• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.6
• /
• pp.730-735
• /
• 2006

This paper proposes a time series prediction method for the short term electrical load will) the fuzzy system and the genetic algorithm. At first, we obtain the optimal fuzzy membership function using the genetic algorithm. With the optimal fuzzy rules and its input differences, a better time prediction system may be obtained. We obtain good results for the time prediction of the short term electric load by the proposed algorithm. In addition we implement the graphic user interface for the proposed algorithms. Finally, we implement the regional prediction system for the electric load.

• ETRI Journal
• /
• v.43 no.2
• /
• 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.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• 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.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• 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.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.409-410
• /
• 2022

This paper proposes a fusion model based on Long-Short Term Memory networks (LSTM) and CNN deep learning methods, and applied to multi-category news datasets, and achieved good results. Experiments show that the fusion model based on deep learning has greatly improved the precision and accuracy of text sentiment classification. This method will become an important way to optimize the model and improve the performance of the model.

• Journal of information and communication convergence engineering
• /
• v.22 no.2
• /
• pp.139-144
• /
• 2024

In this study, four types of fall detection systems - designed with YOLOPose, principal component analysis (PCA), convolutional neural network (CNN), and long short-term memory (LSTM) architectures - were developed and compared in the detection of everyday falls. The experimental dataset encompassed seven types of activities: walking, lying, jumping, jumping in activities of daily living, falling backward, falling forward, and falling sideways. Keypoints extracted from YOLOPose were entered into the following architectures: RAW-LSTM, PCA-LSTM, RAW-PCA-LSTM, and PCA-CNN-LSTM. For the PCA architectures, the reduced input size stemming from a dimensionality reduction enhanced the operational efficiency in terms of computational time and memory at the cost of decreased accuracy. In contrast, the addition of a CNN resulted in higher complexity and lower accuracy. The RAW-LSTM architecture, which did not include either PCA or CNN, had the least number of parameters, which resulted in the best computational time and memory while also achieving the highest accuracy.

• Journal of Information Technology Applications and Management
• /
• v.29 no.5
• /
• 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.

• The Korean Journal of Franchise Management
• /
• v.13 no.2
• /
• 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.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• 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.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.2
• /
• pp.137-142
• /
• 2020

Many studies based on I-vector have been conducted in a variety of environments, from text-dependent short-utterance to text-independent long-utterance. In this paper, we propose a speaker verification system employing a combination of I-vector with Probabilistic Linear Discriminant Analysis (PLDA) and speaker embedding of Long Short Term Memory (LSTM) with attention mechanism in far-field and noisy environments. The LSTM model's Equal Error Rate (EER) is 15.52 % and the Attention-LSTM model is 8.46 %, improving by 7.06 %. We show that the proposed method solves the problem of the existing extraction process which defines embedding as a heuristic. The EER of the I-vector/PLDA without combining is 6.18 % that shows the best performance. And combined with attention-LSTM based embedding is 2.57 % that is 3.61 % less than the baseline system, and which improves performance by 58.41 %.