• Annual Conference on Human and Language Technology
• /
• 2016.10a
• /
• pp.321-323
• /
• 2016

최근 연구에서 기계학습 중 지도학습 방법으로 개체명 인식을 하고 있다. 그러나 지도 학습 방법은 데이터를 만드는 비용과 시간이 많이 필요로 한다. 본 연구에서는 주석 된 말뭉치를 사용하여 지도 학습 방법을 사용 한다. 의생명 개체명 인식은 Protein, RNA, DNA, Cell type, Cell line 등을 포함한 텍스트 처리에 중요한 기초 작업입니다. 그리고 의생명 지식 검색에서 가장 기본과 핵심 작업 중 하나이다. 본 연구에서는 순환형 신경망과 워드 임베딩을 자질로 사용한 조건적 임의 필드에 대한 성능을 비교한다. 조건적 임의 필드에 N_Gram만을 자질로 사용한 것을 기준점으로 설정 하였고, 기준점의 결과는 70.09% F1 Score이다. RNN의 jordan type은 60.75% F1 Score, elman type은 58.80% F1 Score의 성능을 보여준다. 조건적 임의 필드에 CCA, GLOVE, WORD2VEC을 사용 한 결과는 각각 72.73% F1 Score, 72.74% F1 Score, 72.82% F1 Score의 성능을 얻을 수 있다.

• Proceedings of the KIEE Conference
• /
• 2003.07d
• /
• pp.2206-2208
• /
• 2003

LMTT(Linear Motor-based Transfer Technology) is horizontal transfer system in the maritime container terminal for the port automation. The system is modeled PMLSM(Permanent Magnetic Linear Synchronous Motor) that is consists of stator modules on the rail and shuttle car(mover). Because of large variant of movers weight by loading and unloading containers, the difference of each characteristic of stator modules, and a stator module's default etc., LMCS(Linear Motor Conveyance System) is considered as that the system is changed its model suddenly and variously. In this paper, we will introduce the soft-computing method of a multi-step prediction control for LMCS using DR-FNN(Dynamically Constructed Recurrent Fuzzy Neural Network). The proposed control system is used two networks for multi-step prediction. Consequently, the system has an ability to adapt for external disturbance, cogging force, force ripple, and sudden changes of itself.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.7
• /
• pp.2321-2338
• /
• 2021

Compared with vehicle trajectories, pedestrian trajectories have stronger degrees of freedom and complexity, which poses a higher challenge to trajectory prediction tasks. This paper designs a mode to divide the trajectory of pedestrians at a traffic intersection, which converts the trajectory regression problem into a trajectory classification problem. This paper builds a deep model for pedestrian trajectory prediction at intersections for the task of pedestrian short-term trajectory prediction. The model calculates the spatial correlation and temporal dependence of the trajectory. More importantly, it captures the interactive features among pedestrians through the Attention mechanism. In order to improve the training speed, the model is composed of pure convolutional networks. This design overcomes the single-step calculation mode of the traditional recurrent neural network. The experiment uses Vulnerable Road Users trajectory dataset for related modeling and evaluation work. Compared with the existing models of pedestrian trajectory prediction, the model proposed in this paper has advantages in terms of evaluation indicators, training speed and the number of model parameters.

• ETRI Journal
• /
• v.44 no.4
• /
• pp.672-685
• /
• 2022

This article proposes a subject-independent application of brain-computer interfacing (BCI). A 32-channel Electroencephalography (EEG) device is used to measure imagined speech (SI) of four words (sos, stop, medicine, washroom) and one phrase (come-here) across 13 subjects. A deep long short-term memory (LSTM) network has been adopted to recognize the above signals in seven EEG frequency bands individually in nine major regions of the brain. The results show a maximum accuracy of 73.56% and a network prediction time (NPT) of 0.14 s which are superior to other state-of-the-art techniques in the literature. Our analysis reveals that the alpha band can recognize SI better than other EEG frequencies. To reinforce our findings, the above work has been compared by models based on the gated recurrent unit (GRU), convolutional neural network (CNN), and six conventional classifiers. The results show that the LSTM model has 46.86% more average accuracy in the alpha band and 74.54% less average NPT than CNN. The maximum accuracy of GRU was 8.34% less than the LSTM network. Deep networks performed better than traditional classifiers.

• Communications for Statistical Applications and Methods
• /
• v.29 no.6
• /
• pp.709-719
• /
• 2022

Recently, as the importance of environmental protection has emerged, interest in new and renewable energy is also increasing worldwide. In particular, the solar energy sector accounts for the highest production rate among new and renewable energy in Korea due to its infinite resources, easy installation and maintenance, and eco-friendly characteristics such as low noise emission levels and less pollutants during power generation. However, although climate prediction is essential since solar power is affected by weather and climate change, solar radiation, which is closely related to solar power, is not currently forecasted by the Korea Meteorological Administration. Solar radiation prediction can be the basis for establishing a reasonable new and renewable energy operation plan, and it is very important because it can be used not only in solar power but also in other fields such as power consumption prediction. Therefore, this study was conducted for the purpose of improving the accuracy of solar radiation. Solar radiation was predicted by a total of three weather variables, temperature, humidity, and cloudiness, and solar radiation outside the atmosphere, and the results were compared using various models. The CatBoost model was best obtained by fitting and comparing the Boosting series (XGB, CatBoost) and RNN series (Simple RNN, LSTM, GRU) models. In addition, the results were further improved through Time series cross-validation.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.473-474
• /
• 2022

텍스트를 기반으로 하는 패스워드는 다방면에서 가장 많이 사용되고 있는 인증 수단이다. 하지만 이러한 패스워드는 사용자의 기억에 의존하기 때문에 사람들은 일반적으로 기억하기 쉽게 '!iloveY0u'와 같은 암호를 사용한다. 이로 인해 사용자들의 패스워드 간에 규칙성이 생기게 되어 HashCat과 같은 크래킹 도구에 의해 해킹될 수 있다. 딥러닝을 통한 패스워드 예측의 경우, 일반적인 패스워드 크래킹 도구와 달리 패스워드 구조 및 속성에 대한 사전 지식 및 전문적 지식 없이도 패턴을 추출하고 학습할 수 있어 활발히 연구되고 있다. 본 논문에서는 딥러닝 모델 중에서도 순환 신경망을 사용하여 텍스트 기반의 패스워드를 예측하는 연구의 동향에 대해 알아본다.

• Journal of Information Technology Applications and Management
• /
• v.30 no.3
• /
• pp.1-13
• /
• 2023

Demand forecasting is a crucial task for an online retail where has to manage daily fresh foods effectively. Failing in forecasting results loss of profitability because of incompetent inventory management. This study investigated the optimal performance of different forecasting models for a very short shelf-life product. Demand data of 13 perishable items with aging of 210 days were used for analysis. Our comparison results of four methods: Trivial Identity, Seasonal Naïve, Feed-Forward and Autoregressive Recurrent Neural Networks (DeepAR) reveals that DeepAR outperforms with the lowest MAPE. This study also suggests the managerial implications by employing coefficient of variation (CV) as demand variation indicators. Three classes: Low, Medium and High variation are introduced for classify 13 products into groups. Our analysis found that DeepAR is suitable for medium and high variations, while the low group can use any methods. With this approach, the case can gain benefit of better fill-rate performance.

• Korean Chemical Engineering Research
• /
• v.58 no.4
• /
• pp.588-595
• /
• 2020

Prediction and control of nitrogen oxides (NO_x) emission is of great interest in industry due to stricter environmental regulations. Herein, we propose an artificial intelligence (AI)-based framework for prediction of NO_x emission. The framework includes pre-processing of data for training of neural networks and evaluation of the AI-based models. In this work, Long-Short-Term Memory (LSTM), one of the recurrent neural networks, was adopted to reflect the time series characteristics of NO_x emissions. A decision tree was used to determine a time window of LSTM prior to training of the network. The neural network was trained with operational data from a heating furnace. The optimal model was obtained by optimizing hyper-parameters. The LSTM model provided a reliable prediction of NO_x emission for both training and test data, showing an accuracy of 93% or more. The application of the proposed AI-based framework will provide new opportunities for predicting the emission of various air pollutants with time series characteristics.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.5
• /
• pp.93-99
• /
• 2019

In this paper, we propose a smart meter that uses GRU model, which is one of artificial neural networks, for the efficient energy management. We collected power consumption data that train GRU model through the proposed smart meter. The implemented smart meter has automatic power measurement and real-time observation function and load control function through power consumption prediction. We determined a reference value to control the load by using Root Mean Squared Error (RMS), which is one of performance evaluation indexes, with 20% margin. We confirmed that the smart meter with automatic load control increases the efficiency of energy management.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.411-414
• /
• 2021

One of the elements of technology that has become extremely critical within the field of education today is Deep learning. It has been especially used in the area of natural language processing, with some word-representation vectors playing a critical role. However, some of the low-resource languages, such as Swahili, which is spoken in East and Central Africa, do not fall into this category. Natural Language Processing is a field of artificial intelligence where systems and computational algorithms are built that can automatically understand, analyze, manipulate, and potentially generate human language. After coming to discover that some African languages fail to have a proper representation within language processing, even going so far as to describe them as lower resource languages because of inadequate data for NLP, we decided to study the Swahili language. As it stands currently, language modeling using neural networks requires adequate data to guarantee quality word representation, which is important for natural language processing (NLP) tasks. Most African languages have no data for such processing. The main aim of this project is to recognize and focus on the classification of words in English, Swahili, and Korean with a particular emphasis on the low-resource Swahili language. Finally, we are going to create our own dataset and reprocess the data using Python Script, formulate the syllabic alphabet, and finally develop an English, Swahili, and Korean word analogy dataset.