-world applications, we demonstrate HiFIT's superior performance in both outcome prediction and feature importance identification. An R package implementing HiFIT is available on GitHub (https://github.com/BZou-lab/HiFIT).

CAM: a novel aid system to analyse the coloration quality of thick blood smears using image processing and machine learning techniques.

Battling malaria's morbidity and mortality rates demands innovative methods related to malaria diagnosis. Thick blood smears (TBS) are the gold standard for diagnosing malaria, but their coloration quality is dependent on supplies and adherence to standard protocols. Machine learning has been proposed to automate diagnosis, but the impact of smear coloration on parasite detection has not yet been fully explored. To develop Coloration Analysis in Malaria (CAM), an image database containing 600 images was created. The database was randomly divided into training (70%), validation (15%), and test (15%) sets. Nineteen feature vectors were studied based on variances, correlation coefficients, and histograms (specific variables from histograms, full histograms, and principal components from the histograms). The Machine Learning Matlab Toolbox was used to select the best candidate feature vectors and machine learning classifiers. The candidate classifiers were then tuned for validation and tested to ultimately select the best one. This work introduces CAM, a machine learning system designed for automatic TBS image quality analysis. The results demonstrated that the cubic SVM classifier outperformed others in classifying coloration quality in TBS, achieving a true negative rate of 95% and a true positive rate of 97%. An image-based approach was developed to automatically evaluate the coloration quality of TBS. This finding highlights the potential of image-based analysis to assess TBS coloration quality. CAM is intended to function as a supportive tool for analyzing the coloration quality of thick blood smears.

A modified Delphi survey to build expert consensus on the structure and content of an enhanced care pathway for cognitive changes after stroke in the UK

BackgroundEnhancing long-term support for post-stroke cognitive impairment is a top research priority. Addressing current gaps in UK post-stroke cognitive care provision requires a pragmatic and scalable intervention that can be integrated within the existing stroke care pathway. This study aimed to develop consensus on an initial set of core features for a UK-based monitoring and psychoeducational intervention for cognitive changes after stroke.MethodsAn expert panel of UK healthcare professionals and researchers participated in an online modified Delphi survey. Candidate intervention features were identified from clinical guidelines, existing literature, research team/collaborator expertise, and PPI group lived experience. Survey participants indicated whether they agreed/disagreed/had no opinion about including each candidate feature in the intervention and free-text responses were invited. We analysed responses for consensus (≥ 75% agreement) using descriptive statistics, with items not reaching consensus carried into subsequent rounds. Template analysis was used to identify similarities/differences in viewpoints for items that did not reach consensus.ResultsThree survey rounds were completed by 36, 29 and 26 participants, respectively. Participants agreed reviews should include a stroke-specific cognitive screen (97% agree) and assessment of other psychological changes (low mood, anxiety, fatigue: 94%, 90%, 89% agree, respectively). They agreed stroke survivors should be offered at least one review, regardless of their cognitive profile in hospital. They agreed on the importance of various cognition-focused psychoeducation topics, and formal (100% agree) and informal (79% agree) training for those conducting reviews. Consensus was not reached on the review mode (in person/remote options: 67% agree), offering reviews one-year post-discharge to patients without acute cognitive impairments (68% disagree), or including a dementia screen (63% disagree) and/or neuropsychological assessment battery (58% disagree). However, there were similarities in participant viewpoints. For example, participants emphasised the importance of onwards referral where clinically indicated. ConclusionsThe UK-based post-stroke monitoring and psychoeducation intervention was originally conceptualised as a cognitive care pathway, but expert participants agreed on the importance of simultaneously addressing related psychological changes (e.g. low mood, anxiety). There was clear consensus on a minimum set of intervention features. Recommendations outlined here may usefully inform local service improvements.

Multiscale implicit frequency selective network for single‐image dehazing

AbstractImage dehazing is aimed to reconstruct a clear latent image from a degraded image affected by haze. Although vision transformers have achieved impressive success in various computer vision tasks, the limitations in scale and quality of available datasets have hindered the transformer effectiveness for image dehazing. Thus, convolutional neural networks (CNNs) remain the mainstream approach for image dehazing, offering robust performance and adaptability. We further explore the potential of CNNs in image dehazing by proposing a multiscale implicit frequency selection network (MIFSN). The proposed MIFSN enhances multiscale representation learning based on U‐shaped networks. As hazy and clear images considerably differ in high‐frequency components, we introduce an implicit frequency selection module to amplify high‐frequency components of features and generate candidate feature maps. Implicit frequency selection attention is then used to emphasize and merge beneficial frequency components. Results from extensive experiments on synthetic and real‐world datasets demonstrate the superior performance of MIFSN for image dehazing.

Parallel power load abnormalities detection using fast density peak clustering with a hybrid canopy-K-means algorithm

Parallel power loads anomalies are processed by a fast-density peak clustering technique that capitalizes on the hybrid strengths of Canopy and K-means algorithms all within Apache Mahout’s distributed machine-learning environment. The study taps into Apache Hadoop’s robust tools for data storage and processing, including HDFS and MapReduce, to effectively manage and analyze big data challenges. The preprocessing phase utilizes Canopy clustering to expedite the initial partitioning of data points, which are subsequently refined by K-means to enhance clustering performance. Experimental results confirm that incorporating the Canopy as an initial step markedly reduces the computational effort to process the vast quantity of parallel power load abnormalities. The Canopy clustering approach, enabled by distributed machine learning through Apache Mahout, is utilized as a preprocessing step within the K-means clustering technique. The hybrid algorithm was implemented to minimise the length of time needed to address the massive scale of the detected parallel power load abnormalities. Data vectors are generated based on the time needed, sequential and parallel candidate feature data are obtained, and the data rate is combined. After classifying the time set using the canopy with the K-means algorithm and the vector representation weighted by factors, the clustering impact is assessed using purity, precision, recall, and F value. The results showed that using canopy as a preprocessing step cut the time it proceeds to deal with the significant number of power load abnormalities found in parallel using a fast density peak dataset and the time it proceeds for the k-means algorithm to run. Additionally, tests demonstrate that combining canopy and the K-means algorithm to analyze data performs consistently and dependably on the Hadoop platform and has a clustering result that offers a scalable and effective solution for power system monitoring.

Rational Design of Dual-Domain Binding Inhibitors for N-Acetylgalactosamine Transferase 2 with Improved Selectivity over the T1 and T3 Isoforms.

The GalNAc-transferase (GalNAc-T) family, consisting of 20 isoenzymes, regulates the O-glycosylation process of mucin glycopeptides by transferring GalNAc units to serine/threonine residues. Dysregulation of specific GalNAc-Ts is associated with various diseases, making these enzymes attractive targets for drug development. The development of inhibitors is key to understanding the implications of GalNAc-Ts in human diseases. However, developing selective inhibitors for individual GalNAc-Ts represents a major challenge due to shared structural similarities among the isoenzymes and some degree of redundancy among the natural substrates. Herein, we report the development of a GalNAc-T2 inhibitor with higher potency compared to those of the T1 and T3 isoforms. The most promising candidate features bivalent GalNAc and thiophene moieties on a peptide chain, enabling binding to both the lectin and catalytic domains of the enzyme. The binding mode was confirmed by competitive saturation transfer difference NMR experiments and validated through molecular dynamics simulations. The inhibitor demonstrated an IC50 of 21.4 μM for GalNAc-T2, with 8- and 32-fold higher selectivity over the T3 and T1 isoforms, respectively, representing a significant step forward in the synthesis of specific GalNAc-T inhibitors tailored to the unique structural features of the targeted isoform.

Versatile, Modular, and General Strategy for the Synthesis of α-Amino Carbonyls.

Modulating the basicity of alkylamines is a crucial factor in drug design. Consequently, alkylamines with a proximal amide, ester, or ketone have become privileged features in many pharmaceutical candidates. The impact of α-amino carbonyls has made the development of new methods for their preparation a continuous challenge in synthesis. Here, we describe a practical strategy that provides a modular and programmable synthesis of a wide range of α-amino carbonyls. The generality of this process is made possible by an extremely mild method to generate carbamoyl radicals, proceeding via a Lewis acid-visible-light-mediated Norrish type-I fragmentation of a tailored carboxamide reagent and intercepted through addition to in situ generated unbiased imines. Aside from the reaction's broad scope in each component, its capacity to draw on plentiful and diversely populated amine and carbonyl feedstocks is showcased through a two-dimensional array synthesis that is used to construct a library of novel, assay-ready, α-amino amides.

Ultra-short-term Load Forecasting Based on XGBoost-BiGRU

High-precision load forecasting serves as the foundation for power grid scheduling planning and safe economic operation. In scenarios where only historical power load data is available without other external information, fully exploiting meaningful features from the temporal load sequence is crucial for improving the accuracy of load forecasting. Therefore, an ultra-short-term load forecasting method that combines eXtreme gradient boosting (XGBoost) and bidirectional gated recurrent unit (BiGRU) is proposed in this paper. Considering various factors that affect loads, a candidate feature set is established, which includes temporal information and historical loads. XGBoost is used to select the features that contribute significantly to load forecasting, forming an optimal feature set. These optimal features are then used as inputs to the BiGRU, and the bayesian optimization algorithm is applied to optimize the network hyperparameters. Then the load forecasting model for the next 15 minutes based on BiGRU is generated by training iteratively. The proposed XGBoost-BiGRU method is validated on real load data from a province in China. Experimental results demonstrate that the method can effectively avoid the impact of redundant features, improving both prediction accuracy and efficiency. The research has significant importance for guiding real-time supply-demand balance calculations and scheduling in power grids.

FSCME: A Feature Selection Method Combining Copula Correlation and Maximal Information Coefficient by Entropy Weights.

Feature selection is a critical component of data mining and has garnered significant attention in recent years. However, feature selection methods based on information entropy often introduce complex mutual information forms to measure features, leading to increased redundancy and potential errors. To address this issue, we propose FSCME, a feature selection method combining Copula correlation (Ccor) and the maximum information coefficient (MIC) by entropy weights. The FSCME takes into consideration the relevance between features and labels, as well as the redundancy among candidate features and selected features. Therefore, the FSCME utilizes Ccor to measure the redundancy between features, while also estimating the relevance between features and labels. Meanwhile, the FSCME employs MIC to enhance the credibility of the correlation between features and labels. Moreover, this study employs the Entropy Weight Method (EWM) to evaluate and assign weights to the Ccor and MIC. The experimental results demonstrate that FSCME yields a more effective feature subset for subsequent clustering processes, significantly improving the classification performance compared to the other six feature selection methods.

DSFE: Decoding EEG-Based Finger Motor Imagery Using Feature-Dependent Frequency, Feature Fusion and Ensemble Learning.

Accurate decoding finger motor imagery is essential for fine motor control using EEG signals. However, decoding finger motor imagery is particularly challenging compared with ordinary motor imagery. This paper proposed a novel EEG decoding method of feature-dependent frequency band selection, feature fusion, and ensemble learning (DSFE) for finger motor imagery. First, a feature-dependent frequency band selection method based on correlation coefficient (FDCC) was proposed to select feature-specific effective bands. Second, a feature fusion method was proposed to fuse different types of candidate features to produce multiple refined sets of decoding features. Finally, an ensemble model using the weighted voting strategy was proposed to make full use of these diverse sets of final features. The results on a public EEG dataset of five fingers motor imagery showed that the DSFE method is effective and achieves the highest decoding accuracy of 50.64%, which is 7.64% higher than existing studies using exactly the same data. The experiments further revealed that both the effective frequency bands of different subjects and the effective frequency bands of different types of features are different in finger motor imagery. Furthermore, compared with two-hand motor imagery, the effective decoding information of finger motor imagery is transferred to the lower frequency. The idea and findings in this paper provide a valuable perspective for understanding fine motor imagery in-depth.

Pitch-Tracking Metrics as a Predictor of Future Shoulder and Elbow Injuries in Major League Baseball Pitchers: A Machine-Learning and Game-Theory Based Analysis.

Understanding interactions between multiple risk factors for shoulder and elbow injuries in Major League Baseball (MLB) pitchers is important to identify potential avenues by which risk can be reduced while minimizing impact on player performance. To apply a novel game theory-based approach to develop a machine-learning model predictive of next-season shoulder and elbow injuries in MLB pitchers and use this model to understand interdependencies and interaction effects between the most important risk factors. Case-control study; Level of evidence, 3. Pitcher demographics, workload measures, pitch-tracking metrics, and injury data between 2017 and 2022 were used to construct a database of MLB pitcher-years, where each item in the database corresponded to a pitcher's information and metrics for that year. An extreme gradient boosting machine-learning model was trained to predict next-season shoulder and elbow injuries utilizing Shapley additive explanation values to quantify feature importance as well as interdependencies and interaction effects between predictive variables. A total of 3808 pitcher-years were included in this analysis; 606 (15.9%) of these involved a shoulder or elbow injury resulting in placement on the MLB injured list. Of the >65 candidate features (including workload, demographic, and pitch-tracking metrics), the most important contributors to predicting shoulder/elbow injury were increased: pitch velocity (all pitch types), utilization of sliders (SLs), fastball (FB) spin rate, FB horizontal movement, and player age. The strongest game theory interaction effects were that higher FB velocity did not alter a younger pitcher's predicted risk of shoulder/elbow injury versus older pitchers, risk of shoulder/elbow injury increased with the number of high-velocity pitches thrown (regardless of pitch type and in an additive fashion), and FB velocity <95 mph (<152.9 kph) demonstrated strong negative interaction effects with higher SL percentage, suggesting that the overall predicted risk of injury for pitchers throwing a high number of SLs could be attenuated by lower FB velocity. Pitch-tracking metrics were substantially more predictive of future injury than player demographics and workload metrics. There were many significant game theory interdependencies of injury risk. Notably, the increased risk of injury that was conferred by throwing with a high velocity was even further magnified if the pitchers were also older, threw a high percentage of SLs, and/or threw a greater number of pitches.

Feature selection based on neighborhood complementary entropy for heterogeneous data

In practical applications, there exists a large amount of heterogeneous data consisting of a mixture of numerical and categorical data, which are more complex and difficult to handle than a single class. In recent years, feature selection for heterogeneous data has received more and more attention from scholars. However, the current research on feature selection for heterogeneous data seldom takes into account the fineness of the granularity structure and the complementary information contained in the complements of each granularity. Addressing the shortcomings of existing efforts, this paper introduces complementary entropy into the neighborhood rough set model to define an uncertainty measurement system in heterogeneous data, and constructs the corresponding feature selection algorithm. First, the neighborhood complementary entropy and its associated uncertainty measures based on neighborhood relation are defined, and the relevant theoretical properties of these uncertainty measures are investigated. Then, based on the proposed uncertainty measures, a significance function is defined to assess the importance of candidate features. Next, a feature selection method for heterogeneous data is designed using neighborhood complementary entropy. Finally, the feasibility of the method proposed in this paper is demonstrated through an experimental comparative analysis with various existing feature selection methods.

Hybrid genetic optimization for quantum feature map design

Kernel methods are an import class of techniques in machine learning. To be effective, good feature maps are crucial for mapping non-linearly separable input data into a higher dimensional (feature) space, thus allowing the data to be linearly separable in feature space. Previous work has shown that quantum feature map design can be automated for a given dataset using NSGA-II, a genetic algorithm, while both minimizing circuit size and maximizing classification accuracy. However, the evaluation of the accuracy achieved by a candidate feature map is costly. In this work, we demonstrate the suitability of kernel-target alignment as a substitute for accuracy in genetic algorithm-based quantum feature map design. Kernel-target alignment is faster to evaluate than accuracy and does not require some data points to be reserved for its evaluation. To further accelerate the evaluation of genetic fitness, we provide a method to approximate kernel-target alignment. To improve kernel-target alignment and root mean squared error, the final trainable parameters of the generated circuits are further trained using COBYLA to determine whether a hybrid approach applying conventional circuit parameter training can easily complement the genetic structure optimization approach. A total of eight new approaches are compared to the original across nine varied binary classification problems from the UCI machine learning repository, showing that kernel-target alignment and its approximation produce feature map circuits enabling comparable accuracy to the previous work but with larger margins on training data (in excess of 20% larger) that improve further with circuit parameter training.

Cultural relics fragment assembly based on fracture surface contour features

Addressing the issue of registration deviations caused by local fragment loss and shape diversity during the process of cultural relics fragment assembly, this paper proposes a method for assembling cultural relics fragments based on the contour features of fracture surfaces. Initially, the curvature of discrete point clouds is calculated using the quartic surface method and the Weingarten matrix, and curvature discontinuity points are identified using a proportional method as a candidate feature point set. Subsequently, the angle difference between a point and its neighboring points’ directed segments is defined as a neighborhood feature parameter, which further optimizes the feature point set and selects the optimal matching set. Then the 4-points congruent sets (4PCS) algorithm is utilized for the initial registration of the fragments, and the unit quaternion method is employed to calculate the rigid body transformation matrix during the iteration process. Finally, corresponding point pairs are determined by the intersection of a point’s normal with a set of points, improving the iterative closest point (ICP) algorithm to achieve precise assembly of the fragments. The experimental results show that, compared to other assembly algorithms, the proposed method is more accurate in feature point extraction, robust, and effectively enhances the accuracy and efficiency of fragment assembly.

Clinical Features of Surgery Candidates for Different Types of Extraocular Muscle Palsy

Introduction: Clinical manifestations of cranial nerve palsies are of great importance, and surgeons should consider them before planning surgical protocol. Materials and Methods: This retrospective study was conducted on preoperative hospital records of 598 Iranian patients with different types of extraocular muscle palsy, including third (90 patients), fourth (501 patients), and fifth (7 patients) nerve palsy at Farabi Hospital, Tehran Province, Iran. Results: In terms of fourth nerve palsy, the mean spherical equivalent (SE) in the right and left eye was 0.23±1.51 and 0.19±1.45 diopter, respectively. Also, the mean angle of vertical deviation was 15.54±8.85 Δ at near and 15.66±8.93 Δ at far. In patients with third nerve palsy, the mean SE in the right and left eye was -0.02±2.08 and 0.08±1.95 diopter, respectively. Also, the mean angle of vertical deviation was 17.8±17.4 Δ at near and 17.8±17.5 Δ at far. In terms of six nerve palsy, the mean SE in the right and left eye was -1.27±3.37 and -1.08±2.52 diopter, respectively. Also, the mean angle of esotropia was 32.4±7.7 Δ at near and 33±6.7 Δ at far. The frequency of amblyopia in patients with third, fourth, and sixth nerve palsies was 21 patients (23.3%), 70(14%), and 4(57.1%), respectively. Conclusion: The clinical characteristics of patients with different types of EOM palsy are remarkably different, which can be attributed to the different properties of these kinds of deviations.

Integrative deep learning with prior assisted feature selection.

Integrative analysis has emerged as a prominent tool in biomedical research, offering a solution to the "small and large " challenge. Leveraging the powerful capabilities of deep learning in extracting complex relationship between genes and diseases, our objective in this study is to incorporate deep learning into the framework of integrative analysis. Recognizing the redundancy within candidate features, we introduce a dedicated feature selection layer in the proposed integrative deep learning method. To further improve the performance of feature selection, the rich previous researches are utilized by an ensemble learning method to identify "prior information". This leads to the proposed prior assisted integrative deep learning (PANDA) method. We demonstrate the superiority of the PANDA method through a series of simulation studies, showing its clear advantages over competing approaches in both feature selection and outcome prediction. Finally, a skin cutaneous melanoma (SKCM) dataset is extensively analyzed by the PANDA method to show its practical application.