Random Forest, Artificial Neural Network, and Support Vector Machine Models for Honey Classification

Martinez-Castillo, Cecilia; Astray, Gonzalo; Mejuto, J. C.; Simal‐Gándara, Jesús

doi:10.2991/efood.k.191004.001

Cited by 21 publications

(9 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…NIR has been used extensively in applications where determining the quality of food is time consuming due to the use of intrusive approaches [14,33,38,[73][74][75][76]96,97]. The adulteration of expensive food items has become widespread and NIR has been used to successfully determine adulteration levels [36,77,78,87,[98][99][100]. As a low-cost quick method for identifying illnesses, NIR has also been used in health applications [79,80].…”

Section: Discussionmentioning

confidence: 99%

A Review of Machine Learning for Near-Infrared Spectroscopy

Zhang

Kasun

Wang

et al. 2022

Sensors

View full text Add to dashboard Cite

The analysis of infrared spectroscopy of substances is a non-invasive measurement technique that can be used in analytics. Although the main objective of this study is to provide a review of machine learning (ML) algorithms that have been reported for analyzing near-infrared (NIR) spectroscopy from traditional machine learning methods to deep network architectures, we also provide different NIR measurement modes, instruments, signal preprocessing methods, etc. Firstly, four different measurement modes available in NIR are reviewed, different types of NIR instruments are compared, and a summary of NIR data analysis methods is provided. Secondly, the public NIR spectroscopy datasets are briefly discussed, with links provided. Thirdly, the widely used data preprocessing and feature selection algorithms that have been reported for NIR spectroscopy are presented. Then, the majority of the traditional machine learning methods and deep network architectures that are commonly employed are covered. Finally, we conclude that developing the integration of a variety of machine learning algorithms in an efficient and lightweight manner is a significant future research direction.

show abstract

Section: Discussionmentioning

confidence: 99%

A Review of Machine Learning for Near-Infrared Spectroscopy

Zhang

Kasun

Wang

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…As regards the application of random forest in combination with other analytical techniques for honey classification, to the best of our knowledge only two contributions have been until now published. In the first study, electrophoresis was used in order to discriminate between two different honey types [ 48 ]. In the most recent contribution, the classification of honeys belonging to the different floral sources was successfully achieved (prediction accuracy of 98.2%) by means of laser induced breakdown spectroscopy and random forest [ 61 ].…”

Section: Discussionmentioning

confidence: 99%

“…The prediction accuracy obtained by a multitude of decision tree is generally higher than the one obtained with a single tree [ 46 ]. Despite the potential of this classification algorithm, only a few examples of the application of random forest for honey classification can be found in the literature [ 22 , 46 , 48 ].…”

Section: Introductionmentioning

confidence: 99%

Classification of Unifloral Honeys from SARDINIA (Italy) by ATR-FTIR Spectroscopy and Random Forest

et al. 2020

View full text Add to dashboard Cite

Nowadays, the mislabeling of honey floral origin is a very common fraudulent practice. The scientific community is intensifying its efforts to provide the bodies responsible for controlling the authenticity of honey with fast and reliable analytical protocols. In this study, the classification of various monofloral honeys from Sardinia, Italy, was attempted by means of ATR-FTIR spectroscopy and random forest. Four different floral origins were considered: strawberry-tree (Arbutus Unedo L.), asphodel (Asphodelus microcarpus), thistle (Galactites tormentosa), and eucalyptus (Eucalyptus calmadulensis). Training a random forest on the infrared spectra allowed achieving an average accuracy of 87% in a cross-validation setting. The identification of the significant wavenumbers revealed the important role played by the region 1540–1175 cm−1 and, to a lesser extent, the region 1700–1600 cm−1. The contribution of the phenolic fraction was identified as the main responsible for this observation.

show abstract

“…Then, we selected three of the top used machine learning algorithms (Random Forests, SVM and Neural Networks) to estimate if there is a more accurate combination between the different predictions. We selected these classifiers similarly to many studies that only considered them in their research works [42][43][44][45][46][47]. Below is a more detailed description of every selected approach:…”

Section: Ensemble Classificationmentioning

confidence: 99%

COVID-19 Diagnosis in Chest X-rays Using Deep Learning and Majority Voting

et al. 2021

View full text Add to dashboard Cite

The COVID-19 disease has spread all over the world, representing an intriguing challenge for humanity as a whole. The efficient diagnosis of humans infected by COVID-19 still remains an increasing need worldwide. The chest X-ray imagery represents, among others, one attractive means to detect COVID-19 cases efficiently. Many studies have reported the efficiency of using deep learning classifiers in diagnosing COVID-19 from chest X-ray images. They conducted several comparisons among a subset of classifiers to identify the most accurate. In this paper, we investigate the potential of the combination of state-of-the-art classifiers in achieving the highest possible accuracy for the detection of COVID-19 from X-ray. For this purpose, we conducted a comprehensive comparison study among 16 state-of-the-art classifiers. To the best of our knowledge, this is the first study considering this number of classifiers. This paper’s innovation lies in the methodology that we followed to develop the inference system that allows us to detect COVID-19 with high accuracy. The methodology consists of three steps: (1) comprehensive comparative study between 16 state-of-the-art classifiers; (2) comparison between different ensemble classification techniques, including hard/soft majority, weighted voting, Support Vector Machine, and Random Forest; and (3) finding the combination of deep learning models and ensemble classification techniques that lead to the highest classification confidence on three classes. We found that using the Majority Voting approach is an adequate strategy to adopt in general cases for this task and may achieve an average accuracy up to 99.314%.

show abstract

Random Forest, Artificial Neural Network, and Support Vector Machine Models for Honey Classification

Cited by 21 publications

References 52 publications

A Review of Machine Learning for Near-Infrared Spectroscopy

A Review of Machine Learning for Near-Infrared Spectroscopy

Classification of Unifloral Honeys from SARDINIA (Italy) by ATR-FTIR Spectroscopy and Random Forest

COVID-19 Diagnosis in Chest X-rays Using Deep Learning and Majority Voting

Contact Info

Product

Resources

About