• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.42 no.3
• /
• pp.649-660
• /
• 2017

In electronic warfare, the pulse amplitude, one of information of a pulse signal emitted by an enemy, is used for estimating distance from the source and for deinterleaving mixed source signals. An estimate of pulse amplitude is conventionally determined as the maximum magnitude of a Fourier transformed signal within its pulse width which is estimated pre-step in an electronic warfare receiver. However, when frequency modulated signals are received, it is difficult to estimate their pulse amplitudes with this conventional method because the energy of signals is dispersed in frequency domain. In order to overcome this limitation, this paper proposes an enhanced pulse amplitude estimation method which calculates the average power of the received pulse signal in time domain and removes the noise power of the receiver. Simulation results show that even in case the frequency modulated signal is received, the proposed method has the same performance as estimating the pulse amplitude when unmodulated signal is received. In addition, the proposed method is shown to be more robust to an estimation error of pulse width, which affects the estimation performance of pulse amplitude, than the conventional method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.3
• /
• pp.451-457
• /
• 2018

We propose an automatic detection and classification system of sewer damage database based on artificial intelligence and deep learning. In order to optimize the performance, we implemented a robust system against various environmental variations such as illumination and shadow changes. In our proposed system, a crack detection and damage classification method using a deep learning based Convolutional Neural Network (CNN) is implemented. For optimal results, 9,941 CCTV images with $256{\times}256$ pixel resolution were used for machine learning on the damaged area based on the CNN model. As a result, the recognition rate of 98.76% was obtained. Total of 646 images of $720{\times}480$ pixel resolution were extracted from various sewage DB for performance evaluation. Proposed system presents the optimal recognition rate for the automatic detection and classification of damage in the sewer DB constructed in various environments.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.6
• /
• pp.634-638
• /
• 2018

Haze is a factor that degrades the performance of various image processing algorithms, such as those for detection, tracking, and recognition using an electro-optical sensor. For robust operation of an electro-optical sensor-based unmanned system used outdoors, an algorithm capable of effectively removing haze is needed. As a haze removal method using a single electro-optical sensor, the dark channel prior using statistical properties of the electro-optical sensor is most widely known. Previous methods used a square filter in the process of obtaining a transmission using the dark channel prior. When a square filter is used, the effect of removing haze becomes smaller as the size of the filter becomes larger. When the size of the filter becomes excessively small, over-saturation occurs, and color information in the image is lost. Since the size of the filter greatly affects the performance of the algorithm, a relatively large filter is generally used, or a small filter is used so that no over-saturation occurs, depending on the image. In this paper, we propose an improved haze removal method using color image segmentation. The parameters of the color image segmentation are automatically set according to the information complexity of the image, and the over-saturation phenomenon does not occur by estimating the amount of transmission based on the parameters.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.10
• /
• pp.723-730
• /
• 2013

This paper presents the design of an arm gesture recognition system using Kinect sensor. A variety of methods have been proposed for gesture recognition, ranging from the use of Dynamic Time Warping(DTW) to Hidden Markov Models(HMM). Our system learns a unique HMM corresponding to each arm gesture from a set of sequential skeleton data. Whenever the same gesture is performed, the trajectory of each joint captured by Kinect sensor may much differ from the previous, depending on the length and/or the orientation of the subject's arm. In order to obtain the robust performance independent of these conditions, the proposed system executes the feature transformation, in which the feature vectors of joint positions are transformed into those of angles between joints. To improve the computational efficiency for learning and using HMMs, our system also performs the k-means clustering to get one-dimensional integer sequences as inputs for discrete HMMs from high-dimensional real-number observation vectors. The dimension reduction and discretization can help our system use HMMs efficiently to recognize gestures in real-time environments. Finally, we demonstrate the recognition performance of our system through some experiments using two different datasets.

• Journal of Korea Water Resources Association
• /
• v.54 no.12
• /
• pp.1255-1263
• /
• 2021

While it could become an alternative water resource, fog could undermine traffic safety and operational performance of infrastructures. To reduce such adverse impacts, it is necessary to have spatially continuous fog risk information. In this work, tree-based machine-learning models were developed in order to quantify fog risks with routine meteorological observations alone. The Extreme Gradient Boosting (XGB), Light Gradient Boosting (LGB), and Random Forests (RF) were chosen for the regional fog models using operational weather and visibility observations within the Jeollabuk-do province. Results showed that RF seemed to show the most robust performance to categorize between fog and non-fog situations during the training and evaluation period of 2017-2019. While the LGB performed better than in predicting fog occurrences than the others, its false alarm ratio was the highest (0.695) among the three models. The predictability of the three models considerably declined when applying them for an independent period of 2020, potentially due to the distinctively enhanced air quality in the year under the global lockdown. Nonetheless, even in 2020, the three models were all able to produce fog risk information consistent with the spatial variation of observed fog occurrences. This work suggests that the tree-based machine learning models could be used as tools to find locations with relatively high fog risks.

• Journal of Broadcast Engineering
• /
• v.24 no.4
• /
• pp.592-601
• /
• 2019

For coronary procedures, X-ray angiogram images are useful for diagnosing and assisting procedures. It is challenging to accurately segment a coronary artery using only a single segmentation model in 2D X-ray images due to a complex structure of three-dimensional coronary artery, especially from phenomenon of vessels being broken in the middle or end of coronary artery. In order to solve these problems, the initial segmentation is performed using an existing single model, and the candidate regions for the sophisticate correction is estimated based on the initial segment, and the local patch-based correction is performed in the candidate regions. Through this research, not only the broken coronary arteries are re-connected, but also the distal part of coronary artery that is very thin is additionally correctly found. Further, the performance can be much improved by combining the proposed correction method with any existing coronary artery segmentation method. In this paper, the U-net, a fully convolutional network was chosen as a segmentation method and the proposed correction method was combined with U-net to demonstrate a significant improvement in performance through X-ray images from several patients.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.22 no.1
• /
• pp.129-139
• /
• 2019

Mapping urban areas using the earth observation satellites is useful for monitoring urban expansions and measuring urban developments. In this research, the different thresholds for detecting the urban areas separately from the remote-sensing index images (normalized-difference built-up index(NDBI) and urban index(UI) images) generated from the Landsat-8 image acquired in Daegu, South Korea were evaluated through the following steps: (1) the NDBI and UI images were separately generated from the given Landsat-8 image; (2) the different thresholds (-0.4, -0.2, and 0) for detecting the urban areas separately from the NDBI and UI images were evaluated; and (3) the accuracy of each detected urban area was assessed. The experiment results showed that the threshold -0.2 had the best performance for detecting the urban areas from the NDBI image, while the threshold -0.4 had the best performance for detecting the urban areas from the UI image. Some misclassification errors, however, occurred in the areas where the bare soil areas were classified into urban areas or where the high-rise apartments were classified into other areas. In the future research, a robust methodology for detecting urban areas, including the various types of urban features, with less misclassification errors will be proposed using the satellite images. In addition, research on analyzing the pattern of urban expansion will be carried out using the urban areas detected from the multi-temporal satellite images.

• Korean small business review
• /
• v.42 no.4
• /
• pp.285-308
• /
• 2020

This paper analyzes the factors which affect University professors and students on their startup activities, such as (a) University factors: their industrial cooperation organization and systems, their resources for startup support, their knowledge assets, and (b) socioeconomic characteristics in which Universities are located. We used the data and information from the University Information System and the National Statistical Office Publication to analyze 157 4-year Universities in Korea who uploaded their startup-related information on the system. Our analysis shows that Universities' systems, such as the term for Professors' leave of absence for startup activities, and their amount of knowledge assets affect the number of Professor startups significantly positively, while there is no significant effect on their performance, in terms of sales, from those factors, except for the amount of patents that the University has. In the meantime, the number of practical startup courses, the number of startup clubs, and the number of professor startups in the University affect the number of student startups, while the size of industrial cooperation body, the amount of knowledge asset, the area's socioeconomic characteristics didn't affect their performance. The result implies that we need to take different approaches to boost University professor startups and their student startups: better system and more knowledge for the former, more practical courses and programs for the latter. Further study is needed to get a more robust result because this analysis used only one year data, and personal trait data was not included in the analysis. A panel data analysis for several years is recommended for further research.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.1
• /
• pp.51-58
• /
• 2023

In this paper, we propose an organ segmentation technique for the automatic extraction of medical diagnostic indicators from X-ray images. In order to calculate diagnostic indicators of heart disease and spinal disease such as VHS(vertebral heart scale) and Cobb angle, it is necessary to accurately segment the thoracic spine, carina, and heart in a chest X-ray image. A deep neural network model in which the high-resolution representation of the image for each layer and the structure converted into a low-resolution feature map are connected in parallel was adopted. This structure enables the relative position information in the image to be effectively reflected in the segmentation process. It is shown that learning performance can be improved by combining the OCR module, in which pixel information and object information are mutually interacted in a multi-step process, and the channel attention module, which allows each channel of the network to be reflected as different weight values. In addition, a method of augmenting learning data is presented in order to provide robust performance against changes in the position, shape, and size of the subject in the X-ray image. The effectiveness of the proposed theory was evaluated through an experiment using 145 human chest X-ray images and 118 animal X-ray images.

• Journal of Intelligence and Information Systems
• /
• v.28 no.3
• /
• pp.119-137
• /
• 2022

Recent recommendation system studies apply various deep learning models to represent user and item interactions better. One of the noteworthy studies is ONCF(Outer product-based Neural Collaborative Filtering) which builds a two-dimensional interaction map via outer product and employs CNN (Convolutional Neural Networks) to learn high-order correlations from the map. However, ONCF has limitations in recommendation performance due to the problems with CNN and the absence of side information. ONCF using CNN has an inductive bias problem that causes poor performances for data with a distribution that does not appear in the training data. This paper proposes to employ a Vision Transformer (ViT) instead of the vanilla CNN used in ONCF. The reason is that ViT showed better results than state-of-the-art CNN in many image classification cases. In addition, we propose a new architecture to reflect side information that ONCF did not consider. Unlike previous studies that reflect side information in a neural network using simple input combination methods, this study uses an independent auxiliary classifier to reflect side information more effectively in the recommender system. ONCF used a single latent vector for user and item, but in this study, a channel is constructed using multiple vectors to enable the model to learn more diverse expressions and to obtain an ensemble effect. The experiments showed our deep learning model improved performance in recommendation compared to ONCF.