• 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 Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.127-142
• /
• 2016

Deep learning model is a kind of neural networks that allows multiple hidden layers. There are various deep learning architectures such as convolutional neural networks, deep belief networks and recurrent neural networks. Those have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. Among those architectures, convolutional neural networks and recurrent neural networks are classified as the supervised learning model. And in recent years, those supervised learning models have gained more popularity than unsupervised learning models such as deep belief networks, because supervised learning models have shown fashionable applications in such fields mentioned above. Deep learning models can be trained with backpropagation algorithm. Backpropagation is an abbreviation for "backward propagation of errors" and a common method of training artificial neural networks used in conjunction with an optimization method such as gradient descent. The method calculates the gradient of an error function with respect to all the weights in the network. The gradient is fed to the optimization method which in turn uses it to update the weights, in an attempt to minimize the error function. Convolutional neural networks use a special architecture which is particularly well-adapted to classify images. Using this architecture makes convolutional networks fast to train. This, in turn, helps us train deep, muti-layer networks, which are very good at classifying images. These days, deep convolutional networks are used in most neural networks for image recognition. Convolutional neural networks use three basic ideas: local receptive fields, shared weights, and pooling. By local receptive fields, we mean that each neuron in the first(or any) hidden layer will be connected to a small region of the input(or previous layer's) neurons. Shared weights mean that we're going to use the same weights and bias for each of the local receptive field. This means that all the neurons in the hidden layer detect exactly the same feature, just at different locations in the input image. In addition to the convolutional layers just described, convolutional neural networks also contain pooling layers. Pooling layers are usually used immediately after convolutional layers. What the pooling layers do is to simplify the information in the output from the convolutional layer. Recent convolutional network architectures have 10 to 20 hidden layers and billions of connections between units. Training deep learning networks has taken weeks several years ago, but thanks to progress in GPU and algorithm enhancement, training time has reduced to several hours. Neural networks with time-varying behavior are known as recurrent neural networks or RNNs. A recurrent neural network is a class of artificial neural network where connections between units form a directed cycle. This creates an internal state of the network which allows it to exhibit dynamic temporal behavior. Unlike feedforward neural networks, RNNs can use their internal memory to process arbitrary sequences of inputs. Early RNN models turned out to be very difficult to train, harder even than deep feedforward networks. The reason is the unstable gradient problem such as vanishing gradient and exploding gradient. The gradient can get smaller and smaller as it is propagated back through layers. This makes learning in early layers extremely slow. The problem actually gets worse in RNNs, since gradients aren't just propagated backward through layers, they're propagated backward through time. If the network runs for a long time, that can make the gradient extremely unstable and hard to learn from. It has been possible to incorporate an idea known as long short-term memory units (LSTMs) into RNNs. LSTMs make it much easier to get good results when training RNNs, and many recent papers make use of LSTMs or related ideas.

• Journal of Life Science
• /
• v.29 no.6
• /
• pp.747-753
• /
• 2019

Cognitive decline is characterized by reduced long-/short-term memory and attention span, and increased depression and anxiety. Such decline is associated with various degenerative brain disorders, especially Alzheimer's disease (AD) and Parkinson's disease (PD). The increases in elderly populations suffering from cognitive decline create social problems and impose economic burdens, and also pose safety threats; all of these problems have been extensively researched over the past several decades. Possible causes of cognitive decline include metabolic and hormone imbalance, infection, medication abuse, and neuronal changes associated with aging. However, no treatment for cognitive decline is available. In neurodegenerative diseases, changes in the gut microbiota and gut metabolites can alter molecular expression and neurobehavioral symptoms. Changes in the gut microbiota affect memory loss in AD via the downregulation of NMDA receptor expression and increased glutamate levels. Furthermore, the use of probiotics resulted in neurological improvement in an AD model. PD and gut microbiota dysbiosis are linked directly. This interrelationship affected the development of constipation, a secondary symptom in PD. In a PD model, the administration of probiotics prevented neuron death by increasing butyrate levels. Dysfunction of the blood-brain barrier (BBB) has been identified in AD and PD. Increased BBB permeability is also associated with gut microbiota dysbiosis, which led to the destruction of microtubules via systemic inflammation. Notably, metabolites of the gut microbiota may trigger either the development or attenuation of neurodegenerative disease. Here, we discuss the correlation between cognitive decline and the gut microbiota.

• Asia Marketing Journal
• /
• v.12 no.2
• /
• pp.53-81
• /
• 2010

Brand experience has received much attention from considerable marketing research. When consumers consume and use brands, they are exposed to various specific brand-related stimuli. These brand-related stimuli include brand identity and brand communications(e.g., colors, shapes, designs, slogans, mascots, brand characters) components. Brakus, Schmitt, and Zarantonello(2009) conceptualized brand experience as subjective and internal consumer responses evoked by brand-related stimuli. They demonstrated that brand experience can be broken down into four dimensions(sensory, affective, intellectual, and behavioral). Because experiences result from stimulations and lead to pleasurable outcomes, we expect consumers to want to repeat theses experiences. That is, brand experiences, stored in consumer memory, should affect brand loyalty. Consumers with positive experiences should be more likely to buy a brand again and less likely to buy an alternative brand(Fournier 1998; Oliver 1997). Brand attachment, one of dimensions of the consumer-brand relationship, is defined as an emotional bond to the specific brand(Thomson, MacInnis, and Park 2005). Brand attachment is target-specific bond between the consumer and the specific brand. Thus, strong attachment is attended by a rich set of schema that link the brand to the consumer. Previous researches propose that brand attachments should affect consumers' commitment to the brand. Brand experience differs from affective construct such as brand attachment. Brand attachment is based on interaction between a consumer and the brand. In contrast, brand experience occurs whenever there is a direct and indirect interaction with the brand. Furthermore, brand experience is not an emotional relationship concept. Brakus et al.(2009) suggest that brand experience may result in brand attachment. This study aims to distinguish brand experience dimensions and investigate the effects of brand experience on brand attachment and brand commitment. We test research problems with data from 265 customers having brand experiences in various product categories by using multiple regression and structural equation model. The empirical results can be summarized as follows. First, the paths from affective, behavior, and intellectual experience to the brand attachment were found to be positively significant whereas the effect of sensory experience to brand attachment was not supported. In the consumer literature, sensory experiences for consumers are often equated with aesthetic pleasure. Over time, these pleasure experiences can affect consumer satisfaction. However, sensory pleasures are not linked to attachment such as consumers' strong emotional bond(i.e., hot affect). These empirical results confirms the results of previous studies. Second, brand attachment including passion and connection influences brand commitment positively but affection does not influence brand commitment. In marketing context, consumers with brand attachment have intention to have a willingness to stay with the relationship. The results also imply that consumers' emotional attachment is characterized by a set of brand experience dimensions and consumers who are emotionally attached to the brand are committed. The findings of this research contribute to develop differences between brand experience and brand attachment and to provide practical implications on the brand experience management. Recently, many brand managers have focused on short-term view. According to this study, we suggest that effective brand experience management requires taking a long-term view of marketing decisions.

• 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.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 Korea Water Resources Association
• /
• v.54 no.10
• /
• pp.795-805
• /
• 2021

In this study, after developing an LSTM-based deep learning model for estimating daily runoff in the Soyang River Dam basin, the accuracy of the model for various combinations of model structure and input data was investigated. A model was built based on the database consisting of average daily precipitation, average daily temperature, average daily wind speed (input up to here), and daily average flow rate (output) during the first 12 years (1997.1.1-2008.12.31). The Nash-Sutcliffe Model Efficiency Coefficient (NSE) and RMSE were examined for validation using the flow discharge data of the later 12 years (2009.1.1-2020.12.31). The combination that showed the highest accuracy was the case in which all possible input data (12 years of daily precipitation, weather temperature, wind speed) were used on the LSTM model structure with 64 hidden units. The NSE and RMSE of the verification period were 0.862 and 76.8 m³/s, respectively. When the number of hidden units of LSTM exceeds 500, the performance degradation of the model due to overfitting begins to appear, and when the number of hidden units exceeds 1000, the overfitting problem becomes prominent. A model with very high performance (NSE=0.8~0.84) could be obtained when only 12 years of daily precipitation was used for model training. A model with reasonably high performance (NSE=0.63-0.85) when only one year of input data was used for model training. In particular, an accurate model (NSE=0.85) could be obtained if the one year of training data contains a wide magnitude of flow events such as extreme flow and droughts as well as normal events. If the training data includes both the normal and extreme flow rates, input data that is longer than 5 years did not significantly improve the model performance.

• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1143-1154
• /
• 2021

The selection of activation function has a great influence on the groundwater level prediction performance of artificial neural network (ANN) model. In this study, five activation functions were applied to ANN model for two groundwater level observation wells in the middle mountainous area of the Pyoseon watershed in Jeju Island. The results of the prediction of the groundwater level were compared and analyzed, and the optimal activation function was derived. In addition, the results of LSTM model, which is a widely used recurrent neural network model, were compared and analyzed with the results of the ANN models with each activation function. As a result, ELU and Leaky ReLU functions were derived as the optimal activation functions for the prediction of the groundwater level for observation well with relatively large fluctuations in groundwater level and for observation well with relatively small fluctuations, respectively. On the other hand, sigmoid function had the lowest predictive performance among the five activation functions for training period, and produced inappropriate results in peak and lowest groundwater level prediction. The ANN-ELU and ANN-Leaky ReLU models showed groundwater level prediction performance comparable to that of the LSTM model, and thus had sufficient potential for application. The methods and results of this study can be usefully used in other studies.