Publications by authors named "Cheng-Kai Lu"

Conventional thresholding techniques for graph theory analysis, such as absolute, proportional and mean degree, have often been used in characterizing human brain networks under different mental disorders, such as mental stress. However, these approaches may not always be reliable as conventional thresholding approaches are subjected to human biases. Using a mental resilience study, we investigate if data-driven thresholding techniques such as Global Cost Efficiency (GCE-abs) and Orthogonal Minimum Spanning Trees (OMSTs) could provide equivalent results, whilst eliminating human biases.

View Article and Find Full Text PDF

Artificial intelligence has revolutionised smart medicine, resulting in enhanced medical care. This study presents an automated detector chip for age-related macular degeneration (AMD) using a support vector machine (SVM) and three-dimensional (3D) optical coherence tomography (OCT) volume. The aim is to assist ophthalmologists by reducing the time-consuming AMD medical examination.

View Article and Find Full Text PDF

Although iron (Fe) deficiency is an adverse condition to growth and development of plants, it increases the resistance to pathogens. How Fe deficiency induces the resistance to pathogens is still unclear. Here, we reveal that the inoculation of Botrytis cinerea activates the Fe deficiency response of plants, which further induces ethylene synthesis and then resistance to B.

View Article and Find Full Text PDF

Neuroticism has recently received increased attention in the psychology field due to the finding of high implications of neuroticism on an individual's life and broader public health. This study aims to investigate the effect of a brief 6-week breathing-based mindfulness intervention (BMI) on undergraduate neurotic students' emotion regulation. We acquired data of their psychological states, physiological changes, and electroencephalogram (EEG), before and after BMI, in resting states and tasks.

View Article and Find Full Text PDF
Article Synopsis
  • Visual odometry estimates a camera's position in 3D space for autonomous driving, and new methods are emerging that don't need camera calibration and are resilient to noise.
  • A new technique called "windowed pose optimization network" is introduced, which also avoids camera calibration and accurately determines the 6 degrees of freedom for a monocular camera using a supervised learning approach.
  • Evaluated on the KITTI dataset, this method achieved a rotational error of 3.12 degrees per 100 meters, with quick training (41.32 ms) and inference times (7.87 ms), proving its competitive performance against existing techniques.
View Article and Find Full Text PDF

IRON MAN (IMA) peptides, a family of small peptides, control iron (Fe) transport in plants, but their roles in Fe signaling remain unclear. BRUTUS (BTS) is a potential Fe sensor that negatively regulates Fe homeostasis by promoting the ubiquitin-mediated degradation of bHLH105 and bHLH115, two positive regulators of the Fe deficiency response. Here, we show that IMA peptides interact with BTS.

View Article and Find Full Text PDF
Article Synopsis
  • * This paper introduces a modified SegNet model, utilizing convolutional neural networks with enhancements like skip connections and dilated convolutions, aimed at automating polyp segmentation in colonoscopy images.
  • * The model showed impressive performance metrics (e.g., 96.06% accuracy) when tested on multiple databases, indicating its potential to improve colorectal cancer diagnosis and management, with plans to further integrate it into a medical capsule robot for real-world applications.
View Article and Find Full Text PDF
Article Synopsis
  • * It focuses on analyzing olfactory stimuli and their effects on hemodynamic response functions (HRF) related to oxygen levels, using different SVM kernel functions (linear, quadratic, cubic) for data analysis.
  • * The findings indicate that a quadratic kernel function effectively classifies olfactory stimuli using oxyhemoglobin data, while a cubic function works best for combined HRF and photoplethysmography signals, showcasing a strong ability to classify olfactory responses accurately.
View Article and Find Full Text PDF

Background And Objective: The increased incidence of colorectal cancer (CRC) and its mortality rate have attracted interest in the use of artificial intelligence (AI) based computer-aided diagnosis (CAD) tools to detect polyps at an early stage. Although these CAD tools have thus far achieved a good accuracy level to detect polyps, they still have room to improve further (e.g.

View Article and Find Full Text PDF
Article Synopsis
  • This study introduces a new analytical framework using machine learning to identify dynamic task-based functional connectivity (FC) features as biomarkers for emotional sensitivity in nursing students, utilizing functional Near-Infrared Spectroscopy (fNIRS) technology.
  • Through a sliding window correlation analysis, researchers discovered four recurring connectivity states, leading to findings that nursing students were more affected by emotional stimuli compared to registered nurses, who showed a single task-relevant state.
  • The study highlights that the dynamic FC features were more accurate indicators of emotional sensitivity (81.65%) than traditional heart rate variability measures (71.03%) and suggests potential applications in professional training for nursing regarding emotional sensitivity.
View Article and Find Full Text PDF
Article Synopsis
  • Improper baseline return from previous tasks can cause variations in hemodynamic responses (HR), influencing the measurement of mental workload in brain-computer interface systems.
  • * The study introduces a method called vector phase analysis to identify whether the baseline state is optimal or suboptimal, aiming to enhance mental workload estimation.
  • * Findings show significant differences in HR between optimal and suboptimal baseline blocks, supporting the method's effectiveness and emphasizing the importance of tailored recovery durations.
View Article and Find Full Text PDF

This study aims to investigate the generalizability of the semi-metric analysis of the functional connectivity (FC) for functional near-infrared spectroscopy (fNIRS) by applying it to detect the dichotomy in differential FC under affective and neutral emotional states in nursing students and registered nurses during decision making. The proposed method employs wavelet transform coherence to construct FC networks and explores semi-metric analysis to extract network redundancy features, which has not been considered in conventional fNIRS-based FC analyses. The trials of the proposed method were performed on 19 nursing students and 19 registered nurses via a decision-making task under different emotional states induced by affective and neutral emotional stimuli.

View Article and Find Full Text PDF
Article Synopsis
  • Understanding the level of mental workload is crucial for effective brain-computer interface (BCI) cognitive training, as relying on limited brain area signals can lead to inaccurate assessments.
  • The study utilized a multi-channel fNIRS device to develop a new analytical framework that includes a new feature called deep contribution ratio, alongside traditional measures, to more accurately assess mental workload in the prefrontal cortex.
  • The framework demonstrated improved performance, achieving an average accuracy of 80.6% in classifying mental workload levels compared to only 59.8% with conventional methods, highlighting its potential for better BCI applications.
View Article and Find Full Text PDF
Article Synopsis
  • The study addresses issues with analyzing brain networks using non-standardized methods, particularly in the context of measuring brain health through functional integration.
  • A new technique was developed, involving wavelet analysis for correcting motion and using orthogonal minimal spanning trees (OMSTs) for assessing brain connectivity with functional near-infrared spectroscopy (fNIRS).
  • When tested against established methods on an Alzheimer's disease dataset, the new technique not only outperformed these benchmarks in identifying cost-effective networks but also effectively differentiated between mild AD patients and healthy individuals, highlighting its potential for diagnosing Alzheimer's.
View Article and Find Full Text PDF
Article Synopsis
  • * This study analyzes RA and orthopedic datasets using Ensemble methods, including classifiers like bagging, Adaboost, and random subspace, with k-NN and Random Forest as base learners.
  • * Results show that the random subspace classifier with k-NN achieved the best accuracy of 97.50% for the RA dataset, while bagging with Random Forest reached 94.84% for the orthopedic dataset, highlighting the efficiency of different classification approaches.
View Article and Find Full Text PDF

Alzheimer's disease is characterized by the progressive deterioration of cognitive abilities particularly working memory while mild cognitive impairment (MCI) represents its prodrome. It is generally believed that neural compensation is intact in MCI but absent in Alzheimer's disease. This study investigated the effects of increasing task load as a means to induce neural compensation through a novel visual working memory (VSWM) task using functional near-infrared spectroscopy (fNIRS).

View Article and Find Full Text PDF

Purpose: To evaluate and compare the temporal changes in pulse waveform parameters of ocular blood flow (OBF) between non-habitual and habitual groups due to caffeine intake.

Method: This study was conducted on 19 healthy subjects (non-habitual 8; habitual 11), non-smoking and between 21 and 30 years of age. Using laser speckle flowgraphy (LSFG), three areas of optical nerve head were analyzed which are vessel, tissue, and overall, each with ten pulse waveform parameters, namely mean blur rate (MBR), fluctuation, skew, blowout score (BOS), blowout time (BOT), rising rate, falling rate, flow acceleration index (FAI), acceleration time index (ATI), and resistive index (RI).

View Article and Find Full Text PDF

Identification of mutants with impairments in auxin biosynthesis and dynamics by forward genetic screening is hindered by the complexity, redundancy and necessity of the pathways involved. Furthermore, although a few auxin-deficient mutants have been recently identified by screening for altered responses to shade, ethylene, N-1-naphthylphthalamic acid (NPA) or cytokinin (CK), there is still a lack of robust markers for systematically isolating such mutants. We hypothesized that a potentially suitable phenotypic marker is root curling induced by CK, as observed in the auxin biosynthesis mutant CK-induced root curling 1 / tryptophan aminotransferase of Arabidopsis 1 (ckrc1/taa1).

View Article and Find Full Text PDF

We describe a computer-aided measuring tool, named parapapillary atrophy and optic disc region assessment (PANDORA), for automated detection and quantification of both the parapapillary atrophy (PPA) and the optic disc (OD) regions in two-dimensional color retinal fundus images. The OD region is segmented using a combination of edge detection and ellipse fitting methods. The PPA region is identified by the presence of bright pixels in the temporal zone of the OD, and it is segmented using a sequence of techniques, including a modified Chan-Vese approach, thresholding, scanning filter, and multiseed region growing.

View Article and Find Full Text PDF

Purpose: A computer-aided measuring tool was devised to automatically detect and quantify both the parapapillary atrophy (PPA) and the optic disc (OD) regions in two-dimensional color fundus images of the retina.

Methods: The OD region was segmented using the Chan-Vese model with a shape restraint. This region was then removed from the image (OD+PPA), which was cropped in a modified Chan-Vese approach, producing a first-order estimation of the PPA region.

View Article and Find Full Text PDF