Environmental origin classification of coffee beans using infrared spectroscopy

Abstract Coffee is one of tropical agricultural products cultivated in many counties and consumed by people worldwide. The main purpose of this study is to employ the infrared spectroscopy technique to rapidly classify the environmental origins of green coffee bean samples. To achieve this purpose, diffuse reflectance spectral data of coffee samples were collected and acquired in wavelength rang of 1000 – 2500 nm. Classification models were established using principal component analysis (PCA) combined with linear discriminant analysis (LDA). The result showed that coffee bean sample can be classified based on their environmental origins with maximum total explained variance of the first two principal components is 97% (PC1 87% and PC2 10% respectively). Judging from the confusion matrix of the LDA, the classification accuracy reach 92%. It may conclude that infrared spectroscopy approach can be used to rapidly classify and sort coffee beans based on their geographical and environmental origins.

Download Full-text

A Rapid and Nondestructive Approach for the Classification of Different-Age Citri Reticulatae Pericarpium Using Portable Near Infrared Spectroscopy

Sensors ◽

10.3390/s20061586 ◽

2020 ◽

Vol 20 (6) ◽

pp. 1586

Author(s):

Pao Li ◽

Xinxin Zhang ◽

Shangke Li ◽

Guorong Du ◽

Liwen Jiang ◽

...

Keyword(s):

Infrared Spectroscopy ◽

Near Infrared Spectroscopy ◽

Near Infrared ◽

Principal Component ◽

Nondestructive Method ◽

Linear Discriminant ◽

Outer Skin ◽

Data Pretreatment ◽

Pca Method

Citri Reticulatae Pericarpium (CRP), has been used in China for hundreds of years as a functional food and medicine. However, some short-age CRPs are disguised as long-age CRPs by unscrupulous businessmen in order to obtain higher profits. In this paper, a rapid and nondestructive method for the classification of different-age CRPs was established using portable near infrared spectroscopy (NIRS) in diffuse reflectance mode combination with appropriate chemometric methods. The spectra of outer skin and inner capsule of CRPs at different storage ages were obtained directly without destroying the samples. Principal component analysis (PCA) with single and combined spectral pretreatment methods was used for the classification of different-age CRPs. Furthermore, the data were pretreated with the PCA method, and Fisher linear discriminant analysis (FLD) with optimized pretreatment methods was discussed for improving the accuracy of classification. Data pretreatment methods can be used to eliminate the noise and background interference. The classification accuracy of inner capsule is better than that of outer skin data. Furthermore, the best results with 100% prediction accuracy can be obtained with FLD method, even without pretreatment.

Download Full-text

The performance of the C12880MA MEMS sensor for classification of the roasting level of coffee bean

IOP Conference Series Earth and Environmental Science ◽

10.1088/1755-1315/924/1/012021 ◽

2021 ◽

Vol 924 (1) ◽

pp. 012021

Author(s):

A R I Ulinnuha ◽

Z A Bahtiar ◽

A R Nauri ◽

I Rhamadan ◽

R C Wulansari ◽

...

Keyword(s):

Performance Test ◽

Low Cost ◽

Coffee Bean ◽

Full Spectrum ◽

Linear Discriminant ◽

Mems Sensor ◽

Coffee Beans ◽

Mems Technology ◽

Portable Sensor

Abstract The cupping test has been widely used to assess the roasting level of coffee to produce high-quality coffee beans. However, the method requires a longer process and sophisticated sensory analysis. The procedure could only be assessed by the certified panellist. Lately, commercial microelectromechanical system (MEMS) technology has been developed, which could be used for building a small spectrometer sensor. This gives the opportunity to adopt bench-top spectrometer sensing into the low-cost portable sensor. This research aims to study the performance test on the C12880MA MEMS sensor to determine the level of roasted coffee. A total of 90 samples from each 30 medium roasting level (Light to Medium, Medium, and Medium to Dark) was prepared. Spectrum data of samples were measured using a C12880MA sensor ranging from 312.162nm to 868.503nm. Linear Discriminant Analysis (LDA) was performed to classify the roasting level. The result showed that both LDA using full-spectrum and interval spectrum gave 100% accuracy with no falsely classified.

Download Full-text

Detection of adulteration in freshly squeezed orange juice by electronic nose and infrared spectroscopy

Czech Journal of Food Sciences ◽

10.17221/303/2015-cjfs ◽

2016 ◽

Vol 34 (No. 3) ◽

pp. 224-232 ◽

Cited By ~ 11

Author(s):

F. Shen ◽

Q. Wu ◽

A. Su ◽

P. Tang ◽

X. Shao ◽

...

Keyword(s):

Infrared Spectroscopy ◽

Electronic Nose ◽

Orange Juice ◽

Principal Component ◽

Rapid Screening ◽

Gas Chromatography Mass Spectrometry ◽

Attenuated Total Reflectance ◽

Linear Discriminant ◽

Total Reflectance

The use of electronic nose and attenuated total reflectance-Fourier transform infrared spectroscopy (ATR-FTIR) as rapid tools for detection of orange juice adulteration has been preliminarily investigated and compared. Freshly squeezed orange juices were tentatively adulterated with 100% concentrated orange juices at levels ranging from 0% to 30% (v/v). Then the E-nose response signals and FTIR spectra collected from samples were subjected to multivariate analysis by principal component analysis (PCA) and linear discriminant analysis (LDA). PCA indicated that authentic juices and adulterated ones could be approximately separated. For the classification of samples with different adulteration levels, the overall accuracy obtained by LDA in prediction was 91.7 and 87.5% for E-nose and ATR-FTIR, respectively. Gas chromatography-mass spectrometry (GC-MS) results verified that there existed an obvious holistic difference in flavour characteristics between fresh squeezed and concentrated juices. These results demonstrated that both E-nose and FTIR might be used as rapid screening techniques for the detection of this type of juice adulteration.

Download Full-text

Classification of Apple Using near Infrared Spectroscopy Based on Fuzzy Discriminant Analysis

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.710.524 ◽

2013 ◽

Vol 710 ◽

pp. 524-528 ◽

Cited By ~ 2

Author(s):

Xiao Hong Wu ◽

Xing Xing Wan ◽

Bin Wu ◽

Fan Wu

Keyword(s):

Infrared Spectroscopy ◽

Discriminant Analysis ◽

Near Infrared Spectroscopy ◽

Near Infrared ◽

Principal Component ◽

K Nearest Neighbor ◽

Near Infrared Reflectance ◽

Linear Discriminant ◽

Discriminant Information

Classification of apple is an important link in postharvest commercialization processing. To realize the non-destructive, rapid and effective discrimination of apple fruits, the near infrared reflectance spectra of four varieties of apples were collected using near infrared spectroscopy, reduced by principal component analysis (PCA) and used to extract the discriminant information by linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), fuzzy discriminant analysis (FDA) and Foley-Sammon discriminant analysis. Finally k-nearest neighbor finished the classification. The classification results showed that FDA could extract the discriminant information of NIR spectra more effectively, and achieved the highest classification accuracy.

Download Full-text

Structured Laser Illumination Planar Imaging Based Classification of Ground Coffee Using Multivariate Chemometric Analysis

Applied Physics Research ◽

10.5539/apr.v8n3p32 ◽

2016 ◽

Vol 8 (3) ◽

pp. 32 ◽

Cited By ~ 4

Author(s):

Olivier K. Bagui ◽

Kenneth A. Kaduki ◽

Edouard Berrocal ◽

Jeremie T. Zoueu

Keyword(s):

Cluster Analysis ◽

Principal Component ◽

Hierarchical Cluster ◽

Planar Imaging ◽

Reliable Measurement ◽

Laser Illumination ◽

Coffee Beans ◽

Chemometric Techniques ◽

Ground Coffee

Most commercially available ground coffees are processed from Robusta or Arabica coffee beans. In this work, we report on the potential of Structured Laser Illumination Planar Imaging (SLIPI) technique for the classification of five types of Robusta and Arabica commercial ground coffee samples (Familial, Belier, Brazil, Colombia and Malaga). This classification is made, here, from the measurement of the extinction coefficient µe and of the optical depth OD by means of SLIPI. The proposed technique offers the advantage of eliminating the light intensity from photons which have been multiply scattered in the coffee solution, leading to an accurate and reliable measurement of µe. Data analysis uses the chemometric techniques of Principal Component Anaysis (PCA) for variable selection and Hierarchical Cluster Analysis (HCA) for classification. The chemometric model demonstrates the potential of this approach for practical assessment of coffee grades by correctly classifying the coffee samples according to their species.

Download Full-text

AlexNet convolutional neural network to classify the types of Indonesian coffee beans

IOP Conference Series Earth and Environmental Science ◽

10.1088/1755-1315/905/1/012059 ◽

2021 ◽

Vol 905 (1) ◽

pp. 012059

Author(s):

Y Hendrawan ◽

B Rohmatulloh ◽

F I Ilmi ◽

M R Fauzy ◽

R Damayanti ◽

...

Keyword(s):

Neural Network ◽

Computer Vision ◽

Sensitivity Analysis ◽

Convolutional Neural Network ◽

Confusion Matrix ◽

Learning Rate ◽

Agricultural Products ◽

Coffee Bean ◽

Coffee Beans ◽

Non Destructive

Abstract Various types of Indonesian coffee are already popular internationally. Recently, there are still not many methods to classify the types of typical Indonesian coffee. Computer vision is a non-destructive method for classifying agricultural products. This study aimed to classify three types of Indonesian Arabica coffee beans, i.e., Gayo Aceh, Kintamani Bali, and Toraja Tongkonan, using computer vision. The classification method used was the AlexNet convolutional neural network with sensitivity analysis using several variations of the optimizer such as SGDm, Adam, and RMSProp and the learning rate of 0.00005 and 0.0001. Each type of coffee used 500 data for training and validation with the distribution of 70% training and 30% validation. The results showed that all AlexNet models achieved a perfect validation accuracy value of 100% in 1,040 iterations. This study also used 100 testing-set data on each type of coffee bean. In the testing confusion matrix, the accuracy reached 99.6%.

Download Full-text

An analytical strategy based on Fourier transform infrared spectroscopy, principal component analysis and linear discriminant analysis to suggest the botanical origin of resins from Bursera. Application to archaeological Aztec Samples

Journal of Cultural Heritage ◽

10.1016/j.culher.2018.02.006 ◽

2018 ◽

Vol 33 ◽

pp. 48-59 ◽

Cited By ~ 6

Author(s):

Carmen Piña-Torres ◽

Paola Lucero-Gómez ◽

Stephany Nieto ◽

Alfonsina Vázquez ◽

Lauro Bucio ◽

...

Keyword(s):

Principal Component Analysis ◽

Fourier Transform ◽

Infrared Spectroscopy ◽

Discriminant Analysis ◽

Linear Discriminant Analysis ◽

Fourier Transform Infrared Spectroscopy ◽

Principal Component ◽

Botanical Origin ◽

Analytical Strategy ◽

Linear Discriminant

Download Full-text

Determination of HPLC-UV Fingerprints of Spanish Paprika (Capsicum annuum L.) for Its Classification by Linear Discriminant Analysis

Sensors ◽

10.3390/s18124479 ◽

2018 ◽

Vol 18 (12) ◽

pp. 4479 ◽

Cited By ~ 6

Author(s):

Xavier Cetó ◽

Núria Serrano ◽

Miriam Aragó ◽

Alejandro Gámez ◽

Miquel Esteban ◽

...

Keyword(s):

Discriminant Analysis ◽

Linear Discriminant Analysis ◽

Principal Component ◽

Reversed Phase ◽

Classification Rate ◽

Phenolic Profile ◽

Linear Discriminant ◽

Sample Extraction

The development of a simple HPLC-UV method towards the evaluation of Spanish paprika’s phenolic profile and their discrimination based on the former is reported herein. The approach is based on C18 reversed-phase chromatography to generate characteristic fingerprints, in combination with linear discriminant analysis (LDA) to achieve their classification. To this aim, chromatographic conditions were optimized so as to achieve the separation of major phenolic compounds already identified in paprika. Paprika samples were subjected to a sample extraction stage by sonication and centrifugation; extracting procedure and conditions were optimized to maximize the generation of enough discriminant fingerprints. Finally, chromatograms were baseline corrected, compressed employing fast Fourier transform (FFT), and then analyzed by means of principal component analysis (PCA) and LDA to carry out the classification of paprika samples. Under the developed procedure, a total of 96 paprika samples were analyzed, achieving a classification rate of 100% for the test subset (n = 25).

Download Full-text

Characterization and classification of Romanian acacia honey based on its physicochemical parameters and chemometrics

Scientific Reports ◽

10.1038/s41598-020-77685-9 ◽

2020 ◽

Vol 10 (1) ◽

Author(s):

Mihaela Emanuela Crăciun ◽

Oana Cristina Pârvulescu ◽

Andreea Cristina Donise ◽

Tănase Dobre ◽

Dumitru Radu Stanciu

Keyword(s):

Physicochemical Parameters ◽

Stable Carbon Isotopes ◽

Reducing Sugars ◽

Activity Ratio ◽

Sugar Content ◽

Principal Component ◽

Reducing Sugar ◽

Linear Discriminant ◽

Acacia Honey

AbstractThree groups of Romanian acacia honey, i.e., pure, directly adulterated (by mixing the pure honey with three sugar syrups), and indirectly adulterated (by feeding the bees with the same syrups), were characterized and discriminated based on their physicochemical parameters. Moisture, ash, 5-hydroxymethylfurfural (HMF), reducing sugars (fructose and glucose), and sucrose contents, free acidity, diastase activity, ratio between stable carbon isotopes of honey and its proteins (δ13CH and δ13CP) were evaluated. Adulteration led to a significant increase in sucrose content, HMF level, and Δδ13C = δ13CH‒δ13CP as well a decrease in reducing sugar content and diastase activity. Principal component analysis (PCA) and linear discriminant analysis (LDA) were applied to experimental data in order to distinguish between pure and adulterated honey. The most relevant discriminative parameters were diastase activity, HMF, sucrose, and reducing sugar contents. Posterior classification probabilities and classification functions obtained by LDA revealed that 100% of honey samples were correctly assigned to their original group.

Download Full-text