• 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.

• The Journal of the Acoustical Society of Korea
• /
• v.36 no.2
• /
• pp.136-143
• /
• 2017

In this paper, we propose a method for restoring damaged audio files using deep neural network. It is different from the conventional file carving based restoration. The purpose of our method is to infer lost information which can not be restored by existing techniques such as the file carving. We have devised methods that can automate the tasks which are essential for the restoring but are inappropriate for humans. As a result of this study it has been shown that it is possible to restore the damaged files, which the conventional file carving method could not, by using tasks such as speech or nonspeech decision and speech encoder recognizer using a deep neural network.

• Journal of IKEEE
• /
• v.24 no.4
• /
• pp.1176-1179
• /
• 2020

Vessel path prediction methods generally predict the latitude and longitude of a future location directly. However, in the case of direct prediction, errors could be large since the possible output range is too broad. In addition, error accumulation could occur since recurrent neural networks-based methods employ previous predicted data to forecast future data. In this paper, we propose a vessel path prediction method that does not directly predict the longitude and latitude. Instead, the proposed method predicts the acceleration of the vessel. Then the acceleration is employed to generate the velocity and direction, and the values decide the longitude and latitude of the future location. In the experiment, we show that the proposed method makes smaller errors than the direct prediction method, while both methods employ the same model.

• Journal of the Economic Geographical Society of Korea
• /
• v.25 no.1
• /
• pp.171-181
• /
• 2022

The real estate price index plays key roles as quantitative data in real estate market analysis. International organizations including OECD publish the real estate price indexes by country, and the Korea Real Estate Board announces metropolitan-level and municipal-level indexes. However, when the index is set on the smaller spatial unit level than metropolitan and municipal-level, problems occur: missing values. As the spatial scope is narrowed down, there are cases where there are few or no transactions depending on the unit period, which lead index calculation difficult or even impossible. This study suggests a supervised learning-based machine learning model to compensate for missing values that may occur due to no transaction in a specific range and period. The models proposed in our research verify the accuracy of predicting the existing values and missing values.

• Journal of IKEEE
• /
• v.26 no.3
• /
• pp.355-363
• /
• 2022

Korea is pursuing a plan to switch and expand energy sources with a focus on renewable energy with the goal of becoming carbon neutral by 2050. As the instability of energy supply increases due to the intermittent nature of renewable energy, accurate prediction of the amount of renewable energy generation is becoming more important. Therefore, the government has opened a small-scale power brokerage market and is implementing a system that pays settlements according to the accuracy of renewable energy prediction. In this paper, a prediction model was implemented using a statistical model and an artificial intelligence model for the prediction of solar power generation. In addition, the results of prediction accuracy were compared and analyzed, and the revenue from the settlement amount of the renewable energy generation forecasting system was estimated.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.198-198
• /
• 2021

최근 자연적, 사회적, 정책적 관점에서 하천관리의 중요성이 증대되면서 국가하천 정비를 통한 하천시설 관리의 책임이 증대되고 있다. 국가하천 5대강 본류의 친수지구 이용도 변화를 살펴보면 2015년에 비해 2019년에 면적당 이용객 수가 630,813(명/km²)이 증가하였음을 알 수 있었고(국토교통부, 2020) 본 연구에서는 이용자 수 증가율이 높은 편인 한강 내 하천이용시설을 대상으로 선정하여 해당 지역을 기계학습 기반의 수위예측 알고리즘에 적용하였다. 하천이용시설은 하천이용자가 편리하게 하천을 이용하기 위하여 설치한 시설로 공원시설(강서, 난지, 양화, 망원, 여의도, 이촌, 반포, 잠원, 뚝섬, 잠실, 광나루, 구리)을 위주로 분석하였다. 해당 시설의 침수피해를 고려하기 위해 시계열 자료에 특화된 LSTM(Long Short-term Memory)기법을 활용하여 수위예측 알고리즘을 개발하였고 이를 통해 도출된 홍수 예보로 재난을 대비하고 시설물을 체계적으로 관리하는 유지관리의 효과를 분석하고자 하였다. 입력 자료(input data)는 수위 (EL.m), 팔당댐 방류량 (m³/s), 강화대교의 조위(EL.m)를 사용하였으며 수위예측 알고리즘을 통해 6시간 후 예측 수위값을 도출하여 기존 2단계(주의보, 경보)였던 홍수 예보 단계에서 4단계(관심, 보행자통제, 차량통제, 경계)로 구축하였다. 기존과 세분화된 홍수예보를 적용했을 경우의 유지관리 비용과 편익을 산정하여 하천이용시설의 경제성을 비교·분석한 결과, 유지관리 비용이 기존 대비 약 5% 이상 절감되었고 편익은 약 1.5배 이상 증가하였으며 관리등급은 평균 C등급(보통) 이상 달성하였다. 이는 수위예측 알고리즘의 적용으로 하천이용 활성화 및 투자의 효율성에 목적을 두었으며 향후 분석결과를 토대로 경제성모델을 개발하여 국가하천 내 관리그룹에 적용하면 효율적인 유지관리체계를 제시할 수 있을 것으로 기대된다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.332-332
• /
• 2021

도시화가 상당히 이뤄지고 기습적인 폭우의 발생이 불확실하게 나타나는 시점에서 재산 및 인명피해를 야기할 수 있는 내수침수에 대한 위험도가 증가하고 있다. 내수침수에 대한 예측을 위하여 실측강우 또는 확률강우량 시나리오를 참조하고 연구대상 지역에 대한 1차원 그리고 2차원 수리학적 해석을 실시하는 연구가 오랫동안 진행되어 왔으나, 수치해석 모형의 경우 다양한 수문-지형학적 자료 및 계측 자료를 요구하고 집약적인 계산과정을 통한 단기간 예측에 어려움이 있음이 언급되어 왔다. 본 연구에서는 위와 같은 문제점을 해결하기 위하여 단일 도시 배수분구를 대상으로 관측 강우 자료, 1, 2차원 수치해석 모형, 기계학습 및 딥러닝 기법을 적용한 실시간 홍수위험지도 예측 모형을 개발하였다. 강우자료에 대하여 실시간으로 홍수량을 예측할 수 있도록 LSTM(Long-Short Term Memory) 기법을 적용하였으며, 전국단위 강우에 대한 다양한 1차원 도시유출해석 결과를 학습시킴으로써 예측을 수행하였다. 침수심의 공간적 분포의 경우 로지스틱 회귀를 이용하여, 기준 침수심에 대한 예측을 각각 수행하였다. 홍수위험 등급의 경우 침수심, 유속 그리고 잔해인자를 고려한 홍수위험등급 공식을 적용하여 산정하였으며, 이 결과를 랜덤포레스트(Random Forest)에 학습함으로써 실시간 예측을 수행할 수 있도록 개발하였다. 침수범위 및 홍수위험등급에 대한 예측은 격자 단위로 이뤄졌으며, 검증 자료의 부족으로 침수 흔적도를 통하여 검증된 2차원 침수해석 결과와 비교함으로써 예측력을 평가하였다. 본 기법은 특정 관측강우 또는 예측강우 자료가 입력되었을 때에, 도시 유역 단위로 접근이 불가하여 통제해야 할 구간을 실시간으로 예측하여 관리할 수 있을 것으로 판단된다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.37-37
• /
• 2022

유효우량 산정을 위하여 국내에서 주로 사용되는 모형은 NRCS-CN(Natural Resources Conservation Service - curve number) 모형으로, 유역의 유출 능력을 나타내는 유출곡선지수(runoff curve number, CN)와 같은 NRCS-CN 모형의 매개변수들은 관측 강우-유출자료 또는 토양도, 토지피복지도 등을 이용하여 유역마다 결정된 값이 사용되고 있다. 그러나 유역의 CN값은 유역의 토양 상태와 같은 환경적 조건에 따라 달라질 수 있으며, 이를 반영하기 위하여 선행토양함수조건(antecedent moisture condition, AMC)을 이용하여 CN값을 조정하는 방법이 사용되고 있으나, AMC 조건에 따른 CN 값의 갑작스런 변화는 유출량의 극단적인 변화를 가져올 수 있다. NRCS-CN 모형과 더불어 강우 손실량 산정에 많이 사용되는 모형으로 Green-Ampt 모형이 있다. Green-Ampt 모형은 유역에서 발생하는 침투현상의 물리적 과정을 고려하는 모형이라는 장점이 있으나, 모형에 활용되는 다양한 물리적인 매개변수들을 산정하기 위해서는 유역에 대한 많은 조사가 선행되어야 한다. 또한 이렇게 산정된 매개변수들은 유역 내 토양이나 식생 조건 등에 따른 여러 불확실성을 내포하고 있어 실무적용에 어려움이 있다. 따라서 본 연구에서는, 현재 사용되고 있는 강우손실 모형들의 매개변수를 추정하기 위한 방법을 제시하고자 하였다. 본 연구에서 제시하는 방법은 인공지능(AI) 기술 중 하나인 딥러닝(deep-learning) 기법을 기반으로 하고 있으며, 딥러닝 모형으로는 장단기 메모리(Long Short-Term Memory, LSTM) 모형이 활용되었다. 딥러닝 모형의 입력 데이터는 유역에서의 강우특성이나 토양수분, 증발산, 식생 특성들을 나타내는 인자이며, 모의 결과는 유역에서 발생한 총 유출량으로 강우손실 모형들의 매개변수 값들은 이들을 활용하여 도출될 수 있다. 산정된 매개변수 값들을 강우손실 모형에 적용하여 실제 유역들에서의 유효우량 산정에 활용해보았으며, 동역학파 기반의 강우-유출 모형을 사용하여 유출을 예측해보았다. 예측된 유출수문곡선을 관측 자료와 비교 시 NSE=0.5 이상으로 산정되어 유출이 적절히 예측되었음을 확인했다.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.877-885
• /
• 2022

Vision-based activity recognition has been widely attempted at construction sites to estimate productivity and enhance workers' health and safety. Previous studies have focused on extracting an individual worker's postural information from sequential image frames for activity recognition. However, various trades of workers perform different tasks with similar postural patterns, which degrades the performance of activity recognition based on postural information. To this end, this research exploited a concept of human-object interaction, the interaction between a worker and their surrounding objects, considering the fact that trade workers interact with a specific object (e.g., working tools or construction materials) relevant to their trades. This research developed an approach to understand the context from sequential image frames based on four features: posture, object, spatial features, and temporal feature. Both posture and object features were used to analyze the interaction between the worker and the target object, and the other two features were used to detect movements from the entire region of image frames in both temporal and spatial domains. The developed approach used convolutional neural networks (CNN) for feature extractors and activity classifiers and long short-term memory (LSTM) was also used as an activity classifier. The developed approach provided an average accuracy of 85.96% for classifying 12 target construction tasks performed by two trades of workers, which was higher than two benchmark models. This experimental result indicated that integrating a concept of the human-object interaction offers great benefits in activity recognition when various trade workers coexist in a scene.