GA-SVM Algorithm for Improving Land-Cover Classification Using SAR and Optical Remote Sensing Data

Sukawattanavijit, Chanika; Chen, Jie; Zhang, Hongsheng

doi:10.1109/lgrs.2016.2628406

Cited by 151 publications

(64 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The following parameters were identified: minimum number of classes: 8; maximum number of classes: 12; maximum iterations: 30; change threshold: 1%; minimum number of pixels in class: 100; maximum standard deviation: 1; minimum class distance: 3; and maximum merge pairs: 2. The supervised classification was performed using the Supported Vector Machine technique [22,[34][35][36]. The advantage of this technique is that it does not require a large number of training samples [37], and the probability distribution is not assumed a priori [38].…”

Section: Multi-temporal Image Classificationmentioning

confidence: 99%

“…The quality of classification was analyzed based on the classification accuracy, estimated by the User's Accuracy, Producer's Accuracy, Overall Accuracy (OAA) and the Kappa Index of Agreement (KIA) [39][40][41]. The supervised classification was performed using the Supported Vector Machine technique [22,[34][35][36]. The advantage of this technique is that it does not require a large number of training samples [37], and the probability distribution is not assumed a priori [38].…”

Section: Multi-temporal Image Classificationmentioning

confidence: 99%

See 1 more Smart Citation

Wetland Mapping Using SAR Data from the Sentinel-1A and TanDEM-X Missions: A Comparative Study in the Biebrza Floodplain (Poland)

Mleczko

Mróz

2018

Remote Sensing

View full text Add to dashboard Cite

This research is related to the eco-hydrological problems of the herbaceous wetland drying and biodiversity loss in the floodplain lakes of the Middle Basin of the Biebrza River (Poland). An experiment was set up, with its main goals as follows: (i) mapping the vegetation types and the temporarily or permanently flooded areas, and (ii) comparing the usefulness of the C-band Sentinel-1A (S1A) and X-band TerraSAR-X/TanDEM-X (TSX/TDX) for mapping purposes. The S1A imagery was acquired on a regular basis using the dual polarization VV/VH and the Interferometric Wide Swath Mode. The TSX/TDX data were acquired in quad-pol, a fully polarimetric mode, during the Science Phase. The paper addresses the following aspects: (i) wetland mapping with the S1A multi-temporal series; (ii) wetland mapping with the fully polarimetric TSX/TDX data; (iii) comparing the wetland mapping using dual polarization TSX/TDX subsets, that is, the HH-HV, HH-VV and VV-VH; (iv) comparing wetland mapping using the S1A and TSX/TDX data based on the same polarization (VV-VH); (v) studying the suitability of the Shannon Entropy for wetland mapping; and (vi) assessing the contribution of interferometric coherence for wetland classification. Though the experimental results show the main limitations of the S1A dataset, they also highlight the good accuracy that can be achieved using the TSX/TDX data, especially those taken in fully polarimetric mode. Some practical outcomes significant for the study area management using SAR were also described.

show abstract

Section: Multi-temporal Image Classificationmentioning

confidence: 99%

Section: Multi-temporal Image Classificationmentioning

confidence: 99%

Wetland Mapping Using SAR Data from the Sentinel-1A and TanDEM-X Missions: A Comparative Study in the Biebrza Floodplain (Poland)

Mleczko

Mróz

2018

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The search direction is guided by fitness function. It is a search technology that can search global optimization solution quickly in complex search space [13]. When genetic algorithm is applied to SVM parameter optimization, the basic steps of the algorithm are as follows: (a) t = 0; (b) Random selection of initial population P (t); (c) Calculating the fitness function value F (t); (d) If the fitness function corresponding to the optimal individual in the population is large enough or the algorithm has been running for many generations without significant improvement of individual's fitness, it will be transferred to step 8; (e) t = t + 1; (f) The selection operator method is used to select P (t) from P (t -1); (g) After P (t) is crossed and mutated, it should be moved to step 3; (h) The optimal kernel function parameters and penalty factor C are given.…”

Section: Genetic Optimization Algorithmmentioning

confidence: 99%

Wearable Resistive-based Gesture-Sensing Interface Bracelet

Chen

Liang

Assaad

et al. 2019

2019 UK/ China Emerging Technologies (UCET)

View full text Add to dashboard Cite

This paper presents a gesture recognition system based on the pressure changes produced by wrist tendon movements for wearable devices. The data of the pressure variations are captured by means of flexible and ultrathin force resistive sensors. A learning algorithm, Support Vector Machine, helps the system to distinguish various hand gestures through developed programming on MATLAB after extracting the key features of data. In order to achieve rapid gesture recognition with a shorter computational time, higher precision and less space complexity, genetic optimization algorithm is used to find the optimal parameter c (cost factor) and g (kernel function parameters) in SVM algorithm. The SVM parameter optimization improves the classification accuracy and the performance of the classifier. Finally, developed wearable resistive-based wrist-worn gesture sensing system classifies the hand gesture with high accuracy (>70%) and the results are displayed on the GUIDE user interface.

show abstract

“…The following parameters were identified: minimum number of classes: 8; maximum number of classes: 12; maximum iterations: 30; change threshold: 1%; minimum number of pixels in class: 100; maximum standard deviation: 1; minimum class distance: 3; and maximum merge pairs: 2. The supervised classification was performed using the Supported Vector Machine technique [17,[29][30][31]. The advantage of this technique is that it does not require a large number of training samples [32], and the probability distribution is not assumed a priori [33].…”

Section: Multitemporal Image Classificationmentioning

confidence: 99%

Wetland Mapping Using SAR Data from Sentinel-1A and TanDEM-X Missions: Comparative Study in the Biebrza Floodplain (Poland)

Mleczko¹,

Mróz²

2017

Preprint

View full text Add to dashboard Cite

This research is related to the eco-hydrological problems of herbaceous wetland drying and biodiversity loss in the floodplain lakes of the Middle Basin of the Biebrza river (Poland). An experiment was set up, whose main goals were: (i) mapping the vegetation types and the temporarily or permanently flooded areas, and (ii) comparing the usefulness of C-band Sentinel-1A (S1A) and X-band TerraSAR-X/TanDEM-X (TSX/TDX) for mapping purposes. The S1A imagery was acquired on a regular basis using the dual polarization VV/VH and the Interferometric Wide Swath Mode. The TSX/TDX data were acquired in quad-pol, a fully polarimetric mode, during the Science Phase. The paper addresses the following aspects: i) wetland mapping with S1A multi-temporal series; ii) wetland mapping with fully polarimetric TSX/TDX data; iii) comparing the wetland mapping using dual polarization TSX/TDX subsets, i.e. HH-HV, HH-VV and VV-VH; iv) comparing wetland mapping using S1A and TSX/TDX data based on the same polarization (VV-VH); v) studying the suitability of the Shannon Entropy for wetland mapping; and vi) assessing the contribution of interferometric coherence for wetland classification. The experimental results show main limitations of the S1A dataset, while they highlight the good accuracy that can be achieved using the TSX/TDX data, especially those taken in fully polarimetric mode.

show abstract

GA-SVM Algorithm for Improving Land-Cover Classification Using SAR and Optical Remote Sensing Data

Cited by 151 publications

References 12 publications

Wetland Mapping Using SAR Data from the Sentinel-1A and TanDEM-X Missions: A Comparative Study in the Biebrza Floodplain (Poland)

Wetland Mapping Using SAR Data from the Sentinel-1A and TanDEM-X Missions: A Comparative Study in the Biebrza Floodplain (Poland)

Wearable Resistive-based Gesture-Sensing Interface Bracelet

Wetland Mapping Using SAR Data from Sentinel-1A and TanDEM-X Missions: Comparative Study in the Biebrza Floodplain (Poland)

Contact Info

Product

Resources

About