Academic literature on the topic 'PLS-DA models'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'PLS-DA models.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "PLS-DA models"
1
Ballabio, Davide, and Viviana Consonni. "Classification tools in chemistry. Part 1: linear models. PLS-DA." Analytical Methods 5, no. 16 (2013): 3790. http://dx.doi.org/10.1039/c3ay40582f.
Full text
2
Li, Xingpeng, Hongzhe Jiang, Xuesong Jiang, and Minghong Shi. "Identification of Geographical Origin of Chinese Chestnuts Using Hyperspectral Imaging with 1D-CNN Algorithm." Agriculture 11, no. 12 (December 15, 2021): 1274. http://dx.doi.org/10.3390/agriculture11121274.
Full textAbstract:
The adulteration in Chinese chestnuts affects the quality, taste, and brand value. The objective of this study was to explore the feasibility of the hyperspectral imaging (HSI) technique to determine the geographical origin of Chinese chestnuts. An HSI system in spectral range of 400–1000 nm was applied to identify a total of 417 Chinese chestnuts from three different geographical origins. Principal component analysis (PCA) was preliminarily used to investigate the differences of average spectra of the samples from different geographical origins. A deep-learning-based model (1D-CNN, one-dimensional convolutional neural network) was developed first, and then the model based on full spectra and optimal wavelengths were established for various machine learning methods, including partial least squares-discriminant analysis (PLS-DA) and particle swarm optimization-support vector machine (PSO-SVM). The optimal results based on full spectra for 1D-CNN, PLS-DA, and PSO-SVM models were 97.12%, 97.12%, and 95.68%, respectively. Competitive adaptive reweighted sampling (CARS) and a successive projections algorithm (SPA) were individually utilized for wavelengths selection, and the results of simplified models generally improved. The contrasting results demonstrated that the prediction accuracies of SPA-PLS-DA and 1D-CNN both reached 97.12%, but 1D-CNN presented a higher Kappa coefficient value than SPA-PLS-DA. Meanwhile, the sensitivities and specificities of SPA-PLS-DA and 1D-CNN models were both above 90% for the samples from each geographical origin. These results indicated that both SPA-PLS-DA and 1D-CNN models combined with HSI have great potential for the geographical origin identification of Chinese chestnuts.
3
SONG, HAN, FENG LI, PEIWEN GUANG, XINHAO YANG, HUANYU PAN, and FURONG HUANG. "Detection of Aflatoxin B1 in Peanut Oil Using Attenuated Total Reflection Fourier Transform Infrared Spectroscopy Combined with Partial Least Squares Discriminant Analysis and Support Vector Machine Models." Journal of Food Protection 84, no. 8 (March 12, 2021): 1315–20. http://dx.doi.org/10.4315/jfp-20-447.
Full textAbstract:
ABSTRACT This study was conducted to establish a rapid and accurate method for identifying aflatoxin contamination in peanut oil. Attenuated total reflection Fourier transform infrared (ATR-FTIR) spectroscopy combined with either partial least squares discriminant analysis (PLS-DA) or a support vector machine (SVM) algorithm were used to construct discriminative models for distinguishing between uncontaminated and aflatoxin-contaminated peanut oil. Peanut oil samples containing various concentrations of aflatoxin B1 were examined with an ATR-FTIR spectrometer. Preprocessed spectral data were input to PLS-DA and SVM algorithms to construct discriminative models for aflatoxin contamination in peanut oil. SVM penalty and kernel function parameters were optimized using grid search, a genetic algorithm, and particle swarm optimization. The PLS-DA model established using spectral data had an accuracy of 94.64% and better discrimination than did models established based on preprocessed data. The SVM model established after data normalization and grid search optimization with a penalty parameter of 16 and a kernel function parameter of 0.0359 had the best discrimination, with 98.2143% accuracy. The discriminative models for aflatoxin contamination in peanut oil established by combining ATR-FTIR spectral data and nonlinear SVM algorithm were superior to the linear PLS-DA models. HIGHLIGHTS
4
Chen, Zhuoyi, Qingping Wang, Hui Zhang, and Pengcheng Nie. "Hyperspectral Imaging (HSI) Technology for the Non-Destructive Freshness Assessment of Pearl Gentian Grouper under Different Storage Conditions." Sensors 21, no. 2 (January 15, 2021): 583. http://dx.doi.org/10.3390/s21020583.
Full textAbstract:
This study used visible/near-infrared hyperspectral imaging (HSI) technology combined with chemometric methods to assess the freshness of pearl gentian grouper. The partial least square discrimination analysis (PLS-DA) and competitive adaptive reweighted sampling-PLS-DA (CARS-PLS-DA) models were used to classify fresh, refrigerated, and frozen–thawed fish. The PLS-DA model achieved better classification of fresh, refrigerated, and frozen–thawed fish with the accuracy of 100%, 96.43%, and 96.43%, respectively. Further, the PLS regression (PLSR) and CARS-PLS regression (CARS-PLSR) models were used to predict the storage time of fish under different storage conditions, and the prediction accuracy was assessed using the prediction correlation coefficients (Rp2), root mean squared error of prediction (RMSEP), and residual predictive deviation (RPD). For the prediction of storage time, the CARS-PLS model presented the better result of room temperature (Rp2 = 0.948, RMSEP = 0.255, RPD = 4.380) and refrigeration (Rp2 = 0.9319, RMSEP = 1.188, RPD = 3.857), while the better prediction of freeze was by obtained by the PLSR model (Rp2 = 0.9250, RMSEP = 2.910, RPD = 3.469). Finally, the visualization of storage time based on the PLSR model under different storage conditions were realized. This study confirmed the potential of HSI as a rapid and non-invasive technique to identify fish freshness.
5
Khan, Asma, Muhammad Tajammal Munir, Wei Yu, and Brent Young. "Wavelength Selection FOR Rapid Identification of Different Particle Size Fractions of Milk Powder Using Hyperspectral Imaging." Sensors 20, no. 16 (August 18, 2020): 4645. http://dx.doi.org/10.3390/s20164645.
Full textAbstract:
Hyperspectral imaging (HSI) in the spectral range of 400–1000 nm was tested to differentiate three different particle size fractions of milk powder. Partial least squares discriminant analysis (PLS-DA) was performed to observe the relationship of spectral data and particle size information for various samples of instant milk powder. The PLS-DA model on full wavelengths successfully classified the three fractions of milk powder with a coefficient of prediction 0.943. Principal component analysis (PCA) identified each of the milk powder fractions as separate clusters across the first two principal components (PC1 and PC2) and five characteristic wavelengths were recognised by the loading plot of the first three principal components. Weighted regression coefficient (WRC) analysis of the partial least squares model identified 11 important wavelengths. Simplified PLS-DA models were developed from two sets of reduced wavelengths selected by PCA and WRC and showed better performance with predictive correlation coefficients (Rp2) of 0.962 and 0.979, respectively, while PLS-DA with complete spectrum had Rp2 of 0.943. Similarly, classification accuracy of PLS-DA was improved to 92.2% for WRC based predictive model. Calculation time was also reduced to 2.1 and 2.8 s for PCA and WRC based simplified PLS-DA models in comparison to the complete spectrum model that was taking 32.2 s on average to predict the classification of milk powder samples. These results demonstrated that HSI with appropriate data analysis methods could become a potential analyser for non-invasive testing of milk powder in the future.
6
Zhu, Zhou, Gao, Bao, He, and Feng. "Near-Infrared Hyperspectral Imaging Combined with Deep Learning to Identify Cotton Seed Varieties." Molecules 24, no. 18 (September 7, 2019): 3268. http://dx.doi.org/10.3390/molecules24183268.
Full textAbstract:
Cotton seed purity is a critical factor influencing the cotton yield. In this study, near-infrared hyperspectral imaging was used to identify seven varieties of cotton seeds. Score images formed by pixel-wise principal component analysis (PCA) showed that there were differences among different varieties of cotton seeds. Effective wavelengths were selected according to PCA loadings. A self-design convolution neural network (CNN) and a Residual Network (ResNet) were used to establish classification models. Partial least squares discriminant analysis (PLS-DA), logistic regression (LR) and support vector machine (SVM) were used as direct classifiers based on full spectra and effective wavelengths for comparison. Furthermore, PLS-DA, LR and SVM models were used for cotton seeds classification based on deep features extracted by self-design CNN and ResNet models. LR and PLS-DA models using deep features as input performed slightly better than those using full spectra and effective wavelengths directly. Self-design CNN based models performed slightly better than ResNet based models. Classification models using full spectra performed better than those using effective wavelengths, with classification accuracy of calibration, validation and prediction sets all over 80% for most models. The overall results illustrated that near-infrared hyperspectral imaging with deep learning was feasible to identify cotton seed varieties.
7
Yaman, Nihal, and Serap Durakli Velioglu. "Use of Attenuated Total Reflectance—Fourier Transform Infrared (ATR-FTIR) Spectroscopy in Combination with Multivariate Methods for the Rapid Determination of the Adulteration of Grape, Carob and Mulberry Pekmez." Foods 8, no. 7 (June 28, 2019): 231. http://dx.doi.org/10.3390/foods8070231.
Full textAbstract:
Pekmez, a traditional Turkish food generally produced by concentration of fruit juices, is subjected to fraudulent activities like many other foodstuffs. This study reports the use of Fourier transform infrared spectroscopy (FTIR) in combination with chemometric methods for the detection of fraudulent addition of glucose syrup to traditional grape, carob and mulberry pekmez. FTIR spectra of samples were taken in mid-infrared (MIR) range of 400–4000 cm−1 using attenuated total reflectance (ATR) sample accessory. Partial least squares-discriminant analysis (PLS-DA) and PLS chemometric methods were built for qualitative and quantitative analysis of pekmez samples, respectively. PLS-DA models were successfully used for the discrimination of pure pekmez samples and the adulterated pekmez samples with glucose syrup. Sensitivity and specificity of 100%, and model efficiency of 100% were obtained in PLS-DA models for all pekmez groups. Detection of the adulteration ratio of pekmez samples was also accomplished using ATR-FTIR spectroscopy in combination with PLS. As a result, it was shown that ATR-FTIR spectroscopy along with chemometric methods had a great potential for determination of pekmez adulteration with glucose syrup.
8
Szymańska, Ewa, Edoardo Saccenti, Age K. Smilde, and Johan A. Westerhuis. "Double-check: validation of diagnostic statistics for PLS-DA models in metabolomics studies." Metabolomics 8, S1 (July 8, 2011): 3–16. http://dx.doi.org/10.1007/s11306-011-0330-3.
Full text
9
Liu, Wenjing, Zhaotian Sun, Jinyu Chen, and Chuanbo Jing. "Raman Spectroscopy in Colorectal Cancer Diagnostics: Comparison of PCA-LDA and PLS-DA Models." Journal of Spectroscopy 2016 (2016): 1–6. http://dx.doi.org/10.1155/2016/1603609.
Full textAbstract:
Raman spectra of human colorectal tissue samples were employed to diagnose colorectal cancer. High-quality Raman spectra were acquired from normal and cancerous colorectal tissues from 81 patients. Subtle Raman variations, such as for peaks at 1134 cm−1 (protein, C-C/C-N stretching) and 1297 cm−1 (lipid, C-H2 twisting), were observed between normal and cancerous colorectal tissues. The average peak intensity at 1134 and 1297 cm−1 was increased from approximately 235 and 72 in the normal group, respectively, to 315 and 273 in the cancer group. The variations of Raman spectra reflected the changes of cell molecules during canceration. The multivariate statistical methods of principal component analysis-linear discriminant analysis (PCA-LDA) and partial least-squares-discriminant analysis (PLS-DA), together with leave-one-patient-out cross-validation, were employed to build the discrimination model. PCA-LDA was used to evaluate the capability of this approach for classifying colorectal cancer, resulting in a diagnostic accuracy of 79.2%. Further PLS-DA modeling yielded a diagnostic accuracy of 84.3% for colorectal cancer detection. Thus, the PLS-DA model is preferable between the two to discriminate cancerous from normal tissues. Our results demonstrate that Raman spectroscopy can be used with an optimized multivariate data analysis model as a sensitive diagnostic alternative to identify pathological changes in the colon at the molecular level.
10
Sun, Fei, Yu Chen, Yunqi Qiu, Shumei Wang, and Shengwang Liang. "Systematic vs. stepwise parameter optimization for discriminant model development: A case study of differentiating Pinellia ternata from Pinellia pedatisecta with near infrared spectroscopy." Journal of Near Infrared Spectroscopy 28, no. 5-6 (June 14, 2020): 287–97. http://dx.doi.org/10.1177/0967033520924579.
Full textAbstract:
Near infrared (NIR) spectroscopy is an effective technique for adulteration detection in traditional Chinese medicine. The aim is to develop a discriminant model with the aid of chemometrics tools. The discriminant model is conventionally established by the means of stepwise optimization. This approach is often limited to trial-and-error and considered as a burden. In this study, a systematic optimization approach was proposed to develop the discriminant model with the aid of the design of experiment tools and applied to a case study of differentiating Pinellia ternata from Pinellia pedatisecta and adulterated Pinellia ternata using NIR spectroscopy. Spectral pretreatment, variable selection, and discriminant methods were identified as critical factors. The classification accuracy and no-error rate of the calibration set, cross-validation, and the prediction set were calculated to evaluate the performance of discriminant models. A full factorial design was applied to analyze the effect of critical factors at different levels on the model performance and optimize these factors. Three discriminant models including discriminant analysis coupled with principal component analysis (PCA-DA), partial least squares – discriminant analysis (PLS-DA), and k-nearest neighbors (KNN) were obtained by systematic optimization. The performance of PCA-DA and PLS-DA models obtained by systematic optimization was very good, and no samples were misclassified, which were better than those obtained by stepwise optimization. The performance of the KNN model obtained by systematic optimization was not desired and it was equal to that obtained by stepwise optimization. The results showed that Pinellia ternata could be successfully discriminated from Pinellia pedatisecta and adulterated Pinellia ternata by the PCA-DA and PLS-DA models. Compared to the stepwise optimization approach, the systematic optimization approach can improve the PCA-DA and PLS-DA model performance for differentiating Pinellia ternata from Pinellia pedatisecta and adulterated Pinellia ternata.
Dissertations / Theses on the topic "PLS-DA models"
1
SANTOS, Maria de Jesus Lessa. "Classificação de mangas Tommy Atkins y-irradiadas: Um modelo metabolômico." Universidade Federal de Pernambuco, 2014. https://repositorio.ufpe.br/handle/123456789/12433.
Full textAbstract:
Submitted by Danielle Karla Martins Silva (danielle.martins@ufpe.br) on 2015-03-13T13:23:18Z
No. of bitstreams: 2
DISSERTAÇÃO Maria de Jesus Santos.pdf: 2877099 bytes, checksum: 04af70722e8d7edebcc4a65d2877869b (MD5)
license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5)Made available in DSpace on 2015-03-13T13:23:18Z (GMT). No. of bitstreams: 2 DISSERTAÇÃO Maria de Jesus Santos.pdf: 2877099 bytes, checksum: 04af70722e8d7edebcc4a65d2877869b (MD5) license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) Previous issue date: 2014
Neste trabalho foram investigadas as composições dos voláteis a partir de mangas da cultivar Tommy Atkins expostas à radiação gama na dose de 0,5 kGy quando comparadas à composição de voláteis obtidos a partir de mangas que não passaram por este tratamento fitossanitário. O objetivo foi construir um modelo metabolômico para classificar as mangas através de modelo não invasivo. Foram analisadas 80 amostras classificadas com grau de maturação entre 4 e 5, segundo classificação da Embrapa. Os voláteis foram coletados após 18 dias de armazenamento sob temperatura de 12°C, usando um sistema Headspace Dinâmico (HD) e submetidos à corrida cromatográfica em fase gasosa seguida de detecção por espectrometria de massas (GC/MS). Os compostos foram identificados a partir da determinação do Índice de Retenção Van den Dool and Kratz e do espectro de massas, que foram comparados aos descritos na biblioteca de espectros do ADAMS. Foram identificados 16 compostos já mencionados na literatura e classificados como terpenos (mono e sesquiterpenos) e ésteres. Entre os terpenos, o α-Pineno e o 3-Careno foram os majoritários tanto para as mangas irradiadas, como para as não irradiadas. Após a identificação dos mesmos, os cromatogramas foram utilizados para a construção de uma matriz para tratamento estatístico, o qual foi realizado utilizando a plataforma online MetaboAnalyst 2.0 e o software “R Program”. As ferramentas de estatística multivariada utilizadas foram a PCA (Análise de Componentes Principais), PLS-DA (Análise Discriminante e Regressão por Mínimos Quadrados Parciais) e KNN (K-nearest neighbor). A PCA não apresentou um resultado satisfatório para a discriminação entre as mangas irradiadas e não irradiadas. Na PLS-DA, treze compostos foram responsáveis pela discriminação entre as mangas da cultivar Tommy Atkins irradiadas e não irradiadas, com destaque para o Octanoato de Etila, o α-Felandreno e o Germacreno-D. O KNN também indicou que os teores de Octanoato de Etila, α-Felandreno e Germacreno-D são responsáveis pela discriminação entre as mangas irradiadas e não irradiadas. No entanto, a acurácia observada na classificação utilizando KNN foi maior que a observada utilizando PLS-DA. No modelo construído com KNN, o teste de validação cruzada indicou acurácia igual a 81% contra 55% da observada para o modelo construído utilizando PLS-DA. Esse resultado garante um modelo metabolômico que é capaz de classificar as amostras de mangas da cultivar Tommy Atkins que foram expostas, ou não, à radiação gama para fins fitossanitários.
2
Hilgemann, Maurício. "Uso de modelos multivariados para a avaliação do valor de dienos em amostras de gasolina de pirólise." Universidade Federal de Santa Maria, 2005. http://repositorio.ufsm.br/handle/1/10380.
Full textAbstract:
Conselho Nacional de Desenvolvimento Científico e TecnológicoThe quality of gasoline may be affected by the presence of several compounds. Among them, the conjugated dienes play an important role due to the fact that their presence is strongly associated with gum formation, which may clogs the injector of automobiles and may causes damages in the petroleum derivates. The main used method for the determination of total conjugated dienes is the UOP-326 method. However, the long analysis time (from 5 to 6 hours) is the main disadvantages. The available methodologies investigated as alternative to the UOP-326 method do not solve the problem properly. The present work reports the use of multivariate models to assess the diene value (DV) in pyrolysis gasoline samples starting from voltammetric and spectrophotometric data. The calibrations were carried out using the UOP-326 method instead of diene standards. In the voltammetric model, starting from a group of 24 hydrogenated pyrolysis gasoline, the PLS (Partial Least Squares) method was used to predict the DV in an independent group of 7 samples. The deviations observed were lower than 12,2% comparing to the UOP-326 method. In a group of 24 non-hydrogenated pyrolysis gasoline samples, an independent group of 7 samples was also used to predict the DV. The deviations observed were lower than 4,1%. In the spectrophotometric approach, the PLS method was used to predict the DV in an independent group of 5 samples of hydrogenated pyrolysis gasoline (n=21). The deviations observed were lower than 11% by comparing to the UOP-326 method. In a group of 26 non-hydrogenated pyrolysis gasoline samples, an independent group of 10 samples was used to predict the DV. The deviations observed were lower than 5,7%. Comparing the voltammetric and spectrophotometric methods, the former showed more reliable results with lower RMSEP (Root Mean Square Error of Prediction) values.
A qualidade da gasolina é afetada pela presença de diversos compostos. Entre eles, os dienos conjugados possuem um importante papel devido ao fato de estarem associados à formação de goma, que forma depósitos no injetor de combustível de automóveis e diminui a qualidade dos produtos petrolíferos. O método comumente utilizado para a determinação de dienos conjugados totais é o método UOP-326. Contudo, ele apresenta como principal desvantagem o longo tempo de análise (de 5 a 6 horas). As metodologias já investigadas que visam substituir o método UOP-326 na quantificação de dienos conjugados em gasolina não resolvem adequadamente o problema. Dessa forma, o presente trabalho aborda o uso de modelos multivariados para a avaliação do valor de dienos (DV) em amostras de gasolina de pirólise a partir de dados voltamétricos e espectrofotométricos, utilizando o método UOP-326 para a calibração do sistema. No modelo voltamétrico, de um grupo de 24 amostras de gasolina de pirólise hidrogenada, utilizou-se o método PLS (Regressão por Mínimos Quadrados Parciais) para a predição do DV em um grupo independente de 7 amostras, obtendo-se desvios inferiores a 12,2% quando comparado ao método UOP-326. E em 24 amostras de gasolina de pirólise não hidrogenada, um grupo independente de 7 amostras foi utilizado para a predição do DV, obtendo desvios inferiores a 4,1%. No modelo espectrofotométrico, utilizou-se o método PLS para a predição do DV em um grupo independente de 5 amostras de gasolina de pirólise hidrogenada (n=21), obtendo-se desvios inferiores a 11% quando comparado ao método UOP-326. E em 26 amostras de gasolina de pirólise não hidrogenada, um grupo independente de 10 amostras foi utilizado para a predição do DV, obtendo-se desvios inferiores a 5,7%. Na comparação entre os métodos voltamétrico e espectrofotométrico, o primeiro mostrou-se mais confiável, apresentando valores de RMSEP (erro médio dos resíduos quadráticos de predição) inferiores para ambas as amostras.
3
Leite, Érika de Almeida. "Construção do modelo metabonômico baseado em RMN de 1H a partir de amostras de urina para classificar portadores de hepatite B ou C." Universidade Federal de Pernambuco, 2014. https://repositorio.ufpe.br/handle/123456789/12417.
Full textAbstract:
Submitted by Danielle Karla Martins Silva (danielle.martins@ufpe.br) on 2015-03-13T13:14:22Z
No. of bitstreams: 2
license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5)
DISSERTAÇÃO Érika Leite.pdf: 1493066 bytes, checksum: ac90321410c703d0b25329948cfd5555 (MD5)Made available in DSpace on 2015-03-13T13:14:22Z (GMT). No. of bitstreams: 2 license_rdf: 1232 bytes, checksum: 66e71c371cc565284e70f40736c94386 (MD5) DISSERTAÇÃO Érika Leite.pdf: 1493066 bytes, checksum: ac90321410c703d0b25329948cfd5555 (MD5) Previous issue date: 2014
CAPES
As hepatites B e C são consideradas um problema de saúde pública em função de suas magnitudes e gravidades. De acordo com a Organização Mundial da Saúde, 2 bilhões de pessoas foram infectadas pelo HBV e estima-se que de 2 a 3% da população mundial esteja infectada com HCV. Esses índices podem ser maiores, uma vez que muitas pessoas infectadas são assintomáticas. As hepatites B e C possuem alta taxa de cronificação, podendo evoluir para cirrose ou carcinoma hepatocelular. O diagnóstico envolve métodos sorológicos específicos para detecção dos marcadores das hepatites B e C em conjunto com a avaliação dos níveis séricos das aminotransferases (ALT, AST e GGT), fosfatase alcalina, albumina e bilirrubina. Todos esses exames requerem a coleta de sangue do paciente e, portanto, trata-se de um método invasivo. Neste contexto, buscou-se uma alternativa não invasiva ao exame de sangue para se obter o diagnóstico de hepatite. Através da estratégia metabonômica, baseada na espectroscopia de ressonância magnética nuclear (RMN), é possível obter uma "impressão digital metabólica", em biofluido (urina) de pacientes infectados e relacioná-la com a patologia. Objetivo Identificar pacientes com HBV e HCV com base no padrão espectral de RMN de 1H de amostras de urina associadas com ferramentas estatísticas multivariadas (PCA e PLS-DA). Amostras e Análises Foram formados dois grupos: a) 13 pacientes (Grupo I) com o diagnóstico positivo para HBsAg, anti-HBc e DNA de HBV; e b) 18 pacientes (Grupo II) com anticorpos anti-HCV e RNA de HCV positivos e HBsAg negativo. As 31 amostras foram analisadas em 1H RMN e os dados espectrais processados por PCA e PLS-DA. Resultados O modelo metabonômico identificou como positivos 11 dos 13 pacientes com HBV e teve sensibilidade 78,57% e especificidade 84,61%. Para o grupo com HCV, o modelo identificou 15 dos 18 pacientes e teve sensibilidade de 88,23% e especificidade 83,33% Conclusão Neste estudo, o modelo metabonômico foi capaz de classificar corretamente 83,87% dos dados de pacientes com HBV e HCV. As variáveis mais importantes para a discriminação entre os grupos foram os deslocamentos químicos em 3,17 e 3,32 ppm, que, em princípio, podem ser associados à taurina e ao óxido de trimetilamina (TMAO).
4
Sousa, Jonas da Silva. "Desenvolvimento de modelos de calibração multivariada em espectroscopia de infravermelho próximo para ácidos graxos em amostras de carne bovina." Universidade Federal de São Carlos, 2016. https://repositorio.ufscar.br/handle/ufscar/8051.
Full textAbstract:
Submitted by Luciana Sebin (lusebin@ufscar.br) on 2016-09-30T13:02:12Z
No. of bitstreams: 1
DissJSS.pdf: 5198309 bytes, checksum: 1bddd2741512bf6bf9509fe9e86d2ad9 (MD5)Approved for entry into archive by Marina Freitas (marinapf@ufscar.br) on 2016-10-20T19:27:52Z (GMT) No. of bitstreams: 1 DissJSS.pdf: 5198309 bytes, checksum: 1bddd2741512bf6bf9509fe9e86d2ad9 (MD5)
Approved for entry into archive by Marina Freitas (marinapf@ufscar.br) on 2016-10-20T19:27:58Z (GMT) No. of bitstreams: 1 DissJSS.pdf: 5198309 bytes, checksum: 1bddd2741512bf6bf9509fe9e86d2ad9 (MD5)
Made available in DSpace on 2016-10-20T19:28:07Z (GMT). No. of bitstreams: 1 DissJSS.pdf: 5198309 bytes, checksum: 1bddd2741512bf6bf9509fe9e86d2ad9 (MD5) Previous issue date: 2016-03-21
Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)
The Brazilian cattle have shown promise prominence in the international market compared to other commodities. It already knows the important role of fatty acids in the complimentarily of human nutrition. On the other hand, studies have linked the consumption of beef with increasing rate of diseases associated with high levels of "bad" cholesterol (LDL) in the blood. Because of these two aspects on the topic meat (nutritional value and human health), it is seen necessary to determine the levels oftrans fatty acids in meat. Among the methods for analysis of total lipids and lipid profile, stands out the extraction of fat and chromatography, respectively. In this project was proposed to develop multivariate calibration models for the analysis of total lipids and lipid profile with the use of near-infrared spectroscopy in beef samples which the levels were previously determined. Eighteen properties were analyzed, including: total lipids and myristic fatty acids, pentadecylic, palmitic, margaric, stearic, palmitoleic, oleic, elaidic, linoleic, α-linolenic and families of fatty acids with branched, saturated, monounsaturated (cis), conjugated linoleic (cis, trans), and omega 3 and 6 polyunsaturated. We used 127 bovine meat samples from the calibration steps and internal validation (2/3 to 1/3 calibration and validation for internal and 32 external validation samples. We used the PLSR method for the construction of multivariate models. Flesh spectra were extended from 1111 to 1937, and from 2016 to 2500 nm regions, and regions concerning water and noise judged as interfering in the calibration process were removed during the models construction. We evaluated the performance of the models based on the applied pre-treatments (smoothing, first derivative Savitzky-Golay, SNV), the number of latent variables, consistency, SEC, SEP and determination coefficients (R2 cal/val). The models chosen as having better predictive capacity were those of total lipids, myristic acid, palmitic acid, margárico and saturated fatty acids, demonstrating that the NIRS has a high potential for the quantification of lipid constituents of the beef.
A bovinocultura brasileira tem mostrado promissor destaque no mercado internacional quando comparada a outras commodities. Já se conhece o importante papel de ácidos graxos na complementaridade da alimentação humana. Por outro lado, estudos relacionam o consumo de carne bovina com o aumento de índice de doenças associadas com os altos teores do “mau” colesterol (LDL) no sangue. Em virtude dessas duas vertentes que abordam o tema carne (valor nutricional e a saúde humana), a determinação dos teores de ácidos graxos em carne é importante. Entre as metodologias para análise de lipídeos totais e perfil lipídico, se destacam a extração de gordura e a cromatografia, respectivamente. No presente projeto foi proposto o desenvolvimento de modelos de calibração multivariada para a análise de lipídeos totais e perfil lipídico com o emprego de espectroscopia no infravermelho próximo em amostras de carne bovina cujos teores foram previamente determinados. Foram analisadas dezoito propriedades, entre elas: lipídeos totais e os ácidos graxos mirístico, pentadecílico, palmítico, margárico, esteárico, palmitoleico, oleico, elaídico, linoleico, α-linolênico e as famílias de ácidos graxos com cadeia ramificada, saturados, monoinsaturados (cis), linoleicos conjugados (cis, trans), ômega 3 e 6 e poli-insaturados. Utilizou-se 127 amostras de carne de bovinos entre as etapas de calibração e validação interna (2/3 para a calibração e 1/3 para validação a interna e 32 amostras para validação externa). Empregou-se o método PLSR para construção dos modelos multivariados. Os espectros de carne estenderam-se de 1111 a 1937 nm e de 2016 a 2500 nm, sendo removidas regiões referentes à água e a ruídos, julgados como interferentes no processo de calibração. Avaliou-se o desempenho dos modelos com base nos pré-tratamentos aplicados (alisamento, primeira derivada Savitzky-Golay, SNV), número de variáveis latentes, consistência, SEC, SEP e coeficientes de determinação (R2 cal/val). Os modelos escolhidos como tendo melhor capacidade preditiva foram os de lipídeos totais, ácido mirístico, palmítico, margárico e ácidos graxos saturados, demonstrando que a NIRS possui alto potencial na quantificação dos constituintes lipídicos da carne bovina.
5
Cogo, Gabriel Silva. "Análise da intenção de adoção da computação em nuvem por profissionais da área de TI." reponame:Biblioteca Digital de Teses e Dissertações da UFRGS, 2013. http://hdl.handle.net/10183/78039.
Full textAbstract:
A computação em nuvem emerge quando se trata da necessidade dos desenvolvedores de TI de sempre aumentar ou incluir novas capacidades, o mais rápido possível, com o menor investimento possível. Ela vem sendo apontada como uma das maiores inovações em TI nos últimos anos e por isso vem chamando a atenção tanto da comunidade acadêmica quanto da comercial. Apesar deste crescente interesse na tecnologia pela literatura acadêmica, a maior parte do foco das pesquisas se dá nos aspectos técnicos, como potencial computacional e custos. Pesquisas sobre as preferências dos profissionais da área relativa à computação em nuvem como uma ferramenta de negócios estão limitadas a estudos de consultorias e empresas privadas. Esta pesquisa tem como objetivo apresentar um estudo do impacto de diferentes dimensões sobre a intenção de adoção da computação em nuvem por profissionais de TI. Para isto, utiliza uma variação do modelo TAM/UTAUT para verificação de intenção de adoção de novas tecnologias. O método escolhido foi a pesquisa survey, realizada a partir de um instrumento previamente proposto e adaptado, sendo feita em duas etapas: estudo de pré-teste e estudo final. Diferentes técnicas estatísticas foram empregadas para refinar o instrumento, como Análise de Confiabilidade, Análise Fatorial Exploratória e Análise Fatorial Confirmatória, utilizando o método PLS (Partial Least Squares) para Equações Estruturais. Como resultado deste refinamento emergiu um modelo teórico de pesquisa final contendo 8 dimensões e 36 itens. Como contribuição para a área de SI, o modelo teórico de pesquisa final se mostrou adequado para avaliar a intenção de adoção da computação em nuvem por profissionais de TI. A principal contribuição da pesquisa para a prática gerencial é o modelo de intenção de adoção da computação em nuvem, que pode auxiliar provedores de computação em nuvem, através da mensuração das principais razões para sua adoção, que são Utilidade Percebida e Atitude Frente à Inovação Tecnológica. Também demonstra que não existe uma relação positiva entre Segurança e Confiança e a Intenção Comportamental. Doze hipóteses foram validadas e seis das hipóteses propostas foram negadas pelos dados. Estas informações buscam fornecer material para que se possa inspirar os esforços no desenvolvimento da tecnologia como ferramenta de negócio.Cloud computing emerges when we talk about the necessity of the IT developers to always increase or add new capabilities, as soon as possible, with the lowest investment possible. It has been appointed as one of the biggest IT innovations in the recent years, and for that reason it’s been calling the attention of the academic and management communities. Even with the growing interest by the academic community, most of the research focus on technical aspects, such as computational potencial and costs. Researches involving professionals’ preferences with cloud computing as a business tool are limited to consultant and private studies at most. This research has the purpose of presenting a study about the impact of different dimensions in the intention of adoption of cloud computing by IT professionals. To do so, it uses a variation of the TAM/UTAUT model for the verification of the intention of adopting new technologies. The research method is the survey research, made with a previously proposed and adapted instrument, conducted in two stages: pre-test study and final study. Different statistical techniques were used to refine the instrument, such as Reliability Analisis, Exploratory Factor Analysis and Confirmatory Factor Analysis, this one using the PLS (Partial Least Squares) Path modeling for SEM (Structural Equation Modeling). As a result of this refinement, emerged a theorical research model containing 8 dimensions and 36 measuring items. As contribution to the IS area, the theorical model proved adequate to assess the intention of adoption of cloud computing by IT professionals. The research’s main contribution to the business practice is the model of cloud computing intention of adoption, that aids cloud providers, trought the measurement of the main reasons behind the adoption of the technology, wich are Perceived Utility and Attitude Towards Technology Innovation. Also demonstrates that there are no positive relation between Security and Trust and the Behaviorial Intention. Twelve of the hypothesis were sustained, and six of the proposed hypothesis were denied by the data. This information intends to inspire efforts in developing the technology as a business tool.
6
Sá, Heloísa Carvalho Reis de. "Application of PLS Models by FTIR for Process Control of Coatings." Master's thesis, 2019. https://hdl.handle.net/10216/121876.
Full textBook chapters on the topic "PLS-DA models"
1
Nieto-Ortega, S., Á. Melado-Herreros, I. Olabarrieta, G. Foti, G. Ramilo-Fernández, C. G. Sotelo, B. Teixeira, A. Velasco, and R. Mendes. "Handheld NIR and PLS-DA Models for Onsite Detection of Injected Water and Discrimination of Different Injected Solutions in Tuna." In Sense the Real Change: Proceedings of the 20th International Conference on Near Infrared Spectroscopy, 108–17. Singapore: Springer Nature Singapore, 2022. http://dx.doi.org/10.1007/978-981-19-4884-8_10.
Full text
2
Calegari, Matheus Augusto, Bruno Bresolin Ayres, Larrisa Macedo dos Santos Tonial, and Tatiane Luiza Cadorin Oldoni. "FT-NIR IN THE CONSTRUCTION OF PLS MODELS FOR DETERMINATION OF TOTAL FLAVONOIDS IN SAMPLES OF PROPOLIS SUBMITTED TO DIFFERENT PROCESSES." In A Produção do Conhecimento nas Ciências Exatas e da Terra 2, 148–61. Atena Editora, 2019. http://dx.doi.org/10.22533/at.ed.39519040415.
Full textConference papers on the topic "PLS-DA models"
1
Pahlawan, Muhammad Fahri Reza, and Rudiati Evi Masithoh. "Vis-NIR Spectroscopy and PLS-Da Model for Classification of Arabica and Robusta Roasted Coffee Bean." In Life Science, Materials and Applied Chemistry. Switzerland: Trans Tech Publications Ltd, 2022. http://dx.doi.org/10.4028/p-60bbc9.
Full textAbstract:
Visible-Near Infrared (Vis-NIR) spectroscopy combined with partial least squares discriminant analysis (PLS-DA) was used to classify Arabica and Robusta roasted coffee beans. The number of coffee beans analyzed was 200 samples consisting of 5 origins (Flores, Temanggung, Aceh Gayo, Jawa, and Toraja). Reflectance spectra with a wavelength of 450-950 nm were used to build two types of models, namely single-origin and general models. Single-origin Flores, Temanggung, Aceh Gayo, and Toraja models performed very well to classify coffee beans samples from the same origin with Sen, Spe, Acc, and Rel of 1, as well as TFN and TFP of 0. General PLS-DA model with baseline correction pretreatment yields Sen, Spe, Acc, and Rel of 0.97, as well as TFN and TFP of 0.04. Based on this paper, it was concluded that Vis-NIR combined with PLS-DA perform well in classifying roasted coffee beans based on the variety.
2
Hang, Jiayi, Da Shi, James House, and Jason Neufeld. "Prediction of protein and amino acid contents in whole and ground lentils using near-infrared reflectance spectroscopy." In 2022 AOCS Annual Meeting & Expo. American Oil Chemists' Society (AOCS), 2022. http://dx.doi.org/10.21748/pqtj3002.
Full textAbstract:
Lentil (Lens culinaris Medik) is an important source of plant-based protein, and the protein and amino acid contents have a significant influence on its nutritional value and use. This study developed near-infrared reflectance spectroscopy (NIRS) calibration models to predict the protein and 18 amino acid contents of lentil seeds. The effects of sample status (whole and ground), type of spectrometer (DA 7250 and FT 9700), and amino acid/protein correlation on model performance were analyzed and evaluated. In total, 361 lentil samples grown in Saskatchewan, Canada, were selected as a calibration set. These samples were scanned by spectrometers and analyzed by reference wet chemistry methods to obtain spectral data and reference data, respectively. NIRS models developed by partial least squares (PLS) equation had a satisfactory performance for measuring protein and most amino acids (except for histidine, tyrosine, methionine, and cysteine) in lentils with high coefficients of determination for calibration (R2C = 0.652–0.927) and residual predictive deviation (RPD = 1.570 – 3.101). NIRS models from DA 7250 achieved similar accuracy for the determination of crude protein and amino acids in whole and ground lentils. DA 7250 models had a slightly better predictive ability with higher coefficients of determination for cross-validation (R2CV) and RPD values than FT 9700 models for all compositions except histidine. However, the predicted data of the two spectrometers did not differ significantly (p > 0.05) for every composition. For amino acids highly correlated to crude protein, NIRS generally predicted them with higher accuracy. Overall, NIRS combined with PLS regression yielded significant potential for rapid and simultaneous prediction of protein and most amino acid contents in lentils with satisfactory accuracy, and these models were usable for research purposes or sample screening.
3
Zadeh, Zahra Derakhshan, Seyyed Jabbar Mousavi, Hassan Ranjbar Askari, and Seyyed Mohammad Reza Darbani. "Hair analysis for diagnosis of addiction by Laser Induced Breakdown Spectroscopy (LIBS) combined with Partial Least Square Discriminant Analysis (PLS-DA) and Support Vector Machine (SVM) models." In Bio-Optics: Design and Application. Washington, D.C.: OSA, 2017. http://dx.doi.org/10.1364/boda.2017.jtu4a.19.
Full text
4
Chovancova, Olga, Denisa Macekova, Jozef Kostolny, Andrea Stafurikova, and Terezia Kiskova. "Quantitative Metabolomics Analysis of Depression based on PLS-DA Model." In 2019 42nd International Conference on Telecommunications and Signal Processing (TSP). IEEE, 2019. http://dx.doi.org/10.1109/tsp.2019.8769066.
Full text
5
Chuen, Lee Loong. "Comparison Of Stratified And Random Iterative Sampling In Evaluation Of Pls-Da Model." In 8th International Conference on Multidisciplinary Research 2019. European Publisher, 2020. http://dx.doi.org/10.15405/epsbs.2020.03.03.75.
Full text
6
Correia, Artur Jordão Lima, and William Robson Schwartz. "Partial Least Squares: A Deep Space Odyssey." In Concurso de Teses e Dissertações da SBC. Sociedade Brasileira de Computação, 2021. http://dx.doi.org/10.5753/ctd.2021.15753.
Full textAbstract:
Modern visual pattern recognition models are based on deep convolutional networks. Such models are computationally expensive, hindering applicability on resource-constrained devices. To handle this problem, we propose three strategies. The first removes unimportant structures (neurons or layers) of convolutional networks, reducing their computational cost. The second inserts structures to design architectures automatically, enabling us to build high-performance networks. The third combines multiple layers of convolutional networks, enhancing data representation at negligible additional cost. These strategies are based on Partial Least Squares (PLS) which, despite promising results, is infeasible on large datasets due to memory constraints. To address this issue, we also propose a discriminative and low-complexity incremental PLS that learns a compact representation of the data using a single sample at a time, thus enabling applicability on large datasets.
7
Chen, Dongmei, Xuejuan Lv, Huatang Wang, Jiali Liu, and Xinnian Zeng. "PLS-DA Infrared Spectra Model of Citrus Leaves for the Characterization of Citrus Huanglongbing." In International Conference on Biomedical and Biological Engineering. Paris, France: Atlantis Press, 2016. http://dx.doi.org/10.2991/bbe-16.2016.14.
Full text
8
MAGALHAES, RANIERE, DANIELA DE OLIVEIRA MORAES, DIEGO COSTA SOMBRA, MARCIO ANTONIO AMANTE MELO, and JOAO CARLOS FELIX SOUZA. "O ASSISTENCIALISMO DAS IGREJAS EVANGÉLICAS E SUA EFICIÊNCIA." In Brazilian Congress. brazco, 2020. http://dx.doi.org/10.51162/brc.dev2020-00061.
Full textAbstract:
O assistencialismo, que envolve acoes realizadas com o proposito de atender a demandas sociais emergenciais, tem transformado um direito do cidadao em mero favor ou obra de caridade. As igrejas, em seu papel de pessoa juridica de direito privado, decidem quando e como prestar auxilio aos menos favorecidos. O trabalho busca investigar e identificar os fatores que influenciam essa tomada de decisao, aplicando-se a metodologia de Modelagem de Equacoes Estruturais com Minimos Quadrados Parciais (PLS-SEM), que demonstra as relacoes causais entre as variaveis do modelo. Na segunda parte deste artigo, apresenta-se o grau de eficiencia das acoes realizadas pelas igrejas evangelicas, obtido por meio da aplicacao da metodologia de Analise Envoltoria de Dados (DEA). Conclui-se que Caracteristica Ministerial e Motivacao Pessoal sao os fatores que mais influenciam na decisao de realizar acoes evangelistico-assistenciais, devendo ser os itens prioritarios na atuacao dos lideres e membros das igrejas que desejem analisar ou ponderar suas decisoes. Das 68 igrejas pesquisadas apenas 17,6% alcancaram a eficiencia, conforme demonstra a metodologia utilizada.,