Canonical Correlation Research Articles

SIR-Aided Dynamic Canonical Correlation Analysis for Fault Detection and Isolation of Industrial Automation Systems

SIR-Aided Dynamic Canonical Correlation Analysis for Fault Detection and Isolation of Industrial Automation Systems

Financial inclusion and environmental pollution in sub-Saharan Africa: moderating effects of economic growth and renewable energy

A thriving literature exists about the role of financial inclusion in socio-economic development. Nevertheless, the environmental effects of financial inclusion are largely unknown in the literature, especially in sub-Saharan African countries. Therefore, this study explores the association between financial inclusion and CO2 emissions utilizing data from 23 sub-Saharan Africa for the period 2004–2019. Based on different estimation methods such as dynamic ordinary least squares (DOLS), fully modified ordinary least squares (FMOLS), canonical correlation regression (CCR), and an instrumental variable generalized-method of moment (IV-GMM), the results show that financial inclusion is responsible for a substantial increase in CO2 emissions. In addition, financial inclusion moderates economic growth, resulting in higher CO2 emissions. Alternatively, financial inclusion moderates renewable energy use to lower CO2 emissions. The outcomes also verify the presence of the Environmental Kuznets Curve hypothesis (EKC). This study proposes uniting financial inclusion and environmental policies as a strategy for reducing CO2 emissions in sub-Saharan Africa.

Abstract P367: Cross-Species Epigenomic Maps of Intergenic Loci for Hypertension and Blood Pressure

Many non-coding SNPs identified in Genome-Wide Association Studies (GWAS) likely affect BP-related gene expression through epigenetic mechanisms. This study analyzes the comparative genomic and epigenomic landscapes in human and rat kidney tissues, including kidney proximal tubule (PT) and medullary thick ascending limb (mTAL), focusing on the major challenge of identifying conserved regulatory elements in intergenic regions. The purpose of our study is to identify BP gene regulatory elements in intergenic regions that are conserved from human to rat for in vivo validation and mechanistic studies. Our ultimate goal is to generate high-resolution, genome-wide epigenomic maps of key BP-relevant tissues, using ATAC-seq, Hi-C, CUT&Tag, DNA methylation profiling and RNA-seq. We are creating visualization hubs for human and rat, integrating our data within the UCSC Genome Browser environment. UCSC contains extensive data for humans but very little for rats, particularly for the updated genome assemblies. To address this gap, we integrated our results with data from the Rat Genome Database (RGD). To date, we harmonized ATAC-seq data from human and rat PT and mTAL and displayed these data in RGD’s JBrowse2 genome browser for unique comparative genome views. Based on our initial analysis of data density and intensity, we are developing a novel pattern recognition algorithm to identify epigenomic marks that are conserved across rat and human genomes. Existing algorithms predominantly focus on the conservation of coding genes, gene families, and genomic sequences. Here, average normalized peak intensities for ATAC-seq data across tissues were subject to canonical correlation between human and rat to identify conserved epigenomic patterns within the BP GWAS loci. Here we present an example of a human BP locus in the intergenic region between NPR3 and TARS1 on chromosome 5 which has a region of conserved synteny with rat chromosome 2. Comparative analysis and visualization of this region show significant correlation between ATAC-seq peaks from rat and human PT and mTAL at this locus, with predicted conserved regulatory elements. These visualizations can uncover novel biological insights and identify potential regulatory targets for intervention. This work underscores the importance of advanced visualization techniques in understanding hypertension pathogenesis, facilitating cross-species comparisons, and enhancing the utility of genomic databases.

Convolutional neural network framework for EEG-based ADHD diagnosis in children.

Attention-deficit hyperactivity disorder (ADHD) stands as a significant psychiatric and neuro-developmental disorder with global prevalence. The prevalence of ADHD among school children in India is estimated to range from 5% to 8%. However, certain studies have reported higher prevalence rates, reaching as high as 11%. Utilizing electroencephalography (EEG) signals for the early detection and classification of ADHD in children is crucial. In this study, we introduce a CNN architecture characterized by its simplicity, comprising solely two convolutional layers. Our approach involves pre-processing EEG signals through a band-pass filter and segmenting them into 5-s frames. Following this, the frames undergo normalization and canonical correlation analysis. Subsequently, the proposed CNN architecture is employed for training and testing purposes. Our methodology yields remarkable results, with 100% accuracy, sensitivity, and specificity when utilizing the complete 19-channel EEG signals for diagnosing ADHD in children. However, employing the entire set of EEG channels presents challenges related to the computational complexity. Therefore, we investigate the feasibility of using only frontal brain EEG channels for ADHD detection, which yields an accuracy of 99.08%. The proposed method yields high accuracy and is easy to implement, hence, it has the potential for widespread practical deployment to diagnose ADHD.

An Audiovisual Correlation Matching Method Based on Fine-Grained Emotion and Feature Fusion.

Most existing intelligent editing tools for music and video rely on the cross-modal matching technology of the affective consistency or the similarity of feature representations. However, these methods are not fully applicable to complex audiovisual matching scenarios, resulting in low matching accuracy and suboptimal audience perceptual effects due to ambiguous matching rules and associated factors. To address these limitations, this paper focuses on both the similarity and integration of affective distribution for the artistic audiovisual works of movie and television video and music. Based on the rich emotional perception elements, we propose a hybrid matching model based on feature canonical correlation analysis (CCA) and fine-grained affective similarity. The model refines KCCA fusion features by analyzing both matched and unmatched music-video pairs. Subsequently, the model employs XGBoost to predict relevance and to compute similarity by considering fine-grained affective semantic distance as well as affective factor distance. Ultimately, the matching prediction values are obtained through weight allocation. Experimental results on a self-built dataset demonstrate that the proposed affective matching model balances feature parameters and affective semantic cognitions, yielding relatively high prediction accuracy and better subjective experience of audiovisual association. This paper is crucial for exploring the affective association mechanisms of audiovisual objects from a sensory perspective and improving related intelligent tools, thereby offering a novel technical approach to retrieval and matching in music-video editing.

Multidimensional analysis of heart rate variability and burden of illness in bipolar disorder

IntroductionPatients with bipolar disorder (BD) face disproportionate rates of cardiovascular disease. While several mechanisms have been proposed for this association, both are multifactorial and heterogeneous illnesses, and it is unlikely that any individual factor can account for a significant portion of their association. Potential mediators have been mostly studied in isolation even though they are interrelated. Furthermore, few studies have accounted for baseline cardiovascular functioning or burden of illness. MethodsWe sought to analyze the association between burden of illness, phase of the illness (e.g., depressive) and heart rate variability (HRV) in 48 patients diagnosed with BD using canonical correlation analysis. We hypothesized that the association between burden of illness and HRV measures would be different depending on the clinical phase (i.e., euthymia, depression or (hypo)mania). ResultsA longer duration of (hypo)manic episodes was associated with higher rates of hypertension and increased sympathetic activation, along with lower rates of migraine and family history of suicide. In the second canonical variable, a later age at onset of (hypo)manic episodes was associated with higher parasympathetic activity. LimitationsSmall sample size; while the magnitudes of correlations for these top functions were large, none of the models were statistically significant. ConclusionsThere are different dimensions to the association between burden of illness and HRV in BD. The first dimension could comprise higher sympathetic activation in the context of longer (hypo)manic episodes, with lower rates for clinical variables that have been associated with a predominant depressive polarity (e.g., family history of suicide and migraine).

Canonical correlations between wheat traits in multienvironment trials

ABSTRACT Wheat is a crop of great food importance for food production in Brazil. However, the improvement of this crop is still concentrated in isolated areas, which hinders advances in new cultivation regions due to the extensive demand for existing information. In this investigation, four wheat genotypes analysed to study associations and interrelationships between wheat traits across nine environments during the agricultural years of 2016, 2017 and 2018. The experiment was conducted using a randomised block design with four repetitions, and the analysis was divided into two groups: morphological and productive traits of wheat, comprising three and eleven characteristics, respectively. Canonical correlations between the morphological and productive groups were found to be dependent in most environments. Taller plants with longer main spikes and longer tiller spikes can be indirectly selected to increase grain yield under different sowing conditions. The information generated in this study indicate that some care must be taken when using the interrelations between trait groups to select or recommend genotypes for broader regions, as these relationships are influenced by the specific conditions of each region and sub-region.

How collaborative, interpersonal, and disaster-responsive tendencies work together in non-face-to-face environments: lessons from prolonged pandemic experiences.

This study investigates the dynamics of collaborative characteristics, interpersonal reactivity, and disaster situation responses in non-face-to-face settings, a response mechanism increasingly relevant in the wake of prolonged pandemics. By examining a group of 123 university students engaged in a seven-week non-face-to-face collaborative project, the research identifies relational patterns between collaborative traits such as regulation and efficacy, interpersonal empathy, and responses to disaster situations. The research methodology employs a sophisticated analytical framework comprising factor and canonical correlation analyses to identify how empathy and collaborative efficacy significantly related with disaster response in online collaborations. The mediation and moderation models analyzed confirm mutual mediation effects of collaborative regulation and interpersonal reactivity on situational empathy without significant moderation effects. This suggests there were direct causal relationships of collaborative regulation, collaborative efficacy, interpersonal reactivity on situational empathy. The findings underscore the pivotal role of empathy in collaboration during disasters offering a nuanced understanding of the social and psychological underpinnings that enable collective responses to crises in environments lacking physical interaction and illuminating the critical role of collaborative and interpersonal skills in such settings.

Visual object detection system based on augmented reality and steady-state visual evoked potential

This study investigates a brain-computer interface (BCI) system based on an augmented reality (AR) environment and steady-state visual evoked potentials (SSVEP). The system is designed to facilitate the selection of real-world objects through visual gaze in real-life scenarios. By integrating object detection technology and AR technology, the system augmented real objects with visual enhancements, providing users with visual stimuli that induced corresponding brain signals. SSVEP technology was then utilized to interpret these brain signals and identify the objects that users focused on. Additionally, an adaptive dynamic time-window-based filter bank canonical correlation analysis was employed to rapidly parse the subjects' brain signals. Experimental results indicated that the system could effectively recognize SSVEP signals, achieving an average accuracy rate of 90.6% in visual target identification. This system extends the application of SSVEP signals to real-life scenarios, demonstrating feasibility and efficacy in assisting individuals with mobility impairments and physical disabilities in object selection tasks.

Smccnet 2.0: a comprehensive tool for multi-omics network inference with shiny visualization

SummarySparse multiple canonical correlation network analysis (SmCCNet) is a machine learning technique for integrating omics data along with a variable of interest (e.g., phenotype of complex disease), and reconstructing multi-omics networks that are specific to this variable. We present the second-generation SmCCNet (SmCCNet 2.0) that adeptly integrates single or multiple omics data types along with a quantitative or binary phenotype of interest. In addition, this new package offers a streamlined setup process that can be configured manually or automatically, ensuring a flexible and user-friendly experience.AvailabilityThis package is available in both CRAN: https://cran.r-project.org/web/packages/SmCCNet/index.html and Github: https://github.com/KechrisLab/SmCCNet under the MIT license. The network visualization tool is available at https://smccnet.shinyapps.io/smccnetnetwork/.

Towards Sustainability: Exploring Community Involvement in Tourism Development

ABSTRACT This study examines the relationship between community involvement and sustainable tourism outcomes in Kelardasht, Iran, through the lens of empowerment theory and canonical correlation analysis. Using Pretty's Participation Typology, the research assessed residents' perceptions of seven constructs: self-mobilization, interactive, functional, material incentives, consultation, passive, and manipulative. It also evaluated sustainable tourism indicators across economic, political, social, environmental, cultural, and technological dimensions. Findings reveal that self-mobilization positively influences economic, political, and social sustainability, while interactive participation negatively affects economic, environmental, and cultural sustainability. Participation by consultation was found to reduce technological sustainability. The results indicate that greater participation empowers communities to shape tourism development, fostering economic and social-political cohesion. However, limited interactive engagement or superficial consultation may threaten sustainable development in the community. This study offers important insights into the complex dynamics of community participation and sustainable tourism, guiding efforts to maximize benefits and minimize negative impacts.

Research on the correlation between the degree of digitization of manufacturing process links and economic benefits

PurposeThis paper aims to provide a reference for the development of digital transformation from the perspective of manufacturing process links.Design/methodology/approachThis paper applies canonical correlation analysis based on digital technology patents in the key links of manufacturing industries (product design, procurement, product manufacturing, warehousing and transportation, and wholesale and retail) and the related indicators of economic benefits of regions in China.Findings(1) The degree of digitalization of manufacturing process links is significantly correlated with economic benefits. (2) The improvement of the degree of digitalization in the “product design” link, the “warehousing and transportation” link, the “product manufacturing” link and the “wholesale and retail” link has significant impacts on the economic benefits of manufacturing industry. (3) The digital degree of the “procurement” link has no obvious influence on the economic benefits of manufacturing industry.Practical implicationsThe research results can provide reference for the formulation and implementation of micro policies. The strategy of improving the level of digital transformation of key links of manufacturing industry is put forward to better promote both the digital transformation of manufacturing industry and economic development.Originality/valueThis paper innovatively studies the relationship between digitalization of manufacturing process links and economic benefits. The findings can provide theoretical and empirical support for the digital transformation of China's manufacturing industry and high-quality development of economy.

Disentangle beneficial effects of strain engraftment after fecal microbiota transplantation in subjects with MetSyn.

Fecal Microbiota Transplantation (FMT) has emerged as a potential modality for mitigating microbiome-associated diseases. Despite this potential, the precise causal pathways by which specific gut microbiota strains induce remission remain inadequately elucidated. In this study, we aimed to discern the impact of engraftment of donor-infused strains on alterations in plasma metabolites, subsequently contributing to the amelioration of clinical parameters involved in subjects with metabolic syndrome (MetSyn) receiving an FMT. We observed that a higher fraction of donor strains engrafted in the recipient is correlated to a reduction in diastolic blood pressure and found specific strain associations through canonical correlation analysis. Integrating the metabolomics profile shows that engraftment of Collinsella aerofaciens and Fusocatenibacter saccharovorans was related to a reduction in 2-oxoarginine in plasma, which was subsequently correlated to a reduction in diastolic blood pressure. In conclusion, we applied a novel framework to elucidate on the complex and heterogenous FMT intervention, establishing a connection between engrafted microbiota and clinical outcome parameters. Our findings underscore the potential therapeutic efficacy of FMT in ameliorating MetSyn, demonstrating a potential contribution of microbial strain engraftment to the improvement of MetSyn via modulation of circulating metabolites.

Manipulating and measuring variation in deep neural network (DNN) representations of objects

We explore how DNNs can be used to develop a computational understanding of individual differences in high-level visual cognition given their ability to generate rich meaningful object representations informed by their architecture, experience, and training protocols. As a first step to quantifying individual differences in DNN representations, we systematically explored the robustness of a variety of representational similarity measures: Representational Similarity Analysis (RSA), Centered Kernel Alignment (CKA), and Projection-Weighted Canonical Correlation Analysis (PWCCA), with an eye to how these measures are used in cognitive science, cognitive neuroscience, and vision science. To manipulate object representations, we next created a large set of models varying in random initial weights and random training image order, training image frequencies, training category frequencies, and model size and architecture and measured the representational variation caused by each manipulation. We examined both small (All-CNN-C) and commonly-used large (VGG and ResNet) DNN architectures. To provide a comparison for the magnitude of representational differences, we established a baseline based on the representational variation caused by image-augmentation techniques used to train those DNNs. We found that variation in model randomization and model size never exceeded baseline. By contrast, differences in training image frequency and training category frequencies caused representational variation that exceeded baseline, with training category frequency manipulations exceeding baseline earlier in the networks. These findings provide insights into the magnitude of representational variations that can be expected with a range of manipulations and provide a springboard for further exploration of systematic model variations aimed at modeling individual differences in high-level visual cognition.

Blood inflammation relates to neuroinflammation and survival in frontotemporal lobar degeneration.

Neuroinflammation is an important pathogenic mechanism in many neurodegenerative diseases, including those caused by frontotemporal lobar degeneration (FTLD). Postmortem and in vivo imaging studies have shown brain inflammation early in these conditions, proportionate to symptom severity and rate of progression. However, evidence for corresponding blood markers of inflammation and their relationship with central inflammation and clinical outcome are limited. There is a pressing need for such scalable, accessible and mechanistically relevant blood markers as these will reduce the time, risk, and costs of experimental medicine trials. We therefore assessed inflammatory patterns of serum cytokines from 214 patients with clinical syndromes associated with FTLD as compared to healthy controls, including their correlation with brain regional microglial activation and disease progression. Serum assays used the MesoScale Discovery V-Plex-Human Cytokine 36 plex panel plus five additional cytokine assays. A sub-group of patients underwent 11C-PK11195 TSPO PET imaging, as an index of microglial activation. A Principal Component Analysis (PCA) was used to reduce the dimensionality of cytokine data, excluding cytokines that were undetectable in >50% of participants. Frequentist and Bayesian analyses were performed on the principal components, to compare each patient cohort to controls, and test for associations with central inflammation, neurodegeneration-related plasma markers and survival. The first component identified by the PCA (explaining 21.5% variance) was strongly loaded by pro-inflammatory cytokines, including TNF-α, TNF-R1, M-CSF, IL-17A, IL-12, IP-10 and IL-6. Individual scores of the component showed significant differences between each patient cohort and controls. The degree to which a patient expressed this peripheral inflammatory profile at baseline correlated negatively with survival (higher inflammation, shorter survival), even when correcting for baseline clinical severity. Higher pro-inflammatory profile scores were associated with higher microglial activation in frontal and brainstem regions, as quantified with 11C-PK11195 TSPO PET. A permutation-based Canonical Correlation Analysis confirmed the association between the same cytokine-derived pattern and central inflammation across brain regions in a fully data-based manner. This data-driven approach identified a pro-inflammatory profile across the FTLD clinical spectrum, which is associated with central neuroinflammation and worse clinical outcome. Blood-based markers of inflammation could increase the scalability and access to neuroinflammatory assessment of people with dementia, to facilitate clinical trials and experimental medicine studies.

A novel hybrid methodology integrating pixel- and object-based techniques for mapping land use and land cover from high-resolution satellite data

ABSTRACT The classification of very high-resolution satellite imagery remains a focal point in remote sensing, attracting increased attention across diverse scientific disciplines. Various classification methods, including pixel- and object-based techniques, have been proposed, and their performances and limitations have been discussed in the literature. This paper presents a hybrid method that combines the strengths of pixel- and object-based methods in image classification to minimize errors associated with the segmentation process, particularly under-segmentation errors in object-based image analysis. The core concept behind the method lies in categorizing segmented image objects as either homogeneous or heterogeneous based on their class probability. In this process, the estimated possibilities from the object-based classification model are considered, and segments are designated as homogeneous or heterogeneous using a user-defined threshold. The object-based classification model determines the class labels for homogeneous image objects, while the heterogeneous ones, containing pixels representing different land cover classes, are classified using the pixel-based model. The performance of hybrid classification models, created by varying thresholds, is analysed using high-resolution WorldView-3 and WorldView-2 imagery and compared with pixel- and object-based classification results. For the implementation of image classification methods, Canonical Correlation Forest (CCF), Extreme Gradient Boosting (XGBoost), and Categorical Boosting (CatBoost) were employed. The findings indicated that employing the suggested hybrid strategy with a threshold value selected within a specific range (e.g. between 60% and 80%) and employing a robust classification algorithm that provides class probabilities (e.g. CCF) results in a statistically significant improvement in overall accuracy compared to pixel and object-based methods, with gains of 5% and 4%, respectively. Visual analysis of the produced thematic maps revealed that the proposed method minimizes the salt-and-pepper effect associated with pixel-based classification while mitigating segmentation problems arising from object-based classification.

General and distinct correspondence between personality disorder and interpersonal functioning

The alternative model of personality disorders (AMPD) in DSM-5 includes interpersonal dysfunction as a core construct as a global severity dimension. However, it is less known how various interpersonal characteristics contribute to both general and distinct dimensions of personality dysfunction. In participants from community sources, we obtained responses to Levels of Personality Functioning Scale-Self Report (LPFS-SR), maladaptive traits (PID-5-BF), and social relationship patterns, including those related to close relationships and quantitative measures of network size. Canonical correlation analysis mapped conjoint associations between two sets of variables (personality scales and social relationship) and identified three distinct modes of correlation as significant. The first canonical pattern represented global dysfunction and was associated with utilitarianism, short-termed, weaker strengths, and smaller network sizes. The second canonical correlation represented externalizing traits and was associated with a larger number of relationships, higher utilitarianism, and short-term relationships with a close significant other. The third canonical correlation represented a detached, unemotional, and callous personality which corresponded with weaker relationship strength with both the mother and a close significant other. Our findings suggest that interpersonal functioning corresponding to personality dysfunction can be distinguished into both common and specific characteristics and further highlight the importance of characterizing distinct patterns within close relationships.

Which dimensions of nature contact in Urban Green Spaces most significantly contribute to mental wellbeing? A multidimensional analysis in Brazilian metropolitan cities

BackgroundUrban environments pose challenges to mental health, an issue that Urban Green Spaces (UGS) can potentially mitigate. While the benefits of nature contact for mental wellbeing are recognized, a multidimensional analysis remains unexplored. PurposeThis study aims to fill this gap by examining the association between nature contact within UGS and mental health. It underscores the importance of considering multiple dimensions of nature engagement—such as naturalness, intensity, duration, frequency, and infrastructure—in enhancing psychological wellbeing. MethodA comprehensive analysis, including canonical correlation, multivariate analyses of variance, and Fisher discriminant analysis, was applied to survey data from several Brazilian metropolitan cities to assess how different aspects of nature contact influence mental health. Results and conclusionsFindings reveal association between these dimensions and mental wellbeing indicators, highlighting the importance of a multidimensional perspective. Practical implicationsResults advocate for incorporating diverse aspects of nature contact in UGS design and policy-making to enhance urban dwellers' mental health. Future directionsFurther research should focus on longitudinal studies and explore the mediating effects of socio-demographic factors. Additionally, expanding research to include other developing countries will provide valuable comparative insights.

Distributed monitoring of nonlinear plant-wide processes based on GA-regularized kernel canonical correlation analysis

Fault detection and diagnosis is important for ensuring process safety and is gaining increasing attention in the system safety field. A regularized kernel canonical correlation analysis (RKCCA) approach is proposed for monitoring nonlinear plantwide processes. For each local unit, genetic algorithm (GA)-based regularization is performed to determine the communication variables from neighboring units, which preserves the maximum correlations and eliminates the irrelevant variables. Then variables from a local unit and the communication variables are mapped into high-dimensional feature spaces, and the feature space of the local unit is decomposed into three orthogonal subspaces, namely the residual subspace, the inner subspace, and the outer-related subspace. Monitoring statistics to identify both the process status and the characteristic of a detected fault are constructed. The proposed RKCCA-based monitoring method considers both the information of a local unit and the beneficial information of related units to facilitate fault detection, thereby exhibiting superior performance to some state-of-the-arts methods. Applications on the Tennessee Eastman benchmark process and an industrial tail gas treatment process demonstrate the superiority of RKCCA monitoring.

Biomechanical behavior of temporomandibular joint movements driven by mastication muscles.

Surgery of jawbones has a high potential risk of causing complications associated with temporomandibular joint disorder (TMD). The objective of this study was to investigate the effects of two drive modeling methods on the biomechanical behavior of the temporomandibular joint (TMJ) including articular disc during mandibular movements. A finite element (FE) model from a healthy human computed tomography was used to evaluate TMJ dynamic using two methods, namely, a conventional spatial-oriented method (displacement-driven) and a compliant muscle-initiated method (masticatory muscle-driven). The same virtual FE model was 3D printed and a custom designed experimental platform was established to validate the accuracy of experimental and theoretical results of the TMJ biomechanics during mandibular movements. The results show that stress distributed to TMJ and articular disc from mandibular movements provided better representation from the muscle-driving approach than those of the displacement-driven modeling. The simulation and experimental data exhibited significant strong correlations during opening, protrusion, and laterotrusion (with canonical correlation coefficients of 0.994, 0.993, and 0.932, respectively). The use of muscle-driven modeling holds promise for more accurate forecasting of stress analysis of TMJ and articular disc during mandibular movements. The compliant approach to analyze TMJ dynamics would potentially contribute to clinic diagnosis and prediction of TMD resulting from occlusal disease and jawbone surgery such as orthognathic surgery or tumor resection.