• Proceedings of the KSRS Conference
• /
• 1999.11a
• /
• pp.433-438
• /
• 1999

The land use type of Korea is high-density. So, the image classification using coarse resolution satellite image may not provide land cover classification results as good as expected. The purpose of this paper is to compare the result of visual interpretation with that of digital image classification of 20 m resolution SPOT satellite image at Kwangju-eup, Kyunggi-do, Korea. Classes are forest, cultivated field, pasture, water and residential area, which are clearly discriminated in visual interpretation. Maximum likelihood classifier was used for digital image classification. Accuracy assessment was done by comparing each classification result with ground truth data obtained from field checking. The classification result from the visual interpretation presented an total accuracy 9.23 percent higher than that of the digital image classification. This proves the importance of visual interpretation for the area with high density land use like the study site in Korea.

• Korean Journal of Remote Sensing
• /
• v.18 no.3
• /
• pp.163-169
• /
• 2002

The land uses of Korean peninsula are very complicated and high-density. Therefore, the image classification using coarse resolution satellite images may not provide good results for the land cover classification. The purpose of this paper is to compare the classification accuracy of visual interpretation with that of digital image classification of satellite remote sensing data such as 20m SPOT and 30m TM. In this study, hybrid classification was used. Classification accuracy was assessed by comparing each classification result with reference data obtained from KOMPSAT-1 EOC imagery, air photos, and field surveys.

• The Journal of Information Technology and Database
• /
• v.2 no.2
• /
• pp.71-85
• /
• 1995

Many research results conducted by neural network researchers have claimed that the classification accuracy of neural networks is superior to, or at least equal to that of conventional methods. However, in series of neural network classifications, it was found that the classification accuracy strongly depends on the characteristics of training data set. Even though there are many research reports that the classification accuracy of neural networks can be different, depending on the composition and architecture of the networks, training algorithm, and test data set, very few research addressed the problem of classification accuracy when the basic assumption of data monotonicity is violated, In this research, development project of automated credit evaluation system is described. The finding was that arrangement of training data is critical to successful implementation of neural training to maintain monotonicity of the data set, for enhancing classification accuracy of neural networks.

• Journal of Korean Society for Geospatial Information Science
• /
• v.8 no.2 s.16
• /
• pp.47-60
• /
• 2000

On this study, Among the classification methods of land cover using satellite imagery, we compared the classification accuracy of Neural Network Classifier and that of Maximum Likelihood Classifier which has the characteristics of parametric and non-parametric classification method. In the assessment of classification accuracy, we analyzed the classification accuracy about testing area as well as training area that many analysts use generally when assess the classification accuracy. As a result, Neural Network Classifier is superior to Maximum Likelihood Classifier as much as 3% in the classification of training data. When ground reference data is used, we could get poor result from both of classification methods, but we could reach conclusion that the classification result of Neural Network Classifier is superior to the classification result of Maximum Likelihood Classifier as much as 10%.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.6
• /
• pp.2751-2756
• /
• 2012

Selection of training set influences the classification accuracy in supervised classification using satellite imagery. Generally, if pure pixels which character of training set is clear were selected, whole accuracy is high while if mixed pixels were selected, accuracy is decreased because of low-resolution imagery or unclear distinguishment. However, it is too difficult to choose the pure pixels as training set actually. Accordingly, this study should be suggested the suitable classification method in case of mixed pixels choice. To achieve this, a few pure pixels were chosen as training set and classification accuracy was calculated which was compared with classification result using an equal number of mixed pixels. As a result, accuracy of SVM was the highest among the classification method using mixed pixels and it was a relatively small difference with the result of classification using pure pixels. Therefore, imagery classification using SVM is most suitable in the mixed area of construction and green because it is high possibility to choose mixed pixels as training set.

• Journal of Ocean Engineering and Technology
• /
• v.8 no.2
• /
• pp.64-79
• /
• 1994

In this study, terrain classification, which was done by using the quantitative classification parameters and suitable interpolation method was applied to improve the accuracy of digital elevation models, and to increase its practical use of aerial photogrammetry. A terrain area was classified into three groups using the quantitative classification parameters to the ratio of horizontal, inclined area, magnitude of harmonic vectors, deviation of vector, the number of breakline and proposed the suitable interpolation. Also, the accuracy of digital elevation models was improved in case of large grid intervals by applying combined interpolation suitable for each terrain group. As a result of this study, I have an algorithm to perform the classification of the topography in the area of interest objectively and decided optimal data interpolation scheme for given topography.

• Korean Journal of Remote Sensing
• /
• v.21 no.3
• /
• pp.189-211
• /
• 2005

This paper makes an effort to compare the recently evolved soft classification method based on Linear Spectral Mixture Modeling (LSMM) with the traditional hard classification methods based on Iterative Self-Organizing Data Analysis (ISODATA) and Maximum Likelihood Classification (MLC) algorithms in order to achieve appropriate results for mapping, monitoring and preserving valuable coastal wetland ecosystems of southern India using Indian Remote Sensing Satellite (IRS) 1C/1D LISS-III and Landsat-5 Thematic Mapper image data. ISODATA and MLC methods were attempted on these satellite image data to produce maps of 5, 10, 15 and 20 wetland classes for each of three contrast coastal wetland sites, Pitchavaram, Vedaranniyam and Rameswaram. The accuracy of the derived classes was assessed with the simplest descriptive statistic technique called overall accuracy and a discrete multivariate technique called KAPPA accuracy. ISODATA classification resulted in maps with poor accuracy compared to MLC classification that produced maps with improved accuracy. However, there was a systematic decrease in overall accuracy and KAPPA accuracy, when more number of classes was derived from IRS-1C/1D and Landsat-5 TM imagery by ISODATA and MLC. There were two principal factors for the decreased classification accuracy, namely spectral overlapping/confusion and inadequate spatial resolution of the sensors. Compared to the former, the limited instantaneous field of view (IFOV) of these sensors caused occurrence of number of mixture pixels (mixels) in the image and its effect on the classification process was a major problem to deriving accurate wetland cover types, in spite of the increasing spatial resolution of new generation Earth Observation Sensors (EOS). In order to improve the classification accuracy, a soft classification method based on Linear Spectral Mixture Modeling (LSMM) was described to calculate the spectral mixture and classify IRS-1C/1D LISS-III and Landsat-5 TM Imagery. This method considered number of reflectance end-members that form the scene spectra, followed by the determination of their nature and finally the decomposition of the spectra into their endmembers. To evaluate the LSMM areal estimates, resulted fractional end-members were compared with normalized difference vegetation index (NDVI), ground truth data, as well as those estimates derived from the traditional hard classifier (MLC). The findings revealed that NDVI values and vegetation fractions were positively correlated ($r^2$= 0.96, 0.95 and 0.92 for Rameswaram, Vedaranniyam and Pitchavaram respectively) and NDVI and soil fraction values were negatively correlated ($r^2$ =0.53, 0.39 and 0.13), indicating the reliability of the sub-pixel classification. Comparing with ground truth data, the precision of LSMM for deriving moisture fraction was 92% and 96% for soil fraction. The LSMM in general would seem well suited to locating small wetland habitats which occurred as sub-pixel inclusions, and to representing continuous gradations between different habitat types.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.3
• /
• pp.1348-1375
• /
• 2018

Support Vector Machine (SVM) is a well-known machine learning classification algorithm, which has been widely applied to many data mining problems, with good accuracy. However, SVM classification speed decreases with increase in dataset size. Some applications, like video surveillance and intrusion detection, requires a classifier to be trained very quickly, and on large datasets. Hence, this paper introduces two filter-based instance selection techniques for optimizing SVM training speed. Fast classification is often achieved at the expense of classification accuracy, and some applications, such as phishing and spam email classifiers, are very sensitive to slight drop in classification accuracy. Hence, this paper also introduces two wrapper-based instance selection techniques for improving SVM predictive accuracy and training speed. The wrapper and filter based techniques are inspired by Cuckoo Search Algorithm and Bat Algorithm. The proposed techniques are validated on three popular e-fraud types: credit card fraud, spam email and phishing email. In addition, the proposed techniques are validated on 20 other datasets provided by UCI data repository. Moreover, statistical analysis is performed and experimental results reveals that the filter-based and wrapper-based techniques significantly improved SVM classification speed. Also, results reveal that the wrapper-based techniques improved SVM predictive accuracy in most cases.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.54 no.2
• /
• pp.47-53
• /
• 2012

Recently many developed countries have used satellite images for classifying cropland areas to reduce time and efforts put into field survey. Korea also has used satellite images for the same purpose since KOMPSAT-2 was successfully launched and operated in 2006, but still far way to go in order to achieve the required accuracy from the products. This study evaluated the accuracy of the calculated croplands by using the objected classification method with various satellite images including ASTER, Spot-5, Rapid eye, Quickbird-2, Geo eye-1. Also, their usability and effectiveness for the cropland survey were verified by comparing with field survey data. As results. Geo eye-1 and Rapid eye showed higher accuracy to calculate the paddy field areas while Geo eye-1 and Quickbird-2 showed higher accuracy to calculate the upland field areas.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.9
• /
• pp.1402-1408
• /
• 2017

Recently, services for personal biometric data analysis based on real-time monitoring systems has been increasing and many of them have focused on recognition of emotions. In this paper, we propose a classification model to classify anxiety emotion using biometric data actually collected from people. We propose to deploy the support vector machine to build a classification model. In order to improve the classification accuracy, we propose two data pre-processing procedures, which are normalization and data deletion. The proposed algorithms are actually implemented based on Real-time Traffic Flow Measurement structure, which consists of data collection module, data preprocessing module, and creating classification model module. Our experiment results show that the proposed classification model can infers anxiety emotions of people with the accuracy of 65.18%. Moreover, the proposed model with the proposed pre-processing techniques shows the improved accuracy, which is 78.77%. Therefore, we can conclude that the proposed classification model based on the pre-processing process can improve the classification accuracy with lower computation complexity.