Including Principle Component Analysis Research Articles

Contamination of trace, non-essential/heavy metals in nutraceuticals/dietary supplements: A chemometric modelling approach and evaluation of human health risk upon dietary exposure

Across the world, nutraceuticals/dietary supplements are commonly consumed without medical supervision, and believing these products are harmless to health. However, these products may contain trace (TMs) and non-essential/heavy metals (nHMs) as contaminants at levels higher than the recommended daily allowance (RDA), which can be hazardous to human health. Consequently, it is crucial to assess the levels of these metals to ensure the safety of these products. This study aimed to analyze the concentration of TMs (Mn, Cu and Zn) and nHMs (Al, Cr, Ni, Cd and Pb) in nutraceuticals/dietary supplements. Metal analysis was conducted using inductively coupled plasma–optical emission spectrometry (ICP-OES). Multivariate and bivariate analysis including principle component analysis (PCA), hierarchical cluster analysis (HCA) and Pearson correlation coefficient (PCC) were applied to understand inter-metal association and sources of these metals. Concentration ranges for TMs were found as, Mn (0.2–4.3 mg/kg), Cu (0.11–2.54 mg/kg), and Zn (0.1–22.66 mg/kg) while the nHMs concentration ranges were: Al (0.046–3.336 mg/kg), Cr (0.11–1.63 mg/kg), Ni (0.18–0.72 mg/kg), Cd (0.04–0.92 mg/kg), and Pb (0.18–1.08 mg/kg). The levels of tolerable dietary intake (TDI) for Cr and Ni, and the provisional tolerable monthly intake (PTMI) limit for Cd, exceeded the values set by the World Health Organization (WHO) and the European Food Safety Authority (EFSA). The estimation of the target hazard quotient (THQ <1), hazard index (HI < 1) and cumulative cancer risk (CCR <1 ✕ 10−3) indicated no significant non-carcinogenic and carcinogenic health risks associated with consuming these products. Therefore, the primary recommendation from this study is to use the nutraceuticals/dietary supplements should be under the supervision of dietitian.

Factors associated to physical activity in patients with COPD: An ecological approach

BackgroundPhysical activity (PA) is low in patients with Chronic Obstructive Pulmonary Disease (COPD). Identifying modifiable and non-modifiable correlates of PA give understanding of the individual behavior and provide future directions for PA enhancing interventions. As PA is complex and multidimensional, it should be embedded within a thorough framework. ObjectiveTo identify correlates of PA in a comprehensive COPD population based on a broad ecological model, including physiological, psychological, socio-demographic and environmental dimensions. MethodsPA was objectively measured using the Dynaport Movemonitor and a comprehensive data collection of physiological, psychological, socio-demographic and environmental factors were collected. Bivariable and multivariable regression analyses (including principle component analysis) were executed. ResultsFor this cross-sectional analysis, we included 148 patients with COPD and valid PA data (mean (SD) age 68 (7) years, FEV1 57 (17) % predicted, 5613 (3596) steps per day). Significant bivariable associations were found for physiological (exercise capacity, muscle force, lung function, symptoms, comorbidities), psychological (e.g. fatigue, motivation, perceived difficulty with PA), socio-demographic (dog owning, use of activity tracker) and environmental (season, daylight, temperature) factors. Based on the multivariable regression model, exercise capacity, beliefs on motivation, importance and self-confidence regarding PA and weather conditions were independent correlates of mean steps per day (R2 = 0.35). Movement intensity during walking was only independently associated with exercise capacity and age (R2 = 0.41). ConclusionAlthough a wide range of potential influence factors were evaluated, variance in PA was only partly explained, supporting that PA is a complex behavior which is difficult to predict.

DigitalExposome: quantifying impact of urban environment on wellbeing using sensor fusion and deep learning

The increasing level of air pollutants (e.g. particulates, noise and gases) within the atmosphere are impacting mental wellbeing. In this paper, we define the term ‘DigitalExposome’ as a conceptual framework that takes us closer towards understanding the relationship between environment, personal characteristics, behaviour and wellbeing using multimodal mobile sensing technology. Specifically, we simultaneously collected (for the first time) multi-sensor data including urban environmental factors (e.g. air pollution including: Particulate Matter (PM1), (PM2.5), (PM10), Oxidised, Reduced, Ammonia (NH3) and Noise, People Count in the vicinity), body reaction (physiological reactions including: EDA, HR, HRV, Body Temperature, BVP and movement) and individuals’ perceived responses (e.g. self-reported valence) in urban settings. Our users followed a pre-specified urban path and collected the data using a comprehensive sensing edge device. The data is instantly fused, time-stamped and geo-tagged at the point of collection. A range of multivariate statistical analysis techniques have been applied including Principle Component Analysis, Regression and Spatial Visualisations to unravel the relationship between the variables. Results showed that Electrodermal Activity (EDA) and Heart Rate Variability (HRV) are noticeably impacted by the level of Particulate Matter in the environment. Furthermore, we adopted Convolutional Neural Network (CNN) to classify self-reported wellbeing from the multimodal dataset which achieved an f1-score of 0.76.

Identification of Serum-Predictive Biomarkers for Subclinical Mastitis in Dairy Cows and New Insights into the Pathobiology of the Disease.

Targeted direct injection/liquid chromatography coupled to tandem mass spectrometry-based metabolomics was employed to identify metabolite alterations that could differentiate subclinical mastitis (SCM) from control (CON) dairy cows at -8, -4, disease diagnosis, +4 and +8 wks relative to parturition. We identified and measured 128 metabolites in the serum. Univariate analysis revealed significant alterations of serum metabolites at all five time points studied. By applying multivariate analyses including principle component analysis and partial least squares-discriminant analysis, some of the metabolites were found to have the strongest power for discriminating the SCM from CON cows. The top five metabolites with the greatest variable importance in projection values were selected as potential biomarkers for SCM. A set of five serum metabolites including lysine, ornithine, isoleucine, LysoPC a C17:0, and leucine at -8 wks and five other metabolites including lysine, leucine, isoleucine, kynurenine, and sphingomyelin (SM) C26:0 at -4 wks prepartum were determined as predictive biomarkers for SCM, which provided highly predictive capabilities with AUC (area under the curve) at 1.00. Five metabolites including lysine, leucine, isoleucine, kynurenine, and SM C26:1 in the serum were identified as diagnostic biomarkers for SCM with the AUC of 1.00. Moreover, we observed that distinct metabolic pathways were affected in SCM cows including lysine degradation, biotin, cysteine, methionine, and glutathione metabolism, valine, leucine, and isoleucine biosynthesis and degradation, and aminoacyl-tRNA biosynthesis prior to and during the occurrence of the disease. Results of this study showed that metabolomics analyses can be used to identify susceptible cows to SCM starting from -8 and -4 wks prepartum and that blood can be used to diagnose cows with SCM.

Surface-enhanced Raman spectral analysis for comparison of PCR products of hepatitis B and hepatitis C

BackgroundSurface-enhanced Raman spectroscopy is a reliable tool for identification and differentiation of two diseases showing similar symptoms, hepatitis B (HBV) and hepatitis C (HCV). ObjectivesTo develop a polymerase chain reaction technique (PCR) based SERS technique for differentiation of two human pathological conditions sharing the same symptoms using multivariate data analysis techniques e.g. principle component analysis (PCA) and partial least square discriminate analysis (PLS-DA). MethodsPCR products of HBV and HCV were differentiated by SERS using silver nanoparticles (AgNPs) as a SERS substrate. For this analysis, PCR products of both the diseases with predetermined viral loads were collected and analyzed under SERS instrument and unique SERS spectra of HBV and HCV was compared showing many differences at various points. Diseased classes of HBV and HCV and their negative control classes (viral load less than 1) were compared. PCR products of true healthy DNA and RNA were also compared, which were significantly separated. Moreover, SERS data was analyzed using multivariate data analysis techniques including principle component analysis (PCA) and partial least square discriminate analysis (PLS-DA) and differences were so prominent to observe. ResultsSERS spectral data of HBV and HCV showed clear differences and were significantly separated using PCA. Negative control samples of both disorders and their true healthy samples of DNA and RNA were separated according to 1st principle component. By analyzing data using partial least square discriminate analysis, differentiation of two disease classes was considered more valid with sensitivity, specificity and accuracy value of 96%, 94% and 98% respectively. Value of area under curve (AUROC) was 0.7527. ConclusionSERS can be employed for identification and comparison of two human pathological conditions sharing the same symptomology.

Classification of pavement climatic regions through unsupervised and supervised machine learnings

This study extracted 16 climatic data variables including annual temperature, freeze thaw, precipitation, and snowfall conditions from the Long-term Pavement Performance (LTPP) program database to evaluate the climatic regionalization for pavement infrastructure. The effect and significance of climate change were firstly evaluated using time as the only predictor and t-test. It was found that both the temperature and humidity increased in most States. Around one third of the 800 weather stations record variation of freeze and precipitation classifications and a few of them show significant change of classifications over time based on the results of logistic regression analyses. Three unsupervised machine learning including Principle Component Analysis (PCA), factor analysis and cluster analysis were conducted to identify the main component and common factors for climatic variables, and then to classify datasets into different groups. Then, two supervised machine learning methods including Fisher’s discriminant analysis and Artificial Neural Networks (ANN) were adopted to predict the climatic regions based on climatic data. Results of PCA and factor analysis show that temperature and humidity are the first two principle components and common factors, accounting for 71.6% of the variance. The 4-means clusters include wet no freeze, dry no freeze, dry freeze and snow freeze. The best k-mean clustering suggested 9 clusters with more temperature clusters. Both the Fisher’s linear discriminant analysis and ANN can effectively predict climatic regions with multiple climatic variables. ANN performs better with higher R square and low misclassification rate, especially for those with more layers and nodes.

Free amino acids in African indigenous vegetables: Analysis with improved hydrophilic interaction ultra-high performance liquid chromatography tandem mass spectrometry and interactive machine learning

A hydrophilic interaction (HILIC) ultra-high performance liquid chromatography (UHPLC) with triple quadrupole tandem mass spectrometry (MS/MS) method was developed and validated for the quantification of 21 free amino acids (AAs). Compared to published reports, our method renders collectively improved sensitivity with lower limit of quantification (LLOQ) at 0.5~42.19 ng/mL with 0.3 μL injection volume (or equivalently 0.15~12.6 pg injected on column), robust linear range from LLOQ up to 3521~5720 ng/mL (or 1056 ~ 1716 pg on column) and a high throughput with total time of 6 min per sample, as well as easier experimental setup, less maintenance and higher adaptation flexibility. Ammonium formate in the mobile phase, though commonly used in HILIC, was found unnecessary in our experimental setup, and its removal from mobile phase was key for significant improvement in sensitivity (4~74 times higher than with 5 mM ammonium formate). Addition of 10 (or up to100 mM) hydrochloric acid (HCl) in the sample diluent was crucial to keep response linearity for basic amino acids of histidine, lysine and arginine. Different HCl concentration (10~100 mM) in sample diluent also excreted an effect on detection sensitivity, and it is of importance to keep the final prepared sample and calibrators in the same HCl level. Leucine and isoleucine were distinguished using different transitions. Validated at seven concentration levels, accuracy was bound within 75~125%, matrix effect generally within 90~110%, and precision error mostly below 2.5%. Using this newly developed method, the free amino acids were then quantified in a total of 544 African indigenous vegetables (AIVs) samples from African nightshades (AN), Ethiopian mustards (EM), amaranths (AM) and spider plants (SP), comprising a total of 8 identified species and 43 accessions, cultivated and harvested in USA, Kenya and Tanzania over several years, 2013~2018. The AN, EM, AM and SP were distinguished based on free AAs profile using machine learning methods (ML) including principle component analysis, discriminant analysis, naïve Bayes, elastic net-regularized logistic regression, random forest and support vector machine, with prediction accuracy achieved at ca. 83~97% on the test set (train/test ratio at 7/3). An interactive ML platform was constructed using R Shiny at https://boyuan.shinyapps.io/AIV_Classifier/ for modeling train-test simulation and category prediction of unknown AIV sample(s). This new method presents a robust and rapid approach to quantifying free amino acids in plants for use in evaluating plants, biofortification, botanical authentication, safety, adulteration and with applications to nutrition, health and food product development.

Tea quality evaluation by applying E-nose combined with chemometrics methods.

Tea is one of the most popular beverage with distinct flavor consumed worldwide. It is of significance to establish evaluation method for tea quality controlling. In this work, electronic nose (E-nose) was applied to assess tea quality grades by detecting the volatile components of tea leaves and tea infusion samples. The "35th s value", "70th s value" and "average differential value" were extracted as features from E-nose responding signals. Three data reduction methods including principle component analysis (PCA), multi-dimensional scaling (MDS) and linear discriminant analysis (LDA) were introduced to improve the efficiency of E-nose analysis. Logistic regression (LR) and support vector machine (SVM) were applied to set up qualitative classification models. The results indicated that LDA outperformed original data, PCA and MDS in both LR and SVM models. SVM had an advantage over LR in developing classification models. The classification accuracy of SVM based on the data processed by LDA for tea infusion samples was 100%. Quantitative analysis was conducted to predict the contents of volatile compounds in tea samples based on E-nose signals. The prediction results of SVM based on the data processed by LDA for linalool (training set: R2 = 0.9523; testing set: R2 = 0.9343), nonanal (training set: R2 = 0.9617; testing set: R2 = 0.8980) and geraniol (training set: R2 = 0.9576; testing set: R2 = 0.9315) were satisfactory. The research manifested the feasibility of E-nose for qualitatively and quantitatively analyzing tea quality grades.

Machine learning models applied to friction stir welding defect index using multiple joint configurations and alloys

Friction stir welding process has been studied extensively in the last decades since its early stage. Most of the research done so far is related to the process development including tool design, material weldability, post-weld mechanical behavior, and microstructural properties. More recently, in-line process monitoring and artificial intelligence algorithms are introduced into this process, but mainly to specific material configuration and joint thicknesses. This study will focus on the evaluation of different machine learning approaches including principle component analysis, K-nearest neighbor, multilayer perceptron, single vector machine, and random forest methods on a friction stir welding cell environment. The input variables provided from this cell environment are namely divided into two groups: one group refers to the application variables and the other group is related to the friction stir welding process variables. The application variables target the aluminum alloys, joint configuration, sheet thicknesses, initial mechanical properties, and their chemical composition. The friction stir welding process variables dictate the rotational speed, travel speed, forging force, longitudinal and transverse forces, torque, and specific energy. The output response to model from these machine learning algorithms is the defect index, which has been quantified using high-resolution immersed bath ultrasounds. This nondestructive evaluation technique has been described previously, which can detect defects ≥150 µm in thin sheets. The defect index has been classified into five classes, which is distinguished by the nature of defect, cold weld, or hot weld, as well as the width of the internal volumetric defect upon ultrasound C-scan result. The dataset, which is composed of around 500 various process conditions, has been generated over the last few years and the variables were taken exclusively in constant weld regime and in the force control mode using the output average values. This paper compares the best resulting machine learning methods applied on a friction stir welding cell basis, which is the K-nearest neighbor and multilayer perceptron algorithms. The K-nearest neighbor model reaches a deviation of 0.55 on the defect index in comparison with the experimental values, which is slightly better than the multilayer perceptron model, which obtains a score of 0.69. Over the initial 59 available model parameters, 10 and 15 of them were retained in the final algorithm using these techniques. The main predictors include the material thickness, base material ultimate tensile stress, rotational speed, travel speed, weld forces, and specific energy. The K-nearest neighbor model was able to provide a map of defect indices with regard to rotational speed and travel speed but was only possible when a higher density of data was found within the prediction area. A data density score was also included within the model to inform the end-user about the prediction reliability. The machine learning models are mainly about differentiating various cases rather than representing the physical phenomena as determined using the finite element analysis. That being said, in order to improve the prediction reliability as well as the machine learning models, the data twinning concept, which consists of generating simulated friction stir welding process conditions by finite element analysis, is briefly discussed.

Detection of edge debonding in composite patch using novel post processing method of thermography

In the present work, the step heating thermography technique has been used to detect disbond defects at the edge of the adhered carbon/epoxy patch on the aluminum plate. The four common post-processing algorithms including principle component analysis (PCA), thermal signal reconstruction (TSR), Fourier transform (FT), and one-dimensional wavelet transform (1D WT) have been applied to the infrared thermal images obtained from the composite patch thermography inspection. A novel post processing method based on the area under temperature-time curve (Thermal Signal Area: TSA) has been proposed for the infrared thermal image analysis. The proposed post-processing method is fast and non-sensitive to noise. A comparison of the new proposed method with the four common post-processing methods has been carried out on disbond detection in a composite patch in a quantitative and qualitative manner. Furthermore, a data fusion of the proposed method with the 1D wavelets transform has been applied to disbond defect characterization which improves the accuracy by decreasing noise level.

Effectiveness of spectral data reduction in detection of salt-affected soils in a small study area

Data reduction is used to aggregate or amalgamate the large data sets into smaller and manageable information pieces in order to fast and accurate classification of different attributes. However, excessive spatial or spectral data reduction may result in losing or masking important radiometric information. Therefore, we conducted this research to evaluate the effectiveness of the different spectral data reduction algorithms including Principle Component Analysis (PCA) and Minimum Noise Fraction (MNF) transformation, Pixel Purity Index (PPI), and n Dimensional Visualizer (n-DV) algorithms on accuracy of the supervised classification of the salt-affected soils applying ETM+ data beside 188 ground control points. Results revealed that data reduction caused around 20 to 30 % decreases in classification results compared to none reduced data. It seems that applying spectral data reduction algorithm in small study areas is not only supportive, but also has negative effects on classification results. Therefore, it may better to not to use the algorithms in small areas.

Determination of alkaloids and phenols in the chewable husk products of Areca catechu L. Using HPLC-UV and UHPLC-MS/MS

The chewable husk products of Areca catechu L., named “Binglang” including Qingguo and Yanguo are widely used as a stimulant by people in southern China. However, no quality control analytical method has yet been developed for chewable Binglang. A high performance liquid chromatography coupled with UV detector (HPLC-UV) method for quantitative analysis of four characteristic areca alkaloids is being reported here. In addition, an ultra high-pressure liquid chromatography tandem mass spectrometry (UHPLC-MS/MS) method for determination of usually overlooked constituents of Binglang products, including eight phenols, and one minor alkaloid has also been developed for the first time. Moreover, fingerprint similarity evaluation, and pattern recognition including principle component analysis (PCA) and random forest (RF) were applied to analyze the obtained spectrometric data. The results firstly revealed substantial variations in the levels of areca alkaloids among Qingguo, Yanguo, raw husk, and the seed products. Two phenols, i.e. (+)-catechin and p-hydroxybenzoic acid, among the analytes were found to be considerably high in the husk products. This study presents the first important step toward providing a systematic method for comprehensive quality control of Binglang products.

Multivariate data analysis applied in alkali-based pretreatment of corn stover

In this paper, variables of Pulp Refining Instrument (PFI) refining assisted alkaline pretreatment and hydrolysis saccharification of corn stover were analyzed. The process parameters were characterized by multivariate data analysis methods including Principle Component Analysis and Partial Least Square (PCA and PLS) to investigate the specific relationships of primary variables in alkali-based pretreatment of biomass. In this paper, pretreatment system was multivariate and the variables were inter-related to each other. Total alkaline charge and removal rate of lignin had greatest impact on the pretreatment and enzymatic hydrolysis.

Portable Optoelectronic Nose for Monitoring Meat Freshness

A disposable colorimetric sensor array (CSA) made from printing various chemically responsive dyes was combined with a hand-held device for on-site assessment and monitoring of the freshness of five meat products: beef, chicken, fish, pork, and shrimp. The hand-held device takes advantage of an on-board diaphragm micropump and a commercial 1D CMOS camera (CIS) which enables the real-time collection of colorimetric data. The sensor array shows excellent sensitivity to gaseous analytes, especially amines and sulfides at low ppb levels; excellent discrimination among meat volatiles in terms of meat type and storage time was demonstrated with multiple chemometric approaches including principle component analysis, hierarchical cluster analysis, and support vector machine analysis. This optoelectronic nose proves to be a promising supplement to other available techniques for meat product inspection.

Water Bodies’ Mapping from Sentinel-2 Imagery with Modified Normalized Difference Water Index at 10-m Spatial Resolution Produced by Sharpening the SWIR Band

Monitoring open water bodies accurately is an important and basic application in remote sensing. Various water body mapping approaches have been developed to extract water bodies from multispectral images. The method based on the spectral water index, especially the Modified Normalized Difference Water Index (MDNWI) calculated from the green and Shortwave-Infrared (SWIR) bands, is one of the most popular methods. The recently launched Sentinel-2 satellite can provide fine spatial resolution multispectral images. This new dataset is potentially of important significance for regional water bodies’ mapping, due to its free access and frequent revisit capabilities. It is noted that the green and SWIR bands of Sentinel-2 have different spatial resolutions of 10 m and 20 m, respectively. Straightforwardly, MNDWI can be produced from Sentinel-2 at the spatial resolution of 20 m, by upscaling the 10-m green band to 20 m correspondingly. This scheme, however, wastes the detailed information available at the 10-m resolution. In this paper, to take full advantage of the 10-m information provided by Sentinel-2 images, a novel 10-m spatial resolution MNDWI is produced from Sentinel-2 images by downscaling the 20-m resolution SWIR band to 10 m based on pan-sharpening. Four popular pan-sharpening algorithms, including Principle Component Analysis (PCA), Intensity Hue Saturation (IHS), High Pass Filter (HPF) and À Trous Wavelet Transform (ATWT), were applied in this study. The performance of the proposed method was assessed experimentally using a Sentinel-2 image located at the Venice coastland. In the experiment, six water indexes, including 10-m NDWI, 20-m MNDWI and 10-m MNDWI, produced by four pan-sharpening algorithms, were compared. Three levels of results, including the sharpened images, the produced MNDWI images and the finally mapped water bodies, were analysed quantitatively. The results showed that MNDWI can enhance water bodies and suppressbuilt-up features more efficiently than NDWI. Moreover, 10-m MNDWIs produced by all four pan-sharpening algorithms can represent more detailed spatial information of water bodies than 20-m MNDWI produced by the original image. Thus, MNDWIs at the 10-m resolution can extract more accurate water body maps than 10-m NDWI and 20-m MNDWI. In addition, although HPF can produce more accurate sharpened images and MNDWI images than the other three benchmark pan-sharpening algorithms, the ATWT algorithm leads to the best 10-m water bodies mapping results. This is no necessary positive connection between the accuracy of the sharpened MNDWI image and the map-level accuracy of the resultant water body maps.

An Unsupervised Urban Change Detection Procedure by Using Luminance and Saturation for Multispectral Remotely Sensed Images

AbstractUnsupervised change detection techniques have been widely employed in the remote-sensing area when suitable reference data is not available. Image (or Index) differencing is one of the most commonly used methods due to its simplicity. However, past applications of image differencing were often inefficient in separating real change and noise due to the lack of steps for feature selection and integration of contextual information. To address these issues, we propose a novel unsupervised procedure which uses two complementary features, namely luminance and saturation, extracted from multispectral images, and combines T-point thresholding, Bayes fusion, and Markov Random Fields. Through a case study, the performance of our proposed procedure was compared with other three unsupervised changedetection methods including Principle Component Analysis (PCA), Fuzzy c-means (FCM), and Expectation Maximum-Markov Random Field (EM-MRF). The change detection results from our proposed method are more compact with less noise than those from other methods over urban areas. The quantitative accuracy assessment indicates that the overall accuracy and Kappa statistic of our proposed procedure are 95.1 percent and 83.3 percent, respectively, which are significantly higher than the other three unsupervised change detection methods.

Fatty acid profiles based adulteration detection for flaxseed oil by gas chromatography mass spectrometry

Flaxseed oil is popular edible oil and an important additive in functional foods and feeds. Recently, economically motivated adulteration as a type of oil fraud becomes emerging risk. In this study, the fatty acid profiles of flaxseed oil were analyzed by gas chromatography-mass spectrometry operating in selected ion monitoring mode and then used to detect adulterated flaxseed oil with the help of multivariate statistical methods including principle component analysis (PCA), and recursive support vector machine (R-SVM). The detection results indicate that the discriminant model built with 28 fatty acids can identify adulterated flaxseed oil samples (10%) with high accuracy of 95.6%. Therefore, fatty acid profiles based adulteration detection for flaxseed oil is an important strategy for preventing customers far from adulterated flaxseed oil.

Comparative study of regression modeling methods for online coal calorific value prediction from flame radiation features

In this paper, multiple regression methods are presented and compared for online coal calorific value prediction from multi-spectral flame radiation features. Several statistical approaches including principle component analysis (PCA), independent component analysis (ICA) and partial least squares analysis (PLSA) were used in linear and nonlinear regression analyses. Analyzing results show that nonlinear regression model can better approximate the relationship between the coal calorific value and the flame radiation features than linear regression model. In linear regression analysis, the performance of the linear coal calorific value prediction models was not improved by involving the statistical approaches. In nonlinear regression analysis, however, the performance of the prediction models was significantly improved when combined with the statistical approaches. The variation of coefficients of multiple regression showed that only the PLSA-based nonlinear regression model can discriminate useful feature components from useless feature components. The PLSA-based nonlinear regression model showed the best performance for coal calorific value prediction with the number of features reduced to about a third of that in the other models. With the PLSA-based nonlinear regression model, online coal calorific value prediction from the multi-band flame radiation features under the operating conditions used by the industrial boiler has the mean absolute error, standard deviation of the absolute errors, mean relative error and standard deviation of the relative errors of 148.76kJ/kg, 291.86kJ/kg, 0.76% and 1.53%, respectively.

Effects of seasonal climatic variability on several toxic contaminants in urban lakes: Implications for the impacts of climate change

Climate change is supposed to have influences on water quality and ecosystem. However, only few studies have assessed the effect of climate change on environmental toxic contaminants in urban lakes. In this research, response of several toxic contaminants in twelve urban lakes in Beijing, China, to the seasonal variations in climatic factors was studied. Fluorides, volatile phenols, arsenic, selenium, and other water quality parameters were analyzed monthly from 2009 to 2012. Multivariate statistical methods including principle component analysis, cluster analysis, and multiple regression analysis were performed to study the relationship between contaminants and climatic factors including temperature, precipitation, wind speed, and sunshine duration. Fluoride and arsenic concentrations in most urban lakes exhibited a significant positive correlation with temperature/precipitation, which is mainly caused by rainfall induced diffuse pollution. A negative correlation was observed between volatile phenols and temperature/precipitation, and this could be explained by their enhanced volatilization and biodegradation rates caused by higher temperature. Selenium did not show a significant response to climatic factor variations, which was attributed to low selenium contents in the lakes and soils. Moreover, the response degrees of contaminants to climatic variations differ among lakes with different contamination levels. On average, temperature/precipitation contributed to 8%, 15%, and 12% of the variations in volatile phenols, arsenic, and fluorides, respectively. Beijing is undergoing increased temperature and heavy rainfall frequency during the past five decades. This study suggests that water quality related to fluoride and arsenic concentrations of most urban lakes in Beijing is becoming worse under this climate change trend.

Automated phenotyping and advanced data mining exemplified in rats transgenic for Huntington's disease.

The need for improving throughput, validity, and reliability in the behavioral characterization of rodents may benefit from integrating automated intra-home-cage-screening systems allowing the simultaneous detection of multiple behavioral and physiological parameters in parallel. To test this hypothesis, transgenic Huntington's disease (tgHD) rats were repeatedly screened within phenotyping home-cages (PhenoMaster and IntelliCage for rats), where spontaneous activity, feeding, drinking, temperature, and metabolic performance were continuously measured. Cognition and emotionality were evaluated within the same environment by means of operant learning procedures and refined analysis of the behavioral display under conditions of novelty. This investigator-independent approach was further correlated with behavioral display of the animals in classical behavioral assays. Multivariate analysis (MVA) including Principle Component Analysis (PCA) and Partial Least Squares Discriminant Analysis (PLS-DA) was used to explore correlation patterns of variables within and across the two genotypes. The automated systems traced previously undetected aspects in the phenotype of tgHD rats (circadian activity, energy metabolism, rearing), and out of those spontaneous free rearing correlated with individual performance in the accelerod test. PCA revealed a segregation by genotype in juvenile tgHD rats that differed from adult animals, being further resolved by PLS-DA detecting "temperature" (juvenile) and "rearing" (adult) as phenotypic key variables in the tgHD model. Intra-home-cage phenotyping in combination with MVA, is capable of characterizing a complex phenotype by detecting novel physiological and behavioral markers with high sensitivity and standardization using fewer human resources. A broader application of automated systems for large-scale screening is encouraged.