• 한국시뮬레이션학회:학술대회논문집
• /
• 한국시뮬레이션학회 2001년도 The Seoul International Simulation Conference
• /
• pp.321-324
• /
• 2001

The robot soccer simulation game is a dynamic multi-agent environment. In this paper we suggest a new reinforcement learning approach to each agent's dynamic positioning in such dynamic environment. Reinforcement Beaming is the machine learning in which an agent learns from indirect, delayed reward an optimal policy to choose sequences of actions that produce the greatest cumulative reward. Therefore the reinforcement loaming is different from supervised teaming in the sense that there is no presentation of input-output pairs as training examples. Furthermore, model-free reinforcement loaming algorithms like Q-learning do not require defining or loaming any models of the surrounding environment. Nevertheless it can learn the optimal policy if the agent can visit every state-action pair infinitely. However, the biggest problem of monolithic reinforcement learning is that its straightforward applications do not successfully scale up to more complex environments due to the intractable large space of states. In order to address this problem, we suggest Adaptive Mediation-based Modular Q-Learning(AMMQL) as an improvement of the existing Modular Q-Learning(MQL). While simple modular Q-learning combines the results from each learning module in a fixed way, AMMQL combines them in a more flexible way by assigning different weight to each module according to its contribution to rewards. Therefore in addition to resolving the problem of large state space effectively, AMMQL can show higher adaptability to environmental changes than pure MQL. This paper introduces the concept of AMMQL and presents details of its application into dynamic positioning of robot soccer agents.

• 한국태양에너지학회:학술대회논문집
• /
• 한국태양에너지학회 2009년도 춘계학술발표대회 논문집
• /
• pp.184-189
• /
• 2009

In order to improve the operation of energy systems, it is necessary for the urban communities to have reliable optimization routines, both computerized and manual, implemented in their organizations. However, before a production plan for the energy system units can be constructed, a prediction of the energy systems first needs to be determined. So, several methodologies have been proposed for energy demand prediction, but due to uncertainties in urban community, many of them will fail in practice. The main topic of this paper has been the development of a method for energy demand prediction at urban community. Energy demand prediction is important input parameters to plan for the energy planing. This paper presents a energy demand prediction method which estimates heat and electricity for various building categories. The method has been based on artificial neural networks(ANN). The advantage of ANN with respect to the other method is their ability of modeling a multivariable problem given by the complex relationships between the variables. Also, the ANN can extract the relationships among these variables by means of learning with training data. In this paper, the ANN have been applied in oder to correlate weather conditions, calendar data, schedules, etc. Space heating, cooling, hot water and HVAC electricity can be predicted using this method. This method can produce 10% of errors hourly load profile from individual building to urban community.

• Asian Pacific Journal of Cancer Prevention
• /
• 제17권8호
• /
• pp.3855-3859
• /
• 2016

Colorectal cancer (CRC) is reproted to be the third most common cancer worldwide and the fourth most common cause of cancer related deaths. CRC is considered to be a multifactorial disease whose risk varies due to the complex interaction between individual genetic basis and disposure to multiple endogenous factors. Glutathione S-transferases are pro-carcinogenic in CRC and are required for the conjugation between chemotherapeutics and broad spectrum xenobiotics. One hundred and eleven patients with CRC and 128 control subjects without any cancer history were enrolled in this study. Multiplex PCR was applied to determine polymorphisms for the GSTT1 and M1 genes, and PCR-RFLP was applied for the GSTP1 (Ile105Val) gene polymorphism. Values p<0.05 were defined as statistically significant. We detected a significant high correlation between predisposition for CRC and presence of the Ile/Ile genotype of the GSTP1 (IIe105Val) gene polymorphism, but we did not find a significant relationship between predisposition for CRC and GSTT1 and M1 deletion polymorphisms. In addition, we did not determine a relationship between GSTT1, M1 and P1 gene polymorphisms and any clinicopathological features of CRC. GSTT1 null/GSTM1 positive and GSTT1 null/GSTM1 positive/GSTP1 Ile/Ile genotypes were significantly higher in the patient group. Our results revealed that there is no relationship among CRC, its clinicopathologic features, and GSTT1 M1 gene polymorphisms. However, there was a significant correlation between CRC and the GSTP1 Ile/Ile genotype. Further studies with larger patient groups are required to delineate the relationships between GST gene polymorphisms and the clinicopathologic features of CRC in Turkey.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권6호
• /
• pp.2480-2496
• /
• 2020

Considering that high-dose X-ray radiation during CT scans may bring potential risks to patients, in the medical imaging industry there has been increasing emphasis on low-dose CT. Due to complex statistical characteristics of noise found in low-dose CT images, many traditional methods are difficult to preserve structural details effectively while suppressing noise and artifacts. Inspired by the deep learning techniques, we propose a densely connected residual network (DCRN) for low-dose CT image noise cancelation, which combines the ideas of dense connection with residual learning. On one hand, dense connection maximizes information flow between layers in the network, which is beneficial to maintain structural details when denoising images. On the other hand, residual learning paired with batch normalization would allow for decreased training speed and better noise reduction performance in images. The experiments are performed on the 100 CT images selected from a public medical dataset-TCIA(The Cancer Imaging Archive). Compared with the other three competitive denoising algorithms, both subjective visual effect and objective evaluation indexes which include PSNR, RMSE, MAE and SSIM show that the proposed network can improve LDCT images quality more effectively while maintaining a low computational cost. In the objective evaluation indexes, the highest PSNR 33.67, RMSE 5.659, MAE 1.965 and SSIM 0.9434 are achieved by the proposed method. Especially for RMSE, compare with the best performing algorithm in the comparison algorithms, the proposed network increases it by 7 percentage points.

• 디지털융복합연구
• /
• 제13권4호
• /
• pp.377-385
• /
• 2015

본 연구의 목적은 2014 코리아컵 국제체조대회 링 종목 결승전에 참여한 국내외 우수선수를 대상으로 난도 점수, 실행 점수 및 실시기술에 대한 난도요소 분포, 그룹요소별 기술 분포 등에 대한 연기내용을 분석한 융복합연구로서 경기력 향상을 위한 훈련방향 설정과 연기구성 및 기술 습득 전략 수립에 기여하고자 수행하였다. 자료 수집은 경기 성적표와 심판들에게 배포되는 경기결과 자료 및 경기영상을 촬영한 것을 이용하였다. 연기내용 분석 결과에 대한 결론은 다음과 같다. 첫째, 우리나라 선수들의 경기기술은 난도가 높은 힘 버티기 보다는 스윙기에 의존하는 특성을 보였다. 둘째, 스윙기 기술에 익숙한 특성을 살려서 난도가 높은 Jonasson과 Roll bwd. slowly with str. arms and body to swallow(2s.) 기술 습득이 필요하다. 셋째, 버티기 기술과 고난도 기술 습득을 위한 기술 감각훈련 및 근력 강화 프로그램이 개발되어야 한다.

• 산업경영시스템학회지
• /
• 제39권2호
• /
• pp.129-137
• /
• 2016

To identify the cause of the error and maintain the health of system, an administrator usually analyzes event log data since it contains useful information to infer the cause of the error. However, because today's systems are huge and complex, it is almost impossible for administrators to manually analyze event log files to identify the cause of an error. In particular, as OpenStack, which is being widely used as cloud management system, operates with various service modules being linked to multiple servers, it is hard to access each node and analyze event log messages for each service module in the case of an error. For this, in this paper, we propose a novel message-based log analysis method that enables the administrator to find the cause of an error quickly. Specifically, the proposed method 1) consolidates event log data generated from system level and application service level, 2) clusters the consolidated data based on messages, and 3) analyzes interrelations among message groups in order to promptly identify the cause of a system error. This study has great significance in the following three aspects. First, the root cause of the error can be identified by collecting event logs of both system level and application service level and analyzing interrelations among the logs. Second, administrators do not need to classify messages for training since unsupervised learning of event log messages is applied. Third, using Dynamic Time Warping, an algorithm for measuring similarity of dynamic patterns over time increases accuracy of analysis on patterns generated from distributed system in which time synchronization is not exactly consistent.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 1996년도 10월 학술대회지
• /
• pp.456-463
• /
• 1996

In this paper, we discussed three cases to see the effects of the characteristics of Hangul writing system. In applications such as computer Hangul shorthands for ordinary people and pushbuttons with Hangul characters engraved, we found that there is much advantage in using Hangul. In case of Hangul Transliteration, we discussed some problems which are related with the characteristics of Hangul writing system. Shorthands use 3-set keyboards in England, America, and Korea. We saw how ordinary people can do computer Hangul shorthands, whereas only experts can do computer shorthands in other countries. Specifically, the facts that 1) Hangul characters are grouped into syllables (syllabic blocks) and that 2) there is already a 3-set Hangul keyboard for ordinary people allow ordinary people to do computer Hangul shorthands without taking special training as with English shorthands. This study was done by the author under the codename of 'Sejong 89'. In contrast like QWERTY or DVORAK, a 2-set Hangul keyboard cannot be used for shorthands. In case of English pushbuttons, one digit is associated with only one character. However, by engraving only syllable-initial characters on the phone pushbuttons, we can associate one Hangul "syllable" with one digit. Therefore, for a given number of digits, we can associate longer words or more meaningful words in Hangul than in English. We discussed the problems of the Hangul Transliteration system proposed by South Korea and suggested their solutions, if available. 1) We are incorrectly using the framework of transcription for transliteration. To solve the problem, the author suggests that a) we include all complex characters in the transliteration table, and that b) we specify syllable-initial and -final characters separately in the table. 2) The proposed system cannot represent independent characters and incomplete syllables. 3) The proposed system cannot distinguish between syllable-initial and -final characters.

• 대한원격탐사학회지
• /
• 제36권5_2호
• /
• pp.961-973
• /
• 2020

본 논문에서는 CNN (Convolutional Neural Network) 기반의 영상융합 기법을 제안하고자 하였다. 딥러닝 구조의 성능을 향상시키기 위하여, CNN 기법에서 대표적인 합성곱(convolution) 방법으로 알려진 팽창된 합성곱(dilated convolution) 모델을 활용하여 모델의 깊이와 복잡성을 증대시키고자 하였다. 팽창된 합성곱을 기반으로 하여 학습과정에서의 효율을 향상시키기 위하여 잔차 네트워크(residual network)도 활용하였다. 또한, 본 연구에서는 모델학습을 위하여 전통적인 L1 노름(norm) 기반의 손실함수와 함께, 공간 상관도를 활용하였다. 본 연구에서는 전정색 영상만을 이용하거나 전정색 영상과 다중분광 영상을 모두 활용하여 구조에 적용한 DRNet을 개발하여 실험을 수행하였다. KOMPSAT-3A를 활용한 전정색 영상과 다중분광 영상을 이용한 DRNet은 융합영상의 분광특성에 과적합되는 결과를 나타냈으며, 전정색 영상만을 이용한 DRNet이 기존 기법들과 비교하여 융합영상의 공간적 특성을 효과적으로 반영함을 확인하였다.

• 한국HCI학회논문지
• /
• 제1권1호
• /
• pp.29-36
• /
• 2006

촉감 제시 방법은 다른 사람에게 방해를 주지 않고 은밀하게 정보를 전달할 수 있는 장점이 있으며, 특히 시각 혹은 청각 장애인에게는 반드시 필요한 정보 전달의 수단이다. 또한 촉감을 이용한 정보의 전달은 시각 또는 청각을 이용한 정보전달의 방법을 보완하거나 때로는 대체할 수도 있다. 본 논문에서는 웨어러블, 모바일, 또는 유비쿼터스 컴퓨팅 환경에서 사용할 수 있는 착용 가능한 진동촉감 제시 장치를 제안한다. 이 진동촉감 제시 장치는 25개의 진동모터를 $5{\times}5$의 형태로 배열하여 문자, 숫자뿐만 아니라 다양하고 복잡한 패턴을 표시할 수 있다. 코인형 진동모터 각각을 스펀지로 감싸고 푹신푹신한 재질의 패드에 세워서 배열하여 진동의 퍼짐을 최소화하고 사람의 글씨 쓰는 순서에 따라 진동모터를 순차적으로 구동시키는 새로운 추적모드를 제안하여 사용자의 문자 및 숫자 인식률을 크게 향상시켰다. 사용자 성능 평가에서는 사용자의 발등에 영문 알파벳을 표시하여 86.7%의 인식률을 얻었으며 주행 또는 주차 중인 운전자에게 방향 정보를 제시한 실험에서도 83.9%의 정답률을 확인하였다. 또한 진동촉감 제시장치를 이용하여 휴대폰에서의 발신자 정보표시를 한다거나 네비게이션 시스템에 적용할 수 있는 등의 유용한 응용분야를 제시하였다.

• Asian Pacific Journal of Cancer Prevention
• /
• 제14권8호
• /
• pp.4819-4822
• /
• 2013

Background: Lung cancer is the leading cause of cancer mortality in the world. Many factors can protect against or facilitate its development. A TNF family member TRAIL, has a complex physiological role beyond that of merely activating the apoptotic pathway in cancer cells. Vitamin D is converted to its active form locally in the lung, and is also thought to play an important role in lung health. Our goal was to investigate the possible clinical significance of serum sTRAIL and 1,25-dihydroxyvitamin D(3) levels in patients with non-small cell lung cancer (NSCLC). Materials and Methods: Totals of 18 consecutive adenocarcinoma and 22 squamous cell carcinoma patients with stage-IV non-small cell lung cancer referred to our institute were included in this study. There were 12 men and 6 women, with ages ranging from 38 to 97 (mean 60.5) years with adenocarcinoma, and 20 men and 2 women, with ages ranging from 46 to 80 (mean 65) years with squamous cell carcinoma. Serum levels of sTRAIL and 1,25-dihydroxyvitamin D(3) were measured in all samples at the time of diagnosis. Results: sTRAIL levels in NSCLC patients were higher than in the control group. Although there was no correlation between patient survival and sTRAIL levels, the highest sTRAIL levels were correlated with age and cigarette smoking in the adenocarcinoma patients. sTRAIL level in healthy individuals were correlated with serum 1,25-dihydroxyvitamin D(3). Conclusions: Serum sTRAIL concentrations were increased in NSCLC patients, and correlated with age and smoking history, but not with overall survival.