Component Canonical Analysis Research Articles

Fault detection using machine learning based dynamic ICA-distributed CCA: Application to industrial chemical process

Unexpected accidents and events in industrial chemical processes have resulted in a considerable number of causalities and property damage. Safety process management in industrial chemical processes is critical to avoid and ensure casualties and property damage. However, due to the immense scope and high complexity of current industrial chemical processes, the traditional safety process management approaches cannot address these challenges to attain adequate fault detection accuracy. To address this issue, an innovative machine learning-based distributed canonical correlation analysis-dynamic independent component analysis (DICA-DCCA) approach is needed to improve the fault detection effectiveness of complicated systems. The (DICA-DCCA) model could potentially detect anomalies and faults in industrial chemical data by utilizing three essential statistics:Id2,Ie2and squared prediction error (SPE). The practical effectiveness of the proposed frameworks is evaluated and compared using a continuous stirred tank reactor (CSTR) framework as a standard benchmark study. The research findings present that the suggested (DICA-DCCA) approach is more resilient and effective in detecting abnormalities and faults than the ICA and DICA approaches with FDR 100 % and FAR 0 %. The implied research approach is robust, operational, and productive.

Multivariate Analysis of Copepod’s Distribution in Jallo Lake, Lahore Pakistan

Copepods are valuable zooplankton found globally. Fish eat them. Any water ecosystem has food chains and webs. Their diversity and density depend on physicochemical factors. Objective: The Jallo Lake was targeted for the investigation of the spatio-temporal distribution of copepods from January to December 2023. Methods: Copepods were collected from Jallo Park's freshwater with a zooplankton mesh. These organisms were species-classified using conventional keys. Separate water samples were taken to examine physicochemical characteristics. Sedgwick Rafter chamber for species counting. PAST software was used for PCA I & II and CCA. Results: Ten species and their nauplius larvae from seven orders were identified in this study. The study examined conductivity, oxygen saturation, dissolved oxygen, pH, and transparency. Air and water temperature was also recorded. Analysis of Variance (ANOVA) for physicochemical properties, excluding transparency, was statistically significant at (= 0.05, P = 0.000). Copepod variety and density peaked in June and July and dropped in October and December. The dendrogram showed three cluster-level variations. Plotting copepod species and month abundance curves. Principal component analysis (PCA I, PCA II) was used to correlate months, copepod species, and physicochemical parameters. Canonical component analysis (CCA) shows diversity similarities between sites on the same water body and links species abundance to environmental conditions. Conclusions: Only ten copepod species from seven orders and nauplius larvae were isolated from the aquatic body under research during the study months. Copepod diversity and density in freshwater lakes depended on environmental conditions.

Assessing environmental awareness activism to river decay and recurring pollution using parallel multiple mediator model

ABSTRACT The decay of rivers coupled with its escalated pollution is a concern worldwide. The present study intends to assess the agony of the riverine people due to the contamination of the Churni River and the transformation of their grievance into environmental activism at individual and community levels for rejuvenating the river and for a secured livelihood. The study observed an enriched concentration of biological oxygen demand, nitrate, and phosphate and a reduced concentration of dissolved oxygen during 2011–2020 due to the release of untreated industrial wastewater, sewage from urban areas, and agricultural runoff into the river. A systematic investigation reveals pollution-induced socio-psychological trauma and community awareness leading to the active involvement of the people in the environmental awareness movement, which was mediated by self-efficacy, self-responsibility, self-identity, and community value. A parallel multiple mediator model was employed, which included 29 parameters for exploring the key-mediated factors for the environmental movement. The model-based results identified that self-responsibility and community-value for upper stretch villages and self-efficacy and community-value for the lower stretch villages are significant mediators of environmental activism. A canonical component analysis predicted socio-demographic factors (e.g. age, dependency ratio female-male ratio, etc.) as intrinsically linked to environmental activism. This study is significant because it reveals how pollution and river degradation affect riverine people. It also clarifies how local grievances turned into environmental activism as a result of the documented socio-psychological trauma and growing community awareness. This study would thus play a pivotal role in understanding the human-nature complex to better planning and river restoration.

Diversity and community structure of soil microarthrophods of several moorlands in Gumukmas District, Jember Regency, East Java

<p>The effectiveness of soil microarthropods as a bioindicator was studied to evaluate various soils in the conditions of various lands, including moorland in Gumukmas District, Jember Regency. This study focuses on data collection of the diversity and structure of soil microarthropod communities along with the assessment of their ecological parameters. Field observations were carried out in five villages in Gumukmas District from August-September 2022 using the hand sorting method. The data were analyzed using α-diversity parameters (Dominance Index, Simpson Index, Evenness, Shannon-Weiner Index, Brillouin Index, and Margalef Species Richness). Habitat similarities were presented by UPGMA multivariate analysis and the estimation of abiotic factors that influence soil microarthropod composition was estimated by Canonical Component Analysis (CCA). The observations showed a total of 24 families from 13 soil microarthropod orders that spread across Gumukmas District. The abundance of diversity based on the α-diversity is still relatively low to moderate, nevertheless, the correlation of microarthropod orders to environmental factors can reveal conditions of the soil cycle through the study site. The results of the study are expected to assist in efforts to restore the diversity of soil microarthropods to support better soil quality.</p>

Characterization of central manifestations in patients with Niemann-Pick disease type C

PurposeNiemann-Pick disease type C (NPC) is a rare lysosomal storage disease characterized by progressive neurodegeneration and neuropsychiatric symptoms. This study investigated pathophysiological mechanisms underlying motor deficits, particularly speech production, and cognitive impairment. MethodsWe prospectively phenotyped 8 adults with NPC and age-sex-matched healthy controls using a comprehensive assessment battery, encompassing clinical presentation, plasma biomarkers, hand-motor skills, speech production, cognitive tasks, and (micro-)structural and functional central nervous system properties through magnetic resonance imaging. ResultsPatients with NPC demonstrated deficits in fine-motor skills, speech production timing and coordination, and cognitive performance. Magnetic resonance imaging revealed reduced cortical thickness and volume in cerebellar subdivisions (lobule VI and crus I), cortical (frontal, temporal, and cingulate gyri) and subcortical (thalamus and basal ganglia) regions, and increased choroid plexus volumes in NPC. White matter fractional anisotropy was reduced in specific pathways (intracerebellar input and Purkinje tracts), whereas diffusion tensor imaging graph theory analysis identified altered structural connectivity. Patients with NPC exhibited altered activity in sensorimotor and cognitive processing hubs during resting-state and speech production. Canonical component analysis highlighted the role of cerebellar-cerebral circuitry in NPC and its integration with behavioral performance and disease severity. ConclusionThis deep phenotyping approach offers a comprehensive systems neuroscience understanding of NPC motor and cognitive impairments, identifying potential central nervous system biomarkers.

A data expansion technique based on training and testing sample to boost the detection of SSVEPs for brain-computer interfaces

Objective. Currently, steady-state visual evoked potentials (SSVEPs)-based brain-computer interfaces (BCIs) have achieved the highest interaction accuracy and speed among all BCI paradigms. However, its decoding efficacy depends deeply on the number of training samples, and the system performance would have a dramatic drop when the training dataset decreased to a small size. To date, no study has been reported to incorporate the unsupervised learning information from testing trails into the construction of supervised classification model, which is a potential way to mitigate the overfitting effect of limited samples. Approach. This study proposed a novel method for SSVEPs detection, i.e. cyclic shift trials (CSTs), which could combine unsupervised learning information from test trials and supervised learning information from train trials. Furthermore, since SSVEPs are time-locked and phase-locked to the onset of specific flashes, CST could also expand training samples on the basis of its regularity and periodicity. In order to verify the effectiveness of CST, we designed an online SSVEP-BCI system, and tested this system combined CST with two common classification algorithms, i.e. extended canonical correlation analysis and ensemble task-related component analysis. Main results. CST could significantly enhance the signal to noise ratios of SSVEPs and improve the performance of systems especially for the condition of few training samples and short stimulus time. The online information transfer rate could reach up to 236.19 bits min−1 using 36 s calibration time of only one training sample for each category. Significance. The proposed CST method can take full advantages of supervised learning information from training samples and unsupervised learning information of testing samples. Furthermore, it is a data expansion technique, which can enhance the SSVEP characteristics and reduce dependence on sample size. Above all, CST is a promising method to improve the performance of SSVEP-based BCI without any additional experimental burden.

Structural and functional pathology in cocaine use disorder with polysubstance use: A multimodal fusion approach structural-functional pathology in cocaine use disorder

Cocaine use disorder (CUD) is described as a compulsive urge to seek and consume cocaine despite the inimical consequences. MRI studies from different modalities have shown that CUD patients exhibit structural and/or functional connectivity pathology among several brain regions. Nevertheless, both connectivities are commonly studied and analyzed separately, which may potentially obscure its relationship between them, and with the clinical pathology. Here, we compare structural and functional brain networks in CUD patients and healthy controls (HC) using multimodal fusion. The sample consisted of 63 (8 females) CUD patients and 42 (9 females) healthy controls (HC), recruited as part of the SUDMEX CONN database. For this, we computed a battery of graph-based measures from multi-shell diffusion-weighted imaging and resting state fc-fMRI to quantify local and global connectivity. Then we used multimodal canonical component analysis plus joint independent component analysis (mCCA+jICA) to compare between techniques and evaluate group differences and its association with clinical alteration. Unimodal results showed a striatal decrease in the participation coefficient but applied supervised data fusion revealed other regions with cocaine-related alterations in joint functional communication. When performing multimodal fusion analysis, we observed a higher centrality of the interrelationship and a lower participation coefficient in patients with CUD. In contrast to the unimodal approach, the multimodal fusion method was able to reveal latent information about brain regions involved in impairment due to cocaine abuse. The present results could help in understanding the pathology of CUD to develop better pre-treatment/post-treatment intervention designs.

Revolutionizing sentiment classification: A deep learning approach using self-attention based encoding–decoding transformers with feature fusion

In recent times, the growth of human computer interaction and Artificial Intelligence attains more interest especially in facial expression detection. Though the field has attained tremendous progress, still many issues are pertained as the facial expressions are complex. Therefore the present study aims to increase the efficiency in classifying the emotions of humans from the images of FER-2013 dataset and strives to attain optimal accuracy. Most of the studies have averted multi-modal parameters like a video for emotion detection. Moreover, existing studies lacked a detection rate due to ineffective feature extraction that negatively impacted the classification rate. For avoiding such pitfalls, this study proposes suitable data mining-based algorithms with the main intention to attain high accuracy. The present study proposes Deep Location Attention Forest method for emotion detection with higher accuracy. To accomplish this, DLFAT (Deep Location Feed Attention Transformers) is used for feature extraction from various sub-space representation at different position of the image. CK-PCA (Canonical Kernel-Principal Component Analysis) is performed feature fusion to improve the performance of the classifier. MRF (Modified Random Forest) is proposed to perform classification and predicts the emotions based on the facial expressions. The main intention of RF relies on learning all the data subset weights that alleviate loss amongst the predicted value for accomplishing better input classification to the related label. The proposed system is validated by the performance metrics in which the outcome is found to be 0.96197 as accuracy, 0.96 as F1-Score, 0.97 as recall and 0.96 as precision and the outcomes reveal the efficacy of the system in emotion detection.

One-Shot Distributed Generalized Eigenvalue Problem (DGEP): Concept, Algorithm and Experiments

This paper focuses on the design of a distributed algorithm for generalized eigenvalue problems (GEPs) in one-shot communication. Since existing distributed methods for eigenvalue decomposition cannot be applied to GEP, a general one-shot distributed GEP framework is proposed. The theoretical analysis of the approximation error reveals its relation to the divergence of the data covariance, the eigenvalues of the empirical data covariance, and the number of local servers. If the symmetric data covariance has repeated eigenvalues in GEP, e.g., in canonical component analysis, we further modify the method for better convergence and prove the necessity experimentally. Numerical experiments validate the effectiveness of the proposed algorithms both on synthetic and real-world datasets.

A case of integrative taxonomy based on traditional morphology, molecular systematics and geometric morphometrics in the taxonomy of Torrenticolidae (Acari, Hydrachnidiae)

An integrative taxonomy based on traditional morphological method, molecular systematics and geometric morphometrics was tested to identify two species of torrenticolid mites, which are similar in morphology. A new species of the water mite genus Torrenticola from China, T. nipponicella Gu & Guo sp. nov., was described and illustrated in this paper. The descriptions included morphological features, molecular data, geometric morphometric data, and a discussion of their taxonomic status and integrative taxonomy. Meanwhile, some potential taxonomic characters of those species were analyzed by canonical variate analysis and principal component analysis. Those analyses of two landmark configurations revealed important taxonomical characters in dorsal (dorsoglandularia 1–3) and ventral shields (coxoglandularia 2, 4, ventroglandularia 3).

Canonical Variate Nonlinear Principal Component Analysis for Monitoring Nonlinear Dynamic Processes

Conventional multivariate statistical process monitoring methods constrained by the assumptions of linear and normal distributions for the measurements, such as principal component analysis and canonical variate analysis, demonstrate significantly higher fault alarm rates and lower fault detection rates in nonlinear dynamic industrial process monitoring. Kernel principal component analysis (KPCA) based on the radial basis function, has already been applied in numerous nonlinear industrial processes. However, an infinite-dimensional nonlinear mapping might be inefficient and redundant. To improve the efficiency of traditional methods, this study proposes the implementation of canonical variate nonlinear principal component analysis for monitoring nonlinear dynamic processes. The training data are first preprocessed by performing canonical variate analysis to reduce the effects of the dynamic characteristics of the data. Then, the state vectors are projected into a high dimension feature space by an explicit second-order polynomial mapping. The first k principal components and the remaining residual vectors are obtained in the feature space via conventional principal component analysis for fault detection. The combined statistic Qc is proposed for monitoring the variations in the linear and nonlinear residual spaces; its upper control limits can be estimated by the kernel density function. In comparison to the results of KPCA and nonlinear dynamic principal component analysis, the proposed method yielded significantly higher fault detection rates and relatively lower fault alarm rates in a simulated nonlinear dynamic process and the benchmark Tennessee Eastman process.

Strong Environmental Filtering Based on Hydraulic Traits Occurring in the Lower Water Availability of Temperate Forest Communities.

The trait-based approaches have made progress in understanding the community assembly process. Here, we explore the key traits that may shape community assembly patterns of the same community type but within different water availabilities. Natural Quercus wutaishanica forests were chosen as a suitable study system to test the difference between economic and hydraulic traits across water availability on the Loess Plateau (LP, drought region) and Qinling Mountains (QL, humid region) of China. A total of 75 plots were established separately in two sites, and 12 functional traits (seven hydraulic traits and five economic traits) of 167 species were studied. Community-weighted mean trait values and functional diversity indices were compared between the two sites. Canonical component analysis was performed to infer whether the changes of community traits and their relationships are driven by intraspecific variation or species turnover. Evidence for likely community assembly processes was tested using the null model to determine whether functional structure among seven hydraulic traits and five economic traits was dominated by different ecological processes between two sites. We found that forests in the Loess Plateau and Qinling Mountains showed different hydraulic and economic traits. Hydraulic and economic traits coupled at the community level were driven by species turnover. Hydraulic traits showed more significant convergent patterns on LP than that in QL. Our results suggest a strong environmental filtering process occurred in hydraulic-based community assembly in the temperate forest with low water availability. Reveal the relationship of hydraulic and economic traits at the community level. Emphasize the critical role of multi-dimensional traits selecting like hydraulic traits in community ecology.

Comparison between two multivariate analyses for the evaluation of genetic divergence for carcass and meat quality traits in alternative lines of chicken

The univariate analysis is becoming harder to use due the increasing number of characteristics of economic importance in agricultural industry. The multivariate approach provides an answer to this issue, allowing to analyze several traits when comparing different methodologies, genetics and products. This study aimed to use and compare the canonical variable analysis (CVA) and principal component analysis (PCA) to evaluate 7 genotypes of alternative lines of chicken (Caboclo, Carijó, Colorpak, Gigante Negro, Pesadão Vermelho, Naked Neck and Tricolor). The study evaluated 840 male chicks reared at 91 days from these genotypes, in a completely randomized design with 4 replicates per genotype. Different traits (23) were measured, and only 7 remained relevant after the multivariate approach: Carcass yield, Breast Yield, Back Yield, Cooking Loss, lightness, yellowness and water holding capacity. Both analyses remained with two variables explaining the variating. The Pearson correlation was used to measure the traits responsible for the most variance between genotypes. On the principal component cooking loss, carcass and breast yields, and the color parameters lightness and yellowness were the most relevant, while on canonical variables it was carcass yield, breast yield, lightness, yellowness and back yield. Both analysis resulted in similar conclusion, allowing to classify the genotypes in three major groups: 1 (Pesadão vermelho, Carijó, Colorpak, Nacked Neck), 2 (Gigante Negro and Caboclo) and 3 (Tricolor). PCA and CVA facilitate the interpretation of data with several traits of importance, showing the main traits responsible for genetic divergence.

Brain multimodal co-alterations related to delay discounting: a multimodal MRI fusion analysis in persons with and without cocaine use disorder

BackgroundDelay discounting has been proposed as a behavioral marker of substance use disorders. Innovative analytic approaches that integrate information from multiple neuroimaging modalities can provide new insights into the complex effects of drug use on the brain. This study implemented a supervised multimodal fusion approach to reveal neural networks associated with delay discounting that distinguish persons with and without cocaine use disorder (CUD).MethodsAdults with (n = 35) and without (n = 37) CUD completed a magnetic resonance imaging (MRI) scan to acquire high-resolution anatomical, resting-state functional, and diffusion-weighted images. Pre-computed features from each data modality included whole-brain voxel-wise maps for gray matter volume, fractional anisotropy, and regional homogeneity, respectively. With delay discounting as the reference, multimodal canonical component analysis plus joint independent component analysis was used to identify co-alterations in brain structure and function.ResultsThe sample was 58% male and 78% African–American. As expected, participants with CUD had higher delay discounting compared to those without CUD. One joint component was identified that correlated with delay discounting across all modalities, involving regions in the thalamus, dorsal striatum, frontopolar cortex, occipital lobe, and corpus callosum. The components were negatively correlated with delay discounting, such that weaker loadings were associated with higher discounting. The component loadings were lower in persons with CUD, meaning the component was expressed less strongly.ConclusionsOur findings reveal structural and functional co-alterations linked to delay discounting, particularly in brain regions involved in reward salience, executive control, and visual attention and connecting white matter tracts. Importantly, these multimodal networks were weaker in persons with CUD, indicating less cognitive control that may contribute to impulsive behaviors.

Steady-State Visual Evoked Potential Classification Using Complex Valued Convolutional Neural Networks.

The steady-state visual evoked potential (SSVEP), which is a kind of event-related potential in electroencephalograms (EEGs), has been applied to brain–computer interfaces (BCIs). SSVEP-based BCIs currently perform the best in terms of information transfer rate (ITR) among various BCI implementation methods. Canonical component analysis (CCA) or spectrum estimation, such as the Fourier transform, and their extensions have been used to extract features of SSVEPs. However, these signal extraction methods have a limitation in the available stimulation frequency; thus, the number of commands is limited. In this paper, we propose a complex valued convolutional neural network (CVCNN) to overcome the limitation of SSVEP-based BCIs. The experimental results demonstrate that the proposed method overcomes the limitation of the stimulation frequency, and it outperforms conventional SSVEP feature extraction methods.

Behavioural and physiological responses of male and female beef cattle to weaning at 30, 75 or 180 days of age

Weaning calves at a young age can generate great stress, but it is widely practiced in the industry despite that. So, to what extend weaning in early ages is more stressful than at later ones, in terms of the amount of stress, is currently unknown. Thus, we studied the behavioural and physiological impacts in beef calves at three ages at weaning (30, 75, and 180 days) and the consequences of the calf's sex. Thirty-six calves were weaned and distributed in hyper-early (W30), early (W75), and conventional (W180) weaning groups, which are weaning ages that occur in practice. Behavioural activities and physiological parameters were measured on days 0, 1, 2, and 7 after weaning. Canonical component analysis (CCA) and analysis of variance (ANOVA) were used to evaluate behavioural and physiological parameters. The variables analysed were influenced by the treatment, day of evaluation and interaction between treatment × day, and without effect for sex. The younger the calf, the greater the intensity of responses to the weaning stress. In this sense, the behavioural results (percentages of observations ± SEM) demonstrate that on D0, W30 calves emitted more extreme vocalization (61 %) compared to W75 (15 %) and W180 (0%) (P < 0.001); on D1, W30 and W75 calves expressed more extreme sounds (61 % and 50 %, respectively) than W180 (21 %) (P = 0.028). Similarly, W30 and W75 calves showed a higher number of cross-sucking (P = 0.006). On D0, differences in the frequency of walking (P < 0.001) were observed, once calves of W30 (45.5 ± 6.21 %) and W75 (39.9 ± 6.03 %) spent more time in this activity than W180 ones (17.3 ± 3.80 %). Also, more visiting the feeder without eating feed events were verified (P = 0.014) on D0 (11.5 ± 2.59 %) and D1 (6.2 ± 1.65 %) for W30 when compared to W180 calves (2.6 ± 1.73 % and 0.0 ± 0.00 %, respectively). In physiological terms, a higher respiratory rate (P = 0.043) on D0 was identified for W30 calves (66.3 ± 2.90 breaths/min) than for W75 (57.8 ± 2.30 breaths/min) or W180 (47.3 ± 2.02 breaths/min). Cortisol concentrations were higher (P = 0.019) on D0 for W30 animals (15.6 ± 3.40 ng/mL) than for W180 ones (9.7 ± 1.90 ng/mL). The peak of cortisol occurred on D1 for W30 and D2 for W75 and W180. Therefore, behavioural and physiological changes at young ages indicate greater calf suffering, which may have negative consequences on a productive life.

A new fault detection scheme based on canonical independent component analysis with application to hot strip mill process

Aiming at the problems of inaccurate fault detection and error alarm in the process of hot strip mill process, a fault detection scheme of canonical independent component analysis is proposed. The new scheme first uses canonical variable analysis to calculate the canonical variable matrix of observation data, which effectively solves the problem of autocorrelation and cross-correlation. Then the canonical variable matrix is decomposed by independent component analysis to obtain independent elements. Finally, the data are monitored online through constructing statistics. It is proved that the accuracy of the scheme for identifying fault data is reached to 100%, and the misjudgment rate data are reduced to less than 0.6% through the simulation study of the hot strip mill process data.

Evaluation of Soil Biodiversity in Alpine Habitats through eDNA Metabarcoding and Relationships with Environmental Features

Soil biodiversity is fundamental for ecosystems, ensuring many ecosystem functions, such as nutrient cycling, organic matter decomposition, soil formation, and organic carbon pool increase. Due to these roles, there is a need to study and completely understand how soil biodiversity is composed through different habitats. The aim of this study was to describe the edaphic soil community of the alpine environments belonging to the Gran Paradiso National Park, thus detecting if there are any correlation with environmental features. We studied soil fauna through environmental DNA metabarcoding. From eDNA metabarcoding, 18 families of arthropods were successfully detected, and their abundance expressed in terms of the relative frequency of sequences. Soil faunal communities of mixed coniferous forests were characterized by Isotomidae, Entomobriydae, Hypogastruridae, and Onychiuridae; while mixed deciduous forests were composed mostly by Isotomidae, Cicadidae, Culicidae, and Neelidae. Calcicolous and acidic grasslands also presented families that were not detected in forest habitats, in particular Scarabaeidae, Curculionidae, Brachyceridae, and had in general a more differentiated soil community. Results of the Canonical Component Analysis revealed that the main environmental features affecting soil community for forests were related to vegetation (mixed deciduous forests, tree basal area, tree biomass, Shannon index), soil (organic layers and organic carbon stock), and site (altitude); while for prairies, soil pH and slope were also significant in explaining soil community composition. This study provided a description of the soil fauna of alpine habitats and resulted in a description of community composition per habitat and the relation with the characteristic of vegetation, soil, and topographic features of the study area. Further studies are needed to clarify ecological roles and needs of these families and their role in ecosystem functioning.

Evaluation of ecosystem services in a protected mountain area: Soil organic carbon stock and biodiversity in alpine forests and grasslands

Ecosystem services (ES) evaluation is included in the environmental programs and policy strategies of protected natural areas in many countries. Alpine forests and grasslands play an important role in climate regulation but their contribution is still unknown. In this study, we estimated soil organic carbon (SOC) stocks for forest and grassland habitats by collecting samples from 87 plots in Gran Paradiso National Park (western Italian Alps). Results of the LMM show that habitat type affects SOC stock; grasslands and mixed broadleaf forests store higher SOC than mixed coniferous forests, spruce forests and larch forests. We investigate the relationships between biodiversity, SOC stock, OC stock in organic layers, soil types, forests structure and other environmental features using a canonical component analysis and a Pearson correlation matrix. The results show that biodiversity is mainly influenced by the altitude, OC stock in organic layers OH and habitats of coniferous forests. Biodiversity positively correlates to organic layers (Staphylinidae, Formicidae, Orthoptera), forests’ Shannon and evenness indices (Carabidae, Formicidae, Orthoptera, Aranea, Lepidoptera) and forests’ basal areas and stem density (Staphylinidae, Formicidae, Aranea). Further studies are needed to better investigate the relation between biodiversity and habitat features on ecosystem functions and thus on the provision of ES.

Quality monitoring method based on enhanced canonical component analysis

In continuous processes, the quality variables generally can be interpreted by the process variables due to intercorrelation. However, in particular condition, the past quality trends may be responsible for interpretation due to the auto-correlation. The existing methods only reveal one of the correlations. Considering the effects of two types of correlations for quality monitoring, this study develops enhanced canonical component analysis (ECCoA) method based on Canonical Correlation Analysis (CCA). For revealing the intercorrelation, CCA is performed to extract the quality related features from the process variables. However, the components of CCA ignore the variance formation in the data. To retain both cross-data (process variables and quality variables) correlation information and the variance information within process variables, principle projective-CCA (PP-CCA) method is proposed, generating the primary feature subspace to capture the variation of quality variables. Moreover, as for the auto-correlation, on the residual obtained in PP-CCA method, a residual-CCA (R-CCA) method is proposed for modelling and generating the complementary feature subspace, reflecting the trends of quality variables. Sequentially, statistical indexes and decision-making logic are established for online monitoring. A numerical case and the Tennessee Eastman process are tested for validation. The achieved results indicate the feasibility and efficiency of the proposed enhanced canonical component analysis method.