scholarly journals Very Deep Convolutional Neural Networks for Complex Land Cover Mapping Using Multispectral Remote Sensing Imagery

2018 ◽  
Vol 10 (7) ◽  
pp. 1119 ◽  
Author(s):  
Masoud Mahdianpari ◽  
Bahram Salehi ◽  
Mohammad Rezaee ◽  
Fariba Mohammadimanesh ◽  
Yun Zhang
Keyword(s):  
Remote Sensing ◽  
Neural Networks ◽  
Computer Vision ◽  
Support Vector Machine ◽  
State Of The Art ◽  
Support Vector ◽  
Learning Tools ◽  
Deep Convolutional Neural Networks ◽  
Multispectral Remote Sensing

Despite recent advances of deep Convolutional Neural Networks (CNNs) in various computer vision tasks, their potential for classification of multispectral remote sensing images has not been thoroughly explored. In particular, the applications of deep CNNs using optical remote sensing data have focused on the classification of very high-resolution aerial and satellite data, owing to the similarity of these data to the large datasets in computer vision. Accordingly, this study presents a detailed investigation of state-of-the-art deep learning tools for classification of complex wetland classes using multispectral RapidEye optical imagery. Specifically, we examine the capacity of seven well-known deep convnets, namely DenseNet121, InceptionV3, VGG16, VGG19, Xception, ResNet50, and InceptionResNetV2, for wetland mapping in Canada. In addition, the classification results obtained from deep CNNs are compared with those based on conventional machine learning tools, including Random Forest and Support Vector Machine, to further evaluate the efficiency of the former to classify wetlands. The results illustrate that the full-training of convnets using five spectral bands outperforms the other strategies for all convnets. InceptionResNetV2, ResNet50, and Xception are distinguished as the top three convnets, providing state-of-the-art classification accuracies of 96.17%, 94.81%, and 93.57%, respectively. The classification accuracies obtained using Support Vector Machine (SVM) and Random Forest (RF) are 74.89% and 76.08%, respectively, considerably inferior relative to CNNs. Importantly, InceptionResNetV2 is consistently found to be superior compared to all other convnets, suggesting the integration of Inception and ResNet modules is an efficient architecture for classifying complex remote sensing scenes such as wetlands.

Detection of magnetite in the Roossenekal area of the Eastern Bushveld Complex, South Africa, using multispectral remote sensing data

2020 ◽  
Vol 123 (4) ◽  
pp. 573-586
Author(s):  
M. Twala ◽  
R. J. Roberts ◽  
C. Munghemezulu
Keyword(s):  
Remote Sensing ◽  
Support Vector Machine ◽  
Maximum Likelihood ◽  
Bushveld Complex ◽  
Support Vector ◽  
Classification Algorithms ◽  
Error Matrix ◽  
Geological Processes ◽  
Multispectral Remote Sensing ◽  
Eastern Limb

Abstract Multispectral sensors, along with common and advanced algorithms, have become efficient tools for routine lithological discrimination and mineral potential mapping. It is with this paradigm in mind that this paper sought to evaluate and discuss the detection and mapping of magnetite on the Eastern Limb of the Bushveld Complex, using high spectral resolution multispectral remote sensing imagery and GIS techniques. Despite the wide distribution of magnetite, its economic importance, and its potential as an indicator of many important geological processes, not many studies had looked at the detection and exploration of magnetite using remote sensing in this region. The Maximum Likelihood and Support Vector Machine classification algorithms were assessed for their respective ability to detect and map magnetite using the PlanetScope Analytic data. A K-fold cross-validation analysis was used to measure the performance of the training as well as the test data. For each classification algorithm, a thematic landcover map was created and an error matrix, depicting the user’s and producer’s accuracies as well as kappa statistics, was derived. A pairwise comparison test of the image classification algorithms was conducted to determine whether the two classification algorithms were significantly different from each other. The Maximum Likelihood Classifier significantly outperformed the Support Vector Machine algorithm, achieving an overall classification accuracy of 84.58% and an overall kappa value of 0.79. Magnetite was accurately discriminated from the other thematic landcover classes with a user’s accuracy of 76.41% and a producer’s accuracy of 88.66%. The overall results of this study illustrated that remote sensing techniques are effective instruments for geological mapping and mineral investigation, especially iron oxide mineralization in the Eastern Limb of the Bushveld Complex.

scholarly journals Investigating Deep Feedforward Neural Networks for Classification of Transposon-Derived piRNAs

2020 ◽  
Author(s):  
Alisson Hayasi da Costa ◽  
Renato Augusto C. dos Santos ◽  
Ricardo Cerri
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
State Of The Art ◽  
Feedforward Neural Networks ◽  
The State ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Advantages And Disadvantages ◽  
Large Application

AbstractPIWI-Interacting RNAs (piRNAs) form an important class of non-coding RNAs that play a key role in the genome integrity through the silencing of transposable elements. However, despite their importance and the large application of deep learning in computational biology for classification tasks, there are few studies of deep learning and neural networks for piRNAs prediction. Therefore, this paper presents an investigation on deep feedforward networks models for classification of transposon-derived piRNAs. We analyze and compare the results of the neural networks in different hyperparameters choices, such as number of layers, activation functions and optimizers, clarifying the advantages and disadvantages of each configuration. From this analysis, we propose a model for human piRNAs classification and compare our method with the state-of-the-art deep neural network for piRNA prediction in the literature and also traditional machine learning algorithms, such as Support Vector Machines and Random Forests, showing that our model has achieved a great performance with an F-measure value of 0.872, outperforming the state-of-the-art method in the literature.

scholarly journals Classification of the Complex Agricultural Planting Structure with a Semi-Supervised Extreme Learning Machine Framework

2020 ◽  
Vol 12 (22) ◽  
pp. 3708 ◽  
Author(s):  
Ziyi Feng ◽  
Guanhua Huang ◽  
Daocai Chi
Keyword(s):  
Remote Sensing ◽  
Support Vector Machine ◽  
Computational Efficiency ◽  
Large Scale ◽  
Statistical Data ◽  
Support Vector ◽  
Small Scale ◽  
Remote Sensing Images ◽  
Learning Machine

Many approaches have been developed to analyze remote sensing images. However, for the classification of large-scale problems, most algorithms showed low computational efficiency and low accuracy. In this paper, the newly developed semi-supervised extreme learning machine (SS-ELM) framework with k-means clustering algorithm for image segmentation and co-training algorithm to enlarge the sample sets was used to classify the agricultural planting structure at large-scale areas. Data sets collected from a small-scale area within the Hetao Irrigation District (HID) at the upper reaches of the Yellow River basin were used to evaluate the SS-ELM framework. The results of the SS-ELM algorithm were compared with those of the random forest (RF), ELM, support vector machine (SVM) and semi-supervised support vector machine (S-SVM) algorithms. Then the SS-ELM algorithm was applied to analyze the complex planting structure of HID in 1986–2010 by comparing the remote sensing estimated results with the statistical data. In the small-scale case, the SS-ELM algorithm performed better than the RF, ELM, SVM, and S-SVM algorithms. For the SS-ELM algorithm, the average overall accuracy (OA) was in a range of 83.00–92.17%. On the contrary, for the other four algorithms, their average OA values ranged from 56.97% to 92.84%. Whereas, in the classification of planting structure in HID, the SS-ELM algorithm had an excellent performance in classification accuracy and computational efficiency for three major planting crops including maize, wheat, and sunflowers. The estimated areas by using the SS-ELM algorithm based on the remote sensing images were consistent with the statistical data, and their difference was within a range of 3–25%. This implied that the SS-ELM framework could be served as an effective method for the classification of complex planting structures with relatively fast training, good generalization, universal approximation capability, and reasonable learning accuracy.

Spectral-Spatial Classification of Hyperspectral Image Based on Support Vector Machine

2021 ◽  
Vol 16 (1) ◽  
pp. 56-74
Author(s):  
Weiwei Yang ◽  
Haifeng Song
Keyword(s):  
Support Vector Machine ◽  
Classification Accuracy ◽  
Spatial Information ◽  
Hyperspectral Image ◽  
State Of The Art ◽  
Support Vector ◽  
Svm Classifier ◽  
Spatial Classification ◽  
Homogeneous Regions

Recent research has shown that integration of spatial information has emerged as a powerful tool in improving the classification accuracy of hyperspectral image (HSI). However, partitioning homogeneous regions of the HSI remains a challenging task. This paper proposes a novel spectral-spatial classification method inspired by the support vector machine (SVM). The model consists of spectral-spatial feature extraction channel (SSC) and SVM classifier. SSC is mainly used to extract spatial-spectral features of HSI. SVM is mainly used to classify the extracted features. The model can automatically extract the features of HSI and classify them. Experiments are conducted on benchmark HSI dataset (Indian Pines). It is found that the proposed method yields more accurate classification results compared to the state-of-the-art techniques.

Sign in / Sign up

Export Citation Format

Share Document