Full Feature Research Articles

Identify Diabetes-related Targets based on ForgeNet_GPC.

Research on potential therapeutic targets and new mechanisms of action can greatly improve the efficiency of new drug development. Polygenic genetic diseases, such as diabetes, are caused by the interaction of multiple gene loci and environmental factors. In this study, a disease target identification algorithm based on protein recognition is proposed. In this method, the related and unrelated targets are collected from literature databases for treating diabetes. The transcribed proteins corresponding to each target are queried in order to construct a protein dataset. Six protein feature extraction algorithms (AAC, CKSAAGP, DDE, DPC, GAAP, and TPC) are utilized to obtain the feature vectors of each protein, which are merged into the full feature vectors. A novel classifier (forgeNet_GPC) based on forgeNet and Gaussian process classifier (GPC) is proposed to classify the proteins. In forgeNet_GPC, forgeNet is utilized to select the important features, and GPC is utilized to solve the classification problem. The experimental results reveal that forgeNet_GPC performs better than 22 classifiers in terms of ROC-AUC, PR-AUC, MCC, Youden Index, and Kappa.

Robust Cooperative Control for Heterogeneous Uncertain Nonlinear High-Order Fully Actuated Multiagent Systems.

This research is intended to address a robust cooperative control problem of heterogeneous uncertain nonlinear high-order fully actuated multiagent systems (HUN-HOFAMASs). A nonlinear HOFA system model is used to describe the multiagent systems (MASs) with heterogeneous uncertain nonlinear dynamics, which is called the HUN-HOFAMASs. A predictive terminal sliding-mode control-based robust cooperative control scheme is presented to address this problem. In this scheme, heterogeneous nonlinear dynamics of original system are offset to establish a linear constant HOFA system with the help of full actuation feature. Then, a terminal sliding-mode variable for enhancing the system robustness is introduced to handle the uncertainties. Furthermore, a linear incremental prediction model is developed in a HOFA form by means of a Diophantine equation. According to this model, the multistep terminal sliding-mode predictions are yielded to optimize the robust cooperative control performance and compensate for the network-induced communication constraints in the feedback and forward channels. Based on a linear matrix inequality (LMI) method, a necessary and sufficient criterion is derived to discuss the simultaneous consensus and stability of closed-loop HUN-HOFAMASs. The simulation and comparison results of cooperative flying around of multiple spacecraft system are shown to illustrate the capability and advantage of the presented predictive terminal sliding-mode control for robust cooperative control.

Multi-grained alignment method based on stable topics in cross-social networks.

The user alignment of cross-social networks is divided into user and group alignments, respectively. Obtaining users' full features is difficult due to social network privacy protection policies in user alignment mode. In contrast, the alignment accuracy is low due to the large number of edge users in the group alignment mode. To resolve this issue, First, stable topics are obtained from user-generated content (UGC) based on embedded topic jitter time, and the weight of user edges is updated by using vector distances. An improved Louvain algorithm, called Stable Topic-Louvain (ST-L), is designed to accomplish multi-level community detection without predetermined tags. It aims to obtain fuzzy topic features of the community and finalize the community alignment across social networks. Furthermore, iterative alignment is executed from coarse-grained communities to fine-grained sub-communities until user-level alignment occurs. The process can be terminated at any layer to achieve multi-granularity alignment, which resolves the low accuracy issue of edge user alignment at a single granularity and improves the accuracy of user alignment. The effectiveness of the proposed method is shown by implementing real datasets.

Optical properties of cotton and mulching film and feature bands selection in the 400 to 1120 nm range

Cotton is prone to being mixed with mulching film during the harvesting and packing process in China, which can significantly decrease the quality of cotton fiber and impact the quality of subsequent textile products. Mulching film is a translucent material that makes it challenging to detect optically, which presents an urgent challenge for cotton quality testing due to the lack of research on its detection mechanism. In this study, the absorption coefficient (μa), reduced scattering coefficient (μs'), and scattering anisotropy factor (g) of cotton lint and mulching film in the spectral region of 400–1120 nm were obtained using an integrating sphere-based spectroscopic measurement system. The accuracy of the system was validated using liquid phantoms made from polystyrene particles and absorbing dyes. The interval random frog (iRF) algorithm was used to select feature bands, and multivariate analysis of variance (MANOVA) was employed to assess the differences between cotton and mulching film in terms of μa and μs' in the selected feature bands. Support vector machine (SVM) and linear discriminant analysis (LDA) were utilized to classify the concatenation of μa, μs', μa and μs' of cotton and mulching film in full wavelengths and feature bands. The results demonstrated that there were significant differences in μa, μs' and g between cotton and mulching film due to their different chemical compositions, surface morphology, and tensile properties. The selected feature bands were in the blue band (456.1 nm), red bands (605.8 nm, 628.9 nm, 685.6 nm), and near-infrared bands (805.4 nm, 837 nm, 1006.3 nm). The SVM classification results of the concatenation of μa, μs', μa and μs' for cotton and mulching film were 100 % in both full wavelengths and feature bands. This study makes a significant contribution by reporting the optical properties of cotton and mulching film, which were used to determine the detection sensitive bands. These findings will serve as a theoretical foundation and data set for the development of detection equipment to identify mulching film in the cotton production process.

Human Emotion Recognition Based on Machine Learning Algorithms with low Resource Environment

It is difficult to discover significant audio elements and conduct systematic comparison analyses when trying to automatically detect emotions in speech. In situations when it is desirable to reduce memory and processing constraints, this research deals with emotion recognition. One way to achieve this is by reducing the amount of features. In this study, propose "Active Feature Selection" (AFS) method and compares it against different state-of-the-art techniques. According to the results, smaller subsets of features than the complete feature set can produce accuracy that is comparable to or better than the full feature set. The memory and processing requirements of an emotion identification system will be reduced, which can minimise the hurdles to using health monitoring technology. The results show by using 696 characteristics, the AFS technique for emobase yields a Unweighted average recall (UAR) of 75.8%.

A machine learning-based prediction model for postoperative delirium in cardiac valve surgery using electronic health records

BackgroundPrevious models for predicting delirium after cardiac surgery remained inadequate. This study aimed to develop and validate a machine learning-based prediction model for postoperative delirium (POD) in cardiac valve surgery patients.MethodsThe electronic medical information of the cardiac surgical intensive care unit (CSICU) was extracted from a tertiary and major referral hospital in southern China over 1 year, from June 2019 to June 2020. A total of 507 patients admitted to the CSICU after cardiac valve surgery were included in this study. Seven classical machine learning algorithms (Random Forest Classifier, Logistic Regression, Support Vector Machine Classifier, K-nearest Neighbors Classifier, Gaussian Naive Bayes, Gradient Boosting Decision Tree, and Perceptron.) were used to develop delirium prediction models under full (q = 31) and selected (q = 19) feature sets, respectively.ResultThe Random Forest classifier performs exceptionally well in both feature datasets, with an Area Under the Curve (AUC) of 0.92 for the full feature dataset and an AUC of 0.86 for the selected feature dataset. Additionally, it achieves a relatively lower Expected Calibration Error (ECE) and the highest Average Precision (AP), with an AP of 0.80 for the full feature dataset and an AP of 0.73 for the selected feature dataset. To further evaluate the best-performing Random Forest classifier, SHAP (Shapley Additive Explanations) was used, and the importance matrix plot, scatter plots, and summary plots were generated.ConclusionsWe established machine learning-based prediction models to predict POD in patients undergoing cardiac valve surgery. The random forest model has the best predictive performance in prediction and can help improve the prognosis of patients with POD.

Discriminative feature selection using signed Laplacian restricted Boltzmann machine for speed and generalization improvement of high dimensional data classification

Deep classifiers require lots of computations due to the use of multi-layer structure and processing of bulk input samples. Selecting effective features that have the same accuracy as full features, has recently been considered. Using feature selection, less calculation is needed to update the weights and consequently the speed of the training/testing process is increased. In this research, a new deep feature selection method called Discriminative Deep Feature Selection using Signed Laplacian Restricted Boltzmann Machine (DDFS-SLRBM) is proposed. In the approach, full training samples are fed into a SLRBM model. In the updates, the weight matrix is recomputed using the neighborhood matrix of similar and dissimilar classes which results in the discriminative property of the approach. Then, selected features are identified based on the minimum reconstruction error criterion. The efficiency of the proposed algorithm is demonstrated by performing different experiments on MNIST, GISETTE and Protein datasets. The experiments show that the proposed method is able to improve the classification accuracy and the generalizability of the approach while reducing the processing time. Also, the proposed approach shows scalability on the type of the problem, number of original features, number of samples and the number of final selected features.

Application of UAV-Borne Visible-Infared Pushbroom Imaging Hyperspectral for Rice Yield Estimation Using Feature Selection Regression Methods

Rice yield estimation is vital for enhancing food security, optimizing agricultural management, and promoting sustainable development. However, traditional satellite/aerial and ground-based/tower-based platforms face limitations in rice yield estimation, and few studies have explored the potential of UAV-borne hyperspectral remote sensing for this purpose. In this study, we employed a UAV-borne push-broom hyperspectral camera to acquire remote sensing data of rice fields during the filling stage, and the machine learning regression algorithms were applied to rice yield estimation. The research comprised three parts: hyperspectral data preprocessing, spectral feature extraction, and model construction. To begin, the preprocessing of hyperspectral data involved geometric distortion correction, relative radiometric calibration, and rice canopy mask construction. Challenges in geometric distortion correction were addressed by tracking linear features during flight and applying a single-line correction method. Additionally, the NIR reflectance threshold method was applied for rice canopy mask construction, which was subsequently utilized for average reflectance extraction. Then, spectral feature extraction was carried out to reduce multicollinearity in the hyperspectral data. Recursive feature elimination (RFE) was then employed to identify the optimal feature set for model performance. Finally, six machine learning regression models (SVR, RFR, AdaBoost, XGBoost, Ridge, and PLSR) were used for rice yield estimation, achieving significant results. PLSR showed the best R2 of 0.827 with selected features, while XGBoost had the best R2 of 0.827 with full features. In addition, the spatial distribution of absolute error in rice yield estimation was assessed. The results suggested that this UAV-borne imaging hyperspectral-based approach held great potential for crop yield estimation, not only for rice but also for other crops.

Fractal feature selection model for enhancing high-dimensional biological problems

The integration of biology, computer science, and statistics has given rise to the interdisciplinary field of bioinformatics, which aims to decode biological intricacies. It produces extensive and diverse features, presenting an enormous challenge in classifying bioinformatic problems. Therefore, an intelligent bioinformatics classification system must select the most relevant features to enhance machine learning performance. This paper proposes a feature selection model based on the fractal concept to improve the performance of intelligent systems in classifying high-dimensional biological problems. The proposed fractal feature selection (FFS) model divides features into blocks, measures the similarity between blocks using root mean square error (RMSE), and determines the importance of features based on low RMSE. The proposed FFS is tested and evaluated over ten high-dimensional bioinformatics datasets. The experiment results showed that the model significantly improved machine learning accuracy. The average accuracy rate was 79% with full features in machine learning algorithms, while FFS delivered promising results with an accuracy rate of 94%.

Supervised Feature Selection based on the Law of Total Variance

Feature selection is a fundamental pre-processing step in machine learning that decreases data dimensionality by removing superfluous and irrelevant features. This study proposes a supervised feature selection method based on feature relevance by employing the law of total variance (LTV). Specifically, the LTV is used to quantify the relevance of features by analysing the association between features and class label. Six classifiers were employed to evaluate the performance and reliability of the proposed method pertaining to classification accuracy. The results proved that a feature subset given by the proposed method has the capability to achieve comparable classification accuracy to the full feature set when just half or less than half of the original features are retained. The proposed method was also proven to be versatile as it can achieves adequate classification accuracy with all six classifiers with different learning schemes. In addition, a comparison with a similar type of feature selection method (AmRMR) shows that the proposed method yields a more accurate classification.

Machine Learning Prediction of the Experimental Transition Temperature of Fe(II) Spin-Crossover Complexes.

Spin-crossover (SCO) complexes are materials that exhibit changes in the spin state in response to external stimuli, with potential applications in molecular electronics. It is challenging to know a priori how to design ligands to achieve the delicate balance of entropic and enthalpic contributions needed to tailor a transition temperature close to room temperature. We leverage the SCO complexes from the previously curated SCO-95 data set [Vennelakanti et al. J. Chem. Phys. 159, 024120 (2023)] to train three machine learning (ML) models for transition temperature (T1/2) prediction using graph-based revised autocorrelations as features. We perform feature selection using random forest-ranked recursive feature addition (RF-RFA) to identify the features essential to model transferability. Of the ML models considered, the full feature set RF and recursive feature addition RF models perform best, achieving moderate correlation to experimental T1/2 values. We then compare ML T1/2 predictions to those from three previously identified best-performing density functional approximations (DFAs) which accurately predict SCO behavior across SCO-95, finding that the ML models predict T1/2 more accurately than the best-performing DFAs. In addition, we study ML model predictions for a set of 18 SCO complexes for which only estimated T1/2 values are available. Upon excluding outliers from this set, the RF-RFA RF model shows a strong correlation to estimated T1/2 values with a Pearson's r of 0.82. In contrast, DFA-predicted T1/2 values have large errors and show no correlation to estimated T1/2 values over the same set of complexes. Overall, our study demonstrates slightly superior performance of ML models in comparison with some of the best-performing DFAs, and we expect ML models to improve further as larger data sets of SCO complexes are curated and become available for model training.

Curriculum Consistency Learning and Multi-Scale Contrastive Constraint in Semi-Supervised Medical Image Segmentation.

Data scarcity poses a significant challenge in medical image segmentation, thereby highlighting the importance of leveraging sparse annotation data. In addressing this issue, semi-supervised learning has emerged as an effective approach for training neural networks using limited labeled data. In this study, we introduced a curriculum consistency constraint within the context of semi-supervised medical image segmentation, thus drawing inspiration from the human learning process. By dynamically comparing patch features with full image features, we enhanced the network's ability to learn. Unlike existing methods, our approach adapted the patch size to simulate the human curriculum process, thereby progressing from easy to hard tasks. This adjustment guided the model toward improved convergence optima and generalization. Furthermore, we employed multi-scale contrast learning to enhance the representation of features. Our method capitalizes on the features extracted from multiple layers to explore additional semantic information and point-wise representations. To evaluate the effectiveness of our proposed approach, we conducted experiments on the Kvasir-SEG polyp dataset and the ISIC 2018 skin lesion dataset. The experimental results demonstrated that our method surpassed state-of-the-art semi-supervised methods by achieving a 9.2% increase in the mean intersection over union (mIoU) for the Kvasir-SEG dataset. This improvement substantiated the efficacy of our proposed curriculum consistency constraint and multi-scale contrastive loss.

An inpatient fall risk assessment tool: Application of machine learning models on intrinsic and extrinsic risk factors

BackgroundThis study aimed to identify the most impactful set of intrinsic and extrinsic fall risk factors and develop a data-driven inpatient fall risk assessment tool (FRAT). MethodsThe dataset used for the study comprised in-hospital fall records from 2012 to 2017. Four machine learning (ML) algorithms, Support Vector Machine (SVM), Random Forest (RF), Gradient Boosting (Gboost), and Deep Neural Network (DNN) were utilized to predict the inpatient fall risk level. To enhance the performance of the prediction models, two approaches were implemented, including (1) feature selection to identify the optimal feature set and (2) the development of three distinct shift-wise models. Furthermore, the optimal feature sets in the shift-wise models were extracted. ResultsAccording to the results, DNN outperformed other methods by reaching an accuracy, sensitivity, specificity, and AUC of 0.71, 0.8, 0.6, and 0.7, respectively, considering the full set of features. The performance of the models was further improved (by 3-5 %) by conducting a feature selection process for all models. Specifically, the DNN model achieved an accuracy of 0.74 while considering the optimal set of predictors. Moreover, the shift-wise RF models demonstrated higher accuracies (by 4-10 %) compared to the same model using a full feature set. ConclusionsThis study's outcome confirms ML models' compelling capability in developing an inpatient FRAT while considering intrinsic and extrinsic factors. The insight from such models could form a foundation to (1) monitor the inpatients’ fall risk, (2) identify the major factors involved in inpatient falls, and (3) create subject-specific self-care plans.

Designing accurate lightweight intrusion detection systems for IoT networks using fine-tuned linear SVM and feature selectors

Intrusion detection systems (IDSs) play a crucial role in ensuring the security and integrity of Internet of Things (IoT) networks by blocking unwanted packets and facilitating secure traffic flow. However, traditional IDSs based on data mining, fuzzy logic, heuristics, rough sets, or conventional machine learning (ML) techniques often lack accuracy and are not energy efficient, primarily due to inappropriate feature selection or the use of all features in datasets. To address these challenges, this study proposes a lightweight, accurate, and high-performance IDSs for IoT networks using fine-tuned Linear Support Vector Machines (LSVMs) and feature selection methods. Four feature selectors, including Importance Coefficient-, Forward- and Backward-Sequential-, and Correlation Coefficient-based approaches, were applied to identify the most important and efficient features from three datasets: KDD Cup-1999, BotIoT-2018, and N-BaIoT-2021. The fine-tuned LSVMs algorithm was then trained on subsets of the selected and full features of the datasets to detect various IoT botnet attacks. Evaluation results show that the IDS models trained with subsets of relevant features outperform those trained with the full feature sets of the datasets in terms of training and test performance and accuracy. The study concludes that it is possible to develop lightweight IDSs by training them with a reduced number of features (6) instead of using the full features (40, 15, 115) in KDD Cup-1999, BotIoT-2018, and N-BaIoT-2021, respectively. The findings highlight a potential for significantly improving the efficiency and accuracy of IDSs on IoT networks using the fine-tuned feature selectors and LSVMs.

A Hybrid Dimensionality Reduction for Network Intrusion Detection

Due to the wide variety of network services, many different types of protocols exist, producing various packet features. Some features contain irrelevant and redundant information. The presence of such features increases computational complexity and decreases accuracy. Therefore, this research is designed to reduce the data dimensionality and improve the classification accuracy in the UNSW-NB15 dataset. It proposes a hybrid dimensionality reduction system that does feature selection (FS) and feature extraction (FE). FS was performed using the Recursive Feature Elimination (RFE) technique, while FE was accomplished by transforming the features into principal components. This combined scheme reduced a total of 41 input features into 15 components. The proposed systems’ classification performance was determined using an ensemble of Support Vector Classifier (SVC), K-nearest Neighbor classifier (KNC), and Deep Neural Network classifier (DNN). The system was evaluated using accuracy, detection rate, false positive rate, f1-score, and area under the curve metrics. Comparing the voting ensemble results of the full feature set against the 15 principal components confirms that reduced and transformed features did not significantly decrease the classifier’s performance. We achieved 94.34% accuracy, a 93.92% detection rate, a 5.23% false positive rate, a 94.32% f1-score, and a 94.34% area under the curve when 15 components were input to the voting ensemble classifier.

Abstract 13871: Portrayal of Acute Myocardial Infarction in Popular Film

Introduction: The representation of cardiovascular disease (CVD) in popular media plays a pivotal role in shaping public conceptions about CV health. CVD is the leading cause of death among women and disproportionately affects racial/ethnic minority populations in the United States, yet recent national surveys indicate a significant decline in public awareness. Our study sought to investigate the portrayal of acute myocardial infarction (AMI) in popular film. Hypothesis: Portrayal of AMI in film will predominantly show white men exhibiting symptoms of chest pain. Women, racial/ethnic minority populations, and subtle symptoms of AMI will be underrepresented. Aims: To examine 100 full length feature film scenes depicting AMI and evaluate the representation of gender, race/ethnicity, and symptoms. Methods: The 100 most popular films with scenes depicting AMI were identified using the Internet Movie Database (IMDb). Scenes and AMI symptoms were analyzed by cardiologists/cardiology fellows. Gender and race/ethnicity were acquired via movie plots/scripts or via actor self-identification if the former was unavailable. Results: Of the 100 scenes analyzed, 10% depicted women. The representation of people of color was only 6% in contrast to the 94% of scenes featuring non-Hispanic whites. Of the 10 women portrayed, 1 was non-white. The distribution of gender and race/ethnicity for all scenes is shown in Figure 1. The most prevalent presenting symptom observed in 65% of scenes was chest pain accompanied by loss of consciousness. Conclusions: Popular film depictions of AMI appear to be under representative of women and racial/ethnic minority populations. This may be a contributing factor to the inaccurate public perception that CVD does not affect these populations. Film depictions of AMI, which predominantly portray dramatic symptoms of chest pain and loss of consciousness may also perpetuate false beliefs on typical (or even atypical) symptoms of AMI.

Non-destructive prediction of TVB-N using color-texture features of UV-induced fluorescence image for freeze-thaw treated frozen-whole-round tilapia.

The investigation of UV-induced fluorescence imaging coupled with machine learning was conducted to non-destructively detect the total volatile basic nitrogen (TVB-N) of frozen-whole-round tilapia (FWRT) during freezing and thawing. The UV-induced fluorescence images of FWRT at the wavelength of 365 nm were acquired by self-developed fluorescence image acquisition system. In total, 169 color and texture features based on RGB, hue-saturation-intensity and L*a*b* color spaces and gray level co-occurrence matrix were extracted, respectively. Successive projections algorithm (SPA) was employed to select the optimal 16 features to achieve feature dimension reduction modeling. With full and extracted features as input, the models of partial least squares regression (PLSR), least-squares support vector machine (LSSVM) and convolutional neural network (CNN) were established for TVB-N prediction. Results indicated that the full features-based CNN performed better than SPA based prediction models (SPA-PLSR and SPA-LSSVM). The CNN model was determined to be the optimal with an RP2 value of 0.9779, RMSEP value of 1.1502 × 10-2 g N kg-1 and RPD value of 6.721 for TVB-N content predictiin. The CNN method based on UV fluorescence imaging technology has potential for quality and safety detection of FWRT. © 2023 Society of Chemical Industry.

UP-Net: Uncertainty-Supervised Parallel Network for Image Manipulation Localization

Image manipulation localization remains a hot topic due to its inherent semantic-independent nature and realistic needs. Virtually all localization studies are devoted to solving arbitrary tampering using multi-branch networks based on deep features or skip-connection structures based on full features, which may induce the loss of manipulation details or noisy interference from image semantics. This poses a challenge for existing localization methods to fully capture invisible manipulations, especially in post-processing settings and across dataset scenarios. To address the above issues, we propose an uncertainty-supervised parallel network (UP-Net) for image tampering localization that preserves more manipulation details while avoiding semantic noise. UP-Net cascades the frequency and RGB domains of the manipulated image as dual-domain embedding, instead of dual-domain parallel learning as in previous work. To learn semantic-independent manipulation features, two structurally identical parallel branches are designed to learn tampering inconsistencies from intermediate and deep coding features for gradually obtaining the initial and final localization predictions. Where attention-guided partial decoder (AGPD) integrates more precise manipulation edges and manipulation semantics without introducing additional noise by focusing on channel correlation and spatial dependence, making a significant contribution to performance. Moreover, the new concept of uncertainty-constrained loss supervision is introduced to guide UP-Net to continuously improve confidence in locating difficult pixels, which are easily misclassified due to post-processing operations. Experiments on three public manipulation datasets and two real challenge datasets show that our end-to-end UP-Net achieves significant performance in manipulation localization, generalization across datasets, and robustness compared to state-of-the-art methods.

45 The Influence of Wearing Face Mask on Facial Emotion Recognition in Preschoolers

Objective:During the COVID-19 pandemic, wearing face masks is an important strategy to prevent people from infection, allowing people to find a balance between maintaining social interaction and keeping social distancing. Since face mask might disrupt information processing of social cognition, it could lead to less functional connectivity of occipital face area, fusiform face area, and superior temporal sulcus which interrupted the development of medial prefrontal cortex (MPFC) for mentalizing. However with better executive function (EF) people could process facial stimuli more efficiently. The objective of this study is to examine the effect of wearing face masks on preschoolers' facial emotion recognition, and the factors which might affect the development of facial emotion recognition.Participants and Methods:In this study, preschoolers (N=44, 24 boys and 20 girls, aged 3 to 5 years-old) recruited from the community were asked to identify the emotions expressed in the 36 stimulus photos, each randomly presented with six emotion (happy, sad, angry, surprised, fearful, and disgusted). The total face stimulus photos were 2 (face sex) × 6 emotions × 3 facial features (full face, presenting upper counterparts of face with face mask covering the mouth, and presenting lower counterparts of face with hat covering the eyes). The EF of preschoolers and their parent were also evaluated to examine whether EF could predict the correct score of facial emotion recognition.Results:It was found that the correct score of emotion recognition increased with age. The recognition with full face feature were better than with upper feature and lower feature. When recognizing happy and disgust, participant tended to use lower features. When recognizing sad and angry, participant tended to use upper features. The EF of preschoolers could predict the correct score of emotion recognition. The EF of parents could predict the preschoolers' correct score of positive emotion recognition.Conclusions:The ability of facial emotion recognition evolved rapidly in preschool age with the accumulation of social interaction experience and improved the development of auditory and visual subcortical cortex and the connectivity of MPFC. This study examined the emotion recognition ability of preschoolers and found that the face features preschoolers used to recognized emotion were consist with previous study. However, when the presenting stimulus were covered by face mask or hat, it was more difficult for preschoolers to recognizing emotion which would result in difficulty of understanding the social context and development of MPFC for mentalizing. In this study, it was found that preschooler's with better EF could be more efficiently recognizing facial emotion. Also, parents with better EF showed more positive emotion in daily life which lead to their children more sensitive to positive facial emotion.

Intelligent Fault Diagnosis of Rolling Bearings Based on a Complete Frequency Range Feature Extraction and Combined Feature Selection Methodology

The utilization of multiscale entropy methods to characterize vibration signals has proven to be promising in intelligent diagnosis of mechanical equipment. However, in the current multiscale entropy methods, only the information in the low-frequency range is utilized and the information in the high-frequency range is discarded. In order to take full advantage of the information, in this paper, a fault feature extraction method utilizing the bidirectional composite coarse-graining process with fuzzy dispersion entropy is proposed. To avoid the redundancy of the full frequency range feature information, the Random Forest algorithm combined with the Maximum Relevance Minimum Redundancy algorithm is applied to feature selection. Together with the K-nearest neighbor classifier, a rolling bearing intelligent diagnosis framework is constructed. The effectiveness of the proposed framework is evaluated by a numerical simulation and two experimental examples. The validation results demonstrate that the extracted features by the proposed method are highly sensitive to the bearing health conditions compared with hierarchical fuzzy dispersion entropy, composite multiscale fuzzy dispersion entropy, multiscale fuzzy dispersion entropy, multiscale dispersion entropy, multiscale permutation entropy, and multiscale sample entropy. In addition, the proposed method is able to identify the fault categories and health states of rolling bearings simultaneously. The proposed damage detection methodology provides a new and better framework for intelligent fault diagnosis of rolling bearings in rotating machinery.