• 한국지능시스템학회논문지
• /
• 제16권6호
• /
• pp.730-735
• /
• 2006

본 논문은 퍼지 시스템과 유전자 알고리즘을 이용하여 단기 전력 부하 예측 방법을 제안한다. 우선 유전자 알고리즘을 이용하여 최적의 퍼지 소속함수를 구한다. 최적의 퍼지 규칙과 시계열 입력 차이를 이용하여 보다 더 나은 예측 시스템을 구한다. 제안된 방법을 이용하여 단기 전력 부하 예측에서 좋은 결과를 얻었다. 또한 제안된 알고리즘에 대한 그래픽 사용자 인터페이스를 구현한다. 마지막으로, 전력부하에 대한 지역 예측 시스템을 구현한다.

• ETRI Journal
• /
• 제43권2호
• /
• pp.288-298
• /
• 2021

Abstractive text summarization is a process of making a summary of a given text by paraphrasing the facts of the text while keeping the meaning intact. The manmade summary generation process is laborious and time-consuming. We present here a summary generation model that is based on multilayered attentional peephole convolutional long short-term memory (MAPCoL; LSTM) in order to extract abstractive summaries of large text in an automated manner. We added the concept of attention in a peephole convolutional LSTM to improve the overall quality of a summary by giving weights to important parts of the source text during training. We evaluated the performance with regard to semantic coherence of our MAPCoL model over a popular dataset named CNN/Daily Mail, and found that MAPCoL outperformed other traditional LSTM-based models. We found improvements in the performance of MAPCoL in different internal settings when compared to state-of-the-art models of abstractive text summarization.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2020년도 제62차 하계학술대회논문집 28권2호
• /
• pp.617-618
• /
• 2020

우리나라의 지리적인 여건상 대륙과 연결되지 않기 때문에 해상운송에 절대적으로 의존하고 있다. 해상운송에 있어 항만시설의 확보가 필요하며 대외무역의존도가 높은 우리나라의 경우 더욱 중요한 역할을 한다. 항만시설은 장기적인 항만수요예측을 통해 대규모 인프라투자를 결정하며 단기적인 예측은 항만운영의 효율성을 개선하고 항만의 경쟁력을 제고하는데 기여하므로 예측의 정확성을 높이기 위해 많은 노력이 필요하다. 본 논문에서는 딥러닝 모델 중에 하나인 LSTM(Long Short Term Memory)을 적용하여 우리나라 주요항만의 컨테이너 물동량 단기예측을 수행하여 선행연구들에서 주류를 이뤘던 ARIMA류의 시계열모델과 비교하여 예측성능을 평가할 것이다. 본 논문은 학문적으로 항만수요예측에 관한 새로운 예측모델을 제시하였다는 측면에서 의미가 있으며 실무적으로 항만수요예측에 대한 정확성을 개선하여 항만투자의사결정에 과학적인 근거로서 활용이 가능할 것으로 기대된다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2022년도 학술발표회
• /
• pp.35-35
• /
• 2022

최근에 딥 러닝(Deep learning) 기반의 많은 방법들이 수문학적 모형 및 예측에서 의미있는 결과를 보여주고 있지만 더 많은 연구가 요구되고 있다. 본 연구에서는 수자원의 가장 대표적인 모델링 구조인 강우유출의 관계의 규명에 대한 모형을 Long Short-Term Memory (LSTM) 기반의 변형 된 방법으로 제시하고자 한다. 구체적으로 본 연구에서는 반응변수인 유출량에 대한 직접적인 고려가 아니라 그의 1차 도함수 (First derivative)로 정의되는 Delta기반으로 모형을 구축하였다. 또한, Attention 메카니즘 기반의 모형을 사용함으로써 강우유출의 관계의 규명에 있어 정확성을 향상시키고자 하였다. 마지막으로 확률 기반의 예측를 생성하고 이에 대한 불확실성의 고려를 위하여 Denisty 기반의 모형을 포함시켰고 이를 통하여 Epistemic uncertainty와 Aleatory uncertainty에 대한 상대적 정량화를 수행하였다. 본 연구에서 제시되는 모형의 효용성 및 적용성을 평가하기 위하여 미국 전역에 위치하는 총 507개의 유역의 일별 데이터를 기반으로 모형을 평가하였다. 결과적으로 본 연구에서 제시한 모형이 기존의 대표적인 딥 러닝 기반의 모형인 LSTM 모형과 비교하였을 때 높은 정확성뿐만 아니라 불확실성의 표현과 정량화에 대한 유용한 것으로 확인되었다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 추계학술대회
• /
• pp.409-410
• /
• 2022

본 논문은 LSTM(Long-Short Term Memory) 네트워크와 CNN 딥러닝 기법을 기반으로 하는 융합 모델을 제안하고 다중 카테고리 뉴스 데이터 세트에 적용하여 좋은 결과를 얻었다. 실험에 따르면 딥 러닝 기반의 융합 모델이 텍스트 감정 분류의 정밀도와 정확도를 크게 향상시켰다. 이 방법은 모델을 최적화하고 모델의 성능을 향상시키는 중요한 방법이 될 것이다.

• Journal of Information Technology Applications and Management
• /
• 제29권5호
• /
• pp.27-37
• /
• 2022

This study intends to link agricultural machine history data with related organizations or collect them through IoT sensors, receive input from agricultural machine users and managers, and analyze them through AI algorithms. Through this, the goal is to track and manage the history data throughout all stages of production, purchase, operation, and disposal of agricultural machinery. First, LSTM (Long Short-Term Memory) is used to estimate oil consumption and recommend maintenance from historical data of agricultural machines such as tractors and combines, and C-LSTM (Convolution Long Short-Term Memory) is used to diagnose and determine failures. Memory) to build a deep learning algorithm. Second, in order to collect historical data of agricultural machinery, IoT sensors including GPS module, gyro sensor, acceleration sensor, and temperature and humidity sensor are attached to agricultural machinery to automatically collect data. Third, event-type data such as agricultural machine production, purchase, and disposal are automatically collected from related organizations to design an interface that can integrate the entire life cycle history data and collect data through this.

• 한국프랜차이즈경영연구
• /
• 제13권2호
• /
• pp.17-31
• /
• 2022

Purpose: With the development of the Internet, consumers can quickly access the electronic word-of-mouth. Consumers seek to reduce uncertainty by referring to the opinions of other consumers about products and services when making purchase decisions. In the food service industry, evaluating a restaurant before an actual visitation is difficult. Therefore, electronic word-of-mouth is important to interact with the customer in restaurants. as it can be used as an exchange of information in which consumers participate and interact with other customers. This study was conducted to verify how online word-of-mouth characteristics (Consensus, Vividness, Neutrality) on attitudes and visit intention from the perspective of social exchange theory. And it was performed to verify the structural relationship between short-term visit intention, mid-term visit and long-term visit intention. Research design, data, and methodology: A survey was conducted on customers who have visited restaurants. Of a total of 312 responses, 306 responses were used, excluding insincere responses and missing values for factors analysis. SPSS 25.0 and AMOS 25.0 were used for statistical analysis, and hypothesis testing was conducted after verifying the validity and reliability of the questionnaire items. Result: The result of the analysis showed that, consensus and neutrality have a positive effect on attitude but not much on vividness. In addition, consensus, vividness, and neutrality have no effect on the short-term visit intention. Finally, the short-term visit intention has a positive effect on mid-term visit intention, and mid-term visit intention has a positive effect on long-term visit intention. Conclusions: Based on the results, this study suggested that it is necessary to have practical implications for marketing and monitoring restaurant reviews in consideration of the characteristics of electronic word-of-mouth. When managing electronic-word-of-mouth, it is necessary to manage the consensus and neutrality is essential to provide sufficient information about the restaurant. The focus should not only be on vividness, such as photos and videos. In addition, restaurants should also provide a good experience for first-time visitors as the short-term visit intention positively affects mid-term and long-term visit intention.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2020년도 학술발표회
• /
• pp.101-101
• /
• 2020

Traditional stochastic simulation of hydroclimatological variables often underestimates the variability and correlation structure of larger timescale due to the difficulty in preserving long-term memory. However, the Long Short-Term Memory (LSTM) model illustrates a remarkable long-term memory from the recursive hidden and cell states. The current study, therefore, employed the LSTM model in stochastic generation of hydrologic and climate variables to examine how much the LSTM model can preserve the long-term memory and overcome the drawbacks of conventional time series models such as autoregressive (AR). A trigonometric function and the Rössler system as well as real case studies for hydrological and climatological variables were tested. Results presented that the LSTM model reproduced the variability and correlation structure of the larger timescale as well as the key statistics of the original time domain better than the AR and other traditional models. The hidden and cell states of the LSTM containing the long-memory and oscillation structure following the observations allows better performance compared to the other tested conventional models. This good representation of the long-term variability can be important in water manager since future water resources planning and management is highly related with this long-term variability.

• 한국음향학회지
• /
• 제39권2호
• /
• pp.137-142
• /
• 2020

문장 종속 짧은 발화에서 문장 독립 긴 발화까지 다양한 환경에서 I-vector 특징에 기반을 둔 많은 연구가 수행되었다. 본 논문에서는 원거리 잡음 환경에서 녹음한 데이터에서 Probabilistic Linear Discriminant Analysis(PLDA)를 적용한 I-vector와 주의 집중 기법을 접목한 Long Short Term Memory(LSTM) 기반의 화자 임베딩을 추출하여 결합한 화자 검증 알고리즘을 소개한다. LSTM 모델의 Equal Error Rate(EER)이 15.52 %, Attention-LSTM 모델이 8.46 %로 7.06 % 성능이 향상되었다. 이로써 본 논문에서 제안한 기법이 임베딩을 휴리스틱 하게 정의하여 사용하는 기존 추출방법의 문제점을 해결할 수 있는 것을 확인하였다. PLDA를 적용한 I-vector의 EER이 6.18 %로 결합 전 가장 좋은 성능을 보였다. Attention-LSTM 기반 임베딩과 결합하였을 때 EER이 2.57 %로 기존보다 3.61 % 감소하여 상대적으로 58.41 % 성능이 향상되었다.

• ALGAE
• /
• 제18권1호
• /
• pp.49-58
• /
• 2003

The short-term dynamics of the summer phytoplankton community structure were investigated in coastal waters around Namhae Island, the Southern Sea of Korea. The study was based on a comprehensive survey constituting 39 collections from 13 stations on July 18-22, August 1-2, 14-16 and 27-30, respectively. The community structure was analysed using cluster analysis and important environmental correlates of the assemblage structure were identified with canonical correspondence analysis (CCA). Water temperature, salinity, NO₂, NO₃, NH₄, PO₄, chlorophyll a and transparency were measured as physico-chemical environmental factors which may be associated with the phytoplankton community structure. Variations of salinity and concentrations of NO₃ and chlorophyll a were not significant. In addition to warmer water temperature, concentrations of NO₂, NO₄and PO₄ decreased at the beginning of August. And transparency was deeper and water column became very unstable after the middle of August. A wide taxonomic diversity was encountered during the survey, including a total of 121 taxa which was composed of 72 diatoms, 48 dinoflagellates and 1 euglenoid species. Cluster analysis showed that the Phytoplankton community could be divided into 4 distinct groups, indicating rapid changes of the community in the short course of this survey. These phytoplankton groups also showed distinctive dispersion patterns in 2-dimensional canonical space, indicating distinct groupings for stations at each survey. Dominant taxa of diatoms (Chaetoceros curvisetus, Chaetoceros spp., Leptocylindrus danicus, Leptocylindrus mediteraneus, Skeletonema costanum, and Pseudo-nitzschia pungen) clustered in region of CCA space corresponding to stations surveyed at the middle of July. Dominant taxa of dinoflagellates were tightly associated with stations surveyed at the middle (Karenia breve) and end (Cochlodinium polykrikoides and Polykrikos schwartzii) of August. The CCA also showed that the phytoplankton community compositions were highly associated with water temperature, transparency, NO₂, NH₄ and PO₄, suggesting that gradients in physical and nutrient conditions affect short-term changes in phytoplankton composition.