scholarly journals Classification of Sentinel-2 Images Utilizing Abundance Representation

Proceedings ◽  
2018 ◽  
Vol 2 (7) ◽  
pp. 328 ◽  
Author(s):  
Eleftheria Mylona ◽  
Vassiliki Daskalopoulou ◽  
Olga Sykioti ◽  
Konstantinos Koutroumbas ◽  
Athanasios Rontogiannis
Keyword(s):  
Clustering Algorithm ◽  
Nearest Neighbor ◽  
Unsupervised Classification ◽  
Bare Soil ◽  
Spectral Unmixing ◽  
Support Vector ◽  
Endmember Extraction ◽  
Bayes Algorithm ◽  
Sentinel 2

This paper deals with (both supervised and unsupervised) classification of multispectral Sentinel-2 images, utilizing the abundance representation of the pixels of interest. The latter pixel representation uncovers the hidden structured regions that are not often available in the reference maps. Additionally, it encourages class distinctions and bolsters accuracy. The adopted methodology, which has been successfully applied to hyperpsectral data, involves two main stages: (I) the determination of the pixel’s abundance representation; and (II) the employment of a classification algorithm applied to the abundance representations. More specifically, stage (I) incorporates two key processes, namely (a) endmember extraction, utilizing spectrally homogeneous regions of interest (ROIs); and (b) spectral unmixing, which hinges upon the endmember selection. The adopted spectral unmixing process assumes the linear mixing model (LMM), where each pixel is expressed as a linear combination of the endmembers. The pixel’s abundance vector is estimated via a variational Bayes algorithm that is based on a suitably defined hierarchical Bayesian model. The resulting abundance vectors are then fed to stage (II), where two off-the-shelf supervised classification approaches (namely nearest neighbor (NN) classification and support vector machines (SVM)), as well as an unsupervised classification process (namely the online adaptive possibilistic c-means (OAPCM) clustering algorithm), are adopted. Experiments are performed on a Sentinel-2 image acquired for a specific region of the Northern Pindos National Park in north-western Greece containing water, vegetation and bare soil areas. The experimental results demonstrate that the ad-hoc classification approaches utilizing abundance representations of the pixels outperform those utilizing the spectral signatures of the pixels in terms of accuracy.

scholarly journals Delineating Smallholder Maize Farms from Sentinel-1 Coupled with Sentinel-2 Data Using Machine Learning

2021 ◽  
Vol 13 (9) ◽  
pp. 4728
Author(s):  
Zinhle Mashaba-Munghemezulu ◽  
George Johannes Chirima ◽  
Cilence Munghemezulu
Keyword(s):  
Machine Learning ◽  
Food Security ◽  
Rural Communities ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Subsistence Agriculture ◽  
Smallholder Farms ◽  
Main Driver ◽  
Sentinel 2

Rural communities rely on smallholder maize farms for subsistence agriculture, the main driver of local economic activity and food security. However, their planted area estimates are unknown in most developing countries. This study explores the use of Sentinel-1 and Sentinel-2 data to map smallholder maize farms. The random forest (RF), support vector (SVM) machine learning algorithms and model stacking (ST) were applied. Results show that the classification of combined Sentinel-1 and Sentinel-2 data improved the RF, SVM and ST algorithms by 24.2%, 8.7%, and 9.1%, respectively, compared to the classification of Sentinel-1 data individually. Similarities in the estimated areas (7001.35 ± 1.2 ha for RF, 7926.03 ± 0.7 ha for SVM and 7099.59 ± 0.8 ha for ST) show that machine learning can estimate smallholder maize areas with high accuracies. The study concludes that the single-date Sentinel-1 data were insufficient to map smallholder maize farms. However, single-date Sentinel-1 combined with Sentinel-2 data were sufficient in mapping smallholder farms. These results can be used to support the generation and validation of national crop statistics, thus contributing to food security.

scholarly journals RB-Bayes algorithm for the prediction of diabetic in Pima Indian dataset

2019 ◽  
Vol 9 (6) ◽  
pp. 4866
Author(s):  
Rajni Rajni ◽  
Amandeep Amandeep
Keyword(s):  
Nearest Neighbor ◽  
Naive Bayes ◽  
Early Stage ◽  
Human Life ◽  
Naïve Bayes ◽  
Support Vector ◽  
Pima Indians ◽  
K Nearest Neighbor ◽  
Fast Pace ◽  
Bayes Algorithm

<p>Diabetes is a major concern all over the world. It is increasing at a fast pace. People can avoid diabetes at an early stage without any test. The goal of this paper is to predict the probability of whether the person has a risk of diabetes or not at an early stage. This would lead to having a great impact on their quality of human life. The datasets are Pima Indians diabetes and Cleveland coronary illness and consist of 768 records. Though there are a number of solutions available for information extraction from a huge datasets and to predict the possibility of having diabetes, but the accuracy of their mining process is far from accurate. For achieving highest accuracy, the issue of zero probability which is generally faced by naïve bayes analysis needs to be addressed suitably. The proposed framework RB-Bayes aims to extract the required information with high accuracy that could survive the problem of zero probability and also configure accuracy with other methods like Support Vector Machine, Naive Bayes, and K Nearest Neighbor. We calculated mean to handle missing data and calculated probability for yes (positive) and no (negative). The highest value between yes and no decide the value for the tuple. It is mostly used in text classification. The outcomes on Pima Indian diabetes dataset demonstrate that the proposed methodology enhances the precision as a contrast with other regulated procedures. The accuracy of the proposed methodology large dataset is 72.9%.</p>

Adaptive Median Filtering Based on Unsupervised Classification of Pixels

2013 ◽  
pp. 273-296 ◽  
Author(s):  
J. K. Mandal ◽  
Somnath Mukhopadhyay
Keyword(s):  
Clustering Algorithm ◽  
Digital Images ◽  
Unsupervised Classification ◽  
Median Filtering ◽  
Adaptive Window ◽  
Novel Approach ◽  
Weighted Median ◽  
Window Selection ◽  
Filtering Approach

This chapter deals with a novel approach which aims at detection and filtering of impulses in digital images through unsupervised classification of pixels. This approach coagulates directional weighted median filtering with unsupervised pixel classification based adaptive window selection toward detection and filtering of impulses in digital images. K-means based clustering algorithm has been utilized to detect the noisy pixels based adaptive window selection to restore the impulses. Adaptive median filtering approach has been proposed to obtain best possible restoration results. Results demonstrating the effectiveness of the proposed technique are provided for numeric intensity values described in terms of feature vectors. Various benchmark digital images are used to show the restoration results in terms of PSNR (dB) and visual effects which conform better restoration of images through proposed technique.

scholarly journals A Deep Learning Based Method for the Non-Destructive Measuring of Rock Strength through Hammering Sound

2019 ◽  
Vol 9 (17) ◽  
pp. 3484
Author(s):  
Shuai Han ◽  
Heng Li ◽  
Mingchao Li ◽  
Timothy Rose
Keyword(s):  
Clustering Algorithm ◽  
Nearest Neighbor ◽  
Rock Strength ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Strength Measurement ◽  
Regression Algorithms ◽  
Almost All ◽  
The Relationship ◽  
Non Destructive

Hammering rocks of different strengths can make different sounds. Geological engineers often use this method to approximate the strengths of rocks in geology surveys. This method is quick and convenient but subjective. Inspired by this problem, we present a new, non-destructive method for measuring the surface strengths of rocks based on deep neural network (DNN) and spectrogram analysis. All the hammering sounds are transformed into spectrograms firstly, and a clustering algorithm is presented to filter out the outliers of the spectrograms automatically. One of the most advanced image classification DNN, the Inception-ResNet-v2, is then re-trained with the spectrograms. The results show that the training accurate is up to 94.5%. Following this, three regression algorithms, including Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Random Forest (RF) are adopted to fit the relationship between the outputs of the DNN and the strength values. The tests show that KNN has the highest fitting accuracy, and SVM has the strongest generalization ability. The strengths (represented by rebound values) of almost all the samples can be predicted within an error of [−5, 5]. Overall, the proposed method has great potential in supporting the implementation of efficient rock strength measurement methods in the field.

scholarly journals Distinguishing Photosynthetic and Non-Photosynthetic Vegetation: How Do Traditional Observations and Spectral Classification Compare?

2019 ◽  
Vol 11 (21) ◽  
pp. 2589 ◽  
Author(s):  
Claire Fisk ◽  
Kenneth Clarke ◽  
Steven Delean ◽  
Megan Lewis
Keyword(s):  
Full Range ◽  
Significant Proportion ◽  
Ground Cover ◽  
Bare Soil ◽  
Remotely Sensed ◽  
Spectral Unmixing ◽  
Field Methodology ◽  
Wheat Leaves ◽  
Vegetation Samples

Remotely sensed ground cover maps are routinely validated using field data collected by observers who classify ground cover into defined categories such as photosynthetic vegetation (PV), non-photosynthetic vegetation (NPV), bare soil (BS), and rock. There is an element of subjectivity to the classification of PV and NPV, and classifications may differ between observers. An alternative is to estimate ground cover based on in situ hyperspectral reflectance measurements (HRM). This study examines observer consistency when classifying vegetation samples of wheat (Triticum aestivum var. Gladius) covering the full range of photosynthetic activity, from completely senesced (0% PV) to completely green (100% PV), as photosynthetic or non-photosynthetic. We also examine how the classification of spectra of the same vegetation samples compares to the observer results. We collected HRM and photographs, over two months, to capture the transition of wheat leaves from 100% PV to 100% NPV. To simulate typical field methodology, observers viewed the photographs and classified each leaf as either PV or NPV, while spectral unmixing was used to decompose the HRM of the leaves into proportions of PV and NPV. The results showed that when a leaf was ≤25% or ≥75% PV observers tended to agree, and assign the leaf to the expected category. However, as leaves transitioned from PV to NPV (i.e., PV ≥ 25% but ≤ 75%) observers’ decisions differed more widely and their classifications showed little agreement with the spectral proportions of PV and NPV. This has significant implications for the reliability of data collected using binary methods in areas containing a significant proportion of vegetation in this intermediate range such as the over/underestimation of PV and NPV vegetation and how reliably this data can then be used to validate remotely sensed products.

scholarly journals Classification of fruits and vegetables using ResNet model.

2021 ◽  
Author(s):  
P. Sukhetha ◽  
N. Hemalatha ◽  
Raji Sukumar
Keyword(s):  
Deep Learning ◽  
Fruits And Vegetables ◽  
Nearest Neighbor ◽  
Support Vector ◽  
Agricultural Field ◽  
K Nearest Neighbor ◽  
New Techniques ◽  
Learning Techniques ◽  
A Current

Abstract Agriculture is one of the important parts of Indian economy. Agricultural field has more contribution towards growth and stability of the nation. Therefore, a current technologies and innovations can help in order to experiment new techniques and methods in the agricultural field. At Present Artificial Intelligence (AI) is one of the main, effective, and widely used technology. Especially, Deep Learning (DL) has numerous functions due to its capability to learn robust interpretations from images. Convolutional Neural Networks (CNN) is the major Deep Learning architecture for image classification. This paper is mainly focus on the deep learning techniques to classify Fruits and Vegetables, the model creation and implementation to identify Fruits and Vegetables on the fruit360 dataset. The models created are Support Vector Machine (SVM), K Nearest Neighbor (KNN), Decision Tree (DT), ResNet Pretrained Model, Convolutional Neural Network (CNN), Multilayer Perceptron (MLP). Among the different models ResNet pretrained Model performed the best with an accuracy of 95.83%.

scholarly journals Classification of EEG Signals using Nonlinear Features and Preprocessing Techniques

2021 ◽  
Vol 10 (5) ◽  
pp. 297-301
Author(s):  
Saneesh Cleatus T ◽  
Dr. Thungamani M
Keyword(s):  
Brain Tumor ◽  
Nearest Neighbor ◽  
Processing Technique ◽  
Support Vector ◽  
Statistical Features ◽  
K Nearest Neighbor ◽  
Eeg Signals ◽  
Mode Decomposition ◽  
Nonlinear Features

In this paper we study the effect of nonlinear preprocessing techniques in the classification of electroencephalogram (EEG) signals. These methods are used for classifying the EEG signals captured from epileptic seizure activity and brain tumor category. For the first category, preprocessing is carried out using elliptical filters, and statistical features such as Shannon entropy, mean, standard deviation, skewness and band power. K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) were used for the classification. For the brain tumor EEG signals, empirical mode decomposition is used as a pre-processing technique along with standard statistical features for the classification of normal and abnormal EEG signals. For epileptic signals we have achieved an average accuracy of 94% for a three-class classification and for brain tumor signals we have achieved a classification accuracy of 98% considering it as a two class problem.

scholarly journals Studi Komparasi Metode Machine Learning untuk Klasifikasi Citra Huruf Vokal Hiragana

2021 ◽  
Vol 5 (3) ◽  
pp. 905
Author(s):  
Muhammad Afrizal Amrustian ◽  
Vika Febri Muliati ◽  
Elsa Elvira Awal
Keyword(s):  
Machine Learning ◽  
Comparative Study ◽  
Image Classification ◽  
Nearest Neighbor ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
The Comparative Study

Japanese is one of the most difficult languages to understand and read. Japanese writing that does not use the alphabet is the reason for the difficulty of the Japanese language to read. There are three types of Japanese, namely kanji, katakana, and hiragana. Hiragana letters are the most commonly used type of writing. In addition, hiragana has a cursive nature, so each person's writing will be different. Machine learning methods can be used to read Japanese letters by recognizing the image of the letters. The Japanese letters that are used in this study are hiragana vowels. This study focuses on conducting a comparative study of machine learning methods for the image classification of Japanese letters. The machine learning methods that were successfully compared are Naïve Bayes, Support Vector Machine, Decision Tree, Random Forest, and K-Nearest Neighbor. The results of the comparative study show that the K-Nearest Neighbor method is the best method for image classification of hiragana vowels. K-Nearest Neighbor gets an accuracy of 89.4% with a low error rate.

Sign in / Sign up

Export Citation Format

Share Document