• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.5
• /
• pp.975-986
• /
• 2022

Deep learning is attracting great attention, showing excellent performance in image processing, but is vulnerable to adversarial attacks that cause the model to misclassify through perturbation on input data. Adversarial examples generated by adversarial attacks are minimally perturbated where it is difficult to identify, so visual features of the images are not generally changed. Unlikely deep learning models, people are not fooled by adversarial examples, because they classify the images based on such visual features of images. This paper proposes adversarial attack detection method using Symbolic Representation, which is a visual and symbolic features such as color, shape of the image. We detect a adversarial examples by comparing the converted Symbolic Representation from the classification results for the input image and Symbolic Representation extracted from the input images. As a result of measuring performance on adversarial examples by various attack method, detection rates differed depending on attack targets and methods, but was up to 99.02% for specific target attack.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.7
• /
• pp.956-962
• /
• 2022

Diffuse thyroid disease has ambiguous diagnostic criteria and many errors occur according to the subjective diagnosis of skilled practitioners. If image processing technology is applied to ultrasound images, quantitative data is extracted, and applied to a computer auxiliary diagnostic system, more accurate and political diagnosis is possible. In this paper, 19 parameters were extracted by applying the Gray level co-occurrence matrix (GLCM) algorithm to ultrasound images classified as normal, mild, and moderate in patients with thyroid disease. Using these parameters, an artificial neural network (ANN) was applied to analyze diffuse thyroid ultrasound images. The final classification rate using ANN was 96.9%. Using the results of the study, it is expected that errors caused by visual reading in the diagnosis of thyroid diseases can be reduced and used as a secondary means of diagnosing diffuse thyroid diseases.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.477-477
• /
• 2023

빗물이용시설은 집수면적에 내린 빗물을 모아 이용가능하도록 처리하는 시설이며, 일정 면적 이상의 건축물에는 법적으로 빗물이용시설을 설치·운영하여야한다. 빗물이용시설의 저류조 용량은 간편식과 시뮬레이션, 수문모형으로 산정가능하며, 설계계획 수립시 대상지역의 강우 특성, 사용수량 등 지역 특성과 목적을 고려하여 저류조 용량이 결정된다. 저류조 용량 산정시 시뮬레이션을 이용하는 방법은 수문모형 사용에 비하여 용이하지만, 일단위 물수지분석을 구현하는데까지 시간이 소요된다. 간편식은 집수면적에 규모계수 0.05를 곱하여 간단히 구할 수 있지만, 지역 특성과 목적이 고려되어있지 않으며 초기 계획수립 및 개략 평가를 제외하고는 활용에 제약이 존재한다. 이에따라, 본 연구에서는 지역적 특성을 고려한 빗물저류조의 적정 규모 산정을 위해 개선된 간편식을 개발하였다. 빗물이용시설 물수지 분석 Excel 도구를 개발하였으며, 해당 물수지분석 결과에 상수대체율 효율을 기준으로 지역별 적정 저류조 규모 산정을 위한 규모계수를 도출하였다. 빗물사용 용도로써 폭염저감, 미세먼지저감, 조경, 화장실을 채택하였으며, 용도별 1일 사용수량을 산정 및 적용하였다. 7개의 연구대상지역 물수지분석을 위해 연구지역의 최근 10년 강우·미세먼지·기온데이터를 기상청으로부터 적용하였으며, 집수면적은 500-2500m²까지 500m²씩 증분, 저류조용량은 5-700m³까지 5m³씩 증분하여 지역별 적정 저류조 용량 규모계수를 선정하였다. 그 결과 연구대상지역의 적정 저류조 용량산정시 완도군의 규모계수는 평균 0.058이었으며, 보령시의 규모계수는 평균 0.040으로 도출되었다. 본 연구를 통하여 다양한 용도의 빗물사용처에 따른 지역별 저류조 용량 선정을 위한 지원도구로써 사용될 것으로 판단한다.

• Journal of Internet of Things and Convergence
• /
• v.10 no.2
• /
• pp.17-23
• /
• 2024

Losses in domestic water supply due to leaks are very large, such as fractures and defects in pipelines. Therefore, preventive measures to prevent water leakage are necessary. We propose the development of a leakage detection sensor utilizing vibration sensors and present an optimal leakage detection algorithm leveraging artificial intelligence. Vibrational sound data acquired from water pipelines undergo a preprocessing stage using FFT (Fast Fourier Transform), followed by leakage classification using an optimized tree-based boosting algorithm. Applying this method to approximately 260,000 experimental data points from various real-world scenarios resulted in a 97% accuracy, a 4% improvement over existing SVM(Support Vector Machine) methods. The processing speed also increased approximately 80 times, confirming its suitability for edge device applications.

• Journal of Bio-Environment Control
• /
• v.29 no.4
• /
• pp.344-353
• /
• 2020

Plants native in Korea have not only ornamental values but also have excellent environmental adaptability, so they can be used as garden plants. Studies on proper volumetric water content (VWC) of substrates have been reported, but many have been conducted in glasshouse conditions where environmental factors were controlled. When considering garden planting, it is necessary to perform the automated irrigation system in outdoor conditions where rainfall occurs at frequent intervals. This research aimed to investigate the VWC suitable for the growth of Minuartia laricina, Arenaria juncea, and Corydalis speciosa in open filed. Sandy soil which consisted of particles of weathered rock was used, and the VWC of 0.15, 0.20, 0.25, and 0.30 ㎥·m^-3 was maintained using an automated irrigation system with capacitance soil moisture sensors and a data logger. No significant differences in growth and antioxidant enzymes activity of A. juncea were observed among VWC treatments. However, the survival rate was low at VWC 0.30 ㎥·m^-3 treatment, which was the highest soil moisture content. Even considering the efficiency of water use, we recommended that VWC 0.15-0.20 ㎥·m^-3 is suitable for the cultivation of A. juncea. Minuartia laricina showed better growth with lower VWC. Because of frequent rainfall in open field, plant volume and survival rate was high even in VWC 0.15 ㎥·m^-3 treatment. In C. speciosa, the plant height, number of shoots and lateral shoots, and fresh and dry weight were higher in plants grown in VWC 0.25 ㎥·m^-3 as compared with that in the plants grown at 0.15, 0.20, and 0.30 ㎥·m^-3. Based on these results, M. laricina needed less water in open filed, and A. juncea and C. speciosa required higher VWC, but excessive water should be avoided.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1211-1224
• /
• 2023

Clouds cause many difficult problems in observing land surface phenomena using optical satellites, such as national land observation, disaster response, and change detection. In addition, the presence of clouds affects not only the image processing stage but also the final data quality, so it is necessary to identify and remove them. Therefore, in this study, we developed a new cloud detection technique that automatically performs a series of processes to search and extract the pixels closest to the spectral pattern of clouds in satellite images, select the optimal threshold, and produce a cloud mask based on the threshold. The cloud detection technique largely consists of three steps. In the first step, the process of converting the Digital Number (DN) unit image into top-of-atmosphere reflectance units was performed. In the second step, preprocessing such as Hue-Value-Saturation (HSV) transformation, triangle thresholding, and maximum likelihood classification was applied using the top of the atmosphere reflectance image, and the threshold for generating the initial cloud mask was determined for each image. In the third post-processing step, the noise included in the initial cloud mask created was removed and the cloud boundaries and interior were improved. As experimental data for cloud detection, CAS500-1 L2G images acquired in the Korean Peninsula from April to November, which show the diversity of spatial and seasonal distribution of clouds, were used. To verify the performance of the proposed method, the results generated by a simple thresholding method were compared. As a result of the experiment, compared to the existing method, the proposed method was able to detect clouds more accurately by considering the radiometric characteristics of each image through the preprocessing process. In addition, the results showed that the influence of bright objects (panel roofs, concrete roads, sand, etc.) other than cloud objects was minimized. The proposed method showed more than 30% improved results(F1-score) compared to the existing method but showed limitations in certain images containing snow.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.2
• /
• pp.138-148
• /
• 2001

Digital Video (DV) coding standards for digital video cassette recorder are based mainly on DCT and variable length coding. DV has low hardware complexity but high compressed bit rate of about 26 Mb/s. Thus, it is necessary to encode video with low complex video coding at the studios and then transcode compressed video into MPEG-2 for video-on-demand system. Because these coding methods exploit DCT, transcoding in the DCT domain can reduce computational complexity by excluding duplicated procedures. In transcoding DV into MPEC-2 intra coding, multiplying matrix by transformed data is used for 4:1:1-to-4:2:2 chroma format conversion and the conversion from 2-4-8 to 8-8 DCT mode, and therefore enables parallel processing. Variance of sub block for MPEG-2 rate control is computed completely in the DCT domain. These are verified through experiments. We estimate motion hierarchically using DCT coefficients for transcoding into MPEG-2 inter coding. First, we estimate motion of a macro block (MB) only with 4 DC values of 4 sub blocks and then estimate motion with 16-point MB using IDCT of 2$\times$2 low frequencies in each sub block, and finish estimation at a sub pixel as the fifth step. ME with overlapped search range shows better PSNR performance than ME without overlapping.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.8
• /
• pp.187-195
• /
• 2013

Most of former studies for car license plate detection restrict the image acquisition environment. The aim of this research is to diminish the restrictions by proposing a new method of using SIFT and neural network. SIFT can be used in diverse situations with less restriction because it provides size- and rotation-invariance and large discriminating power. SIFT extracted from the license plate image is divided into the internal(inside class) and the external(outside class) ones and the classifier is trained using them. In the proposed method, by just putting the various types of license plates, the trained neural network classifier can process all of the types. Although the classification performance is not high, the inside class appears densely over the plate region and sparsely over the non-plate regions. These characteristics create a local feature map, from which we can identify the location with the global maximum value as a candidate of license plate region. We collected image database with much less restriction than the conventional researches. The experiment and evaluation were done using this database. In terms of classification accuracy of SIFT keypoints, the correct recognition rate was 97.1%. The precision rate was 62.0% and recall rate was 50.2%. In terms of license plate detection rate, the correct recognition rate was 98.6%.

• Proceedings of the Technology Innovation Conference
• /
• 2003.06a
• /
• pp.41-56
• /
• 2003

다양한 제품들이 존재하는 시장에는 타 제품에 비하여 품질대비 가격이 낮은 혁신적인 경쟁력있는 제품과 그렇지 못한 제품들이 혼재하고 있다. 그러나 정보의 부족(limited information), 제한적 합리성(bounded rationality) 등 여러 가지 원인으로 인하여 혁신적인 제품들만이 소비자들에게 선택되어 소비되는 것은 아니다. 본 연구에서는 이러한 현상을 설명하기 위하여 소비효율성(consumption efficiency)라는 개념을 도입, 제시하고자 한다. 만약 소비효율성이 극도로 낮다면 혁신적인 제품을 내어놓는다 하더라도 소비자들에게 선택되어 이윤이 발생될 확률이 낮기 때문에 생산자 입장에서는 혁신의 유인(innovation incentive)이 낮아질 수밖에 없게 된다. 이처럼 소비효율성의 문제는 혁신의 유인과 결과를 이해하는데 중요한 단초를 제공할 수 있게 된다. 이에 반하여 혁신을 이해하기 위한 기존의 분석틀은 생산경제이론(production economics)에 기반하고 있고, 효율성의 개념도 생산효율성(production efficiency) 혹은 기술적 효율성(technical efficiency)의 범주에서 다루어져 왔다. 본 연구에서 제시하는 소비효율성의 개념은 효용이론에 근거하고 있다는 점에서 기존 연구와 차별화된다. 본 연구는 효용함수 극대화이론에서 출발하여 경계헤도닉함수(frontier hedomic function)을 도출하는 이론적 유도과정을 제시한다. 실증분석을 위해서는 SFA(Stochastic Frontier Analysis)의 방법론 체계를 적용하였다. 제시된 분석틀은 국내 PC산업의 데이터에 적용되었다. 분석의 결과 몇 가지 가정하에 국내 PC산업이 약 13%정도의 비효율성을 안고 있는 것으로 판단할 수 있으며, 초기혁신구매자(early adopter)들은 일정 정도의 비효율성을 기꺼이 감수할 것으로 분석되었다. 궤적 분석에서는 각 산업별 기술의 특성을 분석하는 것으로, 특정 기술 지식의 활용 기간을 통해 기술 주기를 도출하고, 산업 내 평균 권리 청구 항목 수를 이용하여 각 산업의 기술 범위를 비교하였다. 각각의 동적 분석을 통해 시간에 따른 변화 양상이 관찰하였고, ANOVA 분석을 이용하여 통계적 유의성을 검증하였다. 본 연구는 현재의 기술 패러다임 내에서 Pavitt이 제시한 산업 분류의 근거를 보충 설명하였고 특허 정보를 이용하여 기술혁신의 산업별 유형에 대한 폭넓은 분석방법을 제시하였다.별 시간대별 효과분석을 통하여 정책의 시행여부가 결정되어야 할 것이다. 한편, 화물전용차선의 설치로 인한 물류비용의 절감을 보다 효과적으로 달성하기 위해서는 종합류류 전산망의 시급한 구축과 함께 화물차의 적재율을 높이고 공차율을 낮출 수 있는 운송체계의 수립이 필요한 것으로 판단된다. 그라나 이러한 화물전용차선의 효과는 단기적인 치유책일 수밖에 없기 때문에 물류유통 시설의 확충을 위한 사회간접자본의 구축을 서둘러 시행하여야 할 것이다.으로 처리한 Machine oil, Phenthoate EC 및 Trichlorfon WP는 비교적 약효가 낮았다.>$^{\circ}$E/$\leq$30$^{\circ}$NW 단열군이 연구지역 내에서 지하수 유동성이 가장 높은 단열군으로 추정된다. 이러한 사실은 3개 시추공을 대상으로 실시한 시추공 내 물리검층과 정압주입시험에서도 확인된다.. It was resulted from increase of weight of single cocoon. "Manta"2.5ppm produced 22.2kg of cocoon. It is equal to 9% increase in index, as compared to that of control. In case of R-20458, the increasing

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.3C
• /
• pp.374-386
• /
• 2004

The mammogram provides the way to observe detailed internal organization of breasts to radiologists for the early detection. This paper is mainly focused on efficiently detecting the Microcalcification's Region Of Interest(ROI)s. Breast cancers can be caused from either microcalcifications or masses. Microcalcifications are appeared in a digital mammogram as tiny dots that have a little higher gray levels than their surrounding pixels. We can roughly determine the area which possibly contain microcalifications. In general, it is very challenging to find all the microcalcifications in a digital mammogram, because they are similar to some tissue parts of a breast. To efficiently detect microcalcifications ROI, we used four sequential processes; preprocessing for breast area detection, modified multilevel thresholding, ROI selection using simple thresholding filters and final ROI selection with two stages of neural networks. The filtering process with boundary conditions removes easily-distinguishable tissues while keeping all microcalcifications so that it cleans the thresholded mammogram images and speeds up the later processing by the average of 86％. The first neural network shows the average of 96.66％ recognition rate. The second neural network performs better by showing the average recognition rate 98.26％. By removing all tissues while keeping microcalcifications as much as possible, the next parts of a CAD system for detecting breast cancers can become much simpler.