• 토지주택연구
• /
• 제4권1호
• /
• pp.89-98
• /
• 2013

최근 도시의 정책적 패러다임이 지속가능한 도시성장관리 중심으로 전환됨에 따라 교통정책도 승용차중심에서 대중교통중심으로 정책변화가 요구되고 있다. 이러한 배경 하에 복합환승센터의 도입은 매우 필연적이라고 볼 수 있다. 따라서 국가에서 주도하는 국가기간망중심의 환승센터 뿐 만 아니라 광역 및 지역중심의 환승시설에 대한 도입도 필요한 실정이다. 이에 본 연구에서는 효과적인 복합환승시설 도입을 위해 다양한 지역적 특성(영향권, 입지위치, 도시규모, 도시기능)과 환승시설기능(환승공간 이용방법, 연계교통수단)을 고려하여 66개의 사례를 유형화하였다. 또한 통계적인 유의성 검정을 통해 영향권-연계교통수단-도시기능조합과 도시규모-입지위치조합의 2가지 복합화된 유형을 제시하였다. 유형분류를 이용한 기존의 66개 사례지역을 정리해 본 결과 국내외 모두 비교적 규모가 큰 대도시를 중심으로 지역간 연계를 기반으로 하는 복합환승시설이 주류를 이루고 있음을 알 수 있다. 본 연구의 결과를 통해 향후 복합환승시설에 대한 자료가 지속적으로 축적되어질 경우 좀 더 신뢰성이 높은 유형분류의 결과를 기대해 본다.

• Journal of Positioning, Navigation, and Timing
• /
• 제11권3호
• /
• pp.163-172
• /
• 2022

Typical anti-jamming technologies based on array antennas, Space Time Adaptive Process (STAP) & Space Frequency Adaptive Process (SFAP), are very effective algorithms to perform nulling and beamforming. However, it does not perform equally well for all types of jamming signals. If the anti-jamming algorithm is not optimized for each signal type, anti-jamming performance deteriorates and the operation stability of the system become worse by unnecessary computation. Therefore, jamming classification technique is required to obtain optimal anti-jamming performance. Machine learning, which has recently been in the spotlight, can be considered to classify jamming signal. In general, performing supervised learning for classification requires a huge amount of data and new learning for unfamiliar signal. In the case of jamming signal classification, it is difficult to obtain large amount of data because outdoor jamming signal reception environment is difficult to configure and the signal type of attacker is unknown. Therefore, this paper proposes few-shot jamming signal classification technique using meta-learning and transfer-learning to train the model using a small amount of data. A training dataset is constructed by anti-jamming algorithm input data within the GNSS receiver when jamming signals are applied. For meta-learning, Model-Agnostic Meta-Learning (MAML) algorithm with a general Convolution Neural Networks (CNN) model is used, and the same CNN model is used for transfer-learning. They are trained through episodic training using training datasets on developed our Python-based simulator. The results show both algorithms can be trained with less data and immediately respond to new signal types. Also, the performances of two algorithms are compared to determine which algorithm is more suitable for classifying jamming signals.

• 대한의용생체공학회:의공학회지
• /
• 제39권5호
• /
• pp.213-219
• /
• 2018

Stomach cancer is the most diagnosed cancer in Korea. When gastric cancer is detected early, the 5-year survival rate is as high as 90%. Gastroscopy is a very useful method for early diagnosis. But the false negative rate of gastric cancer in the gastroscopy was 4.6~25.8% due to the subjective judgment of the physician. Recently, the image classification performance of the image recognition field has been advanced by the convolutional neural network. Convolutional neural networks perform well when diverse and sufficient amounts of data are supported. However, medical data is not easy to access and it is difficult to gather enough high-quality data that includes expert annotations. So This paper evaluates the efficacy of transfer learning in gastroscopy classification and diagnosis. We obtained 787 endoscopic images of gastric endoscopy at Gil Medical Center, Gachon University. The number of normal images was 200, and the number of abnormal images was 587. The image size was reconstructed and normalized. In the case of the ResNet50 structure, the classification accuracy before and after applying the transfer learning was improved from 0.9 to 0.947, and the AUC was also improved from 0.94 to 0.98. In the case of the InceptionV3 structure, the classification accuracy before and after applying the transfer learning was improved from 0.862 to 0.924, and the AUC was also improved from 0.89 to 0.97. In the case of the VGG16 structure, the classification accuracy before and after applying the transfer learning was improved from 0.87 to 0.938, and the AUC was also improved from 0.89 to 0.98. The difference in the performance of the CNN model before and after transfer learning was statistically significant when confirmed by T-test (p < 0.05). As a result, transfer learning is judged to be an effective method of medical data that is difficult to collect good quality data.

• Nuclear Engineering and Technology
• /
• 제55권6호
• /
• pp.2026-2033
• /
• 2023

Due to Thailand's nuclear energy public acceptance problem, the understanding of nuclear energy public perception was the key factor affecting to re-consideration of the nuclear energy program. Thailand Institute of Nuclear Technology and its alliances together developed the classification model for the nuclear energy public perception from the big data comments on social media using Facebook using deep transfer learning. The objective was to insight into the Thailand nuclear energy public perception on Facebook social media platform using sentiment analysis. The supervised learning was used to generate up-to-date classification model with more than 80% accuracy to classify the public perception on nuclear power plant news on Facebook from 2009 to 2022. The majority of neutral sentiments (80%) represented the opportunity for Thailand to convince people to receive a better nuclear perception. Negative sentiments (14%) showed support for other alternative energies due to nuclear accident concerns while positive sentiments (6%) expressed support for innovative nuclear technologies.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제3권2호
• /
• pp.134-146
• /
• 2009

Traffic classification seeks to assign packet flows to an appropriate quality of service(QoS) class based on flow statistics without the need to examine packet payloads. Classification proceeds in two steps. Classification rules are first built by analyzing traffic traces, and then the classification rules are evaluated using test data. In this paper, we use self-organizing map and K-means clustering as unsupervised machine learning methods to identify the inherent classes in traffic traces. Three clusters were discovered, corresponding to transactional, bulk data transfer, and interactive applications. The K-nearest neighbor classifier was found to be highly accurate for the traffic data and significantly better compared to a minimum mean distance classifier.

• 한국도서관정보학회지
• /
• 제18권
• /
• pp.139-192
• /
• 1991

Though the computer has become deeply entrenched as the major tool in information processing(library works), it may be obvious that automatic book classification techniques ate still under experimentation, and the techniques have not yet been tested against the criterion of usefulness. The purpose of this study is to design of knowledge base for automatic book classification which can be put to use in library operation, and to present a methodology of application of the automatic classification into the library. Since the enumerative classification schemes which are existing are manual systems, it cannot be applied to the automatic classification, the principle of faceted classification based on concept analysis is brought in and studied. The result of this study are summarized as follows : 1. The design of knowledge base confined the field of agriculture and medicine. 2. If title is entered by the computer keyboard it will be searched in knowledge base, and then be classified by the principle of automatic classification. 3. Program flowcharts are designed as a bases of classification procedures for automatic subject recognition and classification. 4. 283 books in agriculture, 196 books in medicine were drawn at random from Taegu University Library and Young-Nal Medical Center Library respectively. 5. The experiment of automatic classification is performed 143 books in agriculture 166 books in medicine except for other subject books. 6. It was proved that automatic book classification is possible by design of knowledge base. In addition the expected values from design of knowledge base for automatic book classification are as follows : 1. The prompt and accurate process of classification is possible. 2. Though some title is classified in any library, it can be classified the some classification number by a program. 3. The user can retrieve the classification codes of books for which he or she wants to search through the computer. 4. Since the concept coordination method is employed the representing of a multisubject concept is make simple. 5. By performing automatic book classification the automation of total system can be achieved. 6. The efficient international information transfer will be advanced since all the institution maintain unified classification number.

• 한국기록관리학회지
• /
• 제12권3호
• /
• pp.71-92
• /
• 2012

공공기록물 관리에 관한 법률에 따른 기록물관리전문요원의 배치가 이루어지면서 기록물관리는 어느 정도 자리를 잡아가고 있으며, 법률에 따른 기록물관리를 이루기 위해 많은 노력을 기울이고 있다. 기록물관리는 기록물의 생산 분류 정리 이관 수집 평가 폐기 보존 공개 활용 및 이에 부수되는 제반업무를 말한다. 이중에서도 기록물 이관은 해당 기록물이 처리과에서 기록관으로 관리주체가 변경되는 최초 단계를 수행하는 중요한 업무라고 할 수 있다. 이에 따라 본 연구에서는 부산지역 16개 기초자치단체의 이관현황을 살펴보고, 기관의 기록물관리전문요원들의 인터뷰를 통해 이관진행과정에서 발생하는 문제점을 살펴보고 비전자기록물 이관업무 개선방안을 제시하였다.

• 대한기계학회논문집B
• /
• 제35권12호
• /
• pp.1383-1389
• /
• 2011

본 연구는 태양열 발전에 사용하는 공기식 다채널 체적식 흡수기의 일관성 있는 열전달 해석에 초점을 두고 있다. 이를 위해 흡수 소재 물성과 채널 형상 변화의 영향을 몬테카를로 광선추적법에 기반한 광학 모델과 전도, 대류, 복사를 고려한 1 차원 열전달 모델에 동시에 반영하였다. 광학 모델 결과는 채널 반경 대비 길이의 형상비가 매우 커서 대부분의 태양 에너지는 15 mm 이내의 짧은 길이에서 흡수됨을 증명하고 있다. 복사 열손실 분류를 통해 채널의 낮은 흡수율에서는 방사 손실은 줄지만 반사손실이 증가하여 흡수기 효율이 감소하는 것을 보였다. 큰 채널 반경이나 작은 질량 유량으로 인해 흡수기 평균 온도가 상승할 때, 방사 손실과 반사 손실 모두 증가하지만 방사 손실의 영향이 더 큰 것으로 나타났다.

• 품질경영학회지
• /
• 제32권3호
• /
• pp.198-215
• /
• 2004

Technology competitiveness evaluates environmental and engineered technology and process at both the scientific and market levels. There are increasing concerns to measure the effects of the technology variables on the potential market feasibility levels. However, there are very little empirical analysis studies on that issue. This study investigates the impacts of technology variables on the levels of market feasibility based on 230 data obtained from Korea Technology Transfer Center. As various statistical analysis, the canonical discriminant model, logit discriminant model and classification model were used and their results were compared. This study results showed that major technology variables had very significant relations to discriminate high and low categories of market feasibility. Finally, this study will help building management strategies to level up the potential market performance and also help financial Institutions to decide funds needed for small-sized technology firms.

• 한국경제지리학회지
• /
• 제15권2호
• /
• pp.332-342
• /
• 2012

본 연구는 합리적 버스 환승체계 구축을 위한 버스정류장의 환승센터로서의 유형 구분에 목적을 두고 있다. 이 분야 기존 연구는 주로 버스정류장 이용 수요의 특성과 버스정류장을 역세권으로 보았을 때 주변의 토지이용 특성을 확인하고, 이를 근거로 정류장의 유형을 구분한 후 구분된 유형들 각각의 특성을 요약하는 방식으로 진행되었다. 이러한 전통적 역세권 연구들의 공통적인 문제점은 대표적 연구 변수인 토지이용 특성과 정류장 이용 특성 등 횡단면적 snapshot의 특성만을 고려하여 환승의 본질인 통행 연계의 detail을 확보하지 못한다는 데 있다. 이에 본 연구에서는 환승통행 발생 정류장의 기능 구분을 위해 통행연계 변수로서 교통수단연계, 경유지연계, 이용시간연계 등의 변수 값이 각 정류장이 환승센터로서의 특성을 고려할 때 어느 정도와 방향인지를 확인토록 한다. 이를 위해 2009년 4월 20일 월요일 하루 동안 경기도 버스에 승하차한 통행 샘플을 분석하였다. 분석 결과 버스정류장은 연계성 관련 변수를 기준으로 비교적 뚜렷한 구분이 가능하였다. 이러한 결과는 환승센터 입지 선정이나 설계에 유용한 정보를 줄 것으로 기대된다.