• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.88-88
• /
• 2021

최근 수자원과 수질관리 분야에 자료기반 머신러닝 모델과 딥러닝 모델의 활용이 급증하고 있다. 그러나 딥러닝 모델은 Blackbox 모델의 특성상 고전적인 질량, 운동량, 에너지 보존법칙을 고려하지 않고, 데이터에 내재된 패턴과 관계를 해석하기 때문에 물리적 법칙을 만족하지 않는 예측결과를 가져올 수 있다. 또한, 딥러닝 모델의 예측 성능은 학습데이터의 양과 변수 선정에 크게 영향을 받는 모델이기 때문에 양질의 데이터가 제공되지 않으면 모델의 bias와 variation이 클 수 있으며 정확도 높은 예측이 어렵다. 최근 이러한 자료기반 모델링 방법의 단점을 보완하기 위해 프로세스 기반 수치모델과 딥러닝 모델을 결합하여 두 모델링 방법의 장점을 활용하는 연구가 활발히 진행되고 있다(Read et al., 2019). Process-Guided Deep Learning (PGDL) 방법은 물리적 법칙을 반영하여 딥러닝 모델을 훈련시킴으로써 순수한 딥러닝 모델의 물리적 법칙 결여성 문제를 해결할 수 있는 대안으로 활용되고 있다. PGDL 모델은 딥러닝 모델에 물리적인 법칙을 해석할 수 있는 추가변수를 도입하며, 딥러닝 모델의 매개변수 최적화 과정에서 Cost 함수에 물리적 법칙을 위반하는 경우 Penalty를 추가하는 알고리즘을 도입하여 물리적 보존법칙을 만족하도록 모델을 훈련시킨다. 본 연구의 목적은 대청호의 수심별 수온을 예측하기 위해 역학적 모델과 딥러닝 모델을 융합한 PGDL 모델을 개발하고 적용성을 평가하는데 있다. 역학적 모델은 2차원 횡방향 평균 수리·수질 모델인 CE-QUAL-W2을 사용하였으며, 대청호를 대상으로 2017년부터 2018년까지 총 2년간 수온과 에너지 수지를 모의하였다. 기상(기온, 이슬점온도, 풍향, 풍속, 운량), 수문(저수위, 유입·유출 유량), 수온자료를 수집하여 CE-QUAL-W2 모델을 구축하고 보정하였으며, 모델은 저수위 변화, 수온의 수심별 시계열 변동 특성을 적절하게 재현하였다. 또한, 동일기간 대청호 수심별 수온 예측을 위한 순환 신경망 모델인 LSTM(Long Short-Term Memory)을 개발하였으며, 종속변수는 수온계 체인을 통해 수집한 수심별 고빈도 수온 자료를 사용하고 독립 변수는 기온, 풍속, 상대습도, 강수량, 단파복사에너지, 장파복사에너지를 사용하였다. LSTM 모델의 매개변수 최적화는 지도학습을 통해 예측값과 실측값의 RMSE가 최소화 되로록 훈련하였다. PGDL 모델은 동일 기간 LSTM 모델과 동일 입력 자료를 사용하여 구축하였으며, 역학적 모델에서 얻은 에너지 수지를 만족하지 않는 경우 Cost Function에 Penalty를 추가하여 물리적 보존법칙을 만족하도록 훈련하고 수심별 수온 예측결과를 비교·분석하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.133-153
• /
• 2023

In this paper, we propose a novel approach to investigating brain-signal measurement technology using Electroencephalography (EEG). Traditionally, researchers have combined EEG signals with bio-signals (BSs) to enhance the classification performance of emotional states. Our objective was to explore the synergistic effects of coupling EEG and BSs, and determine whether the combination of EEG+BS improves the classification accuracy of emotional states compared to using EEG alone or combining EEG with pseudo-random signals (PS) generated arbitrarily by random generators. Employing four feature extraction methods, we examined four combinations: EEG alone, EG+BS, EEG+BS+PS, and EEG+PS, utilizing data from two widely-used open datasets. Emotional states (task versus rest states) were classified using Support Vector Machine (SVM) and Long Short-Term Memory (LSTM) classifiers. Our results revealed that when using the highest accuracy SVM-FFT, the average error rates of EEG+BS were 4.7% and 6.5% higher than those of EEG+PS and EEG alone, respectively. We also conducted a thorough analysis of EEG+BS by combining numerous PSs. The error rate of EEG+BS+PS displayed a V-shaped curve, initially decreasing due to the deep double descent phenomenon, followed by an increase attributed to the curse of dimensionality. Consequently, our findings suggest that the combination of EEG+BS may not always yield promising classification performance.

• Journal of The Korean Association For Science Education
• /
• v.26 no.4
• /
• pp.475-491
• /
• 2006

In physics education, the research on students' conceptions has developed in the discussion on the nature and the difficulty of conceptual change. Recently, mental models have been a theoretical background in concrete arguments on "how students' conceptions are constructed or created." Mental models that integrate information in the presented problem and individual knowledge in their long-term memory have important information about not only expressed ideas but also in the thinking process behind the expressed ideas. The purpose of this study is to investigate the forming process and the characteristics of high school student's mental models about circular motion, and how they were changed by instruction. We used the think-aloud method based on the instrument for identifying student's mental models about circular motion, pretest of physics concept, mind map and interview for investigating student's characteristics. The results of the study showed that instructions based on the mental model theory facilitated scientific expressed model, but several factors that affected forming mental models like epistemological belief didn't change scientifically after 3 lessons.

• The Journal of Engineering Geology
• /
• v.32 no.4
• /
• pp.697-723
• /
• 2022

Data-driven models to predict groundwater levels 30 days in advance were developed for 12 groundwater monitoring stations in the middle-Jeju watershed, Jeju Island. Stacked long short-term memory (stacked-LSTM), a deep learning technique suitable for time series forecasting, was used for model development. Daily time series data from 2001 to 2022 for precipitation, groundwater usage amount, and groundwater level were considered. Various models were proposed that used different combinations of the input data types and varying lengths of previous time series data for each input variable. A general procedure for deep-learning-based model development is suggested based on consideration of the comparative validation results of the tested models. A model using precipitation, groundwater usage amount, and previous groundwater level data as input variables outperformed any model neglecting one or more of these data categories. Using extended sequences of these past data improved the predictions, possibly owing to the long delay time between precipitation and groundwater recharge, which results from the deep groundwater level in Jeju Island. However, limiting the range of considered groundwater usage data that significantly affected the groundwater level fluctuation (rather than using all the groundwater usage data) improved the performance of the predictive model. The developed models can predict the future groundwater level based on the current amount of precipitation and groundwater use. Therefore, the models provide information on the soundness of the aquifer system, which will help to prepare management plans to maintain appropriate groundwater quantities.

• Journal of Intelligence and Information Systems
• /
• v.26 no.4
• /
• pp.127-148
• /
• 2020

The data center is a physical environment facility for accommodating computer systems and related components, and is an essential foundation technology for next-generation core industries such as big data, smart factories, wearables, and smart homes. In particular, with the growth of cloud computing, the proportional expansion of the data center infrastructure is inevitable. Monitoring the health of these data center facilities is a way to maintain and manage the system and prevent failure. If a failure occurs in some elements of the facility, it may affect not only the relevant equipment but also other connected equipment, and may cause enormous damage. In particular, IT facilities are irregular due to interdependence and it is difficult to know the cause. In the previous study predicting failure in data center, failure was predicted by looking at a single server as a single state without assuming that the devices were mixed. Therefore, in this study, data center failures were classified into failures occurring inside the server (Outage A) and failures occurring outside the server (Outage B), and focused on analyzing complex failures occurring within the server. Server external failures include power, cooling, user errors, etc. Since such failures can be prevented in the early stages of data center facility construction, various solutions are being developed. On the other hand, the cause of the failure occurring in the server is difficult to determine, and adequate prevention has not yet been achieved. In particular, this is the reason why server failures do not occur singularly, cause other server failures, or receive something that causes failures from other servers. In other words, while the existing studies assumed that it was a single server that did not affect the servers and analyzed the failure, in this study, the failure occurred on the assumption that it had an effect between servers. In order to define the complex failure situation in the data center, failure history data for each equipment existing in the data center was used. There are four major failures considered in this study: Network Node Down, Server Down, Windows Activation Services Down, and Database Management System Service Down. The failures that occur for each device are sorted in chronological order, and when a failure occurs in a specific equipment, if a failure occurs in a specific equipment within 5 minutes from the time of occurrence, it is defined that the failure occurs simultaneously. After configuring the sequence for the devices that have failed at the same time, 5 devices that frequently occur simultaneously within the configured sequence were selected, and the case where the selected devices failed at the same time was confirmed through visualization. Since the server resource information collected for failure analysis is in units of time series and has flow, we used Long Short-term Memory (LSTM), a deep learning algorithm that can predict the next state through the previous state. In addition, unlike a single server, the Hierarchical Attention Network deep learning model structure was used in consideration of the fact that the level of multiple failures for each server is different. This algorithm is a method of increasing the prediction accuracy by giving weight to the server as the impact on the failure increases. The study began with defining the type of failure and selecting the analysis target. In the first experiment, the same collected data was assumed as a single server state and a multiple server state, and compared and analyzed. The second experiment improved the prediction accuracy in the case of a complex server by optimizing each server threshold. In the first experiment, which assumed each of a single server and multiple servers, in the case of a single server, it was predicted that three of the five servers did not have a failure even though the actual failure occurred. However, assuming multiple servers, all five servers were predicted to have failed. As a result of the experiment, the hypothesis that there is an effect between servers is proven. As a result of this study, it was confirmed that the prediction performance was superior when the multiple servers were assumed than when the single server was assumed. In particular, applying the Hierarchical Attention Network algorithm, assuming that the effects of each server will be different, played a role in improving the analysis effect. In addition, by applying a different threshold for each server, the prediction accuracy could be improved. This study showed that failures that are difficult to determine the cause can be predicted through historical data, and a model that can predict failures occurring in servers in data centers is presented. It is expected that the occurrence of disability can be prevented in advance using the results of this study.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.1-25
• /
• 2020

In this paper, we suggest an application system architecture which provides accurate, fast and efficient automatic gasometer reading function. The system captures gasometer image using mobile device camera, transmits the image to a cloud server on top of private LTE network, and analyzes the image to extract character information of device ID and gas usage amount by selective optical character recognition based on deep learning technology. In general, there are many types of character in an image and optical character recognition technology extracts all character information in an image. But some applications need to ignore non-of-interest types of character and only have to focus on some specific types of characters. For an example of the application, automatic gasometer reading system only need to extract device ID and gas usage amount character information from gasometer images to send bill to users. Non-of-interest character strings, such as device type, manufacturer, manufacturing date, specification and etc., are not valuable information to the application. Thus, the application have to analyze point of interest region and specific types of characters to extract valuable information only. We adopted CNN (Convolutional Neural Network) based object detection and CRNN (Convolutional Recurrent Neural Network) technology for selective optical character recognition which only analyze point of interest region for selective character information extraction. We build up 3 neural networks for the application system. The first is a convolutional neural network which detects point of interest region of gas usage amount and device ID information character strings, the second is another convolutional neural network which transforms spatial information of point of interest region to spatial sequential feature vectors, and the third is bi-directional long short term memory network which converts spatial sequential information to character strings using time-series analysis mapping from feature vectors to character strings. In this research, point of interest character strings are device ID and gas usage amount. Device ID consists of 12 arabic character strings and gas usage amount consists of 4 ~ 5 arabic character strings. All system components are implemented in Amazon Web Service Cloud with Intel Zeon E5-2686 v4 CPU and NVidia TESLA V100 GPU. The system architecture adopts master-lave processing structure for efficient and fast parallel processing coping with about 700,000 requests per day. Mobile device captures gasometer image and transmits to master process in AWS cloud. Master process runs on Intel Zeon CPU and pushes reading request from mobile device to an input queue with FIFO (First In First Out) structure. Slave process consists of 3 types of deep neural networks which conduct character recognition process and runs on NVidia GPU module. Slave process is always polling the input queue to get recognition request. If there are some requests from master process in the input queue, slave process converts the image in the input queue to device ID character string, gas usage amount character string and position information of the strings, returns the information to output queue, and switch to idle mode to poll the input queue. Master process gets final information form the output queue and delivers the information to the mobile device. We used total 27,120 gasometer images for training, validation and testing of 3 types of deep neural network. 22,985 images were used for training and validation, 4,135 images were used for testing. We randomly splitted 22,985 images with 8:2 ratio for training and validation respectively for each training epoch. 4,135 test image were categorized into 5 types (Normal, noise, reflex, scale and slant). Normal data is clean image data, noise means image with noise signal, relfex means image with light reflection in gasometer region, scale means images with small object size due to long-distance capturing and slant means images which is not horizontally flat. Final character string recognition accuracies for device ID and gas usage amount of normal data are 0.960 and 0.864 respectively.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.39 no.3
• /
• pp.26-38
• /
• 2011

The purpose of this study was to analyze the commemoration culture of Vietnam War Memorials (VWM) in Vietnam. Through site survey, the researcher selected 23 VWM in Vietnam and analyzed 5 categories: memorial type, design concept and narratives, location and spatial form, landscape elements, and content expressed in landscape details. The results are as follows: 1. Because of the long, drawn out Vietnam War, which lasted from 1955 to 1975, VWM were divided into 10 types mainly as soldier cemeteries based on a traditional memorial style, battlefields and places of tragedies considering sense of place, war museums representing victory and atrocity in war, and peace parks promoting reconciliation and peacemaking. 2. The analysis revealed that the main concepts and narratives of VWM were to value the victims of the Vietnam War, remember soldiers' contributions, highlight the victory in war and resistance to the United States, and express a sense of place. Peacemaking applied only to My Lai Peace Park and Han-Viet Hoa Binh Cong Vien, built by international cooperation. 3. Cemeteries and appreciation memorials were designed to follow a traditional memorial space form that highly regard both axis and symmetry. The design concept at battlefields and places where tragedies occurred depended mainly upon a sense of place and used symbolic landscape elements to compensate for the undefined concept. 4. Sculptures and towers were mainly used to highlight war victory and resistance as the representative style of a Socialist country, weapons and pictures exhibited in war museums and battlefield showed the reality and strain of war. Symbolic elements of Buddhism and Confucianism were often introduced as a way to venerate the memory of deceased persons. 5. The state and heroic actions in the Vietnam War were realistically depicted on sculptures and walls. Also, the symbolic phrase, 'TO-QUOC-GUI-CONG' meaning 'our country remember your achievement', were written on the memorial tower and 'Quagmiire' was used to metaphorically represent the difficulties faced by the U.S. military on battlefields during the war and the uncertainly that pervaded U.S. society in those days. 6. In VWM, ideologies like nationalism, patriotism, socialism, capitalism were mixed and traditional cultures like Buddhism, Confucianism, Taoism were inherent. Differing from their Confucianism culture, war heroes, particularly including women, were often described by sculpture, monument, and pictures and the conflict in and outside the country regarding the Vietnam War was shown. Further study will be required to analyze design characteristics of VWM in the u.s. and to understand the difference in commemoration cultures between Vietnam and the U.S.

• Cartoon and Animation Studies
• /
• s.30
• /
• pp.169-199
• /
• 2013

In various directions of cartoon, vertical stroll direction is opposite to the page direction of existing published cartoon with the popularity of webtoon and established new genre. Lots of studies on published cartoon focus on the cut direction by page, but webtoon doesn't have any concept of page. The pivot of cartoon oriented people is changed from paper to computer monitor as times go by, characteristics of media are changed and media is gradually diversified. Like the strengthening of mobile caused by smart phone's popularity, tablet PC's propagation in public education, etc. cartoon is included to the environment of media which is rapidly changed. In this situation, one of cartoon's unchanged important identities can be the direction made by harmony between picture and text. This thesis analyzed symbolic characteristics and effective value of hyogwatae, mimetic words of cartoon, focusing on works of Heo, Young Man. Hyogwatae just delivers not only sound but also shape, feeling, status, etc. and has significant characteristics by invoking the imaginary structure of literature. Strengths of modern Korean, various linguistic expressions and syllabic systems, let people feel minute feeling of language and difference of emotion and remember the memory through the direct and indirect experiences, so it makes it nuance. Because of the characteristics, representative works of Heo, Young Man have commercialization and writer characteristics, have communicated with people for a long time and have plentiful knowledge of Korean cartoon. The characteristics of hyogwatae in Heo, Young Man's cartoon make a lot of effects for the expression and delivery of cartoon more than the general expectation. When conducting the study focusing on the symbolic process of language, uncertainty and vague standard of judgement caused by the wide factors of study on the direction of general cartoon could be endured. And, through the Heo, Young Man's deep analysis on hyogwatae's direction, readers enjoy the process while inferring actually and intellectually between pictures and sentences. In the process, the equipment stimulating imagination more than pictures, effects and dialogues is hyogwatae. It's reader's equipment of active participation and its strength is symbolic structure.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.253-266
• /
• 2018

This paper proposes a methodology applying sequence tagging methodology to improve the performance of NER(Named Entity Recognition) used in QA system. In order to retrieve the correct answers stored in the database, it is necessary to switch the user's query into a language of the database such as SQL(Structured Query Language). Then, the computer can recognize the language of the user. This is the process of identifying the class or data name contained in the database. The method of retrieving the words contained in the query in the existing database and recognizing the object does not identify the homophone and the word phrases because it does not consider the context of the user's query. If there are multiple search results, all of them are returned as a result, so there can be many interpretations on the query and the time complexity for the calculation becomes large. To overcome these, this study aims to solve this problem by reflecting the contextual meaning of the query using Bidirectional LSTM-CRF. Also we tried to solve the disadvantages of the neural network model which can't identify the untrained words by using ontology knowledge based feature. Experiments were conducted on the ontology knowledge base of music domain and the performance was evaluated. In order to accurately evaluate the performance of the L-Bidirectional LSTM-CRF proposed in this study, we experimented with converting the words included in the learned query into untrained words in order to test whether the words were included in the database but correctly identified the untrained words. As a result, it was possible to recognize objects considering the context and can recognize the untrained words without re-training the L-Bidirectional LSTM-CRF mode, and it is confirmed that the performance of the object recognition as a whole is improved.

• Journal of Acupuncture Research
• /
• v.22 no.6
• /
• pp.229-239
• /
• 2005

Objectives : Allergic rhinitis is a prevalent disease. Nasal obstruction is one of the main symptom in allergic rhinitis. It induces sleep disturbances, depression, attention deficit, memory impairments. Acupuncture treatment for rhinitis was mentioned in literature, but there is not enough report that provide evidence by well designed clinical study. The purpose of this research is to examine the effect of acupuncture treatment for nasal obstruction of allergic rhinitis. Methods : In this randomized, single blind, placebo-controlled study, we compared active acupuncture with minimal acupuncture for the treatment of nasal obstruction owing to persistent allergic rhinitis. Acupoints used in active acupuncture group were I120($Y{\hat{o}}nghyang$), GV23($Sangs{\hat{o}}ng$), IL4(Hapkok). Volunteers who satisfied the requirements were enrolled in study. Total nasal volume(NV) and total nasal minimum cross-sectional area(MCA) were measured by acoustic rhinometry before and after treatments(0min, 7.5min, 15min). Results : 101 subjects finished study. There were not difference between two groups on age, sex, weight, height, blood pressure, pulse, respiratory rate, severity of persistent allergic rhinitis, number of positive antigen. After treatment(0min) total NV were significantly increased compared with before treatment in active acupuncture group(p=0.0007) and minimal acupuncture group(p=0.0175). After treatment(15min) total NV of minimal acupuncture group was decreased compared with before treatment(p=0.2560), but total NV of active acupuncture group was maintained increasing in degree of borderline significance(p=0.0871). After treatment(0min) total NV were significantly increased compared with before treatment in active acupuncture group(0.0007) and minimal acupuncture group(p=0.0175). After treatment(Omin) total MCA were significantly increased compared with before treatment in active acupuncture group(p<0.000l) and minimal acupuncture group(p=0.0005). After treatment(15min) total MCA of minimal acupuncture group was decreased compared with before treatment(p=0.6082), but total NV of active acupuncture group was maintained increasing in degree of borderline significance(p=0.0929). Conclusion : Acupuncture treatment reduced nasal obstruction in persistent allergic rhinitis. Further study in the form of long term is needed.