• 융합신호처리학회논문지
• /
• 제3권3호
• /
• pp.1-5
• /
• 2002

본 논문에서는 실용적인 한국어 가격 문장인식기를 구성하기 위한 유한 상태 망(FSN)의 개선된 문법적인 구조를 제안한다. 기존에 제안된 가격 문장의 문법 제한은 실용적인 한국어 가격 문장의 인식을 위하여 문법 제한과 문법적인 구조를 수정해야 할 필요가 있다. 문법 제한은 실용적 관점에서 한국어 가격 문장의 세 번째와 네 번째 문법 제한을 개선하였다. 본 논문에서는 기존의 문법 제한을 개선하였고, FSN[1]의 문법적인 구조의 단점을 보완하였다. 개선된 문법적 구조의 성능평가를 위하여 FSN0, FSN-1, FSN-2의 세 가지 실험을 하여 평가하였다. 가격 문장의 인식결과, 단어 인식률은 FSN0, FSN1, FSN2의 경우에 각각 81.37%, 83.92%, 85.49%의 성능을 보였다. 또한 문장 인식률은 FSN0, FSN1, FSN2의 경우에 각각 35%, 45%, 52%의 성능을 보였다.

• Journal of Information Processing Systems
• /
• 제19권4호
• /
• pp.498-512
• /
• 2023

The traditional newspaper industry faces the opportunities and challenges of industry transformation and integration with new media. Consequently, the catalogs of newspapers and magazines are also updated. In this study, necessary information on catalogs was obtained and used to analyze the overall development trend of the newspaper industry. A word frequency analysis was then performed on the introduction and product categories of the catalogs, and the content and types of newspapers and magazines were examined. Furthermore, related factors such as price, number of pages, publishing frequency, and best-selling status were analyzed; the correlation among factors affecting best-selling status was also explored. Subsequently, each element and a combination of elements were used to generate a dataset, build three classification models, and analyze the accuracy of predictions of whether newspapers sold well under other circumstances. The experimental results showed that price is the most critical factor affecting the best-selling status of newspapers and magazines. Publishing frequency and the number of pages were also found to be significant indicators that impact people's subscription choices. Finally, a competitive strategy regarding content, price, quality, and positioning was developed.

• Journal of Information Processing Systems
• /
• 제20권1호
• /
• pp.76-84
• /
• 2024

This study constructed a VAR model with cotton futures and spot price data from April 30, 2009 to November 16, 2022, for empirical analysis utilizing the Granger causality test to analyze the dynamic relationship between cotton futures and spot market prices in China. The impulse response function and variance decomposition analysis showed that the cotton spot prices at flowering have a causal relationship with each other; in terms of mutual influence and impact, futures prices are higher than spot prices. Finally, it proposed countermeasures and suggestions from the perspective of establishing a standardized cotton spot market, improving the laws and regulations of the cotton futures market and trading system, and optimizing the structure of investment subjects.

• 농업과학연구
• /
• 제49권2호
• /
• pp.285-296
• /
• 2022

Food consumption trends in Korea are becoming more health-oriented, and consumers have become interested in high-quality foods that are also beneficial to health. The goals of this study are to examine consumers' impressions of black garlic and to investigate the preferred optimal attribute combinations related to black garlic. To do this, a survey of 352 consumers was used to analyze the current status of consumer purchases of black garlic. A conjoint analysis was conducted to analyze certain aspects of consumer preferences, such as price, health functional food certification status, processing type, and taste. Consumers' purchase experiences with black garlic were relatively few, but those with purchase experience reported that they consumed it mainly for their health. The results show that consumers are not satisfied with the taste and flavor of black garlic despite their perceiving it as a beneficial food for health. Despite the fact that consumers' purchase intentions were found to be low, it can greatly increase if improvements in price, flavor, and taste can be realized and if offering substantial benefits. The results of the conjoint analysis of the preference attributes of black garlic products are as follows. Consumers considered price among the four attributes as most important. The taste of black garlic and the processing style were similar in terms of importance, and health functional food certification was less important. Finally, the results suggest that continuous improvements in price and flavor are needed to spread the consumption of black garlic.

• 한국인터넷방송통신학회논문지
• /
• 제23권4호
• /
• pp.79-84
• /
• 2023

최근 분산 및 병렬 처리 기술 중 빠른 처리 속도를 제공하는 Apache Spark는 실시간 기능 및 머신러닝 기능을 제공하고 있다. 이러한 기능에 대한 공식 문서 가이드가 제공되고 있지만, 기능들을 융합하여 실시간으로 특정 값을 예측하는 방안은 제공되고 있지 않다. 따라서 본 논문에서는 이러한 기능들을 융합하여 실시간으로 데이터의 값을 예측할 수 있는 연구를 진행했다. 전체적인 구성은 Python 프로그래밍 언어에서 제공하는 주가 데이터를 다운로드하여 수집한다. 그리고 머신러닝 기능을 통해 회귀분석의 모델을 생성하고, 실시간 스트리밍 기능을 머신러닝 기능과 융합하여 실시간으로 주가 데이터 중 조정종가를 예측한다.

• 한국정보처리학회논문지
• /
• 제7권5S호
• /
• pp.1620-1628
• /
• 2000

Existing internet auction systems have adopted the form which gives a win to the auction bidder who proposes the top bid price for the goods posted on the auction board. But they haven't been satisfying the automatical one-step processing for user's convenience because they must require continuous care of user for bidding and checking as well as neglecting the convenience of user interface while participating in the electronic bidding system. The AuctionBot system of Michigan Univ. is known as the representative internet auction system. It has merit allowing the various kids of bidding. But it does not support automatic a process which can replaces what user has to do using an agent. To improve this kind of user interface, we propose an automatic bidding price strategy algorithm which composes the auction system using agent and design for auto-bidding system using agent so that I can replace user's bidding activity. This mechanism gives an auction system the efficient bidding price strategy.

• 농업과학연구
• /
• 제47권2호
• /
• pp.283-290
• /
• 2020

In 2018, 647 thousand tons of eggs were produced and consumed. However, the issue of pesticides used for egg in 2017 made Korean consumers worry about the food safety of eggs, and the volume of egg consumption decreased. The Korean egg industry also has another problem due to an unclear and inefficient marketing structure at the farm level. This marketing situation of eggs at the farm level in Korea needs a large-scale restructuring of the market structure, including introducing an EPC (egg processing center). Especially, the introduction of an EPC has been discussed by government officers and specialists, but the social benefit of an EPC, which will be the driving point for approving an EPC, has not been measured yet. The purpose of this study was to measure the effect of introducing an EPC in Korea. Through an analysis using EDM (equilibrium displacement model), a few findings are presented. First, the introduction of an EPC may increase the transparency of price discovery and decrease the transaction cost. And thus, it results in a higher producer price, lower consumer price, and larger quantity at market equilibrium. Second, an EPC will improve the level of food safety of eggs, which can increase the satisfaction of domestic producers and consumers. Third, the introduction of an EPC may create new consumption of eggs. Based on these three effects, the new social benefits in monetary terms from the introduction of an EPC in Korea could be 23.9 - 35.2 billion won.

• Soft Computing and Machine Intelligence
• /
• 제1권1호
• /
• pp.11-23
• /
• 2021

House price prediction is a significant financial decision for individuals working in the housing market as well as for potential buyers. From investment to buying a house for residence, a person investing in the housing market is interested in the potential gain. This paper presents machine learning algorithms to develop intelligent regressions models for House price prediction. The proposed research methodology consists of four stages, namely Data Collection, Pre Processing the data collected and transforming it to the best format, developing intelligent models using machine learning algorithms, training, testing, and validating the model on house prices of the housing market in the Capital, Islamabad. The data used for model validation and testing is the asking price from online property stores, which provide a reasonable estimate of the city housing market. The prediction model can significantly assist in the prediction of future housing prices in Pakistan. The regression results are encouraging and give promising directions for future prediction work on the collected dataset.

• 한국시뮬레이션학회논문지
• /
• 제23권4호
• /
• pp.1-8
• /
• 2014

클라우드 컴퓨팅은 정보의 다양성과 빅데이터를 IT자원을 이용하여 처리할 수 있는 컴퓨팅 개념이다. 정부는 신재생에너지를 활용한 전력생산을 장려하기 위해 RPS를 시행하였고 시스템을 구축하여 지리적으로 분산되어 있는 빅데이터를 수집하여 운영하고 있다. RPS제도를 이행하는 발전사업자들은 의무할당량 중 REC 부족분을 타 발전사업자들로부터 REC를 구매하여 조달해야 한다. REC는 자율시장에 근거하여 거래되고 있고, 매매가격의 편차가 크기 때문에 RPS 빅데이터를 통해 형평성있는 REC가격을 예측할 필요가 있다. 본 연구에서는 부정확한 가격추이와 규칙을 정량적으로 표현하여, 클라우드 환경에서 퍼지기반으로 REC가격을 예측하는 방법을 제안한다. 클라우드 환경에서 RPS 빅데이터를 통한 상호연관성과 가격결정에 영향을 주는 변수들에 대한 분석이 가능하고 시뮬레이션을 통해 REC 가격을 예측할 수 있다. 클라우드 환경에서 퍼지로직은 매물수량과 매매가격을 이용하여 투명성있는 REC 가격을 예측하고 장기적으로 수렴된 가격을 제시할 것이다.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제11권1호
• /
• pp.19-28
• /
• 2022

최근 암호화폐가 많은 주목을 받음에 따라 암호화폐의 종가 예측 연구들이 활발히 진행되고 있다. 특히 딥 러닝 모델을 적용시켜 예측 성능을 높이려는 연구들이 지속되고 있다. 딥 러닝 모델 중 시계열 데이터에서 높은 예측 성능을 보이는 LSTM (Long Short-Term Memory) 모델이 다각도로 응용되고 있으나 변동성이 큰 암호화폐 종가 데이터에서는 낮은 예측 성능을 보인다. 이를 해결하기 위해 새로운 입력 변수를 찾아내고, 이를 사용하는 종가 예측 연구가 수행되고 있다. 그러나 딥 러닝 기반의 암호화폐 종가 예측에 사용되는 데이터들의 각 입력 변수들이 예측 성능에 미치는 영향력이나 학습에 효율적인 입력 변수들의 조합에 관한 연구 사례가 부족한 실정이다. 따라서 본 논문에서는 Bitcoin과 Ethereum을 포함한 6가지 암호화폐의 최근 동향 자료를 수집하였고, 통계와 딥 러닝을 통해 입력 변수들이 암호화폐 종가 예측에 미치는 영향력을 분석한다. 실험 결과 모든 암호화폐의 종가 예측 성능 평가에서 종가 변동률을 제외한 개장가, 고가, 저가, 거래량, 종가를 조합했을 때 가장 우수한 성능을 보였다.