• Korean Journal of Remote Sensing
• /
• v.25 no.2
• /
• pp.113-126
• /
• 2009

With high temporal resolution, four times receiving during a day, MODIS images from Terra and Aqua satellites provide several advantages for monitoring spacious land. Especially, diverse MODIS products related to land, atmosphere, and ocean have been provided with radiance MODIS images. The products such as surface reflectance, NDVI, cloud mask, aerosol etc. are based on theoretical algorithms developed in academic areas. Comparing with other change detection studies mainly using the vegetation index, this study investigated temporal surface reflectance of landcovers for five years from 2004 to 2008. The near infrared (NIR) reflectance in urbanized and burned areas showed considerable difference before and after events. The specific characteristics of surface reflectance temporal profiles are possibly useful for the detection of landcover changes and classification.

• Korean Journal of Remote Sensing
• /
• v.22 no.2
• /
• pp.123-129
• /
• 2006

High-resolution aerial color image offers great possibilities for geometric and semantic information for spatial data generation. However, shadow casts by buildings and trees in high-density urban areas obscure much of the information in the image giving rise to potentially inaccurate classification and inexact feature extraction. Though many researches have been implemented for solving shadow casts, few studies have been carried out about the extraction of features hindered by shadows from aerial color images in urban areas. This paper presents a asphalt road boundary extraction technique that combines information from aerial color image and LIDAR (LIght Detection And Ranging) data. The following steps have been performed to remove shadow effects and to extract road boundary from the image. First, the shadow regions of the aerial color image are precisely located using LEAR DSM (Digital Surface Model) and solar positions. Second, shadow regions assumed as road are corrected by shadow path reconstruction algorithms. After that, asphalt road boundary extraction is implemented by segmentation and edge detection. Finally, asphalt road boundary lines are extracted as vector data by vectorization technique. The experimental results showed that this approach was effective and great potential advantages.

• Journal of Convergence for Information Technology
• /
• v.9 no.10
• /
• pp.101-107
• /
• 2019

This paper proposes a method for detecting faults in conveyor systems used for transportation of raw materials needed in the thermal power plant and cement industries. A small drone was designed in consideration of the difficulty in accessing the industrial site and the need to use it in wide industrial site. In order to apply the system to the embedded microprocessor, hardware and algorithms considering limited memory and execution time have been proposed. At this time, the failure determination method measures the peak frequency through the measurement, detects the continuity of the high frequency, and performs the failure diagnosis with the high frequency components of noise. The proposed system consists of experimental environment based on the data obtained from the actual thermal power plant, and it is confirmed that the proposed system is useful by conducting virtual environment experiments with the drone designed system. In the future, further research is needed to improve the drone's flight stability and to improve discrimination performance by using more intelligent methods of fault frequency.

• Proceedings of the Plant Resources Society of Korea Conference
• /
• 2019.10a
• /
• pp.87-87
• /
• 2019

The consumption of herbal medicine and related products (herbal products) have increased in South Korea. At the same time the quality, safety, and efficacy of herbal products is being raised. Currently, the herbal products are standardized and controlled according to the requirements of the Korean Pharmacopoeia, the National Institute of Health and the Ministry of Public Health and Social Affairs. The validation of herbal products and their medicinal component is important, since many of these herbal products are composed of two or more medicinal plants. However, there are no tools to support the validation process. Interest in deep learning has exploded over the past decade, for herbal medicine using algorithms to achieve herb recognition, symptom related target prediction, and drug repositioning have been reported. In this study, individual images of four herbs (Panax ginseng C.A. Meyer, Atractylodes macrocephala Koidz, Poria cocos Wolf, Glycyrrhiza uralensis Fischer), actually sold in the market, were achieved. Certain image preprocessing steps such as noise reduction and resize were formatted. After the features are optimized, we applied GoogLeNet_Inception v4 model for herb image recognition. Experimental results show that our method achieved test accuracy of 95%. However, there are two limitations in the current study. Firstly, due to the relatively small data collection (100 images), the training loss is much lower than validation loss which possess overfitting problem. Secondly, herbal products are mostly in a mixture, the applied method cannot be reliable to detect a single herb from a mixture. Thus, further large data collection and improved object detection is needed for better classification.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.7
• /
• pp.903-909
• /
• 2021

Caenorhabditis elegans whose DNA sequence was completely identified is a representative species used in various research fields such as gene functional analysis and animal behavioral research. In the mean time, many researches on the bio-monitoring system to determine whether water is contaminated or not by using the swimming activities of nematodes. In this paper, we show the possibility of using the swimming activities of C. elegans in the development of a machine learning based bio-monitoring system which identifies chemicals that cause water pollution. To characterize swimming activities of nematode, BLS entropy is computed for the nematode in a frame. And, BLS entropy profile, an assembly of entropies, are classified into several patterns using clustering algorithms. Finally these patterns are used to construct data sets. We recorded images of swimming behavior of nematodes in the arenas in which formaldehyde, benzene and toluene were added at a concentration of 0.1 ppm, respectively, and evaluate the performance of the developed HMM.

• Journal of Digital Convergence
• /
• v.16 no.11
• /
• pp.185-199
• /
• 2018

The purpose of this study is to derive the core technologies of VR using patent analysis and to explore the direction of social and public interest in VR using news analysis. In Study 1, we derived keywords using the frequency of words in patent texts, and we compared by company, year, and technical classification. Netminer, a network analysis program, was used to analyze the IPC codes of patents. In Study 2, we analyzed news articles using T-LAB program. TF-IDF was used as a keyword selection method and chi-square and association index algorithms were used to extract the words most relevant to VR. Through this study, we confirmed that VR is a fusion technology including optics, head mounted display (HMD), data analysis, electric and electronic technology, and found that optical technology is the central technology among the technologies currently being developed. In addition, through news articles, we found that the society and the public are interested in the formation and growth of VR suppliers and markets, and VR should be developed on the basis of user experience.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.30 no.4
• /
• pp.275-281
• /
• 2019

A synthetic aperture radar(SAR) satellite is more effective than an optical satellite for target analysis because an SAR satellite can provide two-dimensional electromagnetic scattering distribution of a target during all-weather and day-and-night operations. To conduct target analysis while considering the earth observation interval of an SAR satellite, observing a specific area as wide as possible would be advantageous. However, wider the observation area, worse is the resolution of the associated SAR satellite image. Although conventional methods for improving the resolution of radar images can be employed for addressing this issue, few studies have been conducted for improving the resolution of SAR satellite images and analyzing the performance. Hence, in this study, the applicability of conventional methods to SAR satellite images is investigated. SAR target detection was first applied to Korea Multipurpose Satellite-5(KOMPSAT-5) SAR images provided by Korea Aerospace Research Institute for extracting target responses. Extrapolation, RELAX, and MUSIC algorithms were subsequently applied to the target responses for improving the resolution, and the corresponding performance was thereby analyzed.

• Electronics and Telecommunications Trends
• /
• v.34 no.4
• /
• pp.15-22
• /
• 2019

Recent technological advances in three-dimensional (3D) sensing devices and machine learning such as deep leaning has enabled data-driven 3D applications. Research on artificial intelligence has developed for the past few years and 3D deep learning has been introduced. This is the result of the availability of high-quality big data, increases in computing power, and development of new algorithms; before the introduction of 3D deep leaning, the main targets for deep learning were one-dimensional (1D) audio files and two-dimensional (2D) images. The research field of deep leaning has extended from discriminative models such as classification/segmentation/reconstruction models to generative models such as those including style transfer and generation of non-existing data. Unlike 2D learning, it is not easy to acquire 3D learning data. Although low-cost 3D data acquisition sensors have become increasingly popular owing to advances in 3D vision technology, the generation/acquisition of 3D data is still very difficult. Even if 3D data can be acquired, post-processing remains a significant problem. Moreover, it is not easy to directly apply existing network models such as convolution networks owing to the various ways in which 3D data is represented. In this paper, we summarize technological trends in AI-based 3D content generation.

• Journal of the Korea Convergence Society
• /
• v.10 no.8
• /
• pp.59-65
• /
• 2019

There are various subtypes of cells in cancer tissues, but it is hard to confirm their composition experimentally. Here, we estimated the cell composition of each sample from gene expression data by using statistical machine learning approaches, two different regression models and investigated whether the cell composition was different between cancer and normal tissue. As a result, we found that CD8 T cell and Neutrophil were increased in oral cancer tissues compared to normal tissues. In addition, we applied t-SNE, which is one of the unsupervised learning, to verify whether normal tissue and oral cancer tissue can be clustered by the derived cell composition. Moreover, we showed that it is possible to predict oral cancer and normal tissue by several supervised classification algorithms. The study would help to improve the understanding of the immune cell infiltration at oral cancer.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.14 no.5
• /
• pp.277-286
• /
• 2019

In this paper, we propose an efficient hyperplane generation technique to classify human activity from combination of events and sequence information obtained from multiple-event sensors. By generating hyperplane efficiently, our machine learning algorithm classify with less memory and run time than the LSVM (Linear Support Vector Machine) for embedded system. Because the fact that light weight and high speed algorithm is one of the most critical issue in the IoT, the study can be applied to smart home to predict human activity and provide related services. Our approach is based on reducing numbers of hyperplanes and utilizing robust string comparing algorithm. The proposed method results in reduction of memory consumption compared to the conventional ML (Machine Learning) algorithms; 252 times to LSVM and 34,033 times to LSTM (Long Short-Term Memory), although accuracy is decreased slightly. Thus our method showed outstanding performance on accuracy per hyperplane; 240 times to LSVM and 30,520 times to LSTM. The binarized image is then divided into groups, where each groups are converted to binary number, in order to reduce the number of comparison done in runtime process. The binary numbers are then converted to string. The test data is evaluated by converting to string and measuring similarity between hyperplanes using Levenshtein algorithm, which is a robust dynamic string comparing algorithm. This technique reduces runtime and enables the proposed algorithm to become 27% faster than LSVM, and 90% faster than LSTM.