• 한국문헌정보학회지
• /
• 제54권2호
• /
• pp.419-434
• /
• 2020

본 연구의 목적은 랜드마크 이미지의 AI 학습용 데이터 구축을 위한 메타데이터 표준 설계 방안을 제시하기 위함이다. 이를 위해, 이미지 검색시스템의 종류와 각각의 색인 방식에 관한 최신 기술 현황을 포괄적으로 조사하여 분석하고, AI 머신러닝을 적용한 랜드마크 인식에 필수적인 학습용 공개 데이터셋과 이미지 객체 인식에 관한 기계학습 도구를 조사하였다. 이를 통해, 랜드마크 이미지 AI 학습용 데이터에 최적화된 메타데이터 요소를 선정하고 각각의 요소에 대한 입력 데이터를 정의하였다. 결론 및 제언에서는 랜드마크 인식을 활용한 추천시스템을 포함한 응용서비스 개발 방안을 논의하였다.

• 한국광학회지
• /
• 제9권6호
• /
• pp.385-389
• /
• 1998

본 논문에서는 공간정합필터의 데이터 베이스로써 체적 홀로그램을 이용한 광상관기를 구성하였다. 광상관 시스템은 광학의 고속 및 병렬처리 특징을 지니며, 공간정합필터가 기록된 체적홀로그램은 방대한 저장 능력과 실시간 랜덤 엑세스의 장점을 갖는다. 데이터 베이스로 사용되는 영상들은 각가 공간광변조기에 디스플레이 되어 퓨리에 변환 렌즈를 통과한 후 퓨리에 변환된 공간정합필터의 형태로 광굴절 매질에 기록된다. 대용량의 데이터 베이스를 구성하기 위한 다중화 방법으로 스텝 모터를 이용하여 광굴절 매질을 회전하는 각다중화 기술을 사용하였다. 체적홀로그래픽 광상관 실험을 통하여 지문인식에의 응용 가능성을 제시하였다.

• 한국지능시스템학회논문지
• /
• 제19권6호
• /
• pp.834-839
• /
• 2009

지능로봇시스템과 같은 HCI 환경에서 사람의 감정을 인식하기 위한 매개정보인 얼굴영상 기반 정서특징 검출문제는 관련분야의 매우 중요한 이슈이다. 본 논문에서는 보편화된 시스템 기반에서 임의의 사용자에 대한 정서 인식을 수행하기 위해 사람의 얼굴에서 나타나는 최적의 정서특징을 가장 효율적으로 추출하기 위한 연구로서 본 연구실에서 기존에 제안한 FACS와 AAM을 이용한 Bayesian Network 기반 얼굴표정 인식 시스템을 보완한 Advanced AAM을 기반 얼굴영상 정서 특징을 검출 시스템에 대한 연구를 진행하였다. 이를 수행하기 위하여 정규화된 이미지에서의 Statistical Shape Analysis로서 Advanced AAM과 얼굴 표정 분석 시스템인 FACS를 이용하여, 임의의 사용자에 대한 자동적인 정서특징 검출이 가능하도록 연구를 진행하였다.

• 대한인간공학회지
• /
• 제31권4호
• /
• pp.499-505
• /
• 2012

Objective: Research on the transformation of interaction between mobile machines and users through analysis on current gesture interface technology development trend. Background: For smooth interaction between machines and users, interface technology has evolved from "command line" to "mouse", and now "touch" and "gesture recognition" have been researched and being used. In the future, the technology is destined to evolve into "multi-modal", the fusion of the visual and auditory senses and "3D multi-modal", where three dimensional virtual world and brain waves are being used. Method: Within the development of computer interface, which follows the evolution of mobile machines, actively researching gesture interface and related technologies' trend and development will be studied comprehensively. Through investigation based on gesture based information gathering techniques, they will be separated in four categories: sensor, touch, visual, and multi-modal gesture interfaces. Each category will be researched through technology trend and existing actual examples. Through this methods, the transformation of mobile machine and human interaction will be studied. Conclusion: Gesture based interface technology realizes intelligent communication skill on interaction relation ship between existing static machines and users. Thus, this technology is important element technology that will transform the interaction between a man and a machine more dynamic. Application: The result of this study may help to develop gesture interface design currently in use.

• 한국실내디자인학회논문집
• /
• 제39호
• /
• pp.116-123
• /
• 2003

The purpose of this study is to demonstrate the relationship between the results of the analysis of the overseas railroad station buildings, which was conducted using the factors of environmental cognition for the purpose of designing an interior environment for the Incheon International Airport Railroad station that will be newly constructed, and the plan that could be applied to the design of interior environment for the airport railroad station. The station with a complex interior space layout and relatively larger space tends to be difficult to predict or forecast passenger's needs or recognition element in approaching stage of intoner environment design since the human's biological memory system is greatly affected by such factors. Cognitive approach at empirical standpoint would possibly create the design, of which elements will Implement the functions of their own as such approach enables necessary information to be structured in a systematical way and manner In implementing interior environment design for such stations to be built for the first time in Korea, behavioral approach based on systematic theory proved to be very crucial. Under such a background, the study was aimed at extracting the assessment elements for interior environment design, then setting the frame of cognitive approach to eventually propose the guideline in approaching to interior environment design.

• 한국실내디자인학회논문집
• /
• 제14권4호
• /
• pp.122-133
• /
• 2005

This study could begin with the improvement of computer graphic technology The graphic technology is the standards of computer technology level and up-to-date technology intensive. Above all, the technology of virtual reality has developed rapidly and the development of the program has changed from professional one only for the experts to easy of access ones for the space designers. Moreover, the program which major internet user's can experience the virtual model has been made, as the development of virtual reality technology that is based on the web. These graphic technology and the development of the web helped to extract human experiences on the space design step. However, to find the meeting point with real recognition is not easy though the virtual reality technology develops. Because the real space is made up of various senses that people feel in their surroundings. But, this study was possible because most of the space recognition is based on the visual organ, even though it can't satisfy all sensible factors that we feel in reality. Therefore, the significant of this study is the standards and criteria of evaluation, the technological proposal, expecting to make more advanced alternative design than before.

• The Plant Pathology Journal
• /
• 제37권3호
• /
• pp.291-298
• /
• 2021

False smut caused by Ustilaginoidea virens is an important rice fungal disease that significantly decreases its production. In the recent past, conventional methods have been developed for its detection that is time-consuming and need high-cost equipments. The research and development in nanotechnology have made it possible to assemble efficient recognition interfaces in biosensors. In this study, we present a simple, sensitive, and selective oxidized graphene-based geno-biosensor for the detection of rice false smut. The biosensor has been developed using a probe DNA as a biological recognition element on paper electrodes, and oxidized graphene to enhance the limit of detection and sensitivity of the sensor. Probe single-stranded DNA (ssDNA) and target ssDNA hybridization on the interface surface has been quantitatively measured with the electrochemical analysis tools namely, cyclic voltammetry, and linear sweep voltammetry. To confirm the selectivity of the device, probe hybridization with non-complementary ssDNA target has been studied. In our study, the developed sensor was able to detect up to 10 fM of target ssDNA. The paper electrodes were employed to produce an effective and cost-effective platform for the immobilization of the DNA and can be extended to design low-cost biosensors for the detection of the other plant pathogens.

• 한국군사과학기술학회지
• /
• 제26권2호
• /
• pp.122-128
• /
• 2023

The target must be located within the main-lobe of the antenna in order to measure the direction of the target by using sum-delta monopulse technique. The most common way if the target is located within the main-lobe is to compare the amplitude of the sum channel received signal with the delta channel received signal. However, in the case of the single-ring circular array antenna, it is difficult to apply the conventional method due to its structural limitation where antenna elements do not exist in the center of the array. In this paper, we proposed a novel method to identify whether a target is located within the main-lobe by appropriately adjusting the feeding amplitude of each element constituting the single-ring circular array antenna through the particle swarm optimization method. Simulation results showed that the proposed method can determine whether the target is located within the main-lobe of the single-ring circular array antenna.

• International journal of advanced smart convergence
• /
• 제11권4호
• /
• pp.68-80
• /
• 2022

Since the launch of AI, technology development to implement complete and sophisticated AI functions has continued. In efforts to develop technologies for complete automation, Machine Learning techniques and deep learning techniques are mainly used. These techniques deal with supervised learning, unsupervised learning, and reinforcement learning as internal technical elements, and use the Big-data Analysis method again to set the cornerstone for decision-making. In addition, established decision-making is being improved through subsequent repetition and renewal of decision-making standards. In other words, big data analysis, which enables data classification and recognition/recognition, is important enough to be called a key technical element of AI function. Therefore, big data analysis itself is important and requires sophisticated analysis. In this study, among various tools that can analyze big data, we will use a Python program to find out what variables can affect addiction according to smartphone use in a decision tree environment. We the Python program checks whether data classification by decision tree shows the same performance as other tools, and sees if it can give reliability to decision-making about the addictiveness of smartphone use. Through the results of this study, it can be seen that there is no problem in performing big data analysis using any of the various statistical tools such as Python and R when analyzing big data.

• 비파괴검사학회지
• /
• 제21권5호
• /
• pp.510-517
• /
• 2001

본 연구는 와전류 형상인식 기법을 증기발생기 세관의 보다 실제적인 결함 평가 문제에 적용하기 위한 목적으로 시도되었다. 이를 위해 증기발생기 세관에 발생하는 실제적인 결함을 보다 사실적으로 모사하는 다섯 가지 형태의 외벽 결함을 선택하고, 이들 결함의 크기 인자와 시험주파수를 변화시켜 가면서, 유한요소 수치해석 프로그램을 이용하여 이론적인 결함신호를 생성하였다. 그리고, 이들 결함신호의 분석을 효율적으로 수행하기 위한 도구로서, '와전류 특징추출 프로그램', '와전류 특징분석 프로그램', 그리고 'PNN 결함분류 프로그램'을 자체적으로 개발하였다. 비대칭 단면을 갖는 결함의 신호는 교점이 원점으로부터 이격되는 현상이 관찰되었는데, 이러한 특성을 반영하는 특징을 추가하여 총 18개의 특징을 시험주파수 별로 정의하였다. 이 특징들을 이용하여 결함을 분류하는 확률신경회로망을 구성하고 결함 분류를 수행한 결과, 결함단면의 대칭성 여부를 결정하는 문제에서는 비교적 높은 정확도를 얻었으나, 결함선단의 첨도를 판단하는 문제에서는 낮은 정확도를 얻었다.