Search

In recent years, the focus on mental health care in Japan has increased, leading to a rise in companies addressing employee mental well-being. Chronic stress, stemming from various sources including work and interpersonal relationships, can have severe impacts on individuals' happiness and health. To address this, there is a growing demand for technology capable of measuring chronic stress on a daily basis. In this study, we explore the potential of using facial thermal images (FTI) as a method for daily measurement of chronic stress. We conducted experiments over a 3-month period with healthy adult participants, collecting routine data on chronic stress and capturing FTI. Independent component analysis (ICA) was applied to the FTI data to extract relevant features. In addition, psychological questionnaires were administered to assess chronic stress levels. We aggregated the questionnaire scores using principal component analysis (PCA) to obtain a single chronic stress indicator. Multiple regression analysis (MRA) was then employed to model the relationship between the extracted FTI components and chronic stress scores. Our results indicate a moderate to strong correlation between the predicted and actual chronic stress scores, suggesting the potential utility of FTI in estimating stress levels. Identified features in the FTI, particularly around the upper lip and on the right half of the face, showed significant associations with chronic stress. This study provides insights into the feasibility of using FTI as a non-invasive method for daily monitoring of chronic stress levels. However, limitations such as variations in stress levels among participants and questionnaire administration frequency should be considered in future research. [ABSTRACT FROM AUTHOR]

Detecting violence in images has emerged as an important area of research and application as digital imaging and computer vision advance. Detecting and assessing violent content automatically in visual data holds great promise for enhancing public safety, security, and content moderation. Violent incidents are difficult to detect because of disruptions in optical flow, complications caused by camera aperture variations, and difficulties with illumination and feature tracking. In this work, a novel F3DNN-Net has been proposed for violence detection in images. The input videos from the surveillance camera are initially converted into frame sequences and pre-processed. The Yolov8 (You Only Look Once) algorithm is employed to detect objects within pre-processed frames. Simultaneously, the ego algorithm is applied to the pre-processed images for motion estimation, ensuring comprehensive coverage of information. Afterwards, the features are extracted using the fined feature extraction phase as independent component analysis (ICA), and the selected features are selected using the Dingo algorithm. Then, the fine-tuned fused (FF) features are implemented in the deep neural network (DNN) approach for the categorization of violent and non-violent cases. According to the findings, the proposed F3DNN-Net detects violence in images with an accuracy rate of 99.33%. The proposed DNN enhances an overall F1-score of 10.46%, 6.91%, and 4.44%, better than Alex Net, ResNet, and Dense Net. The proposed F3DNN-Net enhances the overall accuracy by 6%, 0.3%, and 29.33% better than Inception-Resnet-V2, CNN, LSTM, and ResNet50, respectively. [ABSTRACT FROM AUTHOR]

Purpose: While fMRI provides information on the temporal changes in blood oxygenation, 2- [18F]fluoro-2-deoxy-D-glucose ([18F]FDG)-PET has traditionally offered a static snapshot of brain glucose consumption. As a result, studies investigating metabolic brain networks as potential biomarkers for neurodegeneration have primarily been conducted at the group level. However, recent pioneering studies introduced time-resolved [18F]FDG-PET with constant infusion, which enables metabolic connectivity studies at the individual level. Methods: In the current study, this technique was employed to explore Parkinson's disease (PD)-related alterations in individual metabolic connectivity, in comparison to inter-subject measures and hemodynamic connectivity. Fifteen PD patients and 14 healthy controls with comparable cognition underwent sequential resting-state dynamic PET with constant infusion and functional MRI. Intrinsic networks were identified by independent component analysis and interregional connectivity calculated for summed static PET images, PET time series and functional MRI. Results: Our findings revealed an intrinsic sensorimotor network in PD patients that has not been previously observed to this extent. In PD, a significantly higher number of connections in cortical motor areas was observed compared to elderly control subjects, as indicated by both static PET and functional MRI (pBonferroni−Holm = 0.027), as well as constant infusion PET and functional MRI connectomes (pBonferroni−Holm = 0.012). This intensified coupling was associated with disease severity (ρ = 0.56, p = 0.036). Conclusion: Metabolic connectivity, as revealed by both static and dynamic PET, provides unique information on metabolic network activity. Subject-level metabolic connectivity based on constant infusion PET may serve as a potential marker for the metabolic network signature in neurodegeneration. [ABSTRACT FROM AUTHOR]

Background: Juvenile myoclonic epilepsy (JME) is characterized by altered patterns of brain functional connectivity (FC). However, the nature and extent of alterations in the spatiotemporal characteristics of dynamic FC in JME patients remain elusive. Dynamic networks effectively encapsulate temporal variations in brain imaging data, offering insights into brain network abnormalities and contributing to our understanding of the seizure mechanisms and origins. Methods: Resting-state functional magnetic resonance imaging (rs-fMRI) data were procured from 37 JME patients and 37 healthy counterparts. Forty-seven network nodes were identified by group-independent component analysis (ICA) to construct the dynamic network. Ultimately, patients' and controls' spatiotemporal characteristics, encompassing temporal clustering and variability, were contrasted at the whole-brain, large-scale network, and regional levels. Results: Our findings reveal a marked reduction in temporal clustering and an elevation in temporal variability in JME patients at the whole-brain echelon. Perturbations were notably pronounced in the default mode network (DMN) and visual network (VN) at the large-scale level. Nodes exhibiting anomalous were predominantly situated within the DMN and VN. Additionally, there was a significant correlation between the severity of JME symptoms and the temporal clustering of the VN. Conclusions: Our findings suggest that excessive temporal changes in brain FC may affect the temporal structure of dynamic brain networks, leading to disturbances in brain function in patients with JME. The DMN and VN play an important role in the dynamics of brain networks in patients, and their abnormal spatiotemporal properties may underlie abnormal brain function in patients with JME in the early stages of the disease. [ABSTRACT FROM AUTHOR]

With the advances in Internet-of-Things and data mining technologies, deep learning-based approaches have been widely used for intelligent fault diagnosis of manufacturing assets. However, uncertainty caused by the non-stationary process data such as vibration signal and noise interference in practical working environments will greatly affect the performance and reliability of predictions. The present paper develops a trustworthy and intelligent fault diagnosis framework based on a two-stage joint denoising method and evidential neural networks. The proposed denoising method integrating the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and the independent component analysis (ICA) method can effectively reduce data uncertainty caused by noise interference. The stacked gated recurrent unit (SGRU) model has been incorporated into the evidential neural networks as a deep classifier. The proposed evidential SGRU (ESGRU) method can quantify the prediction uncertainty, which estimates the prediction trustworthiness. Predictive entropy and reliability diagrams are used as calibration methods to validate the effectiveness of uncertainty estimation. The proposed framework is validated by two case studies of rolling bearing fault diagnosis in variable noise conditions. Experimental results demonstrate that the proposed method can achieve a high denoising effect and provide reliable uncertainty prediction results which are significant for practical applications. [ABSTRACT FROM AUTHOR]

Background: Functional magnetic resonance imaging (fMRI) studies have revealed extensive functional reorganization in patients with sensorineural hearing loss (SNHL). However, almost no study focuses on the dynamic functional connectivity after hearing loss. Objective: This study aimed to investigate dynamic functional connectivity changes in children with profound bilateral congenital SNHL under the age of 3 years. Materials and methods: Thirty-two children with profound bilateral congenital SNHL and 24 children with normal hearing were recruited for the present study. Independent component analysis identified 18 independent components composing five resting-state networks. A sliding window approach was used to acquire dynamic functional matrices. Three states were identified using the k-means algorithm. Then, the differences in temporal properties and the variance of network efficiency between groups were compared. Results: The children with SNHL showed longer mean dwell time and decreased functional connectivity between the auditory network and sensorimotor network in state 3 (P < 0.05), which was characterized by relatively stronger functional connectivity between high-order resting-state networks and motion and perception networks. There was no difference in the variance of network efficiency. Conclusions: These results indicated the functional reorganization due to hearing loss. This study also provided new perspectives for understanding the state-dependent connectivity patterns in children with SNHL. [ABSTRACT FROM AUTHOR]

This paper studied the problem of multi-user blind signal separation (BSS) in wireless communications. The existing separation algorithms work on quadrature phase shift keying (QPSK). Through our work, two proposed algorithms were presented to enhance the BSS performance. The first proposed algorithm uses wavelet denoising to remove noise from the received signals in time domain. It adopts different modulation techniques such as minimum shift keying (MSK), QPSK, and Gaussian minimum shift keying (GMSK). Then several BSS algorithms such as independent component analysis (ICA), principle component analysis (PCA), and multi-user kurtosis (MUK) algorithms were implemented. The second proposed algorithm transferred the problem of BSS to transform domain and used wavelet denoising to reduce noise effect on received mixture. The BSS with Discrete Sine Transform (DST) and Discrete Cosine Transform (DCT) were investigated and compared to time domain performance. Minimum square error (MSE) and signal to noise ratio (SNR) were used as the evaluating metrics for comparison. Simulation results proved that in time domain, MUK with QPSK gave best performance and wavelet denoising was found to enhance the performance of BSS under all conditions. Signal separation in transform domain was found to give better performance than that in time domain due to the energy compaction process of these transforms and noise reduction due to their averaging effect. [ABSTRACT FROM AUTHOR]

Dyslexia is a specific learning disability that is neurobiological in origin and is characterized by reading and/or spelling problems affecting the development of language-related skills. The aim of this study is to reveal functional markers based on dyslexia by examining the functions of brain regions in resting state and reading tasks and to analyze the effects of special education given during the treatment process of dyslexia. A total of 43 children, aged between 7 and 12, whose native language was Turkish, participated in the study in three groups including those diagnosed with dyslexia for the first time, those receiving special education for dyslexia, and healthy children. Independent component analysis method was employed to analyze functional connectivity variations among three groups both at rest and during the continuous reading task. A whole-brain scanning during task fulfillment and resting states revealed that there were significant differences in the regions including lateral visual, default mode, left frontoparietal, ventral attention, orbitofrontal and lateral motor network. Our results revealed the necessity of adding motor coordination exercises to the training of dyslexic participants and showed that training led to functional connectivity in some brain regions similar to the healthy group. Additionally, our findings confirmed that impulsivity is associated with motor coordination and visuality, and that the dyslexic group has weaknesses in brain connectivity related to these conditions. According to our preliminary results, the differences obtained between children with dyslexia, group of dyslexia with special education and healthy children has revealed the effect of education on brain functions as well as enabling a comprehensive examination of dyslexia. [ABSTRACT FROM AUTHOR]

Precipitation is momentous role in the hydrological cycle, crop irrigation, drinking, and ecosystem maintenance. Excessive and inadequate precipitation leads to flooding, landslides, loss of human lives and properties, and drought. Therefore, precipitation prediction is necessary for planning and protecting water resources and handling natural disasters like floods and drought. This paper proposed a cloud segmentation and precipitation prediction using Machine Learning (ML) algorithms. ML cloud segmentation model is implemented to segment the INSAT-3D Thermal Infra-Red (TIR) image into No-cloud, Low-Level (L-L), Mid-Level (M-L), and High-Level (H-L) clouds and determine the percentage of different clouds over the study area. Fuzzy C-means(FCM) clustering, Gaussian Naïve Bayes (GNB), K-Nearest Neighbor (KNN), Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), Adaptive Boosting (AdaBoost), eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Categorical Boosting (CatBoost) are the ML algorithms considered for cloud segmentation. The precipitation intensity was predicted on the weather dataset using ML regression models: KNN, DT, and RF. The estimated cloud percentage is validated with cloud cover attributes of the weather dataset. Qualitative and quantitative results of cloud segmentation show that XGBoost, LightGBM, and CatBoost are the best performing models. Similarly, quantitative results of precipitation prediction show that RF and KNN are the best and least performing ML regression models. Also, the performance of the ML regression model is improved by including dimensionality reduction techniques such as Principal Component Analysis (PCA), t-distributed Stochastic Neighbor Embedding (t-SNE), and Independent Component Analysis (ICA). [ABSTRACT FROM AUTHOR]

Root cause diagnosis is able to find the propagation path of faults timely when the fault occurs. Therefore, it is of key significance in the maintenance and fault diagnosis of industrial systems. A commonly used method for root cause diagnosis is causal analysis method. In this work, a causal analysis method Extended Convergent Cross Mapping (ECCM) algorithm is used for root cause diagnosis of industry, however, it has difficulties in dealing with large amounts of steady state data and obtaining accurate propagation paths. Therefore, a causal analysis method based on Kernel Independent Component Analysis (KICA) and ECCM is proposed in this study to deal with the above problems. First, the KICA algorithm is used to detect faults to get the transition process data. Second, the ECCM algorithm is used to construct causal relationship among variables based on the transition process data to construct the fault propagation path diagram. Finally, the effectiveness of the proposed KICA-ECCM algorithm is tested by using the Tennessee Eastman Process and Industrial Process Control Test Facility platform. Compared with the ECCM and GC algorithm, the KICA-ECCM algorithm performs better in terms of accuracy and efficiency. [ABSTRACT FROM AUTHOR]

Malicious malware targeting Android systems has alarmingly increased due to the quick spread of Android devices. For these devices to be secure and to protect the private data of users, Android virus detection is essential. The selection of features, model performance, and efficiency are issues with existing Android malware detection techniques. To overcome these drawbacks, we suggest a unique method for identifying malicious Android data that combines Tree Seed Optimization with Support Vector Machines (TSO-SVM).TSO is a nature-inspired optimization technique that looks for the best feature subsets by simulating the tree's seed dispersal process. The efficiency and effectiveness of SVM-based classification are increased by our method's use of TSO to choose the most instructive features from the Android malware dataset. To normalize the features of the Android application dataset before training, we use a data-cleaning method known as Z-Score normalization. Our Android malware detection solution uses Independent Component Analysis (ICA) as a feature reduction method. Our test results show how well the TSO-SVM technique works at detecting Malicious Android data. In terms of accuracy, precision, recall, and F1-Score for malicious detection, the suggested model achieves 97.12%, 96.35%, 97.88%, and 96.84%, respectively. The proposed technique successfully solves the problem of suboptimal classification accuracy in the presence of dynamic and changing malware threats. The results of this work highlight the potential of TSO techniques for enhancing the security of Android-based devices and present a promising direction for further investigation in the area of mobile security. [ABSTRACT FROM AUTHOR]

Independent component analysis (ICA) and dictionary learning (DL) are the most successful blind source separation (BSS) methods for functional magnetic resonance imaging (fMRI) data analysis. However, ICA to higher and DL to lower extent may suffer from performance degradation by the presence of anomalous observations in the recovered time courses (TCs) and high overlaps among spatial maps (SMs). This paper addressed both problems using a novel three-layered sparse DL (TLSDL) algorithm that incorporated prior information in the dictionary update process and recovered full-rank outlier-free TCs from highly corrupted measurements. The associated sequential DL model involved factorizing each subject's data into a multi-subject (MS) dictionary and MS sparse code while imposing a low-rank and a sparse matrix decomposition restriction on the dictionary matrix. It is derived by solving three layers of feature extraction and component estimation. The first and second layers captured brain regions with low and moderate spatial overlaps, respectively. The third layer that segregated regions with significant spatial overlaps solved a sequence of vector decomposition problems using the proximal alternating linearized minimization (PALM) method and solved a decomposition restriction using the alternating directions method (ALM). It learned outlier-free dynamics that integrate spatiotemporal diversities across brains and external information. It differs from existing DL methods owing to its unique optimization model, which incorporates prior knowledge, subject-wise/multi-subject representation matrices, and outlier handling. The TLSDL algorithm was compared with existing dictionary learning algorithms using experimental and synthetic fMRI datasets to verify its performance. Overall, the mean correlation value was found to be 26 % higher for the TLSDL than for the state-of-the-art subject-wise sequential DL (swsDL) technique. [ABSTRACT FROM AUTHOR]

Brain connectivity measures the relationship between brain regions that occur in response to a task (task-related) or in resting state (intrinsic). Although differences in resting-state connectivity are frequently attributed to task-related brain activity, there is currently no valid criterion for directly evaluating task-related connectivity from signal data. This study aims to establish a fuzzy index based on fuzzy Subsethood (FSH) measure for estimating task-related connectivity. First, two sets of simulated time series with linear and nonlinear interactions were used to evaluate the proposed approach. The results of FSH method on simulated data indicate that the fuzzy Subsethood criterion could identify and estimate task-related connectivity. Afterward, an EEG dataset with an SSVEP task in a mobile BCI system was used to test the approach using real-world data. To address the volume conduction effect and the problem of fake connectivity, the signals were first mapped into the domain of independent components using the Fourier-ICA algorithm, and brain connectivity among brain sources was investigated. The FSH approach was then used to estimate task-related connectivity, and a pattern recognition algorithm was used to determine stimulus frequency. The results demonstrated that the FSH approach is robust when modifying the user's speed. Furthermore, at a speed of 2 m/s, the FSH approach significantly outperformed the standard CCA method (79.48% vs. 55%, respectively; p value = 0.0075). Based on the findings, it is possible to conclude that the FSH index is a suitable measure for estimating task-related connectivity. [ABSTRACT FROM AUTHOR]

This study aims to develop an automated method for de-noising cardiac signals using independent component analysis (ICA) on a 37-channel magnetocardiography (MCG) system. The traditional approach of applying ICA involves manual visual inspection to determine the retention or removal of independent component (IC) related to signal or noise, which is time-consuming and lacks assurance in preserving essential attributes of signal components during the de-noising process. To address these challenges, we propose a novel approach. A feature set comprising spectral, statistical, and nonlinear time series properties is computed from the ICs of thirty subjects. These features are then evaluated by a few machine learning (ML) models to optimally select ICs for de-noising cardiac time series. It is found that ICs evaluated by a gradient boosting decision tree (GBDT) classifier could accomplish the task of efficiently selecting components to de-noise MCG with an accuracy of 93%. The performance of the proposed method is qualitatively and quantitatively compared against conventional methods for noise elimination and preserving signal features. The proposed method has extensive application in de-noising multichannel MCG signals where the characteristics of the noise are not clearly known and for routine diagnostic assessments of subjects with cardiac anomalies in hospital settings. [ABSTRACT FROM AUTHOR]

Juvenile myoclonic epilepsy (JME) is associated with brain dysconnectivity in the default mode network (DMN). Most previous studies of patients with JME have assessed static functional connectivity in terms of the temporal correlation of signal intensity among different brain regions. However, more recent studies have shown that the directionality of brain information flow has a more significant regional impact on patients' brains than previously assumed in the present study. Here, we introduced an empirical approach incorporating independent component analysis (ICA) and spectral dynamic causal modeling (spDCM) analysis to study the variation in effective connectivity in DMN in JME patients. We began by collecting resting-state functional magnetic resonance imaging (rs-fMRI) data from 37 patients and 37 matched controls. Then, we selected 8 key nodes within the DMN using ICA; finally, the key nodes were analyzed for effective connectivity using spDCM to explore the information flow and detect patient abnormalities. This study found that compared with normal subjects, patients with JME showed significant changes in the effective connectivity among the precuneus, hippocampus, and lingual gyrus (p < 0.05 with false discovery rate (FDR) correction) with most of the effective connections being strengthened. In addition, previous studies have found that the self-connection of normal subjects' nodes showed strong inhibition, but the self-connection inhibition of the anterior cingulate cortex and lingual gyrus of the patient was decreased in this experiment (p < 0.05 with FDR correction); as the activity in these areas decreased, the nodes connected to them all appeared abnormal. We believe that the changes in the effective connectivity of nodes within the DMN are accompanied by changes in information transmission that lead to changes in brain function and impaired cognitive and executive function in patients with JME. Overall, our findings extended the dysconnectivity hypothesis in JME from static to dynamic causal and demonstrated that aberrant effective connectivity may underlie abnormal brain function in JME patients at early phase of illness, contributing to the understanding of the pathogenesis of JME. [ABSTRACT FROM AUTHOR]

A relationship between migraine without aura (MO) and patent foramen ovale (PFO) has been observed, but the neural basis underlying this relationship remains elusive. Utilizing independent component analysis via functional magnetic resonance imaging, we examined functional connectivity (FC) within and across networks in 146 patients with MO (75 patients with and 71 patients without PFO) and 70 healthy controls (35 patients each with and without PFO) to elucidate the individual effects of MO and PFO, as well as their interaction, on brain functional networks. The main effect of PFO manifested exclusively in the FC among the visual, auditory, default mode, dorsal attention and salience networks. Furthermore, the interaction effect between MO and PFO was discerned in brain clusters of the left frontoparietal network and lingual gyrus network, as well as the internetwork FC between the left frontoparietal network and the default mode network (DMN), the occipital pole and medial visual networks, and the dorsal attention and salience networks. Our findings suggest that the presence of a PFO shunt in patients with MO is accompanied by various FC changes within and across networks. These changes elucidate the intricate mechanisms linked to PFO-associated migraines and provide a basis for identifying novel noninvasive biomarkers. [ABSTRACT FROM AUTHOR]

The acute phase of ischemic stroke presents a critical window for therapeutic intervention, where novel approaches such as hyper-acute cerebral flow augmentation offer promising avenues for neuroprotection. In this study, we investigated the effects of two such therapies, NEH (a combination of norepinephrine and hydralazine) and Sanguinate (pegylated bovine carboxyhemoglobin), on resting-state functional connectivity, global mean signal (GMS), and blood oxygen level-dependent (BOLD) time lag in a pre-clinical canine model of stroke via permanent occlusion of the middle cerebral artery (total of n = 40 IACUC-approved mongrel canines randomly split into control/natural history and two treatment groups). Utilizing group independent component analysis (ICA), we identified and examined the integrity of sensorimotor and visual networks both pre- and post-occlusion, across treatment and control groups. Our results demonstrated that while the control group exhibited significant disruptions in these networks following stroke, the treatment groups showed remarkable preservation of network integrity. Voxel-wise functional connectivity analysis revealed less pronounced alterations in the treatment groups, suggesting maintained neural connections. Notably, the treatments stabilized GMS, with only minimal reductions observed post-occlusion compared to significant decreases in the control group. Furthermore, BOLD time-lag unity plots indicated that NEH and Sanguinate maintained consistent hemodynamic response timing, as evidenced by tighter clustering around the line of unity, suggesting a potential neuroprotective effect. These findings were underscored by robust statistical analyses, including paired T-tests and Mann–Whitney U tests, which confirmed the significance of the connectivity changes observed. The correlation of BOLD time-lag variations with neuroimaging functional biomarkers highlighted the impact of stroke and the efficacy of early therapeutic interventions. Our study supports the further study of flow augmentation therapies such as NEH and Sanguinate in stroke treatment protocols and suggests flow augmentation therapies should be further explored in an effort to improve patient outcomes. [ABSTRACT FROM AUTHOR]

Regional global navigation satellite system (GNSS) network analyses are often affected by spatially correlated errors, also known as common mode errors (CMEs). To better understand and process the CMEs in GNSS observations and to enhance the efficiency and accuracy of data processing, we developed a GNSS coordinate time series analysis software named GTS_CME based on mature principal component analysis (PCA) and independent component analysis (ICA) spatiotemporal filtering methods using MATLAB language. In addition, GTS_CME integrates numerous functions to assist users in the comprehensive analysis of GNSS coordinate time series. It includes standard preprocessing capabilities such as outlier removal, offset detection and removal, and continuous missing value interpolation. Moreover, the software features tools for retrieving surface mass loading data and calling Hector, which can be used for surface mass loading correction, noise characteristic analysis, and accuracy evaluation of GNSS coordinate time series. [ABSTRACT FROM AUTHOR]

Functional networks (FNs) hold significant promise in understanding brain function. Independent component analysis (ICA) has been applied in estimating FNs from functional magnetic resonance imaging (fMRI). However, determining an optimal model order for ICA remains challenging, leading to criticism about the reliability of FN estimation. Here, we propose a SMART (splitting-merging assisted reliable) ICA method that automatically extracts reliable FNs by clustering independent components (ICs) obtained from multi-model-order ICA using a simplified graph while providing linkages among FNs deduced from different-model orders. We extend SMART ICA to multi-subject fMRI analysis, validating its effectiveness using simulated and real fMRI data. Based on simulated data, the method accurately estimates both group-common and group-unique components and demonstrates robustness to parameters. Using two age-matched cohorts of resting fMRI data comprising 1,950 healthy subjects, the resulting reliable group-level FNs are greatly similar between the two cohorts, and interestingly the subject-specific FNs show progressive changes while age increases. Furthermore, both small-scale and large-scale brain FN templates are provided as benchmarks for future studies. Taken together, SMART ICA can automatically obtain reliable FNs in analyzing multi-subject fMRI data, while also providing linkages between different FNs. [ABSTRACT FROM AUTHOR]

Metallic structures produced with laser powder bed fusion (LPBF) additive manufacturing method (AM) frequently contain microscopic porosity defects, with typical approximate size distribution from one to 100 microns. Presence of such defects could lead to premature failure of the structure. In principle, structural integrity assessment of LPBF metals can be accomplished with nondestructive evaluation (NDE). Pulsed infrared thermography (PIT) is a non-contact, one-sided NDE method that allows for imaging of internal defects in arbitrary size and shape metallic structures using heat transfer. PIT imaging is performed using compact instrumentation consisting of a flash lamp for deposition of a heat pulse, and a fast frame infrared (IR) camera for measuring surface temperature transients. However, limitations of imaging resolution with PIT include blurring due to heat diffusion, sensitivity limit of the IR camera. We demonstrate enhancement of PIT imaging capability with unsupervised learning (UL), which enables PIT microscopy of subsurface defects in high strength corrosion resistant stainless steel 316 alloy. PIT images were processed with UL spatial–temporal separation-based clustering segmentation (STSCS) algorithm, refined by morphology image processing methods to enhance visibility of defects. The STSCS algorithm starts with wavelet decomposition to spatially de-noise thermograms, followed by UL principal component analysis (PCA), fine-tuning optimization, and neural learning-based independent component analysis (ICA) algorithms to temporally compress de-noised thermograms. The compressed thermograms were further processed with UL-based graph thresholding K-means clustering algorithm for defects segmentation. The STSCS algorithm also includes online learning feature for efficient re-training of the model with new data. For this study, metallic specimens with calibrated microscopic flat bottom hole defects, with diameters in the range from 203 to 76 µm, were produced using electro discharge machining (EDM) drilling. While the raw thermograms do not show any material defects, using STSCS algorithm to process PIT images reveals defects as small as 101 µm in diameter. To the best of our knowledge, this is the smallest reported size of a sub-surface defect in a metal imaged with PIT, which demonstrates the PIT capability of detecting defects in the size range relevant to quality control requirements of LPBF-printed high-strength metals. [ABSTRACT FROM AUTHOR]

Electroencephalography (EEG) studies increasingly utilize more mobile experimental protocols, leading to more and stronger artifacts in the recorded data. Independent Component Analysis (ICA) is commonly used to remove these artifacts. It is standard practice to remove artifactual samples before ICA to improve the decomposition, for example using automatic tools such as the sample rejection option of the AMICA algorithm. However, the effects of movement intensity and the strength of automatic sample rejection on ICA decomposition have not been systematically evaluated. We conducted AMICA decompositions on eight open-access datasets with varying degrees of motion intensity using varying sample rejection criteria. We evaluated decomposition quality using mutual information of the components, the proportion of brain, muscle, and 'other' components, residual variance, and an exemplary signal-to-noise ratio. Within individual studies, increased movement significantly decreased decomposition quality, though this effect was not found across different studies. Cleaning strength significantly improved the decomposition, but the effect was smaller than expected. Our results suggest that the AMICA algorithm is robust even with limited data cleaning. Moderate cleaning, such as 5 to 10 iterations of the AMICA sample rejection, is likely to improve the decomposition of most datasets, regardless of motion intensity. [ABSTRACT FROM AUTHOR]

The purpose of this paper is to analyze the applicability and quantify potential efficiency of using blind signal separation algorithms to counter interference from stationary plasma thrusters. For various values of interference-to-signal ratio and of the average interference pulse-to-pause ratio, the bit error rate dependence on the signal-to-noise bit ratio is determined on the basis of the developed simulation model of the command-programming data transmission channel of deep-space communication system with the modulation-code scheme based on the GMSK-signal (Gaussian Minimum Shift Keying) and the Reed–Solomon code (255,223). The obtained results allow us to assess quantitatively the potential efficiency of using the SOBI algorithm of blind signal separation in the channels with GMSK-signal under the influence of emission from stationary plasma thrusters and thermal noises of the receiving path. [ABSTRACT FROM AUTHOR]

Cerebral small vessel disease (CSVD) is a common disease that seriously endangers people's health, and is easily overlooked by both patients and clinicians due to its near-silent onset. Dynamic functional connectivity (DFC) is a new concept focusing on the dynamic features and patterns of brain networks that represents a powerful tool for gaining novel insight into neurological diseases. To assess alterations in DFC in CSVD patients, and the correlation of DFC with cognitive function. We enrolled 35 CSVD patients and 31 normal control subjects (NC). Resting-state functional MRI (rs-fMRI) with a sliding-window approach and k-means clustering based on independent component analysis (ICA) was used to evaluate DFC. The temporal properties of fractional windows and the mean dwell time in each state, as well as the number of transitions between each pair of DFC states, were calculated. Additionally, we assessed the functional connectivity (FC) strength of the dynamic states and the associations of altered neuroimaging measures with cognitive performance. A dynamic analysis of all included subjects suggested four distinct functional connectivity states. Compared with the NC group, the CSVD group had more fractional windows and longer mean dwell times in state 4 characterized by sparse FC both inter-network and intra-networks. Additionally, the CSVD group had a reduced number of windows and shorter mean dwell times compared to the NC group in state 3 characterized by highly positive FC between the somatomotor and visual networks, and negative FC in the basal ganglia and somatomotor and visual networks. The number of transitions between state 2 and state 3 and between state 3 and state 4 was significantly reduced in the CSVD group compared to the NC group. Moreover, there was a significant difference in the FC strength between the two groups, and the altered temporal properties of DFC were significantly related to cognitive performance. Our study indicated that CSVD is characterized by altered temporal properties in DFC that may be sensitive neuroimaging biomarkers for early disease identification. Further study of DFC alterations could help us to better understand the progressive dysfunction of networks in CSVD patients. [ABSTRACT FROM AUTHOR]

Electroencephalogram (EEG) is one of the Psycho-acoustic signals which is used in order to analyze brain activity. However, the EEG signal which frequently gets contaminated with several kinds of artifacts. Among these artifacts, Electrooculography (EOG) and Electromyogram (EMG) are the two wide artifacts that contaminate EEG unintentionally. The presence of such kind of artifacts in EEG shows a significant impact on the diagnosis results. Hence, this paper proposes a new and effective artifacts removal strategy in accordance with Multivariate Empirical Mode Decomposition (MEMD). For a given input EEG, the MEMD creates Multivariate Intrinsic Mode Functions (MIMFs) from it and process it through a Independent Vector Analysis (IVA) and statistical Independent Component Analysis (SICA) to eliminate EMGs and, EOGs respectively. Once the artifacts are removed, the signal will be reconstructed and processed for quality assessment. Three metrics, namely Relative Root Mean Square Error (RRMSE), Cross-Correlation Coefficient (CRC), and Signal to Noise Ratio (SNR) are utilized for assessment. The efficiency of the suggested approaches that are State-of-the-Art methods has been demonstrated through extensive simulations on both simulated and actual EEG data. [ABSTRACT FROM AUTHOR]

The article explores advanced image processing techniques for pigment discrimination in rock art paintings, emphasizing color separation using RGB (red, green, blue) and LHCUv (Luminance, Hue, Chroma) imagery. It highlights the use of dimensionality reduction methods such as Principal Components Analisys PCA and Independent Component Analysis (ICA), with a focus on Gaussian Mixture Models (GMM) for probabilistic classification of image elements. This approach, applied to the Chomache archaeological site on the northernmost coast of the Atacama Desert in Chile, reveals previously undetected motifs and details, offering a nuanced perspective in rock art documentation and analysis. This proposal reinforces the value of rock art panel not only as a finished product but as a process. [ABSTRACT FROM AUTHOR]

The accurate identification of combined fetal and maternal electrocardiogram (ECG) signals plays a crucial role in assessing the health and well-being of both the pregnant woman and the fetus. This paper presents a novel framework that addresses key challenges in fetal ECG identification, including reducing the number of inputs/observations and optimizing the number of iterations required for reliable signal detection. The proposed approach leverages a combination of principal component analysis (PCA) and independent component analysis (ICA) on cardiological data obtained from implanted electrodes on the central abdomen of pregnant women.To mitigate the potential adverse effects associated with a large number of electrodes, which can impact maternal and fetal health, this framework emphasizes the importance of controlling the number of inputs. Furthermore, excessive algorithmic complexity is managed by optimizing the number of iterations. Classical statistical methods often exhibit redundancy, thus posing a significant challenge. To overcome this, an intelligent machine is introduced that evaluates the quality of estimated sources or extracted signals through time-scale images classification, employing the specially designed AlexNet Deep Neural Network Architecture. By utilizing minimal inputs, even as low as two, this intelligent machine assesses the performance of the model on test data, employing metrics such as accuracy, precision, recall, and F1 score. These metrics provide valuable insights into the blind separation model's capacity and enable the determination of the optimal number of iterations and inputs, or the simultaneous adjustment of both parameters. The proposed framework offers a comprehensive solution to enhance fetal ECG identification, promoting improved healthcare monitoring and diagnosis during pregnancy. [ABSTRACT FROM AUTHOR]

Prolonged screen time (ST) has adverse effects on autistic characteristics and language development. However, the mechanisms underlying the effects of prolonged ST on the neurodevelopment of children with autism spectrum disorder (ASD) remain unclear. Neuroimaging technology may help to further explain the role of prolonged ST in individuals with ASD. This study included 164 cases, all cases were divided into low-dose ST exposure (LDE group 108 cases) and high-dose ST exposure (HDE group 56 cases) based on the average ST of all subjects. Spatial independent component analysis (ICA) was used to identify resting state networks (RSNs) and investigate intra- and inter-network alterations in ASD children with prolonged ST. We found that the total Childhood Autism Rating Scale (CARS) scores in the HDE group were significantly higher than those in the LDE group (36.2 ± 3.1 vs. 34.6 ± 3.9, p = 0.008). In addition, the developmental quotient (DQ) of hearing and language in the HDE group were significantly lower than those in the LDE group (31.5 ± 13.1 vs. 42.5 ± 18.5, p < 0.001). A total of 13 independent components (ICs) were identified. Between-group comparison revealed that the HDE group exhibited decreased functional connectivity (FC) in the left precuneus (PCUN) of the default mode network (DMN), the right middle temporal gyrus (MTG) of the executive control network (ECN), and the right median cingulate and paracingulate gyri (MCG) of the attention network (ATN), compared with the LDE group. Additionally, there was an increase in FC in the right orbital part of the middle frontal gyrus (ORBmid) of the salience network (SAN), compared with the LDE group. The inter-network analysis revealed increased FC between the visual network (VN) and basal ganglia (BG) and decreased FC between the sensorimotor network (SMN) and DMN, SMN and ATN, SMN and auditory network (AUN), and DMN and SAN in the HDE group, compared with the LDE group. There was a significant negative correlation between altered FC values in MTG and total CARS scores in subjects (r = − 0.18, p = 0.018). Conclusion: ASD children with prolonged ST often exhibit lower DQ of language development and more severe autistic characteristics. The alteration of intra- and inter-network FC may be a key neuroimaging feature of the effect of prolonged ST on neurodevelopment in ASD children. Clinical trial registration: ChiCTR2100051141. What is Known: • Prolonged ST has adverse effects on autistic characteristics and language development. • Neuroimaging technology may help to further explain the role of prolonged ST in ASD. What is New: • This is the first study to explore the impact of ST on intra- and inter-network FC in children with ASD. • ASD children with prolonged ST have atypical changes in intra- and inter-brain network FC. [ABSTRACT FROM AUTHOR]

Previous studies have developed and explored magnetic resonance imaging (MRI)-based machine learning models for predicting Alzheimer's disease (AD). However, limited research has focused on models incorporating diverse patient populations. This study aimed to build a clinically useful prediction model for amyloid-beta (Aβ) deposition using source-based morphometry, using a data-driven algorithm based on independent component analyses. Additionally, we assessed how the predictive accuracies varied with the feature combinations. Data from 118 participants clinically diagnosed with various conditions such as AD, mild cognitive impairment, frontotemporal lobar degeneration, corticobasal syndrome, progressive supranuclear palsy, and psychiatric disorders, as well as healthy controls were used for the development of the model. We used structural MR images, cognitive test results, and apolipoprotein E status for feature selection. Three-dimensional T1-weighted images were preprocessed into voxel-based gray matter images and then subjected to source-based morphometry. We used a support vector machine as a classifier. We applied SHapley Additive exPlanations, a game-theoretical approach, to ensure model accountability. The final model that was based on MR-images, cognitive test results, and apolipoprotein E status yielded 89.8% accuracy and a receiver operating characteristic curve of 0.888. The model based on MR-images alone showed 84.7% accuracy. Aβ-positivity was correctly detected in non-AD patients. One of the seven independent components derived from source-based morphometry was considered to represent an AD-related gray matter volume pattern and showed the strongest impact on the model output. Aβ-positivity across neurological and psychiatric disorders was predicted with moderate-to-high accuracy and was associated with a probable AD-related gray matter volume pattern. An MRI-based data-driven machine learning approach can be beneficial as a diagnostic aid. [ABSTRACT FROM AUTHOR]

We derive limiting distributions of symmetrized estimators of scatter. Instead of considering all n (n - 1) / 2 pairs of the n observations, we only use nd suitably chosen pairs, where d ≥ 1 is substantially smaller than n. It turns out that the resulting estimators are asymptotically equivalent to the original one whenever d = d (n) → ∞ at arbitrarily slow speed. We also investigate the asymptotic properties for arbitrary fixed d. These considerations and numerical examples indicate that for practical purposes, moderate fixed values of d between 10 and 20 yield already estimators which are computationally feasible and rather close to the original ones. [ABSTRACT FROM AUTHOR]

Blind source separation (BSS), as a digital signal processing approach, focuses on estimating the underlying source signals from their linear mixtures without any prior information about the source signals and mixing matrix. Conventional methods for the BSS, however, are incapable of separating the complex-valued source signals. By leveraging the negative conjugate gradient to minimize the least mean square error reconstruction (LMSER) principle in complex domain, this paper proposes a collection of least-squares algorithms for complex-valued BSS (CBSS), including least-mean square (LMS)-type algorithms and recursive least-squares (RLS)-type algorithms. We demonstrate the availability of the proposed algorithms in both circular and non-circular source signals separation. Especially, the RLS algorithm for the CBSS without prewhitening is superior in cross-talking criterion to the others, as verified by computer simulations on artificial source signals. [ABSTRACT FROM AUTHOR]

Background: Monoaminergic network dysfunction is thought to underpin depression in multiple sclerosis (MS) patients. However, longitudinal studies are lacking. Objectives: Here, we investigated the association between development of depressive symptoms in MS and changes of resting-state functional connectivity (RS FC) within monoaminergic networks. Methods: Forty-nine MS patients without depression [Montgomery–Asberg Depression Scale (MADRS) ≤ 9] and 27 healthy controls underwent clinical and 3.0 T RS FC assessment at baseline and after a median follow-up of 1.6 years (interquartile range 1.0–2.1 years). Monoamine-related RS FC was derived by independent component analysis, constrained to PET atlases for dopamine, noradrenaline and serotonin transporters. Longitudinal changes of RS FC within monoaminergic networks and their correlations with MADRS scores were assessed. Results: At baseline, MS patients showed decreased RS FC vs healthy controls in all PET-guided monoaminergic networks in frontal, cingulate and cerebellar cortices, and increased RS FC in parieto-occipital regions. Fourteen (29%) MS patients developed depressive symptoms (MADRS > 9) at follow-up (D-MS) and exhibited widespread RS FC decrease over time in the PET-guided dopamine network, mainly in orbitofrontal, occipital, anterior cingulate and precuneal cortices compared to patients who did not develop depressive symptoms. In D-MS, decreased RS FC over time was also observed in parahippocampal and occipital regions of the PET-guided noradrenaline network. Decreased RS FC over time in dopamine and noradrenaline PET-guided networks correlated with concomitant increased MADRS scores (r = range − 0.65/− 0.61, p < 0.001). Conclusions: The development of depressive symptoms in MS patients was associated with specific RS FC changes within the dopamine and noradrenaline networks. [ABSTRACT FROM AUTHOR]

Guided ultrasonic wave (GUW) monitoring systems are gaining much attention in pipeline condition monitoring. However, the effects of environmental and operational conditions (EOCs), especially temperature and random noise, degrade damage detection performance. When EOC effects produce greater amplitudes than the reflected waves from small damage cases, the reflected waves remain unidentified. This paper proposes an unsupervised learning-based denoising autoencoder (DAE) to reduce the effect of EOCs in GUW monitoring systems. A DAE decodes high-dimensional data into low-dimensional features and reconstructs the original data from these low-dimensional features. By providing GUW signals at a reference temperature, this structure forces the DAE to learn the essential features hidden within complex data. The proposed DAE undergoes comparative analysis with other popular unsupervised learning algorithms used for EOC compensation in GUW monitoring systems, such as principal component analysis, independent component analysis and deep autoencoder algorithms. EOC compensation performance is evaluated through receiver operating characteristics (ROC). From the numerical model and an experimental model, the GUW database is obtained. All four algorithms showed good damage detection performance using a numerical model; however, in the experimental model, the proposed DAE showed superiority among other methods. [ABSTRACT FROM AUTHOR]

Aberrant intrinsic brain networks are consistently observed in individuals with autism spectrum disorder. However, studies examining the strength of functional connectivity across brain regions have yielded conflicting results. Therefore, this study aimed to investigate the functional connectivity of the resting brain in children with low-functioning autism, including during the early developmental stages. We explored the functional connectivity of 43 children with autism spectrum disorder and 54 children with typical development aged 2 to 12 years using resting-state functional magnetic resonance imaging data. We used independent component analysis to classify the brain regions into six intrinsic networks and analyzed the functional connectivity within each network. Moreover, we analyzed the relationship between functional connectivity and clinical scores. In children with autism, the under-connectivities were observed within several brain networks, including the cognitive control, default mode, visual, and somatomotor networks. In contrast, we found over-connectivities between the subcortical, visual, and somatomotor networks in children with autism compared with children with typical development. Moderate effect sizes were observed in entire networks (Cohen’s d = 0.43–0.77). These network alterations were significantly correlated with clinical scores such as the communication sub-score (r = − 0.442, p = 0.045) and the calibrated severity score (r = − 0.435, p = 0.049) of the Autism Diagnostic Observation Schedule. These opposing results observed based on the brain areas suggest that aberrant neurodevelopment proceeds in various ways depending on the functional brain regions in individuals with autism spectrum disorder. [ABSTRACT FROM AUTHOR]

The upper tropospheric water vapor is a key component of Earth's climate. Understanding variations in upper tropospheric water vapor and identifying its influencing factors is crucial for enhancing our comprehension of global climate change. While many studies have shown the impact of El Niño-Southern Oscillation (ENSO) and global warming on water vapor, how they affect the upper tropospheric water vapor remains unclear. Long-term, high-precision ERA5 specific humidity data from the European Centre for Medium-Range Weather Forecasts (ECMWF) provided the data foundation for this study. On this basis, we successfully obtained the patterns of global warming (Independent Component 1, IC1) and ENSO (Independent Component 2, IC2) by employing the strategy of independent component analysis (ICA) combined with non-parametric optimal dimension selection to investigate the upper tropospheric water vapor variations and responses to ENSO and global warming. The results indicate that global warming and ENSO are the primary factors contributing to water vapor variations in the upper troposphere, achieving the significant correlations of 0.87 and 0.61 with water vapor anomalies respectively. Together, they account for 86% of the global interannual variations in water vapor. Consistent with previous studies, our findings also find positive anomalies in upper tropospheric water vapor during El Niño years and negative anomalies during La Niña years. Moreover, the influence extent of ENSO on upper tropospheric water vapor varies with the changing seasons. [ABSTRACT FROM AUTHOR]

Monitoring and predicting the regional groundwater storage (GWS) fluctuation is an essential support for effectively managing water resources. Therefore, taking Shandong Province as an example, the data from Gravity Recovery and Climate Experiment (GRACE) and GRACE Follow-On (GRACE-FO) is used to invert GWS fluctuation from January 2003 to December 2022 together with Watergap Global Hydrological Model (WGHM), in-situ groundwater volume and level data. The spatio-temporal characteristics are decomposed using Independent Components Analysis (ICA), and the impact factors, such as precipitation and human activities, which are also analyzed. To predict the short-time changes of GWS, the Support Vector Machines (SVM) is adopted together with three commonly used methods Long Short-Term Memory (LSTM), Singular Spectrum Analysis (SSA), Auto-Regressive Moving Average Model (ARMA), as the comparison. The results show that: (1) The loss intensity of western GWS is significantly greater than those in coastal areas. From 2003 to 2006, GWS increased sharply; during 2007 to 2014, there exists a loss rate − 5.80 ± 2.28 mm/a of GWS; the linear trend of GWS change is − 5.39 ± 3.65 mm/a from 2015 to 2022, may be mainly due to the effect of South-to-North Water Diversion Project. The correlation coefficient between GRACE and WGHM is 0.67, which is consistent with in-situ groundwater volume and level. (2) The GWS has higher positive correlation with monthly Global Precipitation Climatology Project (GPCP) considering time delay after moving average, which has the similar energy spectrum depending on Continuous Wavelet Transform (CWT) method. In addition, the influencing facotrs on annual GWS fluctuation are analyzed, the correlation coefficient between GWS and in-situ data including the consumption of groundwater mining, farmland irrigation is 0.80, 0.71, respectively. (3) For the GWS prediction, SVM method is adopted to analyze, three training samples with 180, 204 and 228 months are established with the goodness-of-fit all higher than 0.97. The correlation coefficients are 0.56, 0.75, 0.68; RMSE is 5.26, 4.42, 5.65 mm; NSE is 0.28, 0.43, 0.36, respectively. The performance of SVM model is better than the other methods for the short-term prediction. [ABSTRACT FROM AUTHOR]

Approximately 36% of patients with neuromyelitis optica spectrum disorders (NMOSD) suffer from severe visual and motor disability (blindness or light perception or unable to walk) with abnormalities of whole-brain functional networks. However, it remains unclear how whole-brain functional networks and their dynamic properties are related to clinical disability in patients with NMOSD. Our study recruited 30 NMOSD patients (37.70 ± 11.99 years) and 45 healthy controls (HC, 41.84 ± 11.23 years). The independent component analysis, sliding-window approach and graph theory analysis were used to explore the static strength, time-varying and topological properties of large-scale functional networks and their associations with disability in NMOSD. Compared to HC, NMOSD patients showed significant alterations in dynamic networks rather than static networks. Specifically, NMOSD patients showed increased occurrence (fractional occupancy; P < 0.001) and more dwell times of the low-connectivity state (P < 0.001) with fewer transitions (P = 0.028) between states than HC, and higher fractional occupancy, increased dwell times of the low-connectivity state and lower transitions were related to more severe disability. Moreover, NMOSD patients exhibited altered small-worldness, decreased degree centrality and reduced clustering coefficients of hub nodes in dynamic networks, related to clinical disability. NMOSD patients exhibited higher occurrence and more dwell time in low-connectivity states, along with fewer transitions between states and decreased topological organizations, revealing the disrupted communication and coordination among brain networks over time. Our findings could provide new perspective to help us better understand the neuropathological mechanism of the clinical disability in NMOSD. [ABSTRACT FROM AUTHOR]

Text-to-image generation intends to automatically produce a photo-realistic image, conditioned on a textual description. To facilitate the real-world applications of text-to-image synthesis, we focus on studying the following three issues: (1) How to ensure that generated samples are believable, realistic or natural? (2) How to exploit the latent space of the generator to edit a synthesized image? (3) How to improve the explainability of a text-to-image generation framework? We introduce two new data sets for benchmarking, i.e., the Good & Bad, bird and face, data sets consisting of successful as well as unsuccessful generated samples. This data set can be used to effectively and efficiently acquire high-quality images by increasing the probability of generating Good latent codes with a separate, new classifier. Additionally, we present a novel algorithm which identifies semantically understandable directions in the latent space of a conditional text-to-image GAN architecture by performing independent component analysis on the pre-trained weight values of the generator. Furthermore, we develop a background-flattening loss (BFL), to improve the background appearance in the generated images. Subsequently, we introduce linear-interpolation analysis between pairs of text keywords. This is extended into a similar triangular 'linguistic' interpolation. The visual array of interpolation results gives users a deep look into what the text-to-image synthesis model has learned within the linguistic embeddings. Experimental results on the recent DiverGAN generator, pre-trained on three common benchmark data sets demonstrate that our classifier achieves a better than 98% accuracy in predicting Good/Bad classes for synthetic samples and our proposed approach is able to derive various interpretable semantic properties for the text-to-image GAN model. [ABSTRACT FROM AUTHOR]

One of the most crucial components of music is accompaniment creation and chord arrangement is essential to accompanying development. A greater level of musical skill and a thorough knowledge of music theory are often required for competent accompaniment production. To organise and provide space for additional chords, a Bengio Nesterov Momentum optimizer to Bidirectional Encoder Representations from Transformers (BNM-BERT) intuitive computer approach is provided. To replace manual chord creation for accompaniment, the work has generated Optimised Intellectual Natural Language Processing Music Accompaniment. An Overlapping Segmentation based Independent Component Analysis (OS-ICA) technique, which ensuring the frame interval signals are continuous and smoothness is used to begin the procedure after segmentation. Then, theme signal feature extraction is performed using the Dual Fast Transform (DFT), which combines the Continues Wavelet Transform (CWT) and Fast Fourier Transform (FFT) for feature extraction from music audio signals. This results in coefficients for the timbral texture, tonal texture, Pitch class Profile (PCP), and rhythmic activity, among other features of musical information that are specific to the sound spectrum. Then, to enhance the musical accompaniment, very pertinent rhythmic signals are chosen employing HE instated Jellyfish inquiry advancement (HEinit-JSO). The unlabeled audio stream is labelled using average linkage based on hierarchical divisive clustering after the feature is chosen. Finally, automatic chord label creation is done using the BNM- BERT model. The examination reveals that the well-before algorithm outperforms the standards in terms of reconstructive probability and generating effectiveness. Additionally, it shows how cascading effects can be used for accompaniment improvement, texture generation from chord circumstances, and chord analysis. [ABSTRACT FROM AUTHOR]

The article discusses the implementation of independent component analysis (ICA) in the brain and its potential for modeling brain computations. The author suggests that while modeling the brain on statistical and objective levels is promising, modeling the algorithmic level is more challenging due to the difficulty of measuring single neurons and their learning. The author also discusses the interpretation of nonlinear ICA as defining an exponential model and the use of self-supervised learning methods in machine learning. Overall, the article highlights the complexities and challenges of nonlinear ICA as a statistical model and its potential applications in understanding brain computations. [Extracted from the article]

This document discusses the identifiability theory for linear/nonlinear independent component analysis (ICA) models and structural equation models. It acknowledges Professor Hyvärinen for his contributions to machine learning and signal processing. The paper provides a comprehensive survey of the theory and application of nonlinear ICA and causal discovery, written in an accessible form for statisticians. It explores the identifiability of the nonlinear ICA model and discusses methods for solving it, such as exploiting temporal structure and learning via classification using neural networks. The text also mentions other statistical methods that utilize the idea of "learning via classification," such as bridge sampling and noise contrastive estimation. The author suggests that the exponential family interpretation can provide a theoretical basis for developing statistical methods that use pre-trained neural networks as feature extractors. [Extracted from the article]

An old problem in multivariate statistics is that linear Gaussian models are often unidentifiable. In factor analysis, an orthogonal rotation of the factors is unidentifiable, while in linear regression, the direction of effect cannot be identified. For such linear models, non-Gaussianity of the (latent) variables has been shown to provide identifiability. In the case of factor analysis, this leads to independent component analysis, while in the case of the direction of effect, non-Gaussian versions of structural equation modeling solve the problem. More recently, we have shown how even general nonparametric nonlinear versions of such models can be estimated. Non-Gaussianity is not enough in this case, but assuming we have time series, or that the distributions are suitably modulated by observed auxiliary variables, the models are identifiable. This paper reviews the identifiability theory for the linear and nonlinear cases, considering both factor analytic and structural equation models. [ABSTRACT FROM AUTHOR]

Nowadays, detecting fetal electrocardiogram (FECG) signals from a mother's abdominal region is considered a most challenging task because of the high maternal overlapping and fetal signals at this location. Different existing FECG signal extraction techniques have been emphasized for extracting fetal ECG signal features. However, the noises present in the fetal signals still affect the overall performance; also, there is a high chance of missing waveforms and degraded signal-to-noise ratio (SNR) performance. This work proposes a novel extraction and detection technique to overcome these issues. At the initial stage, the FECG signals are collected from two datasets the abdominal and direct fetal ECG database and the Noninvasive fetal ECG database. The signals in the raw dataset with high noises are pre-processed using the twinned Savitzky-Golay filtering (Twin_SGF) model that can effectively enhance the SNR performance. After pre-processing, the FECG signals are fed into the feature extraction technique named Q-Integrated rapid-tune wavelet transform with independent component analysis (Q-IWavCA) to extract essential features from FECG signals. In addition, key characteristic information can be analyzed using the Extreme wavelet genre method (X_WavG) technique. This technique can detect P, T, QRS and ST segments effectively. The performance of a proposed method is analyzed via the MATLAB platform. The effectiveness of the proposed approach is proved by comparing it with different existing approaches in terms of sensitivity (99.3 and 99.5%), positive predictive value (PPV) (99.6 and 99.4%), F-measure (99.2 and 99.54%) are obtained for ADFECG dataset and NIFECG dataset correspondingly. [ABSTRACT FROM AUTHOR]

Background: Treatment-related motor complications may develop progressively over the course of Parkinson's disease (PD). Objective: We investigated intrinsic brain networks functional connectivity (FC) at baseline in a cohort of early PD patients which successively developed treatment-related motor complications over 4 years. Methods: Baseline MRI images of 88 drug-naïve PD patients and 20 healthy controls were analyzed. After the baseline assessments, all PD patients were prescribed with dopaminergic treatment and yearly clinically re-assessed. At the 4-year follow-up, 36 patients have developed treatment-related motor complications (PD-Compl) whereas 52 had not (PD-no-Compl). Single-subject and group-level independent component analyses were used to investigate FC changes within the major large-scale resting-state networks at baseline. A multivariate Cox regression model was used to explore baseline predictors of treatment-related motor complications at 4-year follow-up. Results: At baseline, an increased FC in the right middle frontal gyrus within the frontoparietal network as well as a decreased connectivity in the left cuneus within the default-mode network were detected in PD-Compl compared with PD-no-Compl. PD-Compl patients showed a preserved sensorimotor FC compared to controls. FC differences were found to be independent predictors of treatment-related motor complications over time. Conclusion: Our findings demonstrated that specific FC differences may characterize drug-naïve PD patients more prone to develop treatment-related complications. These findings may reflect the presence of an intrinsic vulnerability across frontal and prefrontal circuits, which may be potentially targeted as a future biomarker in clinical trials. [ABSTRACT FROM AUTHOR]

The article highlights the Development of a Process Monitoring Strategy for a multi-stage manufacturing facility laden with non-normal data. A multi-block variant of the modified independent component analysis (MICA)-based technique has been proposed for building of the said monitoring strategy. For validation of the monitoring strategy thus developed, a case study pertaining to a Copper Cathode Manufacturing Unit (CCMU) has been taking into account. The multi-block MICA (MBMICA)-based monitoring strategy provided a means for hierarchical monitoring and effectively negotiating with non-normal data for the chosen multi-stage CCMU. The detection of faults were achieved by employment of MBMICA score-based Hotelling T2 control chart whose control limit was estimated via application of bootstrap procedure. The fault detection was succeeded by fault diagnosis which was performed via application of appropriate fault diagnosis statistic. The said process monitoring strategy thus developed was able to detect and diagnose the detected fault(s) with appreciable accuracy for a multi-stage CCMU laden with non-normal data. [ABSTRACT FROM AUTHOR]

This study proposes a non-parametric ICA method, called ECOPICA, which describes the joint distribution of data by empirical copulas and measures the dependence between recovery signals by an independent test statistic. We employ the grasshopper algorithm to optimize the proposed objective function. Several acceleration tricks are further designed to enhance the computational efficiency of the proposed algorithm under the parallel computing framework. Our simulation and empirical analysis show that ECOPICA produces better and more robust recovery performances than other well-known ICA approaches for various source distribution shapes, especially when the source distribution is skewed or near-Gaussian. [ABSTRACT FROM AUTHOR]

Background and objective: Previous studies have shown that the salience network (SN) and the thalamus are involved in cluster headache (CH) attacks. However, very little is known regarding the altered thalamus-SN functional connectivity in CH. The aim of this study was to explore alterations of functional connectivity between the thalamus and the SN in patients with CH to further gain insight into the pathophysiology of CH. Materials and methods: The resting-state functional MRI (rs-fMRI) data of 21 patients with CH in the headache attack remission state during in-bout periods and 21 age- and sex-matched normal controls were obtained. The rs-fMRI data were analyzed by the independent component analysis (ICA) method, and the thalamus-SN functional connectivity in patients with right-sided and left-sided CH was compared with that in normal controls. Results: Decreased functional connectivity was found between the thalamus, both ipsilateral and contralateral to the headache side, and the SN during headache remission state in both right-sided CH patients and left-sided CH patients. Conclusions: The findings suggest that the decreased functional connectivity between the thalamus and SN might be one of the pathologies underpinning the CH. This helps us to understand better the nature of the brain dysfunction in CH and the basic pathologies of CH, which implies that this deserves further investigation. [ABSTRACT FROM AUTHOR]

Purpose: Prader-Willi syndrome (PWS) suffers from brain functional reorganization and developmental delays during childhood, but the underlying neurodevelopmental mechanism is unclear. This paper aims to investigate the intra- and internetwork functional connectivity (FC) changes, and their relationships with developmental delays in PWS children. Methods: Resting-state functional magnetic resonance imaging datasets of PWS children and healthy controls (HCs) were acquired. Independent component analysis was used to acquire core resting-state networks (RSNs). The intra- and internetwork FC patterns were then investigated. Results: In terms of intranetwork FC, children with PWS had lower FC in the dorsal attention network, the auditory network, the medial visual network (VN) and the sensorimotor network (SMN) than HCs (FWE-corrected, p < 0.05). In terms of internetwork FC, PWS children had decreased FC between the following pairs of regions: posterior default mode network (DMN) and anterior DMN; posterior DMN and SMN; SMN and posterior VN and salience network and medial VN (FDR-corrected, p < 0.05). Partial correlation analyses revealed that the intranetwork FC patterns were positively correlated with developmental quotients in PWS children, while the internetwork FC patterns were completely opposite (p < 0.05). Intranetwork FC patterns showed an area under the receiver operating characteristic curve of 0.947, with a sensitivity of 96.15% and a specificity of 81.25% for differentiating between PWS and HCs. Conclusion: Impaired intra- and internetwork FC patterns in PWS children are associated with developmental delays, which may result from neural pathway dysfunctions. Intranetwork FC reorganization patterns can discriminate PWS children from HCs. Registration number on the Chinese Clinical Trail Registry: ChiCTR2100046551. [ABSTRACT FROM AUTHOR]

Coronary heart disease (CHD) confers a high risk of cognitive and mental impairments in patients. This study aimed to explore the association of CHD with functional connectivity and topological properties of brain networks. A total of 27 patients with CHD and 44 healthy controls (HCs) participated in this study and underwent a resting-state functional magnetic resonance imaging (rs-fMRI) scan. Intra- and internetwork functional connectivity alterations were explored using independent component analysis in CHD patients. Furthermore, graph theoretical analysis was adopted to assess abnormalities in small-world properties and network efficiency metrics of brain networks. Compared to HCs, CHD patients exhibited increased functional connectivity between the posterior default mode network and posterior visual network, as well as decreased functional connectivity between the left frontoparietal network and auditory network. In terms of graph theoretical analysis, small-world network topology was identified in both CHD patients and HCs. Furthermore, the nodal local efficiency of the left putamen was significantly decreased in CHD patients compared to HCs. This study revealed alterations in brain functional connectivity and topological properties in CHD patients, shedding light on the potential neurological mechanism underlying cognitive and mental impairments in these patients and suggesting unexplored connections between CHD and higher order cognitive processing. [ABSTRACT FROM AUTHOR]

This paper considers the suitability of using multispectral remote sensing data from the Landsat-8 satellite for conducting regional geological and mineralogical mapping of the territory of southeastern Zabaykalsky krai (Russia) under conditions of medium–low mountain relief and continental climate. To increase the spectral information content of Landsat-8 satellite data, statistical processing algorithms are used, including principal component analysis (PCA), minimum noise fraction (MNF), and independent component analysis (ICA). Statistical processing results are compared with the classes of geological materials: minerals of the oxide/hydroxide group containing transitional iron ions (Fe3+ and Fe3+/Fe2+); a group of clay minerals containing Al-OH and Fe, Mg-OH; and minerals containing divalent iron ion (Fe2+) and vegetation cover. Pseudocolor RGB composites are generated and interpreted, reflecting the distribution and multiplication of classes of geological materials. To build a prospectivity scheme for the discovery of the minerals, the integration of informative thematic layers is carried out using a fuzzy logic model. The resulting scheme is compared with geological information, and positive conclusions are made about the suitability of territory for further remote studies on mapping hydrothermally altered zones and hypergenesis products in order to localize areas that are promising for revealing hydrothermal–metasomatic mineralization. [ABSTRACT FROM AUTHOR]

Continuous monitoring of physiological parameters is critical in order to minimize casualties, therefore automated healthcare computer-assisted diagnostic systems require efficient signal processing techniques. It is currently the primary concern upon which the majority of research is concentrated. It is becoming a way of life to reach long age by which accurate and error-free treatments are done. Electrocardiograms (ECGs) are crucial in the current era for minimizing the global mortality rate. An essential clinical feature of electrocardiograms (ECGs) is the determination of heart rate. It is measured in beats per minute. It differs based on age and a number of other associated variables, including body position, temperature, emotion, smoke, and hormonal imbalances, among others. Arrhythmia of the heart, characterised by an irregular heart rate, is currently the leading cause of increased mortality. The complete diagnosis of ECG is accomplished using the blocks such as pre-processing, feature extraction, and detection/classification. Unfortunately, the analysis of ECG becomes complex under the wide variety of the recording datasets which is influenced by variety of noises and artifacts. It motivates to choose a novel combination of above-mentioned blocks which can serve the purpose. The fractional wavelet transform (FrWT) is chosen in conjunction with independent principal component analysis (IPCA) in this article. FrWT, which combines the fractional Fourier transform and the wavelet transform, satisfies the requirements for feature extraction and pre-processing, respectively, whereas IPCA satisfies the requirement for detection and classification. It also helps to understand the cardiac and non-cardiac behaviour of the electrical recording of the specific critical cases. [ABSTRACT FROM AUTHOR]