• 예술인문사회 융합 멀티미디어 논문지
• /
• 제7권10호
• /
• pp.935-943
• /
• 2017

많은 양의 데이터 기반으로 학습하는 neural network 중 이미지 분류나 음성 인식 등에 사용되어 지고 있는 CNN(Convolution neural network)는 현재까지도 우수한 성능을 가진 구조로 계속적으로 발전되고 있다. 제한된 자원을 가진 임베디드 시스템에서 활용하기에는 많은 어려움이 있다. 그래서 미리 학습된 가중치를 사용하지만 여전히 한계점이 있기 때문에 이를 해결하기 위해 GPU의 범용 연산을 위해서 사용하는 GP-GPU(General-Purpose computing on Graphics Processing Units)를 활용하는 추세다. CNN은 단순하고 반복적인 연산을 수행하기 때문에 SIMT(Single Instruction Multiple Thread)기반의 GPGPU에서 스레드 할당과 활용 방법에 따라 연산 속도가 많이 달라진다. 스레드로 Convolution 연산과 Pooling 연산을 수행할 때 쉬어야 하는 스레드가 발생하는 데 이러한 문제를 해결하기 위해 남은 스레드가 다음 피쳐맵과 커널 계산에 활용되는 방법을 사용함으로써 연산 속도를 증가시켰다.

• 한국정보통신학회논문지
• /
• 제16권9호
• /
• pp.2056-2063
• /
• 2012

항만 터미널 내에서 컨테이너의 이동을 위해 야드 트랙터와 크레인 차량을 이용한다. 차량의 빠른 배치를 통한 효율적인 처리를 위해 차량의 위치정보가 중요한 요소로 떠오르고 있다. 현재 대부분의 항만 터미널에서 차량의 위치 정보는 해당 차량이 마지막으로 발생시킨 이벤트를 기반으로 하여 추정하나 차량이 발생시키는 이벤트는 발생 빈도가 낮으며 추정하는 위치 오차가 크게 발생하는 문제가 있다. 본 논문에서는 이러한 문제를 극복하기 위해 차량의 위치를 측정하기 위한 무선 통신 기반 실시간 위치 측정 시스템을 제안한다. 항만 터미널 환경은 컨테이너의 적재로 위치 측정 오차가 크게 발생한다. 이를 해결하기 위해 항만환경에 적합한 하드웨어를 설계 및 구현하고 항만 터미널의 추가적인 문제를 해결한 향상된 다단계 위치 측정 기법을 적용하여 위치 정보의 정확도를 향상시켰다. 제안하는 시스템을 현대 부산 신항만 터미널(HPNT)에서 측정 정밀도를 테스트한 결과 CEP 기준으로 평균 5.87 미터 오차수준의 정확도를 확인하였다.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 1998년도 추계학술대회 논문집
• /
• pp.392-395
• /
• 1998

This paper suggests the“infinite-retailer model”to approximate expected backorders per cycle of the One-warehouse N-retailer distribution system where the warehouse holds back some of the replenishment quantity to satisfy retailer backorders at the end of the cycle through direct shipping to customers. The main objective is to show the functional relationship between the warehouse inventory and the expected backorders per cycle. We illustrate the relationship using a uniform demand case.

• 항공우주시스템공학회지
• /
• 제8권4호
• /
• pp.39-43
• /
• 2014

This paper examines the statistical process that should be performed with caution in the composite material qualification and equivalency process, and describes statistically significant considerations on outlier finding and handling process, data pooling through normalization process, review for data distributions and design allowables determination process for structural analysis. Based on these considerations, the need for guidance on statistical process for aircraft manufacturers who use the composite material properties database are proposed.

• 유통과학연구
• /
• 제13권6호
• /
• pp.97-104
• /
• 2015

Purpose - The distribution of agricultural products is changing due to recent shifts in environmental free trade. Specifically, the competitiveness of domestic agricultural products has weakened as a result of the Korea-China Financial Trade Agreement. Agricultural producers are faced with increasing difficulties and organized production centers are growing in importance daily. To overcome this crisis, agricultural producer organizations are vying for environment-friendly agricultural certifications, Good Agriculture Practices (GAP) and Hazard Analysis and Critical Control Point (HACCP). In particular, as consumer demand for higher safety grows, farmers are increasing their certification rates. Therefore, this certification system is expected to help strengthen the competitiveness of agricultural producer organizations. Research design/data/methodology - Organized production centers are classified by certification. A survey was conducted with 91 organizations using factor analysis and logistic regression analysis for the examination. The factor analysis results are as follows. Raw material procurement, education·specialization, marketing, joint business, organizing ability, business management, effectiveness, certification, and larger organizations were classified as the nine types of factors. These factors affect the organized production centers and are used in the logistic regression analysis. The purpose of such research and analysis is to suggest a direction for future production center policies. Results - The basic statistical results are as follows: analysis of the producer organizations of 91 sites, average number of members per site of 1,624, and average sales of 25,961 million won. Additionally, the average income per farmer is 175 million won, and the pooling system rate is 53.5%. The factor analysis results are as follows. Factor 1 consists of contract cultivation, ongoing shipment, selection subdivision, traceability, and major retailer management. Factor 2 consists of manual cultivation, specialty selection, education program, and R&D. Factor 3 consists of advertising, various dealers, various sales strategies, and a unified sales counter. Factor 4 consists of agricultural materials co-purchase, policy support, co-shipment, and incentives. Factor 5 consists of the co-selection and pooling system. Factor 6 consists of co-branding and operating by the organization's article. Factor 7 consists of the buy-sell ratio and rate of operation of the agriculture promotion center. Factor 8 consists of bargaining power in volume and participation rate of farmer certification. Factor 9 consists of increasing new subscribers. The logistic regression analysis results are as follows. Considering the results by type of certification, the environment-friendly agricultural certification type and the GAP certification type have a (+) influence. GAP and HACCP certification types affecting the education·specialization factor have a (+) influence. Considering the results for each type of certification, the environment-friendly agricultural certification types on the effectiveness factor have (-) influence; the HACCP certification types on the organizing ability and effectiveness factor have a (-) influence. Conclusions - Agricultural producer organizations should develop plans as follows: The organizations need to secure education for agricultural production; increase the pooling system ratio for sustainable organizational development; and, finally, expand the number of agricultural producer organizations.

• Journal of Preventive Medicine and Public Health
• /
• 제50권2호
• /
• pp.91-99
• /
• 2017

Objectives: As in many low-income and middle-income countries, out-of-pocket (OOP) payments by patients or their families are a key healthcare financing mechanism in Bangladesh that leads to economic burdens for households. The objective of this study was to identify whether and to what extent socioeconomic, demographic, and behavioral factors of the population had an impact on OOP expenditures in Bangladesh. Methods: A total of 12 400 patients who had paid to receive any type of healthcare services within the previous 30 days were analyzed from the Bangladesh Household Income and Expenditure Survey data, 2010. We employed regression analysis for identify factors influencing OOP health expenditures using the ordinary least square method. Results: The mean total OOP healthcare expenditures was US dollar (USD) 27.66; while, the cost of medicines (USD 16.98) was the highest cost driver (61% of total OOP healthcare expenditure). In addition, this study identified age, sex, marital status, place of residence, and family wealth as significant factors associated with higher OOP healthcare expenditures. In contrary, unemployment and not receiving financial social benefits were inversely associated with OOP expenditures. Conclusions: The findings of this study can help decision-makers by clarifying the determinants of OOP, discussing the mechanisms driving these determinants, and there by underscoring the need to develop policy options for building stronger financial protection mechanisms. The government should consider devoting more resources to providing free or subsidized care. In parallel with government action, the development of other prudential and sustainable risk-pooling mechanisms may help attract enthusiastic subscribers to community-based health insurance schemes.

• 한국전자거래학회지
• /
• 제20권3호
• /
• pp.89-112
• /
• 2015

본 연구는 모바일 시대의 진입, 글로벌 경쟁격화, 및 의료서비스 요구사항의 확대 등, 의료경영환경의 급격한 변화에 부응하기 위해 새로운 IT 기반 의료서비스가 필수적임에도 불구하고 이를 실현하고 있지 못한 중소형 규모 병원에 클라우드 기반 의료서비스를 제공할 수 있는 '중소형 병원의 클라우드 병원정보시스템(CHISSMH, Cloud Hospital Information System for Small Medium Hospitals)'의 아키텍처와 서비스 모델을 제시하였다. 스마트폰 시대에 진입하면서 개인단위의 클라우드 서비스는 일반화되었지만 비즈니스 단위의 서비스, 특히 병원정보시스템에 대한 클라우드 서비스의 도입은 초기단계이기에 이를 활성화하고자하는 차원에서 CHISSMH의 아키텍처를 개발하여 제시하였다. 특히 본 연구는 병원산업계에 클라우딩 서비스 도입 활성화를 위해 사용자관점이 아닌 서비스 제공자 관점에서 이에 대한 해결책을 제시하였다. 즉, 서비스 제공자가 고품질 및 합리적 가격의 클라우드 의료 서비스를 제공한다면 비록 일부 저해요인이 존재하더라도 도입이 활성화될 것으로 기대한다. 이를 위해 CHISSMH는 하드웨어뿐만 아니라 애플리케이션까지 가상화를 시도하여 자원공용화(Resource Pooling)를 추구함으로써 운영비용의 최소화를 통해 합리적 가격의 서비스를 제공할 수 있는 기술 기반 아키텍처와 서비스 모델을 제시하였다. 또한 CHISSMH이 15개 중소병원을 대상으로 서비스한 자료를 분석하여 CHISSMH의 합리성과 유용성을 제시하였으며, 전통적 소유형 HIS와 비교하여 44.5%의 IT 서비스 비용이 절감되는 것으로 나타났다.

• 한국정보전자통신기술학회논문지
• /
• 제12권6호
• /
• pp.567-572
• /
• 2019

본 논문에서는 이진영상과 이진커널을 사용하여 컨볼루션, 풀링, ReLU 연산을 수행하는 이진 CNN 연산 알고리즘을 제안한다. 256 그레이스케일 영상을 8개의 비트평면으로 분해하고, -1과 1로 구성되는 이진커널을 사용하는 방법이다. 이진영상과 이진커널의 컨볼루션 연산은 가산과 감산으로 수행한다. 논리적으로는 XNOR 연산과 비교기로 구성되는 이진연산 알고리즘이다. ReLU와 풀링 연산은 각각 XNOR와 OR 논리연산으로 수행한다. 본 논문에서 제안한 알고리즘의 유용성을 증명하기 위한 실험을 통해, CNN 연산을 이진 논리연산으로 변환하여 수행할 수 있음을 확인한다. 이진 CNN 알고리즘은 컴퓨팅 파워가 약한 시스템에서도 딥러닝을 구현할 수 있는 알고리즘으로 스마트 폰, 지능형 CCTV, IoT 시스템, 자율주행 자동차 등의 임베디드 시스템에서 다양하게 적용될 수 있는 시스템이다.

• 한국음향학회:학술대회논문집
• /
• 한국음향학회 1994년도 제11회 음성통신 및 신호처리 워크샵 논문집 (SCAS 11권 1호)
• /
• pp.223-228
• /
• 1994

We propose a novel method to incorporate temporal correlations into a speech recognition system based on the conventional hidden Markov model. With the proposed method using the extended logarithmic pool, we approximate a joint conditional PD by separate conditional PD's associated with respective components of conditions. We provide a constrained optimization algorithm with which we can find the optimal value for the pooling weights. The results in the experiments of speaker-independent continuous speech recognition with frame correlations show error reduction by 13.7% with the proposed methods as compared to that without frame correlations.

• IEIE Transactions on Smart Processing and Computing
• /
• 제6권1호
• /
• pp.10-17
• /
• 2017

We propose classification algorithms for human and dog movement. The proposed algorithms use micro-Doppler signals obtained from humans and dogs moving in four different directions. A two-stage classifier based on a support vector machine (SVM) is proposed, which uses a radial-based function (RBF) kernel and $16^{th}$-order linear predictive code (LPC) coefficients as feature vectors. With the proposed algorithms, we obtain the best classification results when a first-level SVM classifies the type of movement, and then, a second-level SVM classifies the moving object. We obtain the correct classification probability 95.54% of the time, on average. Next, to deal with the difficult classification problem of human and dog running, we propose a two-layer convolutional neural network (CNN). The proposed CNN is composed of six ($6{\times}6$) convolution filters at the first and second layers, with ($5{\times}5$) max pooling for the first layer and ($2{\times}2$) max pooling for the second layer. The proposed CNN-based classifier adopts an auto regressive spectrogram as the feature image obtained from the $16^{th}$-order LPC vectors for a specific time duration. The proposed CNN exhibits 100% classification accuracy and outperforms the SVM-based classifier. These results show that the proposed classifiers can be used for human and dog classification systems and also for classification problems using data obtained from an ultra-wideband (UWB) sensor.