• 한국컴퓨터정보학회논문지
• /
• 제25권9호
• /
• pp.31-36
• /
• 2020

본 연구에서는 딥러닝 처리기술을 이용한 이미지 분석을 통하여 위치정보가 없는 사진의 위치를 사용자에게 제공하는 장소이미지 수집기술을 설계하였다. 본 서비스는 사용자가 생활 중에 관심 있는 장소의 이미지 사진을 서비스에 업로드하면 해당 장소의 이름과 위치뿐만 아니라 관련 주변 정보를 확인 할 수 있는 서비스 개발을 목적으로 설계되었다. 본 연구는 이미지에 해당하는 정보를 제공하고 그 위치 정보를 기반으로 사용자가 관심 있는 주변정보를 제공할 수 있는 서비스의 기반기술이다. 이를 통하여 다양한 서비스에 활용이 가능하다.

• International Journal of Computer Science & Network Security
• /
• 제21권6호
• /
• pp.137-142
• /
• 2021

Machine-learning systems have proven their worth in various industries, including healthcare and banking, by assisting in the extraction of valuable inferences. Information in these crucial sectors is traditionally stored in databases distributed across multiple environments, making accessing and extracting data from them a tough job. To this issue, we must add that these data sources contain sensitive information, implying that the data cannot be shared outside of the head. Using cryptographic techniques, Privacy-Preserving Machine Learning (PPML) helps solve this challenge, enabling information discovery while maintaining data privacy. In this paper, we talk about how to keep your data mining private. Because Data mining has a wide variety of uses, including business intelligence, medical diagnostic systems, image processing, web search, and scientific discoveries, and we discuss privacy-preserving in deep learning because deep learning (DL) exhibits exceptional exactitude in picture detection, Speech recognition, and natural language processing recognition as when compared to other fields of machine learning so that it detects the existence of any error that may occur to the data or access to systems and add data by unauthorized persons.

• 대한족부족관절학회지
• /
• 제11권2호
• /
• pp.182-186
• /
• 2007

Purpose: We examined the relationship of interdigital neuroma occurring site and the surrounding structures, including the deep transverse metatarsal ligament (DTML) by cadaver study and clinical results. Materials and Methods: Seventeen fresh frozen cadavers study were done to evaluate the relationship of interdigital neuroma occuring site and the DTML at two phase of the gait cycle with 60 degree of metatarsophalangeal dorsiflexion and with 15 degrees of ankle dorsiflexion. We measured the distance from interdigital nerve bifurcation of the common digital nerve to anterior margin of the DTML and longitudinal length of DTML itself. Clinically, we checked the location of interdigital neuroma and DTML length during surgery in 32 feet. Results: In the second and third web space, the mean distance from bifurcation of the common digital nerve of foot to the anterior margin of DTML was 16.7 mm, 15.1 mm in the mid-stance position, and 15.9 mm. 14.6 mm in heel-off position. Second, Third web space ligament itself length were average 12.8 mm, 10.6 mm. Clinically, all of the cases of interdigital neuroma started at the bifurcation area of the common digital nerve and interdigital neuroma was average 7.5 mm (range; 6-11 mm). Conclusion: Interdigital neuroma were located more distally than DTML in both the mid-stance and heel off stage. The main lesion was located between metatarsal head and metatarsophalangeal joint and more distal than the DTML anterior margin.

• Steel and Composite Structures
• /
• 제36권3호
• /
• pp.307-319
• /
• 2020

The upper chords in half-through truss bridges are prone to buckling due to a lack of the upper transverse connections. Taking into account geometric and material nonlinearity, nonlinear finite-element analysis of a simple supported truss bridge was carried out to exhibit effects of different types of initial imperfections. A half-wave of initial imperfection was proved to be effective in the nonlinear buckling analysis. And a parameter analysis of initial imperfections was also conducted to reveal that the upper chords have the greatest impact on the buckling, followed by the bottom chords, vertical and diagonal web members. Yet initial imperfections of transverse beams have almost no effect on the buckling. Moreover, using influence surface method, the combinatorial effects of initial imperfections were compared to demonstrate that initial imperfections of the upper chords play a leading role. Furthermore, the equivalent effective length coefficients of the upper chord were derived to be 0.2~0.28 by different methods, which implies vertical and diagonal web members still provide effective constraints for the upper chord despite a lack of the upper transverse connections between the two upper chords. Therefore, the geometrical and material nonlinear finite-element method is effective in the buckling analysis due to its higher precision. Based on nonlinear analysis and installation deviations of members, initial imperfection of l/500 is recommended in the nonlinear analysis of half-through truss bridges without initial imperfection investigation.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2022년도 학술발표회
• /
• pp.145-145
• /
• 2022

Availability of abundant water resources data in developing countries is a great concern that has hindered the adoption of deep learning techniques (DL) for disaster prevention and mitigation. On the contrary, over the last two decades, a sizeable amount of DL publication in disaster management emanated from developed countries with efficient data management systems. To understand the current state of DL adoption for solving water-related disaster management in developing countries, an extensive bibliometric review coupled with a theory-based analysis of related research documents is conducted from 2003 - 2022 using Web of Science, Scopus, VOSviewer software and PRISMA model. Results show that four major disasters - pluvial / fluvial flooding, land subsidence, drought and snow avalanche are the most prevalent. Also, recurrent flash floods and landslides caused by irregular rainfall pattern, abundant freshwater and mountainous terrains made India the only developing country with an impressive DL adoption rate of 50% publication count, thereby setting the pace for other developing countries. Further analysis indicates that economically-disadvantaged countries will experience a delay in DL implementation based on their Human Development Index (HDI) because DL implementation is capital-intensive. COVID-19 among other factors is identified as a driver of DL. Although, the Long Short Term Model (LSTM) model is the most frequently used, but optimal model performance is not limited to a certain model. Each DL model performs based on defined modelling objectives. Furthermore, effect of input data size shows no clear relationship with model performance while final model deployment in solving disaster problems in real-life scenarios is lacking. Therefore, data augmentation and transfer learning are recommended to solve data management problems. Intensive research, training, innovation, deployment using cheap web-based servers, APIs and nature-based solutions are encouraged to enhance disaster preparedness.

• 한국전자통신학회논문지
• /
• 제19권2호
• /
• pp.389-396
• /
• 2024

생성형 AI는 최근 모든 분야에서 활용되고 있으며, 심층 데이터 분석 분야에서도 전문가를 대체할 수준으로 발전하고 있다. 그러나 과학기술 문헌에서의 지역명 식별은 학습 데이터의 부족과 이에 따른 인공지능 모델을 적용한 사례가 전무한 실정이다. 본 연구는 Web of Science에서 한국 기관 소속 저자들의 주소 데이터를 활용해 지역명을 분류하기 위한 데이터셋을 구축하고, 머신러닝 및 딥러닝 모델의 적용을 실험 및 평가했다. 실험 결과 BERT 모델이 가장 우수한 성능을 보였으며, 광역 분류에서는 정밀도 98.41%, 재현율 98.2%, F1 점수 98.31%를 기록하였다. 시군구 분류에서는 정밀도 91.79%, 재현율 88.32%, F1 점수 89.54%를 달성하였다. 이 결과는 향후 지역 R&D 현황, 지역 간 연구자 이동성, 지역 공동 연구 등 다양한 연구의 기반 데이터로 활용이 가능하다.

• Steel and Composite Structures
• /
• 제42권6호
• /
• pp.827-841
• /
• 2022

The rotation capacities of the plastic hinges located at beam-ends are significantly reduced in traditional steel framed-tube structures (SFTSs) because of the small span-to-depth ratios of the deep beams, leading to the low ductility and energy dissipation capacities of the SFTSs. High-strength steel framed-tube structures with replaceable shear links (HSSFTS-RSLs) are proposed to address this issue. A replaceable shear link is located at the mid-span of a deep spandrel beam to act as a ductile fuse to dissipate the seismic energy in HSSFTS-RSLs. A 2/3-scaled HSSFTS-RSL specimen with a shear link fabricated of high-strength low-alloy Q355 structural steel was created, and a cyclic loading test was performed to study the hysteresis behaviors of this specimen. The test results were compared to the specimens with soft steel shear links in previous studies to investigate the feasibility of using high-strength low-alloy steel for shear links in HSSFTS-RSLs. The effects of link web stiffener spaces on the cyclic performance of the HSSFTS-RSLs with Q355 steel shear links were investigated based on the nonlinear numerical analysis. The test results indicate that the specimen with a Q355 steel shear link exhibited a reliable and stable seismic performance. If the maximum interstory drift of HSSFTS-RSL is designed lower than 2% under earthquakes, the HSSFTS-RSLs with Q355 steel shear links can have similar seismic performance to the structures with soft steel shear links, even though these shear links have similar shear and flexural strength. For the Q355 steel shear links with web height-to-thickness ratios higher than 30.7 in HSSFTS-RSLs, it is suggested that the maximum intermediate web stiffener space is decreased by 15% from the allowable space for the shear link in AISC341-16 due to the analytical results.

• 한국컴퓨터정보학회논문지
• /
• 제21권7호
• /
• pp.1-8
• /
• 2016

Nowadays, distributed denial of service (DDoS) attacks on web sites reward attackers financially or politically because our daily lifes tightly depends on web services such as on-line banking, e-mail, and e-commerce. One of DDoS attacks to web servers is called HTTP-GET flood attack which is becoming more serious. Most existing techniques are running on the application layer because these attack packets use legitimate network protocols and HTTP payloads; that is, network-level intrusion detection systems cannot distinguish legitimate HTTP-GET requests and malicious requests. In this paper, we propose a practical detection technique against HTTP-GET flood attacks, based on the access behavior of inline objects in a webpage using NetFlow data. In particular, our proposed scheme is working on the network layer without any application-specific deep packet inspections. We implement the proposed detection technique and evaluate the ability of attack detection on a simple test environment using NetBot attacker. Moreover, we also show that our approach must be applicable to real field by showing the test profile captured on a well-known e-commerce site. The results show that our technique can detect the HTTP-GET flood attack effectively.

• 한국인터넷방송통신학회논문지
• /
• 제22권4호
• /
• pp.23-28
• /
• 2022

최근 스마트폰 또는 타블렛 PC와 같은 스마트기기가 정보의 창구 역할을 하게 되면서 다수의 사용자가 웹포털을 통해 웹 뉴스를 소비하는 것이 더욱 중요해졌다. 하지만 인터넷 상에 생성되는 뉴스의 양을 사용자들이 따라가기 힘들며 중복되고 반복되는 폭발하는 뉴스 기사에 오히려 혼란을 야기 시킬 수도 있다. 본 논문에서는 뉴스 포털에서 사용자의 질의로부터 검색된 뉴스후보들 중 KoBART 기반의 문서요약 기술을 활용한 뉴스 추천 시스템을 제안한다. 실험을 통해서 새롭게 수집된 뉴스 데이터를 기반으로 학습한 KoBART의 성능이 사전훈련보다 더욱 우수한 결과를 보여주었으며 KoBART로부터 생성된 요약문을 환용하여 사용자에게 효과적으로 뉴스를 추천하였다.

• 콘크리트학회논문집
• /
• 제19권2호
• /
• pp.171-178
• /
• 2007

경사 보강근이 철근콘크리트 연속 깊은 보의 구조적 거동에 미치는 영향을 파악하기 위하여 내부 전단경간에 개구부를 갖는 연속 깊은 보 12개가 실험되었다. 주요 변수는 개구부 크기와 경사 보강근 양이다. 개구부 주위의 경사 보강근 양과 개구부 크기의 영향을 동시에 고려하기 위한 유효 경사 보강근 계수가 제시되었다. 실험 결과 개구부를 갖는 연속 깊은 보의 하중 분배, 경사균열 폭 및 치대 내력은 유효 경사 보강근 계수에 의해 결정되었다. 유효 경사 보강근 계수가 클수록 경사균열 폭 및 이들의 진전 속도는 낮았다. 특히 유효 경사 보강근 계수가 0.077 이상인 보의 최대 내력은 동일 개구부 없는 보의 것에 비해 높았다. 내부 전단경간에 개구부를 갖는 연속 깊은 보의 최대 내력을 평가하기 위하여 상계치 이론을 이용한 수치해석 모델이 제시되었다. 제시된 모델로부터 얻은 최대 내력은 실험 결과와 잘 일치하였다.