• Journal of the Society of Disaster Information
• /
• v.20 no.1
• /
• pp.199-205
• /
• 2024

Purpose: This study aims to improve the recognition rate of Auto People Counting (APC) in accurately identifying and providing information on remaining evacuees in disaster-vulnerable facilities such as nursing homes to firefighting and other response agencies in the event of a disaster. Methods: In this study, a baseline model was established using CNN (Convolutional Neural Network) models to improve the algorithm for recognizing images of incoming and outgoing individuals through cameras installed in actual disaster-vulnerable facilities operating APC systems. Various algorithms were analyzed, and the top seven candidates were selected. The research was conducted by utilizing transfer learning models to select the optimal algorithm with the best performance. Results: Experiment results confirmed the precision and recall of Densenet201 and Resnet152v2 models, which exhibited the best performance in terms of time and accuracy. It was observed that both models demonstrated 100% accuracy for all labels, with Densenet201 model showing superior performance. Conclusion: The optimal algorithm applicable to APC among various artificial intelligence algorithms was selected. Further research on algorithm analysis and learning is required to accurately identify the incoming and outgoing individuals in disaster-vulnerable facilities in various disaster situations such as emergencies in the future.

• Journal of Wetlands Research
• /
• v.21 no.2
• /
• pp.163-172
• /
• 2019

The USLE P factor is a factor that varies depending on how croplands are managed and cultivated. Previous studies tend to overestimate the amount of soil loss because the factor was estimated from the slope of the watershed rather than the estimate of each cultivated land. In addition, the accuracy of estimating the soil loss is decreasing due to the fact that the factor is calculated without considering various conditions of cultivated land defined by Wishmeier and Smith. In order to overcome these problems, the Ministry of Environment (MOE) has proposed to establish the topsoil notification and calculate the P factor according to the cultivation methods (e.g., tillage system, support practice). However, it is required to apply the conditions proposed in the United States to domestic circumstances as it is causing uncertainties. Thus, this study selected the watersheds where soil loss was serious (Haean, Jaun, Banbyeoncheon), measured the actual slopes and slope lengths, and examined the crop, tillage systems, and support practice for each cultivated land. The P factors were recalculated considering the actual conditions of cultivated land and compared to the factors proposed by the previous studies (MOE). As the result of the study, the P factors calculated based on the previous studies were 0.8 ~ 1.0 in three watersheds. On the other hand, it is confirmed that there is a significant difference between the factors notified by MOE and estimated by reflecting the topography and cultivation methods in this study. Therefore, it is considered that the research for developing the cultivation conditions to calculate the P factor suitable for the domestic environment should be continuously carried out.

• Applied Chemistry for Engineering
• /
• v.20 no.3
• /
• pp.346-350
• /
• 2009

Natural state materials contain a lot of available nutrient components. Among them, natural nutrient substances are utilized not only as the ingredient of functional foods but also as the excipients of functional cosmetics and pharmaceutic. Of these nutrient substances, solubility parameters of each components were calculated to choose the most suitable solvents for solutions. The solubility parameters for each components were composed of the dispersion contribution of the molecular attractive function, the polar contribution of the molecular attractive function and the contribution of the hydrogen bonding force. The chi parameters ($\chi_{12}$) were calculated with the information of the solubility parameter for the solute and solvent and were used as the criteria for the optimal solute-solvent pair. The optimal solvents were suggested with the numerical values of chi parameters for some amino acids.

• Proceedings of the KSME Conference
• /
• 2007.05b
• /
• pp.2609-2614
• /
• 2007

Shell & Tube type Oil Cooler is widely used for hydraulic presses, die casting machines, generation equipments, machine tools and construction heavy machinery. Temperature of oil in the hydraulic system changes viscosity and thickness of oil film. They have a bad effect to performance and lubrication of hydraulic machinery, so it is important to know exactly the heat exchanging efficiency of oil cooler for controlling oil temperature. But most Korean manufacturers do not have test equipment for oil cooler, so they cannot carry out the efficiency test of oil cooler and it is impossible to verify its performance. This paper includes information of construction of necessary utilities for oil cooler test and design and manufacture of test equipment. One can select the optimum product by obtaining performance data through tests of various kinds of oil coolers. And also the paper developed a program which can be easily used for design of 2D and 3D drawings of oil cooler.

• Journal of KIISE:Computing Practices and Letters
• /
• v.9 no.2
• /
• pp.158-165
• /
• 2003

Image similarity is often decided by computing the distance between two feature vectors. Unfortunately, the feature vector cannot always reflect the notion of similarity in human perception. Therefore, most current image retrieval systems use weights measuring the importance of each feature. In this paper new initial weight selection and update rules are proposed for image retrieval purpose. In order to obtain the purpose, database images are first divided into groups based on human perception and, inner and outer query are performed, and, then, optimal feature weights for each database images are computed through searching the group where the result images among retrieved images are belong. Experimental results on 2000 images show the performance of proposed algorithm.

• 한국신재생에너지학회:학술대회논문집
• /
• 2010.06a
• /
• pp.131.1-131.1
• /
• 2010

고분자연료전지(PEMFC)에서 기체확산층(GDL)은 다공성의 카본 종이/천 위에 마이크로한 다공층을 가치는 구조로 촉매층을 지지하고 촉매층과 분리판 사이의 전류전도체 역할을 한다. 또한 촉매층에 연료와 공기 확산 및 생성된 물의 통로 역할을 하며 소수성인 전기전도성 물질로 이루어져 있다. 현재 연료전지에 쓰이는 가스확산층은 대부분 국외 회사에서 제조 수입 사용하는 현황이고 국내에서는 협진 I&C가 연구하고 있으나 상용화는 아직 이루어지지 않고 있다. 본 연구는 탄소섬유의 전도성을 개선하고자 탄소섬유 표면에 금속코팅 시 최적의 접촉계면유지를 위한 표면처리 방법 및 공정을 조사 분석 후 최적 개선방법(농도/온도/압력/시간)을 설정하고자 하였다. 또한 선정된 공정인자별 수준별 시험 후 샘플링 된 시료를 토대로 금속물질이 탄소섬유 표면에 코팅(도금)된 금속-탄소섬유를 대하여 평가하여 최적화시키고자 탄소섬유로부터 carbon paper GDL의 모재를 개발할 계획이다. 앞에서 설명한 바와 같이 탄소섬유를 이용하여 paper making, resin impregnation, molding, carbonization/graphitization의 제조공정을 거쳐 paper형태의 GDL을 생산 및 평가하고자 하였다.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.1
• /
• pp.90-96
• /
• 2014

This paper presents a practical linearization technique for a wide-band bang-bang digital phase locked-loop(BBDPLL) by selecting optimal loop gains. In this paper, limitation of the theoretical design method for BBDPLL is explained, and introduced how to implement practical BBDPLLs with CMOS process. In the proposed BBDPLL, the limited cycle noise is removed by reducing the proportional gain while increasing the integer array and dither gain. Comparing to the conventional BBDPLL, the proposed one shows a small area, low power, linear characteristic. Moreover, the proposed design technique can control a loop bandwidth of the BBDPLL. Performance of the proposed BBDPLL is verified using CppSim simulator.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.3
• /
• pp.209-214
• /
• 2018

This paper suggests simple algorithm of facility location problem in perishable commodities that satisfy with minimum total transportation cost and within the transportation time constraint $L^*$. For this problem, Lee[4] suggests very complex algorithm that decides candidate facility locations, computes total transportation cost for each candidate facility location, then moving the location to optimal location for top two facilities. On the other hand, this paper simply determines the candidate facility locations within $L^*$ using subtree concept, and decides optimal minimal total transportation cost for top two locations in centralized area of required quantity using neighborhood concept.

• Water for future
• /
• v.18 no.4
• /
• pp.347-359
• /
• 1985

This study aims at the development of DP-Model for the establishment of monthly optimal operation policy of single multi-puppose reservoir by which the water demand of downstream can be satisfied under the various physical constraints. Series, A. B. C. of inflow are selected out of future monthly inflow data which are simulated form the past monthly average inflow of Andong dam site. the neight possible alternatives in each inflow series are established in order that Andong dam can supply the water demand of Nagdong main stream of 30% to 100%. Nextly, the reservoir rule curves is derived for each alternative by the detailed seguential analysis of stroage, future inflow and water demand based on the reservoir continuite equation. Then, and alternative which can satisfy the objective function of system based on the rule curves in the exteream is determined as an optimal operation policy from the application of developed DP=Model.

• Annual Conference on Human and Language Technology
• /
• 1997.10a
• /
• pp.175-182
• /
• 1997

지금까지의 한글 문자인식 후처리 연구분야에서 미등록어와 비문맥적 오류 문제는 아직까지 잘 해결하지 못하고 있는 문제이다. 본 논문에서는 단어로서 가능한지를 결정하는 기준으로 확률적 음절 결합 정보를 사용하여 형태소 분석 기법만을 사용했을 때 발생할 수 있는 미등록어 문제를 해결하고, 통사적 기능의 어말 어휘를 고려한 문맥 결합 정보를 이용함으로써 다수의 후보 어절 가운데에서 최적의 후보 어절을 선택하는 방법을 제안한다. 제안된 시스템은 인식기에서 내보낸 후보 음절과 학습된 혼동 음절을 조합하여 하나 이상의 후보 어절을 생성하는 모듈과 통계적 언어 정보를 이용하여 최적의 후보 어절을 선정하는 모듈로 구성되었다. 실험은 1000만 원시 코퍼스에서 추출한 음절 결합 정보와 17만 태깅된 코퍼스에서 추출한 어절 결합 정보를 사용하였으며, 실제 인식 결과에 적용한 결과 문자 단위에서는 94.1%의 인식률을 97.4%로, 어절 단위에서는 87.6%를 96.6%로 향상시켰다. 교정률과 오교정률은 각각 문자 단위에서 56%와 0.6%, 어절 단위에서 83.9%와 1.66%를 보였으며, 전체 실험 어절의 3.4%를 차지한 미등록어 중 87.5%를 올바로 인식하는 한편, 전체 오류의 20.3%인 비문맥 오류에 대해서 91.6%를 올바로 교정하는 후처리 성능을 보였다.