Data mining-based method for identifying discriminant attributes in sensory profiling

Anzanello, Michel J.; Fogliatto, Flávio Sanson; Rossini, Karina

doi:10.1016/j.foodqual.2010.08.010

Cited by 25 publications

(12 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The number of components to be retained is defined according the Scree Graph, as in Rencher . For details about PCA, see Anzanello et al .…”

Section: Materials and Multivariate Techniquesmentioning

confidence: 99%

“…KNN performs the classification considering a limited number of observations close to the observation to be classified, PNN takes into account the influence of all observations to perform such a categorization, and LDA builds discriminant function which inserts observations into classes. In addition, we also decided to use such techniques because of the good results reported in the literature .…”

Section: Materials and Multivariate Techniquesmentioning

confidence: 99%

“…to guide the insertion of wavelengths into the dataset used for classification. According to Anzanello et al , wavelengths with higher v j allegedly enable better categorization of samples into classes. The number of retained principal components, A , is defined according to the Scree Graph .…”

Section: Materials and Multivariate Techniquesmentioning

confidence: 99%

See 2 more Smart Citations

Wavelength selection framework for classifying food and pharmaceutical samples into multiple classes

Anzanello

Fogliatto

Marcelo

et al. 2016

Journal of Chemometrics

View full text Add to dashboard Cite

Near infrared (NIR) spectroscopy is an efficient, low-cost analytical technique widely applied to identify the origin of food and pharmaceutical products. NIR spectra-based classification strategies typically use thousands of equally spaced wavelengths as input information, some of which may not carry relevant information for product classification. When that is the case, the performance of predictive and exploratory multivariate techniques may be undermined by such noisy information. In this paper, we propose an iterative framework for selecting subsets of NIR wavelengths aimed at classifying samples into categories. For that matter, we integrate Principal Components Analysis (PCA) and three classification techniques: k-Nearest Neighbor (KNN), Probabilistic Neural Network (PNN) and Linear Discriminant Analysis (LDA). PCA is first applied to NIR data, and a wavelength importance index is derived based on the PCA loadings. Samples are then categorized using the wavelength with the highest index and the classification accuracy is calculated; next, the wavelength with the second highest index is inserted into the dataset and a new classification is performed. This forward-based iterative procedure is carried out until all original wavelengths are inserted into the dataset used for classification. The subset of wavelengths leading to the maximum accuracy is chosen as the recommended subset. Our propositions performed remarkably well when applied to four datasets related to food and pharmaceutical products.

show abstract

“…The number of components to be retained is defined according the Scree Graph, as in Rencher . For details about PCA, see Anzanello et al .…”

Section: Materials and Multivariate Techniquesmentioning

confidence: 99%

Section: Materials and Multivariate Techniquesmentioning

confidence: 99%

See 1 more Smart Citation

Wavelength selection framework for classifying food and pharmaceutical samples into multiple classes

Anzanello

Fogliatto

Marcelo

et al. 2016

Journal of Chemometrics

View full text Add to dashboard Cite

show abstract

“…For instance, one may identify those particular cases corresponding to high disagreement and discard them altogether. Anzanello, Fogliatto, and Rossini (2011) proposed to retain only those assessors and attributes that achieve a good discrimination of the products. For this purpose, they defined overall indices associated with the assessors (Ledauphin et al, 2006).…”

Section: Pre-treatment Of the Datamentioning

confidence: 99%

Weighted PLS-discriminant analysis with application to conventional sensory profiling

Verdun

Cariou

Qannari

2012

Food Quality and Preference

View full text Add to dashboard Cite

“…difference tests, attribute difference tests and threshold definition tests ( [11], [12] and [13])). The statistical techniques used in this scope can include analysis of variance ( [14], [15] and [16]), regression analysis ( [17] and [18]), multivariate statistics approaches ( [3], [14], [15], [19], [20]), and Receiver Operating Characteristics Curve ( [21] and [22]). Although this field of study seems to be reasonably covered by the literature, integration of the methods that allows individual information on panellists' performance to be incorporated into the final decisions of the panel is still not found.…”

Section: Introductionmentioning

confidence: 99%

Designing a Decision Support System for Tasting Panels

Teixeira

Ramos

Xambre

et al. 2014

Procedia Technology

View full text Add to dashboard Cite

Tasting Panels are used in Sensory Analysis in order to evaluate products according to the way they are perceived by human senses. In this context, the main job of a professional taster is to assess the sensorial characteristics of products, for example in the food industry. Evaluating the individual performance of the tasters is thus essential, so the results produced are as reliable as possible. The tasting process usually generates a large amount of data that is used in decisions about the products and can also be used to evaluate the tasters. The main objective of this work is to specify and conceptualize a Decision Support System (DSS) to help managing and handling the referred data. This is considered a valuable contribution, since there are no known technological decision tools to support the tasting process.

show abstract

Data mining-based method for identifying discriminant attributes in sensory profiling

Cited by 25 publications

References 41 publications

Wavelength selection framework for classifying food and pharmaceutical samples into multiple classes

Wavelength selection framework for classifying food and pharmaceutical samples into multiple classes

Weighted PLS-discriminant analysis with application to conventional sensory profiling

Designing a Decision Support System for Tasting Panels

Contact Info

Product

Resources

About