L 1 -norm loss based twin support vector machine for data recognition

Peng, Xinjun; Xu, Dong; Kong, Lingbing; Chen, Dongjing

doi:10.1016/j.ins.2016.01.023

Cited by 39 publications

(11 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We introduce a twin-support-vector-machine segmentation (TWSVM-Seg) model, which is based on the traditional SVM model is better for segmentation of wheat-ear images (Peng et al, 2016 ). It is similar in form to a traditional SWM with all its advantages.…”

Section: Methodsmentioning

confidence: 99%

Wheat Ears Counting in Field Conditions Based on Multi-Feature Optimization and TWSVM

et al. 2018

View full text Add to dashboard Cite

The number of wheat ears in the field is very important data for predicting crop growth and estimating crop yield and as such is receiving ever-increasing research attention. To obtain such data, we propose a novel algorithm that uses computer vision to accurately recognize wheat ears in a digital image. First, red-green-blue images acquired by a manned ground vehicle are selected based on light intensity to ensure that this method is robust with respect to light intensity. Next, the selected images are cut to ensure that the target can be identified in the remaining parts. The simple linear iterative clustering method, which is based on superpixel theory, is then used to generate a patch from the selected images. After manually labeling each patch, they are divided into two categories: wheat ears and background. The color feature “Color Coherence Vectors,” the texture feature “Gray Level Co-Occurrence Matrix,” and a special image feature “Edge Histogram Descriptor” are then exacted from these patches to generate a high-dimensional matrix called the “feature matrix.” Because each feature plays a different role in the classification process, a feature-weighting fusion based on kernel principal component analysis is used to redistribute the feature weights. Finally, a twin-support-vector-machine segmentation (TWSVM-Seg) model is trained to understand the differences between the two types of patches through the features, and the TWSVM-Seg model finally achieves the correct classification of each pixel from the testing sample and outputs the results in the form of binary image. This process thus segments the image. Next, we use a statistical function in Matlab to get the exact a precise number of ears. To verify these statistical numerical results, we compare them with field measurements of the wheat plots. The result of applying the proposed algorithm to ground-shooting image data sets correlates strongly (with a precision of 0.79–0.82) with the data obtained by manual counting. An average running time of 0.1 s is required to successfully extract the correct number of ears from the background, which shows that the proposed algorithm is computationally efficient. These results indicate that the proposed method provides accurate phenotypic data on wheat seedlings.

show abstract

Section: Methodsmentioning

confidence: 99%

Wheat Ears Counting in Field Conditions Based on Multi-Feature Optimization and TWSVM

et al. 2018

View full text Add to dashboard Cite

show abstract

“…The MAE is a risk metric corresponding to the expected value of the absolute error loss or the L1 –norm loss [41]. It is less sensitive to the occasional very large error because it does not square the errors in the calculation, thus in this study the

MAE

estimated over n data points, is used in obtaining the error measure in the validation period.…”

Section: Model Optimisation and Evaluationmentioning

confidence: 99%

Echo state network‐based radio signal strength prediction for wireless communication in Northern Namibia

Gideon¹,

Nyirenda²,

Temaneh-Nyah³

2017

IET Communications

View full text Add to dashboard Cite

“…The basic idea of this principle is how to minimize the empirical risk and confidence interval. SVM can realize the principle of structural risk minimization and its principle is as follows [18], [19]:…”

Section: The Classifier For Spectrum Dynamic Identification In Tmentioning

confidence: 99%

A Novel Method for Wireless Communication Signal Modulation Recognition in Smart Grid

Yang¹,

Li²,

Zeng³

et al. 2016

JCM

View full text Add to dashboard Cite

Dynamic spectrum access technology and cognitive radio technology are research directions in new types of wireless communications business in smart grid. Modulation recognition technology of wireless communication signals is the premise of wireless communication in smart grid dynamic spectrum access technology and the cognitive radio technology. Currently, high computation complexity happens when the existing support vector machine (SVM) identifies multi-class problems, and the modulation recognition rate is not ideal when the receiving signal noise ratio (SNR) is low. For these two problems, high-order cumulants used in this article can have good anti-noise performance. To begin with, high-order cumulants can be extracted as the characteristic value of signal. Then, SVM is conducted training. Finally, the recognition algorithm routine of conventional SVM is promoted. After this process presented in this article, the simulation result showed that the corresponding average modulation recognition rate can increase by more than 25% than the situation when individually using conventional SVM. Especially, when SNR is 5dB, the recognition rate can reach 90% and the system prone to be achieved, which shows that high-order cumulants has wide application prospect in the application aspect of smart grid dynamic access wireless communication technology. Index Terms-Smart grid dynamic spectrum access, high-order cumulants, feature extraction, SVM, modulation recognition I. INTRODUCTION At present, the communication technology in smart grid includes types of wired and wireless communication and fibre Optical Communication Technology is the main and predominated technical means of power system communication cable. It hosts the relay protection of power line, safety remote control, electric power, telephone, high-definition video, video monitoring, data network remote automation and a variety of other information communication businesses which are from Manuscript

show abstract

L 1 -norm loss based twin support vector machine for data recognition

Cited by 39 publications

References 37 publications

Wheat Ears Counting in Field Conditions Based on Multi-Feature Optimization and TWSVM

Wheat Ears Counting in Field Conditions Based on Multi-Feature Optimization and TWSVM

Echo state network‐based radio signal strength prediction for wireless communication in Northern Namibia

A Novel Method for Wireless Communication Signal Modulation Recognition in Smart Grid

Contact Info

Product

Resources

About