• 한국CDE학회논문집
• /
• 제6권4호
• /
• pp.229-235
• /
• 2001

As the networks (i.e., intranet and internet) proliferate all over the world, it is inevitable to move some (or all) of the enterprise activities into virtual spaces. Differently from business data, product data have complex semantics and thus are not properly exchanged among different application programs. Even though some neutral formats of product data have been developed by standard organizations, exchanging them among various application programs still needs the comprehensive understanding of the complex semantics. Recently, it is widely recognized that capturing more knowledge is the next step to overcome the current difficulties on sharing product data. In this paper, we utilize the ontology concept in order to facilitate information search far product data in the internet environment. A prototype of search system implemented using the ontology for automobile product data is presented.

• 융합신호처리학회논문지
• /
• 제15권1호
• /
• pp.15-22
• /
• 2014

본 논문에서는 '저탄소 녹색성장'의 세계적 추세에 따라 탄소 중립적 에너지원인 우드펠릿(wood pellet)을 사용하는 난방보일러 제어시스템 구현을 제시한다. 본 시스템은 공중전화망 및 이동통신망을 통해 원격으로도 제어 가능한 홈 네트워크 기반의 제어 및 관리시스템 구현도 포함한다. 구현된 시스템은 온도조절기능, 연료공급기능, 점화기능, 화력조절기능, 그을음제거기능 등을 수행하는 보일러 주제어부와 주제어부와의 RS-485 통신링크를 통해 각 방의 개별 온도를 제어 할 수 있는 온도조절기 모듈 및 보일러의 원격제어 및 모니터링이 가능한 공중전화망 및 이동통신망 인터페이스 부분으로 구성된다. 구현된 시스템은 기본동작시험과 원격제어시험을 통해 난방면적 $172m^2$에서 열효율 93.6%, 난방출력 20,640kcal/hr, 연료소모량 5.54kg/hr 으로 나타났다. 이러한 성능지표는 기존 개발된 펠릿보일러에 비해서 우수한 결과로써 기존 보일러에서는 적용하지 않았던 3단계의 점화과정과 그을음제거 기능과 함께 $C_dS$ 센서를 통한 불꽃감지기능 및 셔터개폐의 미세 조정을 통한 화력조절기능을 새롭게 적용한 결과이다.

• 농업과학연구
• /
• 제46권1호
• /
• pp.67-78
• /
• 2019

The purpose of this study was to predict the water quality using the RNN (recurrent neutral network) and LSTM (long short-term memory). These are advanced forms of machine learning algorithms that are better suited for time series learning compared to artificial neural networks; however, they have not been investigated before for water quality prediction. Three water quality indexes, the BOD (biochemical oxygen demand), COD (chemical oxygen demand), and SS (suspended solids) are predicted by the RNN and LSTM. TensorFlow, an open source library developed by Google, was used to implement the machine learning algorithm. The Okcheon observation point in the Geum River basin in the Republic of Korea was selected as the target point for the prediction of the water quality. Ten years of daily observed meteorological (daily temperature and daily wind speed) and hydrological (water level and flow discharge) data were used as the inputs, and irregularly observed water quality (BOD, COD, and SS) data were used as the learning materials. The irregularly observed water quality data were converted into daily data with the linear interpolation method. The water quality after one day was predicted by the machine learning algorithm, and it was found that a water quality prediction is possible with high accuracy compared to existing physical modeling results in the prediction of the BOD, COD, and SS, which are very non-linear. The sequence length and iteration were changed to compare the performances of the algorithms.

• Journal of Electrical Engineering and Technology
• /
• 제10권2호
• /
• pp.699-707
• /
• 2015

Although digit character recognition has got a significant improvement in recent years, it is still challenging to achieve satisfied result if the data contains an amount of distracting factors. This paper proposes a novel digit character recognition approach using a multi-layer hierarchical model, Hybrid Restricted Boltzmann Machines (HRBMs), which allows the learning architecture to be robust to background distracting factors. The insight behind the proposed model is that useful high-level features appear more frequently than distracting factors during learning, thus the high-level features can be decompose into hybrid hierarchical structures by using only small label information. In order to extract robust and compact features, a stochastic 0-1 layer is employed, which enables the model's hidden nodes to independently capture the useful character features during training. Experiments on the variations of Mixed National Institute of Standards and Technology (MNIST) dataset show that improvements of the multi-layer hierarchical model can be achieved by the proposed method. Finally, the paper shows the proposed technique which is used in a real-world application, where it is able to identify digit characters under various complex background images.

• 한국지역지리학회지
• /
• 제20권1호
• /
• pp.30-48
• /
• 2014

본 연구는 도시 간 상호작용 지수(지배력 지수, 상대적 강도 지수, 엔트로피 지수)를 활용하여 출근 흐름과 업무 흐름, 화물 흐름에 있어서 수도권 도시 네트워크의 구조적 특성을 분석하였다. 분석 결과는 수도권의 도시 네트워크가 흔히 네트워크형 도시체계론에서 말하는 수평적이고 상호보완적이며 양방향과 규모 중립적이기 보다는 매우 규모 의존적이고, 수직적이고 최고차 중심도시에 의존적하는 지배 종속적 구조를 가지고 있는 것으로 나타났다. 출근 업무 흐름에 비해 화물 흐름의 네트워크가 다소 균형적이기는 하지만, 상호작용의 계층 구조, 흐름의 상대적 강도, 균형성 등 모든 면에서 출근 업무 흐름이든, 화물 흐름이든 서울과의 상호작용이 결정적이다.

• Journal of Power Electronics
• /
• 제18권2호
• /
• pp.573-587
• /
• 2018

Recently evolved power electronics' based domestic/residential appliances have begun to behave as single phase non-linear loads. Performing as voltage/current harmonic sources, those loads when connected to a three phase distribution network contaminate the line current with harmonics in addition to creating a neutral wire current increase. In this paper, an enhanced performance three phase four leg shunt active power filter (SAPF) controller is presented as a solution for this problem. The presented control strategy incorporates a hybrid predictive fuzzy-logic based technique. The predictive part is responsible for the SAPF compensating current generation while the DC-link voltage control is performed by a fuzzy logic technique. Simulations at various loading conditions are carried out to validate the effectiveness of the proposed technique. In addition, an experimental test rig is implemented for practical validation of the of the enhanced performance of the proposed technique.

• 한국산학기술학회논문지
• /
• 제12권2호
• /
• pp.712-717
• /
• 2011

동적 델타 헤징(Dynamic Delta Hedging)이란 옵션 발행자가 옵션의 만기정산금액(payoff)을 지급하기 위해 주기적으로 델타에 근거한 헤지 포지션을 조절함으로써 옵션의 payoff를 복제하고 옵션 가치변화에 따른 위험을 회피하는 방법이다. 본 연구에서는 헤지에 있어서 주요 변수인 블랙-숄즈의 모형에 의해 산출된 델타의 대체 값을 찾기 위해 기계학습의 일종인 인공신경망 학습을 적용하여 옵션의 만기 시 헤지 비용의 최소화 및 차익 실현을 위한 방법론을 제시하고자 한다. 기초자산의 현재가격, 변동성, 무위험이자율, 만기 등의 시장 상황 변화에 따른 다양한 시나리오에 대한 실험을 통해 본 연구에서 제시하는 방법론의 성능을 분석하고 그 우수성을 보인다.

• KEPCO Journal on Electric Power and Energy
• /
• 제6권4호
• /
• pp.419-425
• /
• 2020

DC distribution system has been evaluated as an excellent one in comparison with existing AC distribution network because it needs fewer power conversion stages and the full capacity of the equipment can be used without consideration for power factor. Recently, research and development on the implementation of DC distribution networks have been progressed globally based on the rapid advancement in power-electronics technology, and the technological developments from the viewpoint of infrastructure are also in progress. However, to configure a distribution network which is a distribution line for DC, more accurate and rapid introduction of analysis technology is needed for the monitoring, control and operation of the system, which ensure the system run flexible and efficiently. However, in case of a bipolar DC distribution network, there are two buses acting as slack buses, so the Jacobian matrix cannot be configured. Without solving this problem, DC distribution network cannot be operated when the network is unbalanced. Therefore, this paper presented a comprehensive method of analysis with consideration of operating elements which are directly connected between neutral electric potential caused by the unbalanced of load in DC distribution network with bipolar structure.

• International Journal of Computer Science & Network Security
• /
• 제21권3호
• /
• pp.206-211
• /
• 2021

Internet users are increasingly invited to express their opinions on various subjects in social networks, e-commerce sites, news sites, forums, etc. Much of this information, which describes feelings, becomes the subject of study in several areas of research such as: "Sensing opinions and analyzing feelings". It is the process of identifying the polarity of the feelings held in the opinions found in the interactions of Internet users on the web and classifying them as positive, negative, or neutral. In this article, we suggest the implementation of a sentiment analysis tool that has the role of detecting the polarity of opinions from people about COVID-19 extracted from social media (tweeter) in the Arabic language and to know the impact of the pre-processing phase on the opinions classification. The results show gaps in this area of research, first of all, the lack of resources when collecting data. Second, Arabic language is more complexes in pre-processing step, especially the dialects in the pre-treatment phase. But ultimately the results obtained are promising.

• Journal of Information Science Theory and Practice
• /
• 제12권2호
• /
• pp.64-78
• /
• 2024

Sentiment analysis is one of the promising approaches for developing a point of interest (POI) recommendation system. It uses natural language processing techniques that deploy expert insights from user-generated content such as reviews and feedback. By applying sentiment polarities (positive, negative, or neutral) associated with each POI, the recommendation system can suggest the most suitable POIs for specific users. The proposed study combines two models for POI recommendation. The first model uses bidirectional long short-term memory (BiLSTM) to predict sentiments and is trained on an election dataset. It is observed that the proposed model outperforms existing models in terms of accuracy (99.52%), precision (99.53%), recall (99.51%), and F1-score (99.52%). Then, this model is used on the Foursquare dataset to predict the class labels. Following this, user and POI embeddings are generated. The next model recommends the top POIs and corresponding coordinates to the user using the LSTM model. Filtered user interest and locations are used to recommend POIs from the Foursquare dataset. The results of our proposed model for the POI recommendation system using sentiment analysis are compared to several state-of-the-art approaches and are found quite affirmative regarding recall (48.5%) and precision (85%). The proposed system can be used for trip advice, group recommendations, and interesting place recommendations to specific users.