Improving the classification accuracy using biomarkers selected from machine learning methods

Abstract Background: Large-dimensional data modelling often relies on variable reduction methods in the pre-processing and in the post-processing stage. However, such a reduction usually provides less information and yields a lower accuracy of the model. Objectives: The aim of this paper is to assess the high-dimensional classification problem of recognizing entrepreneurial intentions of students by machine learning methods. Methods/Approach: Four methods were tested: artificial neural networks, CART classification trees, support vector machines, and k-nearest neighbour on the same dataset in order to compare their efficiency in the sense of classification accuracy. The performance of each method was compared on ten subsamples in a 10-fold cross-validation procedure in order to assess computing sensitivity and specificity of each model. Results: The artificial neural network model based on multilayer perceptron yielded a higher classification rate than the models produced by other methods. The pairwise t-test showed a statistical significance between the artificial neural network and the k-nearest neighbour model, while the difference among other methods was not statistically significant. Conclusions: Tested machine learning methods are able to learn fast and achieve high classification accuracy. However, further advancement can be assured by testing a few additional methodological refinements in machine learning methods.

Download Full-text

A comparison of different optical instruments and machine learning techniques to identify sprouting activity in potatoes during storage

Journal of Food Measurement & Characterization ◽

10.1007/s11694-020-00590-2 ◽

2020 ◽

Vol 14 (6) ◽

pp. 3565-3579

Author(s):

Ahmed M. Rady ◽

Daniel E. Guyer ◽

Irwin R. Donis-González ◽

William Kirk ◽

Nicholas James Watson

Keyword(s):

Machine Learning ◽

Hyperspectral Imaging ◽

Classification Accuracy ◽

Imaging System ◽

Sugar Content ◽

Machine Learning Techniques ◽

Optical Systems ◽

Learning Methods ◽

Machine Learning Methods ◽

Activity Measurements

Abstract The quality of potato tubers is dependent on several attributes been maintained at appropriate levels during storage. One of these attributes is sprouting activity that is initiated from meristematic regions of the tubers (eyes). Sprouting activity is a major problem that contributes to reduced shelf life and elevated sugar content, which affects the marketability of seed tubers as well as fried products. This study compared the capabilities of three different optical systems (1: visible/near-infrared (Vis/NIR) interactance spectroscopy, 2: Vis/NIR hyperspectral imaging, 3: NIR transmittance) and machine learning methods to detect sprouting activity in potatoes based on the primordial leaf count (LC). The study was conducted on Frito Lay 1879 and Russet Norkotah cultivars stored at different temperatures and classification models were developed that considered both cultivars combined and classified the tubers as having either high or low sprouting activity. Measurements were performed on whole tubers and sliced samples to see the effect this would have on identifying sprouting activity. Sequential forward selection was applied for wavelength selection and the classification was carried out using K-nearest neighbor, partial least squares discriminant analysis, and soft independent modeling class analogy. The highest classification accuracy values obtained by the hyperspectral imaging system and was 87.5% and 90% for sliced and whole samples, respectively. Data fusion did not show classification improvement for whole tubers, whereas a 7.5% classification accuracy increase was illustrated for sliced samples. By investigating different optical techniques and machine learning methods, this study provides a first step toward developing a handheld optical device for early detection of sprouting activity, enabling advanced aid potato storage management.

Download Full-text

Fusion of Multispectral Aerial Imagery and Vegetation Indices for Machine Learning-Based Ground Classification

Remote Sensing ◽

10.3390/rs13081411 ◽

2021 ◽

Vol 13 (8) ◽

pp. 1411

Author(s):

Yanchao Zhang ◽

Wen Yang ◽

Ying Sun ◽

Christine Chang ◽

Jiya Yu ◽

...

Keyword(s):

Machine Learning ◽

Classification Accuracy ◽

Vegetation Indices ◽

Machine Learning Algorithms ◽

Support Vector ◽

Multispectral Images ◽

Learning Methods ◽

Machine Learning Methods ◽

Spectral Bands ◽

Vegetation Indexes

Unmanned Aerial Vehicles (UAVs) are emerging and promising platforms for carrying different types of cameras for remote sensing. The application of multispectral vegetation indices for ground cover classification has been widely adopted and has proved its reliability. However, the fusion of spectral bands and vegetation indices for machine learning-based land surface investigation has hardly been studied. In this paper, we studied the fusion of spectral bands information from UAV multispectral images and derived vegetation indices for almond plantation classification using several machine learning methods. We acquired multispectral images over an almond plantation using a UAV. First, a multispectral orthoimage was generated from the acquired multispectral images using SfM (Structure from Motion) photogrammetry methods. Eleven types of vegetation indexes were proposed based on the multispectral orthoimage. Then, 593 data points that contained multispectral bands and vegetation indexes were randomly collected and prepared for this study. After comparing six machine learning algorithms (Support Vector Machine, K-Nearest Neighbor, Linear Discrimination Analysis, Decision Tree, Random Forest, and Gradient Boosting), we selected three (SVM, KNN, and LDA) to study the fusion of multi-spectral bands information and derived vegetation index for classification. With the vegetation indexes increased, the model classification accuracy of all three selected machine learning methods gradually increased, then dropped. Our results revealed that that: (1) spectral information from multispectral images can be used for machine learning-based ground classification, and among all methods, SVM had the best performance; (2) combination of multispectral bands and vegetation indexes can improve the classification accuracy comparing to only spectral bands among all three selected methods; (3) among all VIs, NDEGE, NDVIG, and NDVGE had consistent performance in improving classification accuracies, and others may reduce the accuracy. Machine learning methods (SVM, KNN, and LDA) can be used for classifying almond plantation using multispectral orthoimages, and fusion of multispectral bands with vegetation indexes can improve machine learning-based classification accuracy if the vegetation indexes are properly selected.

Download Full-text

Comparison of medical image classification accuracy among three machine learning methods

Journal of X-Ray Science and Technology ◽

10.3233/xst-18386 ◽

2018 ◽

Vol 26 (6) ◽

pp. 885-893 ◽

Cited By ~ 5

Author(s):

Tomoko Maruyama ◽

Norio Hayashi ◽

Yusuke Sato ◽

Shingo Hyuga ◽

Yuta Wakayama ◽

...

Keyword(s):

Machine Learning ◽

Image Classification ◽

Classification Accuracy ◽

Medical Image ◽

Learning Methods ◽

Machine Learning Methods ◽

Medical Image Classification

Download Full-text

Identification of Amaranthus Species Using Visible-Near-Infrared (Vis-NIR) Spectroscopy and Machine Learning Methods

Remote Sensing ◽

10.3390/rs13204149 ◽

2021 ◽

Vol 13 (20) ◽

pp. 4149

Author(s):

Soo-In Sohn ◽

Young-Ju Oh ◽

Subramani Pandian ◽

Yong-Ho Lee ◽

John-Lewis Zinia Zaukuu ◽

...

Keyword(s):

Machine Learning ◽

Classification Accuracy ◽

Near Infrared ◽

Cross Validation ◽

Nir Spectroscopy ◽

Support Vector ◽

Adaxial Side ◽

Learning Methods ◽

Machine Learning Methods ◽

Geographical Regions

The feasibility of rapid and non-destructive classification of six different Amaranthus species was investigated using visible-near-infrared (Vis-NIR) spectra coupled with chemometric approaches. The focus of this research would be to use a handheld spectrometer in the field to classify six Amaranthus sp. in different geographical regions of South Korea. Spectra were obtained from the adaxial side of the leaves at 1.5 nm intervals in the Vis-NIR spectral range between 400 and 1075 nm. The obtained spectra were assessed with four different preprocessing methods in order to detect the optimum preprocessing method with high classification accuracy. Preprocessed spectra of six Amaranthus sp. were used as input for the machine learning-based chemometric analysis. All the classification results were validated using cross-validation to produce robust estimates of classification accuracies. The different combinations of preprocessing and modeling were shown to have a classification accuracy of between 71% and 99.7% after the cross-validation. The combination of Savitzky-Golay preprocessing and Support vector machine showed a maximum mean classification accuracy of 99.7% for the discrimination of Amaranthus sp. Considering the high number of spectra involved in this study, the growth stage of the plants, varying measurement locations, and the scanning position of leaves on the plant are all important. We conclude that Vis-NIR spectroscopy, in combination with appropriate preprocessing and machine learning methods, may be used in the field to effectively classify Amaranthus sp. for the effective management of the weedy species and/or for monitoring their food applications.

Download Full-text