Search

While functional near-infrared spectroscopy (fNIRS) had previously been suggested for major depressive disorder (MDD) diagnosis, the clinical application to predict antidepressant treatment response (ATR) is still unclear. To address this, the aim of the current study is to investigate MDD ATR at three response levels using fNIRS and micro-ribonucleic acids (miRNAs). Our proposed algorithm includes a custom inter-subject variability reduction based on the principal component analysis (PCA). The principal components of extracted features are first identified for non-responders’ group. The first few components that sum up to 99% of explained variance are discarded to minimize inter-subject variability while the remaining projection vectors are applied on all response groups (24 non-responders, 15 partial-responders, 13 responders) to obtain their relative projections in feature space. The entire algorithm achieved a better performance through the radial basis function (RBF) support vector machine (SVM), with 82.70% accuracy, 78.44% sensitivity, 86.15% precision, and 91.02% specificity, respectively, when compared with conventional machine learning approaches that combine clinical, sociodemographic and genetic information as the predictor. The performance of the proposed custom algorithm suggests the prediction of ATR can be improved with multiple features sources, provided that the inter-subject variability is properly addressed, and can be an effective tool for clinical decision support system in MDD ATR prediction. Clinical and Translational Impact Statement—The fusion of neuroimaging fNIRS features and miRNA profiles significantly enhances the prediction accuracy of MDD ATR. The minimally required features also make the personalized medicine more practical and realizable

This paper presents a novel structural optimization approach for an asymmetrical inline topology with transmission zeros, known as Extracted Pole Unit (EPU) filter using a goal-oriented reinforcement learning method, specifically a hybrid of Soft Actor Critic (SAC) and Hindsight Experience Replay (HER). The recent popularity of reinforcement learning (RL) algorithms for optimizing cavity bandpass filters (BPFs) has led to several limitations. RL algorithms are inherently sample-inefficient, leading to prolonged model training times. A substantial number of training samples are required to achieve accurate results for a complex design using RL models. Additionally, most objective functions used for fitness calculations do not account for predistortion constants, which are crucial in synthesizing asymmetrical inline topologies with three transmission zeros as demonstrated in this work. To address these challenges, the proposed method incorporates predistortion-modified poles and transmission zeros within a feature-assisted objective function for use in the optimization process. Subsequently, a hybrid of SAC and HER is adopted as the optimization algorithm to leverage its improved sample efficiency by encouraging learning from diverse optimization scenarios and outcomes. The proposed method can optimize the self-couplings of the EPU filter in fewer optimization steps, showcasing enhanced training convergence speed and design accuracy.

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. We implemented Phase Slope Index (PSI) to compute effective brain connectivity, and applied data-driven thresholding approaches to filter the brain networks in order to identify key features of low resilience within a cohort of healthy individuals. Our dataset encompassed resting-state EEG recordings gathered from a total of 36 participants (31 females and 5 males). Relevant features were extracted to train and validate a classifier model (Support Vector Machine, SVM). The detection of low stress resilience among healthy individuals using the SVM model scores an accuracy of 80.6% with GCE-abs, and 75% with OMSTs, respectively.

This paper attempts to use a delta robot’s structure and reliable coordinates to develop a self-learning Chinese calligraphy-writing system that requires precise control. Ideally, to achieve human-like behavior, a delta robot can learn stroke trajectories autonomously and present the stroke beauty of calligraphy characters. Unfortunately, state-of-the-art approaches have not yet considered the presentation of stroke beauty resulting from angles of rotation and tilt of the brush. This paper presents an integrated system consisting of a stroke processing module, a hypothesis generation net (HGN) learning model with self-learning capability, a delta robot, and an image capture module. Our approach utilizes both the stroke trajectories from the stroke processing module and angles information from the HGN learning model to automatically produce five degrees of freedom action instructions. Based on the instructions, the delta robot completes calligraphy writing. Then, the image capture module provides feedback to the writing system for error calculation and coordinate correction. We utilize the mean absolute percentage error to verify the performance of the writing results. A correction algorithm and linear regression were used to improve the error correction results (less than 2% error). After several cycles, the written results approached the target sample finally. Consequently, the written results produced by the delta robot prove that our proposed system with learning ability can write Chinese calligraphy aesthetically.

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. Using the property of 3D OCT volume, a modified feature vector connected method called slice-sum is proposed, reducing computational complexity while maintaining high detection accuracy. Compared to previous methods, this method significantly reduces computational complexity by at least a hundredfold. Image adjustment and noise removal steps are excluded for classification accuracy, and the feature extraction algorithm of local binary patterns is determined based on hardware consumption considerations. Through optimisation of the feature vector connection method after feature extraction, the computational complexity of SVM detection is significantly reduced, making it applicable to similar 3D datasets. Additionally, the design supports model replacement, allowing users to train and update classification models as needed. Using TSMC 40 nm CMOS technology, the proposed detector achieves a core area of 0.12 mm2 while demonstrating a classification throughput of 8.87 decisions/s at a maximum operating frequency of 454.54 MHz. The detector achieves a final testing classification accuracy of 92.31%.

Abstract Deep reinforcement learning‐based methods employ an ample amount of computational power that affects the learning process. This paper proposes a novel approach to speed up the training process and improve the performance of autonomous navigation for a tracked robot. The proposed model named “layer normalization dueling double deep Q‐network” has been trained in a virtual environment and then implemented it to a tracked robot for testing in a real‐world scenario. Depth images have been used instead of RGB images to preserve the temporal information. Features are extracted using convolutional neural networks, and actions are derived using the dueling double deep Q‐network. The input data has been normalized before each convolutional layer, which reduces the covariate shift by 69%. This end‐to‐end network architecture of the proposed model provides stability to the network, relieves the burden of computational cost, and converges in much less number of episodes. Compared with three Q‐variant models, the proposed model demonstrates outstanding performance in terms of episodic reward and convergence rate. The proposed model took 12.8% fewer episodes for training compared to other models.

Abstract 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. The cognitive activities were recorded using fNIRS, and the emotional stimuli were adopted from the International Affective Digitized Sound System (IADS). The induction of emotional effects was validated by heart rate variability (HRV) analysis. The experimental results by the proposed method showed significant difference (FDR-adjusted p = 0.004) in the nursing students’ cognitive FC network under the two different emotional conditions, and the semi-metric percentage (SMP) of the right prefrontal cortex (PFC) was found to be significantly higher than the left PFC (FDR-adjusted p = 0.036). The benchmark method (a typical weighted graph theory analysis) gave no significant results. In essence, the results support that the semi-metric analysis can be generalized and extended to fNIRS-based functional connectivity estimation.

Polarization imaging can be used to improve the image quality by reducing the effects of the unwanted light reflection, enhancing the quality of images taken in non-ideal conditions, such as foggy weather, or reconstructing the 3D form of an object based on the shape from polarization. Reconstructing a 3D form requires the acquisition of multiple images and inference of the polarization parameters, such as the degree of polarization and angle of polarization, from these experimental data. The light polarization extraction process should begin by performing the photometric calibration to improve the performance of the polarize instrument measurements by reducing the measurement errors and improving the consistency between measurements. We propose an algorithm based on the kernel ridge regression method to estimate both the polarization parameters and the measurement (angle) errors in the placement of the polarizer. The algorithm was tested on four different sets of images containing different objects based on their responses to light and polarization. The algorithm that uses the mixed kernel function gives the best results.

Eye and systemic diseases are known to manifest themselves in retinal vasculature. Segmentation of retinal vessel is one of the important steps in retinal image analysis. A simple unsupervised method based on Gabor wavelet and Multiscale Line Detector is proposed for retinal vessel segmentation. Vessels are enhanced by linear superposition of first scale Gabor wavelet image and complemented Green channel. Multiscale Line Detector is used to segment the blood vessels. Finally, a simple post processing scheme based on median filtering is deployed to remove false positives. The proposed scheme was evaluated with publicly available datasets called DRIVE, STARE and HRF, obtaining an accuracy of 0.9470, 0.9472, and 0.9559, and a sensitivity of 0.7421, 0.8004, and 0.7207, respectively. These results are comparable to the state-of-the-art methods, albeit with a simpler approach.

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. Through behavioral analysis, we found the students’ anxiety and stress levels significantly reduced after BMI, with p-values of 0.013 and 0.027, respectively. Furthermore, a significant difference between students in emotion regulation strategy, that is, suppression, was also shown. The EEG analysis demonstrated significant differences between students before and after MI in resting states and tasks. Fp1 and O2 channels were identified as the most significant channels in evaluating the effect of BMI. The potential of these channels for classifying (single-channel-based) before and after BMI conditions during eyes-opened and eyes-closed baseline trials were displayed by a good performance in terms of accuracy (~77%), sensitivity (76–80%), specificity (73–77%), and area-under-the-curve (AUC) (0.66–0.8) obtained by k-nearest neighbor (KNN) and support vector machine (SVM) algorithms. Mindfulness can thus improve the self-regulation of the emotional state of neurotic students based on the psychometric and electrophysiological analyses conducted in this study.

This paper proposes a novel hardware design method of scale-invariant feature transform (SIFT) algorithm for implementation on field-programmable gate array (FPGA). To reduce the computing costs, Gaussian kernels are calculated offline for use in Gaussian filters. To eliminate low-contrast points, the inverse of a Hessian matrix is required for hardware implementation, which results in poor performance because dividers are needed. To solve this problem, this paper presents a new mathematical derivation model to implement the low-contrast detection, avoiding the use of any dividers. For the implementation of the normalization module, a large number of dividers are required by traditional methods, which adversely affects the computational efficiency. This paper presents a new architecture using only one divider to implement the normalization function in hardware. Thanks to the parallel processing architecture proposed to design the image pyramid, SIFT detection, and SIFT descriptor, the computational efficiency of the SIFT algorithm is significantly improved. As a result of the proposed design method, the requirement of logic elements in the FPGA hardware is greatly reduced and system frequency is significantly increased. Experimental results show that the proposed hardware architecture outperforms existing techniques in terms of resource usage and computational efficiency for real-time image processing.

Visual odometry is the process of estimating incremental localization of the camera in 3-dimensional space for autonomous driving. There have been new learning-based methods which do not require camera calibration and are robust to external noise. In this work, a new method that do not require camera calibration called the “windowed pose optimization network” is proposed to estimate the 6 degrees of freedom pose of a monocular camera. The architecture of the proposed network is based on supervised learning-based methods with feature encoder and pose regressor that takes multiple consecutive two grayscale image stacks at each step for training and enforces the composite pose constraints. The KITTI dataset is used to evaluate the performance of the proposed method. The proposed method yielded rotational error of 3.12 deg/100 m, and the training time is 41.32 ms, while inference time is 7.87 ms. Experiments demonstrate the competitive performance of the proposed method to other state-of-the-art related works which shows the novelty of the proposed technique.

Colorectal cancer has become the third most commonly diagnosed form of cancer, and has the second highest fatality rate of cancers worldwide. Currently, optical colonoscopy is the preferred tool of choice for the diagnosis of polyps and to avert colorectal cancer. Colon screening is time-consuming and highly operator dependent. In view of this, a computer-aided diagnosis (CAD) method needs to be developed for the automatic segmentation of polyps in colonoscopy images. This paper proposes a modified SegNet Visual Geometry Group-19 (VGG-19), a form of convolutional neural network, as a CAD method for polyp segmentation. The modifications include skip connections, 5 × 5 convolutional filters, and the concatenation of four dilated convolutions applied in parallel form. The CVC-ClinicDB, CVC-ColonDB, and ETIS-LaribPolypDB databases were used to evaluate the model, and it was found that our proposed polyp segmentation model achieved an accuracy, sensitivity, specificity, precision, mean intersection over union, and dice coefficient of 96.06%, 94.55%, 97.56%, 97.48%, 92.3%, and 95.99%, respectively. These results indicate that our model performs as well as or better than previous schemes in the literature. We believe that this study will offer benefits in terms of the future development of CAD tools for polyp segmentation for colorectal cancer diagnosis and management. In the future, we intend to embed our proposed network into a medical capsule robot for practical usage and try it in a hospital setting with clinicians.

The sense of smell is one of the most important organs in humans, and olfactory imaging can detect signals in the anterior orbital frontal lobe. This study assessed olfactory stimuli using support vector machines (SVMs) with signals from functional near-infrared spectroscopy (fNIRS) data obtained from the prefrontal cortex. These data included odor stimuli and air state, which triggered the hemodynamic response function (HRF), determined from variations in oxyhemoglobin (oxyHb) and deoxyhemoglobin (deoxyHb) levels; photoplethysmography (PPG) of two wavelengths (raw optical red and near-infrared data); and the ratios of data from two optical datasets. We adopted three SVM kernel functions (i.e., linear, quadratic, and cubic) to analyze signals and compare their performance with the HRF and PPG signals. The results revealed that oxyHb yielded the most efficient single-signal data with a quadratic kernel function, and a combination of HRF and PPG signals yielded the most efficient multi-signal data with the cubic function. Our results revealed superior SVM analysis of HRFs for classifying odor and air status using fNIRS data during olfaction in humans. Furthermore, the olfactory stimulation can be accurately classified by using quadratic and cubic kernel functions in SVM, even for an individual participant data set.

Rheumatoid arthritis (RA) is an autoimmune illness that impacts the musculoskeletal system by causing chronic, inflammatory, and systemic effects. The disease often becomes progressive and reduces physical function, causes suffering, fatigue, and articular damage. Over a long period of time, RA causes harm to the bone and cartilage of the joints, weakens the joints’ muscles and tendons, eventually causing joint destruction. Sensors such as accelerometer, wearable sensors, and thermal infrared camera sensor are widely used to gather data for RA. In this paper, the classification of medical disorders based on RA and orthopaedics datasets using Ensemble methods are discussed. The RA dataset was gathered from the analysis of white blood cell classification using features extracted from the image of lymphocytes acquired from a digital microscope with an electronic image sensor. The orthopaedic dataset is a benchmark dataset for this study, as it posed a similar classification problem with several numerical features. Three ensemble algorithms such as bagging, Adaboost, and random subspace were used in the study. These ensemble classifiers use k-NN (K-nearest neighbours) and Random forest (RF) as the base learners of the ensemble classifiers. The data classification is accessed using holdout and 10-fold cross-validation evaluation methods. The assessment was based on set of performance measures such as precision, recall, F-measure, and receiver operating characteristic (ROC) curve. The performance was also measured based on the comparison of the overall classification accuracy rate between different ensembles classifiers and the base learners. Overall, it was found that for Dataset 1, random subspace classifier with k-NN shows the best results in terms of overall accuracy rate of 97.50% and for Dataset 2, bagging-RF shows the highest overall accuracy rate of 94.84% over different ensemble classifiers. The findings indicate that the efficiency of the base classifiers with ensemble classifier have substantially improved.