- Advanced Statistical Modeling Techniques
- Sensory Analysis and Statistical Methods
- Advanced Neural Network Applications
- Advanced Image and Video Retrieval Techniques
- Mental Health Research Topics
- Psychometric Methodologies and Testing
- Data Management and Algorithms
- Cognitive Abilities and Testing
- Algorithms and Data Compression
- Visual Attention and Saliency Detection
- Machine Learning and Data Classification
- Robotics and Sensor-Based Localization
- stochastic dynamics and bifurcation
- Advanced Algorithms and Applications
- Infrared Target Detection Methodologies
- Control Systems and Identification
- Graph Theory and Algorithms
- Advanced Measurement and Detection Methods
- Video Surveillance and Tracking Methods
- Matrix Theory and Algorithms
- Optimal Experimental Design Methods
- Bayesian Modeling and Causal Inference
- Image and Object Detection Techniques
- Neural Networks Stability and Synchronization
- Domain Adaptation and Few-Shot Learning
Yanbian University Hospital
2025
University of Notre Dame
2010-2024
Chongqing University of Technology
2011-2024
Tianjin University of Technology and Education
2024
Harbin Engineering University
2023
UNSW Sydney
2022-2023
Wuzhou University
2023
Guizhou University
2022
Institute of Art
2022
Sichuan Institute of Building Research
2017
A central problem in the application of exploratory factor analysis is deciding how many factors to retain (m). Although this inherently a model selection problem, perspective rarely adopted for task. We suggest that Cudeck and Henly's (1991) framework can be applied guide process. Researchers must first identify analytic goal: identifying (approximately) correct m or most replicable m. Second, researchers choose fit indices are congruent with their goal. Consistent theory, simulation study...
ABSTRACT Years of attraction research have established several “principles” with robust evidence. However, a major limitation previous studies is that they almost exclusively relied on well‐controlled experiments, which are often criticized for lacking ecological validity. The current was designed to examine initial in real‐life setting—speed‐dating. Social Relations Model analyses demonstrated function the actor, partner, and unique dyadic relationship between these two. Meta‐analyses...
ABSTRACT Past research on the link between personal characteristics and marital satisfaction has taken either an individual or a dyadic approach. The approach examines how self and/or partner are associated with satisfaction, whereas focuses couple such as similarity. current was designed to integrate both approaches. A modified Actor‐Partner Interdependence Model ( Kashy & Kenny, 2000 ) proposed test simultaneously contributions of characteristics, two types similarity level measured by...
In exploratory factor analysis, rotation is conducted to improve model interpretability. A promising and increasingly popular method geomin rotation. Geomin rotation, however, frequently encounters multiple local solutions. We report a simulation study that explores the frequency of solutions in implications such phenomena. The findings include: (1) exist for variety situations; (2) ϵ = .01 provides satisfactory rotated loadings most (3) 100 random starts appear sufficient examine solution...
With the development of automatic driving technology, traffic sign detection has become a very important task. However, it is challenging task because complex scene and small size target. In recent years, number convolutional neural network (CNN) based object methods have brought great progress to detection. Considering still high false rate, as well time overhead computational overhead, effect not satisfactory. Therefore, we employ lightweight model YOLO v5 (You Only Look Once) our work...
Dynamic factor analysis models with time-varying parameters offer a valuable tool for evaluating multivariate time series data dynamics and/or measurement properties. We use the Model of Activation proposed by Zautra and colleagues (Zautra, Potter, & Reich, 1997) as motivating example to construct dynamic model vector autoregressive relations cross-regression at level. Using techniques drawn from state-space literature, was fitted set daily affect (over 71 days) 10 participants who had been...
Misalignment is an important cause for the early failure of large doubly-fed wind turbines (DFWT). For non-stationary characteristics signals in transmission system DFWT and reality that it difficult to obtain a number fault samples, Solidworks Adams are used simulate different operating conditions corresponding characteristic signals. Improved empirical mode decomposition (IEMD), which improves end effects (EMD) decompose get intrinsic function (IMF), IEMD energy entropy reflecting working...
<title>Abstract</title> <bold>Background:</bold>Spinal cord cysticercosis, a rare subtype of neurocysticercosis (NCC), primarily affects the subarachnoid space. The optimal treatment approach remains uncertain, with both pharmacological and surgical strategies being employed. Spinal stimulation (SCS) has been established as safe effective therapy for chronic pain,we present case neuropathic pain caused by spinal successfully managed SCS. <bold>Case presentation:</bold>A 69-year-old female...
Abstract Emotional memory bias is a common characteristic of internalizing symptomatology and enhanced during sleep. The current study employs bifactor S-1 modeling to disentangle depression-specific anhedonia, anxiety-specific anxious arousal, the factor, general distress, test whether these symptoms interact with sleep influence for emotional neutral information. Healthy adults ( N = 281) encoded scenes featuring either negative objects (e.g., vicious looking snake) or chipmunk) placed on...
Factor rotation is conducted to aid interpretation in exploratory factor analysis (EFA). Target allows researchers directly examine the match between rotated loading matrix and their expected pattern. In some EFA applications, however, have expectations on both pattern correlation We propose extend target such that values can be specified for loadings correlations. illustrate extended with a memory study personality multitrait-multimethod design. also explore statistical properties of using...
In this article, we report a surprising phenomenon: Oblique CF-varimax and oblique CF-quartimax rotation produced similar point estimates for rotated factor loadings correlations but different standard error in an empirical example. Influences of on asymptotic errors are investigated using numerical exploration method. The results (a) CF-varimax, CF-quartimax, CF-equamax, CF-parsimax when the loading matrix is independent cluster solution (b) four methods has more complex structure....
The goal of Generalized Zero-Shot Learning (GZSL) methods is to classify unseen classes during testing, where no available data provided training. Unlike zero-shot recognition, test samples GZSL include both seen and classes. Current feature generation are based on generative adversarial networks, which synthesize visual features for using their semantic descriptors. However, these still struggle address the bias between Therefore, this paper proposes a Semantic Feedback (SF) module models...
Dynamic factor analysis summarizes changes in scores on a battery of manifest variables over repeated measurements terms time series substantially smaller number latent factors. Algebraic formulae for standard errors parameter estimates are more difficult to obtain than the usual intersubject because interdependence successive observations. Bootstrap methods can fill this need, however. The bootstrap individual timepoints is not appropriate it destroys their order and consequently gives...
P-technique factor analysis is an exploratory model for multivariate time series data. Assessing fit of models non-trivial because data are correlated at nearby points. We present a test statistic that appropriate analysis. In addition, the allows researchers to quantify amount error. explore statistical properties with simulated and we illustrate its use empirical study personality states. Results simulation include (1) distributions approximately followed their respective theoretical...
Continuous‐time modelling remains a somewhat ‘idealized’ representation tool. Even though conceptualizing dynamic process as continuous has clear appeal from theoretical standpoint, practical tools that allow researchers to effectively map an idealized model onto set of discrete‐time observed data are still lacking data. Irregularly spaced longitudinal frequently arise in empirical settings because the prevalence studies with partially randomized measurement intervals and other related...