• 한국산학기술학회논문지
• /
• 제20권6호
• /
• pp.541-547
• /
• 2019

최근 자동화 되는 해킹 및 분석 기술의 발전으로 인하여 수많은 소프트웨어 보안 취약점이 빠르게 발표되고 있다. 대표적인 취약점 데이터베이스인 NVD(National Vulnerability Database)에는 2010년부터 2015년까지 보안 취약점(CVE: Common Vulnerability Enumeration) 약 8만 건이 등록되었으며, 최근에도 점차 증가하고 있는 추세이다. 보안 취약점은 빠른 속도로 증가하고 있는 반면, 보안 취약점을 분석하고 대응하는 방법은 전문가의 수동 분석에 의존하고 있어 대응 속도가 느리다. 이런 문제점을 해결하기 위해 자동화된 방법으로 보안 취약점을 탐색하고, 패치하여 악의적인 공격자에게 공격 기회를 줄 수 있는 보안 취약점을 사전에 대응 할 수 있는 기술이 필요하다. 본 논문에서는 복잡도 분석을 통해 취약점 탐색 대상 바이너리의 특징을 추출하고, 특징에 적합한 취약점 탐색 전략을 선정하여 취약점을 자동으로 탐색하는 기술을 제안한다. 제안 기술은 AFL, ANGR, Driller 도구와 비교 검증 하였으며 코드 커버리지는 약 6% 향상, 크래시 개수는 약 2.4배 증가, 크래시 발생율 약 11% 향상 효과를 볼 수 있었다.

• 대한건축학회논문집:계획계
• /
• 제35권10호
• /
• pp.3-10
• /
• 2019

The high school credit system is a system in which students select complete various subjects, depending on their career, and graduate when their accumulated credit reaches the standard. It is expected that the high school credit system, which guarantees the individual's right of choice, will bring an educational effect that can respond to the student's career aptitude. However, it is expected that problems in the aspect of school life, such as the weakening of class belongingness or difficulty of securing a stable base venue within the school building would be accompanied. This research analyzed students' usage condition depending on the living base space environment feature in schools that are implementing moving-selective class in the aspect of activity domain formation and contemplated the venue evaluation. The purpose is to provide the basic data of an architectural plan of a stable living base space within the school building through this. 'Living base center type' and 'living base dispersion type' school buildings among Japanese integral department high schools were used as the target to analyze the usage condition in the aspect of domain formation. As a result, a conclusion was deducted that student's securement of territory consciousness about the base space and venue construction for the community of various studying groups affects life satisfaction.

• 한국정보통신학회논문지
• /
• 제24권12호
• /
• pp.1604-1611
• /
• 2020

마이크로렌즈 어레이 기반의 카메라로 촬영된 라이트필드 영상은 낮은 공간해상도 및 각해상도로 인하여 실제 사용하기에는 많은 제약이 따른다. 고해상도의 공간해상도 영상은 최근 많이 연구되고 있는 단일 영상 초해상도 기법으로 쉽게 얻을 수 있으나 고해상도의 각해상도 영상은 영상사이에 내재된 시점차 정보를 이용하는 과정에서 왜곡이 발생하여 좋은 품질의 각해상도 영상을 얻기 힘든 문제가 있다. 본 논문에서는 영상 사이에 내재된 시점차 정보를 효과적으로 추출하기 위해서 팽창 합성곱 신경망을 이용하여 초기 특징맵을 추출하고 잔차 신경망으로 새로운 시점 영상을 생성하는 라이트 필드 각 초해상도 영상 기법을 제안한다. 제안하는 네트워크는 기존의 각 초해상도 네트워크와 비교하여 PSNR 및 주관적 화질 비교에서 우수한 성능을 보였다.

• Pediatric Gastroenterology, Hepatology & Nutrition
• /
• 제24권2호
• /
• pp.135-144
• /
• 2021

Purpose: Although ultrasonography is the gold standard of diagnosing intussusception, plain abdomen radiograph (AXR) is often used to make differential diagnosis for pediatric patients with abdominal pain. In intussusception patients, we aimed to analyze the AXR and clinical data to determine the characteristics of early AXR findings associated with diagnosis of intussusception and recurrence after reduction. Methods: Between January 2011 and June 2018, 446 patients diagnosed with intussusception based on International Classification of Diseases-10 code of K56.1 were admitted. We retrospectively reviewed medical records of 398 patients who received air reduction; 51 of them have recurred after initial reduction. We evaluated six AXR features including absent ascending colon gas, absent transverse colon gas, target sign, meniscus sign, mass, and ileus. Clinical data and AXR features were compared between single episode and recurrence groups. Results: Two groups did not show significant differences regarding clinical data. Mean time to recurrence from air reduction was 3.4±3.2 days. Absent ascending colon gas (63.9%) was the most common feature in intussusception, followed by mass (29.1%). All of six AXR features were observed more frequently in the recurrence group. Absent transverse colon gas was the most closely associated AXR finding for recurrence (odds ratio, 2.964; 95% confidence interval, 1.327-6.618; p=0.008). Conclusion: In our study, absence of ascending colon gas was the most frequently seen AXR factor in intussusception patients. Extended and careful observation after reduction may be beneficial if such finding on AXR is found in intussusception patients.

• Journal of the Korean Physical Society
• /
• 제73권12호
• /
• pp.1821-1826
• /
• 2018

Uniformity is a key feature of state-of-the-art infrared focal planed array (IRFPA) and infrared imaging system. Unlike traditional infrared telescope facility, a ground-based infrared radiant characteristics measurement system with an IRFPA not only provides a series of high signal-to-noise ratio (SNR) infrared image but also ensures the validity of radiant measurement data. Normally, a long integration time tends to produce a high SNR infrared image for infrared radiant characteristics radiometry system. In view of the variability of and uncertainty in the measured target's energy, the operation of switching the integration time and attenuators usually guarantees the guality of the infrared radiation measurement data obtainted during the infrared radiant characteristics radiometry process. Non-uniformity correction (NUC) coefficients in a given integration time are often applied to a specified integration time. If the integration time is switched, the SNR for the infrared imaging will degenerate rapidly. Considering the effect of the SNR for the infrared image and the infrared radiant characteristics radiometry above, we propose a-wide-dynamic-range NUC algorithm. In addition, this essasy derives and establishes the mathematical modal of the algorithm in detail. Then, we conduct verification experiments by using a ground-based MWIR(Mid-wave Infared) radiant characteristics radiometry system with an Ø400 mm aperture. The experimental results obtained using the proposed algorithm and the traditional algorithm for different integration time are compared. The statistical data shows that the average non-uniformity for the proposed algorithm decreased from 0.77% to 0.21% at 2.5 ms and from 1.33% to 0.26% at 5.5 ms. The testing results demonstrate that the usage of suggested algorithm can improve infrared imaging quality and radiation measurement accuracy.

• 영어영문학
• /
• 제58권2호
• /
• pp.279-304
• /
• 2012

Since the publication of Foucault's Discipline and Punish, theatricality has become one of the key concepts in New Historicism. By defining theatricality as the most definitive feature of early modern society and culture, New Historicists have promoted the idea that theatrical practices in every day life were eventually replaced by textual practices as the western society started to undergo modernization with the advent of print culture and technologies. This paper questions this linear model of English literature, the shift of literary practices from theatricality to textuality in the event of modernization, by closely looking at the ways in which newsbooks and playlets during the English civil wars appealed to their target readers. The early print-based literary commodities during the English civil war (i.e. newsbooks and playlets) were able to win the attention of their audience not by breaking away from theatrical energy and creativity but instead by embracing and taking advantage of them through the use of dramatic conventions, dialogues, and many others. The newsbooks and the playlets during the time, however, did not simply replicate the dramatic forms and experiences of the previous generation. Instead, as the case study of Craftie Cromwell exemplifies, they went further to produce a different mode of theatricality by reshaping everyday lives into serialized drama, whose resolution is always already delayed and postponed into the ever-receding future. In conclusion, the study of the newsbook and playlets during the civil wars suggests that the textuality of modern times, materialized in print forms, have been co-evolved with the development of new theatricality, whose contents and forms are susceptible to the changes of everyday reality.

• 스마트미디어저널
• /
• 제11권4호
• /
• pp.30-37
• /
• 2022

Disease threatens plant growth and recognizing the type of disease is essential to making a remedy. In recent years, deep learning has witnessed a significant improvement for this task, however, a large volume of labeled images is one of the requirements to get decent performance. But annotated images are difficult and expensive to obtain in the agricultural field. Therefore, designing an efficient and effective strategy is one of the challenges in this area with few labeled data. Transfer learning, assuming taking knowledge from a source domain to a target domain, is borrowed to address this issue and observed comparable results. However, current transfer learning strategies can be regarded as a supervised method as it hypothesizes that there are many labeled images in a source domain. In contrast, unsupervised transfer learning, using only images in a source domain, gives more convenience as collecting images is much easier than annotating. In this paper, we leverage unsupervised transfer learning to perform plant disease recognition, by which we achieve a better performance than supervised transfer learning in many cases. Besides, a vision transformer with a bigger model capacity than convolution is utilized to have a better-pretrained feature space. With the vision transformer-based unsupervised transfer learning, we achieve better results than current works in two datasets. Especially, we obtain 97.3% accuracy with only 30 training images for each class in the Plant Village dataset. We hope that our work can encourage the community to pay attention to vision transformer-based unsupervised transfer learning in the agricultural field when with few labeled images.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권11호
• /
• pp.4065-4083
• /
• 2021

Super-resolution can improve the clarity of low-resolution (LR) images, which can increase the accuracy of high-level compute vision tasks. Portable devices have low computing power and storage performance. Large-scale neural network super-resolution methods are not suitable for portable devices. In order to save the computational cost and the number of parameters, Lightweight image processing method can improve the processing speed of portable devices. Therefore, we propose the Enhanced Information Multiple Distillation Network (EIMDN) to adapt lower delay and cost. The EIMDN takes feedback mechanism as the framework and obtains low level features through high level features. Further, we replace the feature extraction convolution operation in Information Multiple Distillation Block (IMDB), with Ghost module, and propose the Enhanced Information Multiple Distillation Block (EIMDB) to reduce the amount of calculation and the number of parameters. Finally, coordinate attention (CA) is used at the end of IMDB and EIMDB to enhance the important information extraction from Spaces and channels. Experimental results show that our proposed can achieve convergence faster with fewer parameters and computation, compared with other lightweight super-resolution methods. Under the condition of higher peak signal-to-noise ratio (PSNR) and higher structural similarity (SSIM), the performance of network reconstruction image texture and target contour is significantly improved.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권1호
• /
• pp.153-172
• /
• 2022

In this study, the authors intend to analyze factors contributing to research performance using Backpropagation Neural Network and Support Vector Machine. The analyzing factors contributing to lecturer research performance start from defining the features. The next stage is to collect datasets based on defining features. Then transform the raw dataset into data ready to be processed. After the data is transformed, the next stage is the selection of features. Before the selection of features, the target feature is determined, namely research performance. The selection of features consists of Chi-Square selection (U), and Pearson correlation coefficient (CM). The selection of features produces eight factors contributing to lecturer research performance are Scientific Papers (U: 154.38, CM: 0.79), Number of Citation (U: 95.86, CM: 0.70), Conference (U: 68.67, CM: 0.57), Grade (U: 10.13, CM: 0.29), Grant (U: 35.40, CM: 0.36), IPR (U: 19.81, CM: 0.27), Qualification (U: 2.57, CM: 0.26), and Grant Awardee (U: 2.66, CM: 0.26). To analyze the factors, two data mining classifiers were involved, Backpropagation Neural Networks (BPNN) and Support Vector Machine (SVM). Evaluation of the data mining classifier with an accuracy score for BPNN of 95 percent, and SVM of 92 percent. The essence of this analysis is not to find the highest accuracy score, but rather whether the factors can pass the test phase with the expected results. The findings of this study reveal the factors that have a significant impact on research performance and vice versa.

• KNOM Review
• /
• 제24권2호
• /
• pp.24-34
• /
• 2021

엣지 컴퓨팅을 사용하는 서비스 공급업체는 높은 수준의 서비스를 제공한다. 이에 따라 다양하고 중요한 정보들이 단말 장치에 저장되면서 탐지하기 더욱 어려운 최신 사이버 공격의 핵심 목표가 됐다. 보안을 위해 침입 탐지시스템과 같은 보안 시스템이 자주 활용되지만, 기존의 침입 탐지 시스템은 탐지 정확도가 낮은 문제점이 존재한다. 따라서 본 논문에서는 엣지 컴퓨팅에서 단말 장치의 더욱 정확한 침입 탐지를 위한 기계 학습 모델을 제안한다. 제안하는 모델은 희소성 제약을 사용하여 입력 데이터의 중요한 특징 벡터들을 추출하는 stacked sparse autoencoder (SSAE)와 convolutional neural network (CNN)를 결합한 하이브리드 모델이다. 최적의 모델을 찾기 위해 SSAE의 희소성 계수를 조절하면서 모델의 성능을 비교 및 분석했다. 그 결과 희소성 계수가 일 때 96.9%로 가장 높은 정확도를 보여주었다. 따라서 모델이 중요한 특징들만 학습할 경우 더 높은 성능을 얻을 수 있었다.