Determining the geographical origin of lettuce with data mining applied to micronutrients and soil properties

Abstract Nuclear magnetic resonance (NMR)-based relaxometry is widely used in various fields of research because of its advantages such as simple sample preparation, easy handling, and relatively low cost compared with metabolomics approaches. However, there have been no reports on the application of the T2 relaxation curves in metabolomics studies involving the evaluation of metabolic mixtures, such as geographical origin determination and feature extraction by pattern recognition and data mining. In this study, we describe a data mining method for relaxometric data (i.e., relaxometric learning). This method is based on a machine learning algorithm supported by the analytical framework optimized for the relaxation curve analyses. In the analytical framework, we incorporated a variable optimization approach and bootstrap resampling-based matrixing to enhance the classification performance and balance the sample size between groups, respectively. The relaxometric learning enabled the extraction of features related to the physical properties of fish muscle and the determination of the geographical origin of the fish by improving the classification performance. Our results suggest that relaxometric learning is a powerful and versatile alternative to conventional metabolomics approaches for evaluating fleshiness of chemical mixtures in food and for other biological and chemical research requiring a nondestructive, cost-effective, and time-saving method.

Download Full-text

Relaxometric learning: a pattern recognition method for T2 relaxation curves based on machine learning supported by an analytical framework

BMC Chemistry ◽

10.1186/s13065-020-00731-0 ◽

2021 ◽

Vol 15 (1) ◽

Author(s):

Yasuhiro Date ◽

Feifei Wei ◽

Yuuri Tsuboi ◽

Kengo Ito ◽

Kenji Sakata ◽

...

Keyword(s):

Machine Learning ◽

Data Mining ◽

Pattern Recognition ◽

Geographical Origin ◽

Learning Algorithm ◽

Analytical Framework ◽

Classification Performance ◽

Optimization Approach ◽

Chemical Research ◽

Relaxation Curves

AbstractNuclear magnetic resonance (NMR)-based relaxometry is widely used in various fields of research because of its advantages such as simple sample preparation, easy handling, and relatively low cost compared with metabolomics approaches. However, there have been no reports on the application of the T2 relaxation curves in metabolomics studies involving the evaluation of metabolic mixtures, such as geographical origin determination and feature extraction by pattern recognition and data mining. In this study, we describe a data mining method for relaxometric data (i.e., relaxometric learning). This method is based on a machine learning algorithm supported by the analytical framework optimized for the relaxation curve analyses. In the analytical framework, we incorporated a variable optimization approach and bootstrap resampling-based matrixing to enhance the classification performance and balance the sample size between groups, respectively. The relaxometric learning enabled the extraction of features related to the physical properties of fish muscle and the determination of the geographical origin of the fish by improving the classification performance. Our results suggest that relaxometric learning is a powerful and versatile alternative to conventional metabolomics approaches for evaluating fleshiness of chemical mixtures in food and for other biological and chemical research requiring a nondestructive, cost-effective, and time-saving method.

Download Full-text

Knowledge discovery from models of soil properties developed through data mining

Ecological Modelling ◽

10.1016/j.ecolmodel.2005.05.021 ◽

2006 ◽

Vol 191 (3-4) ◽

pp. 431-446 ◽

Cited By ~ 55

Author(s):

Elisabeth N. Bui ◽

Brent L. Henderson ◽

Karin Viergever

Keyword(s):

Data Mining ◽

Soil Properties ◽

Knowledge Discovery

Download Full-text

Determining the geographical origin of the medicinal plant Marsdenia tenacissima with multi-element analysis and data mining techniques

Chemometrics and Intelligent Laboratory Systems ◽

10.1016/j.chemolab.2014.05.008 ◽

2014 ◽

Vol 136 ◽

pp. 115-120 ◽

Cited By ~ 10

Author(s):

Chao Li ◽

Sheng-Chao Yang ◽

Qiao-Sheng Guo ◽

Kai-Yan Zheng ◽

Yong-Feng Shi ◽

...

Keyword(s):

Data Mining ◽

Medicinal Plant ◽

Geographical Origin ◽

Element Analysis ◽

Data Mining Techniques ◽

Marsdenia Tenacissima ◽

Multi Element Analysis

Download Full-text

A Decision Support System for Increasing Agricultural Production

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.d1133.029420 ◽

2020 ◽

Vol 9 (4) ◽

pp. 1432-1437

Keyword(s):

Data Mining ◽

Soil Properties ◽

Soil Type ◽

Clustering Algorithms ◽

Chemical Properties ◽

Crop Productivity ◽

Primary Role ◽

Data Mining Technique ◽

Color Structure ◽

Huge Data

Agriculture acts an important and primary role in all countries. Especially in Indian economy, agriculture acts an important factor. So, farmers are always in need to increase their crop productivity, which depends on variety of factors present in soil. If a crop is planted on unsuitable soil, it leads to poor yield. So much more attention is needed while selecting the crop for planting. The huge amount of agricultural data that is available in many resources and data mining performs major role in agriculture. By using this data mining techniques, the hidden required pattern from the huge data can be identified and make them useful to the farmers and decision makers to obtain better yield performance. In our work, data mining technique is applied in the dataset of soil and crops, which belongs to Tamilnadu region. We have analyzed various physical properties and also chemical properties of soil like Soil type, Soil Texture, Color, Structure, WHC (Water Holding Capacity), Soil Moisture, pH, Electrical Conductivity (EC) and Temperature. We have considered Soil Type, pH, EC and Temperature in this work to find the suitable crop for best productivity. This research mainly concentrates on finding the correlation between soil properties and crops by applying clustering algorithms such as Simple K Means (SKM), Filtered Clusterer (FC) and Hierarchical Clusterer (HC) for finding the suitable crop according to the soil properties.

Download Full-text

Relaxometric learning: a pattern recognition method for T2 relaxation curves based on machine learning supported by an analytical framework

10.21203/rs.3.rs-31363/v1 ◽

2020 ◽

Author(s):

Yasuhiro Date ◽

Feifei Wei ◽

Yuuri Tsuboi ◽

Kengo Ito ◽

Kenji Sakata ◽

...

Keyword(s):

Machine Learning ◽

Data Mining ◽

Pattern Recognition ◽

Geographical Origin ◽

Learning Algorithm ◽

Analytical Framework ◽

Classification Performance ◽

Optimization Approach ◽

Chemical Research ◽

Relaxation Curves

Abstract Nuclear magnetic resonance (NMR)-based relaxometry is widely used in various fields of research because of its advantages such as simple sample preparation, easy handling, and relatively low cost compared with metabolomics approaches. However, there have been no reports on the application of the T2 relaxation curves in metabolomics studies involving the evaluation of metabolic mixtures, such as geographical origin determination and feature extraction by pattern recognition and data mining. In this study, we describe a data mining method for relaxometric data (i.e., relaxometric learning). This method is based on a machine learning algorithm supported by the analytical framework optimized for the relaxation curve analyses. In the analytical framework, we incorporated a variable optimization approach and bootstrap resampling-based matrixing to enhance the classification performance and balance the sample size between groups, respectively. The relaxometric learning enabled the extraction of features related to the physical properties of fish muscle and the determination of the geographical origin of the fish by improving the classification performance. Our results suggest that relaxometric learning is a powerful and versatile alternative to conventional metabolomics approaches for evaluating fleshiness of chemical mixtures in food and for other biological and chemical research requiring a nondestructive, cost-effective, and time-saving method.

Download Full-text

Relaxometric learning: a pattern recognition method for T2 relaxation curves based on machine learning supported by an analytical framework

10.21203/rs.3.rs-31363/v3 ◽

2020 ◽

Author(s):

Yasuhiro Date ◽

Feifei Wei ◽

Yuuri Tsuboi ◽

Kengo Ito ◽

Kenji Sakata ◽

...

Keyword(s):

Machine Learning ◽

Data Mining ◽

Pattern Recognition ◽

Geographical Origin ◽

Learning Algorithm ◽

Analytical Framework ◽

Classification Performance ◽

Optimization Approach ◽

Chemical Research ◽

Relaxation Curves

Abstract Nuclear magnetic resonance (NMR)-based relaxometry is widely used in various fields of research because of its advantages such as simple sample preparation, easy handling, and relatively low cost compared with metabolomics approaches. However, there have been no reports on the application of the T 2 relaxation curves in metabolomics studies involving the evaluation of metabolic mixtures, such as geographical origin determination and feature extraction by pattern recognition and data mining. In this study, we describe a data mining method for relaxometric data (i.e., relaxometric learning). This method is based on a machine learning algorithm supported by the analytical framework optimized for the relaxation curve analyses. In the analytical framework, we incorporated a variable optimization approach and bootstrap resampling-based matrixing to enhance the classification performance and balance the sample size between groups, respectively. The relaxometric learning enabled the extraction of features related to the physical properties of fish muscle and the determination of the geographical origin of the fish by improving the classification performance. Our results suggest that relaxometric learning is a powerful and versatile alternative to conventional metabolomics approaches for evaluating fleshiness of chemical mixtures in food and for other biological and chemical research requiring a nondestructive, cost-effective, and time-saving method.

Download Full-text