• 정보처리학회 논문지
• /
• 제13권5호
• /
• pp.209-216
• /
• 2024

부동산 시장은 다양한 요인에 의해 가격이 결정되며 거시경제 변수뿐 만 아니라 뉴스 기사, SNS 등 다양한 텍스트 데이터의 영향을 받는다. 특히 뉴스 기사는 국민들이 느끼는 경제 심리를 반영하고 있으므로 부동산 매매 가격 예측에 있어 중요한 요인이다. 본 연구에서는 뉴스 기사를 감성 분석하여 그 결과를 뉴스 감성 지수로 점수화 한 후 부동산 가격 예측 모델에 적용하였다. 먼저 기사 본문을 요약 후 요약된 내용을 바탕으로 생성 AI를 활용하여 긍정, 부정, 중립으로 분류한 다음 총 점수를 산출하였고 이를 부동산 가격 예측 모델에 적용하였다. 부동산 가격 예측 모델로는 Multi-head attention LSTM 모델과 Vector Auto Regression 모델을 사용하였다. 제안하는 뉴스 감성 지수를 적용하지 않은 LSTM 예측 모델은 1개월, 2개월, 3개월 예측에서 각각 0.60, 0.872, 1.117의 Root Mean Square Error (RMSE)을 보였으며, 뉴스 감성 지수를 적용한 LSTM 예측 모델은 각각 0.40, 0.724, 1.03의 RMSE값을 나타낸다. 또한 뉴스 감성 지수를 적용하지 않은 Vector Auto Regression 예측 모델은 1개월, 2개월, 3개월 예측에서 각각 1.6484, 0.6254, 0.9220, 뉴스 감성 지수를 적용한 Vector Auto Regression 예측 모델은 각각 1.1315, 0.3413, 1.6227의 RMSE 값을 나타낸다. 앞선 아파트 매매가격지수 예측 모델을 통해 사회/경제적 동향을 반영한 부동산 시장 가격 변동을 예측할 수 있을 것으로 보인다.

• 유통과학연구
• /
• 제16권4호
• /
• pp.67-74
• /
• 2018

Purpose - Most of the amendments to the law on the improvement of the distribution structure of mobile communication terminal equipment, the fully self-sufficient system of terminals, and the separated disclosure system on the terminals are aimed at securing transparency of the distribution structure by eliminating or reducing handset subsidies. This study investigates what items are important for the purchase of mobile phones in various and rapidly changing mobile phone markets from the consumer's point of view and tries to make a strategic suggestion for future mobile distribution strategies. Research design, data, and methodology - The procedure of this study takes place in four steps. In step 1, only the SF type respondents selected for this study were extracted through MBTI analysis. In step 2, they were divided into three hierarchies for the AHP analysis and each element was arranged. In step 3, the AHP analysis was converted to a Fuzzy-AHP number using the trigonometric centroid method. This was to eliminate the ambiguity of the response by converting into a fuzzy number even if data consistency was maintained with CI value below 0.1. In step 4, the number of converted 2-layer and 3-layer was combined to derive the priority when the final handset is selected. Results - First, the highest importance among the four items in the second tier was the terminal function item, followed by brand, price, and design item. Second, in the third tier, the highest importance was level of after-sales service, followed by device price, processing speed, ease of use, usefulness, and rate system. Third, the arithmetic average of the determinant of the fuzzy function showed that processing speed, ease of use and usefulness in the function item, level of after-sales service in the brand item, and device price in the price item were the five most important factors among 16 choice factors. Conclusions - First, there will be a change in the consumption patterns of consumers who have compared distributors and dealers to purchase handsets with more subsidies. Second, it is highly likely that people will purchase new handsets only when they need to change their devices because they can not receive subsidies by switching phone brands any more.

• 정보처리학회논문지D
• /
• 제12D권5호
• /
• pp.737-744
• /
• 2005

국방 관련 시스템 구축에 있어 소프트웨어의 비중이 커짐에 따라 국방 소프트웨어 개발비용 산정의 정확성에 대한 요구는 점점 높아가고 있다. 소프트웨어의 개발 초기단계에서 신속하고 합리적인 비용 산정을 하는데 적용할 수 있는 PRICE S는 미국 환경의 매개변수형 산정법으로 국내 실정에 다소 적합하지 않은 부분이 있다. 본 연구는 소프트웨어 개발비용 산정을 위해 국방 소프트웨어 비용 산정에 적용되는 PRICE S의 기존 적용방법을 국내 소프트웨어 개발비용 기준인 한소협 모델과의 비교를 통하여 수정 및 보완한다. 또한, 기능 점수 방식의 소프트웨어 개발비용 산정을 위한 백파이어링 절차를 제시함으로써 향후에 계획된 소프트웨어 개발 사업에 기능 점수 방식의 소프트웨어 개발비용 산정 기법을 적용하는 방안을 제시하여 개발비용 산정의 정확성을 향상시키고 기능 점수 방식의 적용에 대한 대비책을 제공한다.

• 유통과학연구
• /
• 제22권4호
• /
• pp.11-22
• /
• 2024

Purpose: This research delves into the various factors that influence the performance of restaurant businesses on social commerce platforms in Bangkok, Thailand. The study considers both internal and external factors, including but not limited to business characteristics and location. Moreover, this research also analyzes the effects of employing multiple social commerce platforms on business efficiency and explores the underlying reasons for such effects. Research design, data, and methodology: Restaurants can be classified into different price ranges: low, medium, and high. To further investigate, we employed natural language processing AI to analyze online reviews and evaluate algorithm performance using machine learning techniques. We aimed to develop a model to gauge customer satisfaction with restaurants across different price categories effectively. Results: According to the research findings, several factors significantly impact restaurant groups in the low and mid-price ranges. Among these factors are population density and the number of seats at the restaurant. On the other hand, in the mid-and high-price ranges, the price levels of the food and drinks offered by the restaurant play a crucial role in determining customer satisfaction. Furthermore, the correlation between different social commerce platforms can significantly affect the business performance of high-price range restaurant groups. Finally, the level of online review sentiment has been found to influence customer decision-making across all restaurant types significantly. Conclusions: The study emphasizes that restaurants' characteristics based on their price level differ significantly, and social commerce platforms have the potential to affect one another. It is worth noting that the sentiment expressed in online reviews has a more significant impact on customer decision-making than any other factor, regardless of the type of restaurant in question.

• 농업생명과학연구
• /
• 제53권3호
• /
• pp.147-157
• /
• 2019

In this study, we tried to find out the most appropriate pre-processing method and to verify the feasibility of developing a low-price sensing system for predicting the hardy kiwis sugar content based on VNIRS and subsequent spectral analysis. A total of 495 hardy kiwi samples were collected from three farms in Muju, Jeollabukdo, South Korea. The samples were scanned with a spectrophotometer in the range of 730-2300 nm with 1 nm spectral sampling interval. The measured data were arbitrarily separated into calibration and validation data for sugar content prediction. Partial least squares (PLS) regression was performed using various combinations of pre-processing methods. When the latent variable (LV) was 8 with the pre-processing combination of standard normal variate (SNV) and orthogonal signal correction (OSC), the highest R2 values of calibration and validation were 0.78 and 0.84, respectively. The possibility of predicting the sugar content of hardy kiwi was also examined at spectral sampling intervals of 6 and 10 nm in the narrower spectral range from 730 nm to 1200 nm for a low-price optical sensing system. The prediction performance had promising results with R2 values of 0.84 and 0.80 for 6 and 10 nm, respectively. Future studies will aim to develop a low-price optical sensing system with a combination of optical components such as photodiodes, light-emitting diodes (LEDs) and/or lamps, and to locate a more reliable prediction model by including meteorological data, soil data, and different varieties of hardy kiwi plants.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2003년도 춘계학술대회 논문집
• /
• pp.1406-1409
• /
• 2003

There is a great demand for reducing the amount of material used in mass-produced plastics parts, for material cost constitutes a large percentage of the total cost of 60%. It may be noted that the price of plastics is directly rotated to the price of petroleum. Material reduction therefore decreases the amount of oil needed for the manufacture of plastics and thus help conserve this natural resource. Therefore microcellular foaming process(MCPs) was studied for solving this problems alternatively in 1980's at M.I.T Until now in MCPs carbon dioxide gas was mainly used for microcellular foaming. Besides, Talc was used for reducing the price of plastics. Consequently, we must certificate using the Talc in MCPs according to contents of the Talc.

• 대한안전경영과학회지
• /
• 제18권4호
• /
• pp.115-122
• /
• 2016

Price quotations for SOR / RFQ from OEM clients is a very important process in the automotive parts industry. However, OEM clients are demanding a price quote on short duration but it takes long delivery time due to sales, research and development, purchasing, production and cost management departments role and jobs focused on detail and responsibility. And to provide a reasonable alternative with eliminating the waste of non-value processes is to achieve OEM clients satisfaction through standardized and parallel processing, IT system based on the systems and processes of global benchmark companies.

• 통합자연과학논문집
• /
• 제13권4호
• /
• pp.158-169
• /
• 2020

Modern people live in the age of plastics. It has been widely used due to its easy molding processing, mass production, and excellent durability. However, over-produced plastics for convenience cause plastic disasters and adversely affect the ecosystem. Since the COVID-19 outbreak, the use of single-use plastic waste due to the use of delivery services has increased. The COVID-19 pandemic has caused a plastic pandemic. Currently, domestic recycling policies depend only on recycling collection companies and market prices of recyclable resources. This paper confirms whether the outbreak of COVID-19 has affected the price of plastic waste. It also shows that the price of plastic waste is more unstable than metals with a high recycling rate. This urges businesses to share the cost of recycling on plastic waste, no longer being dependent on market prices for recyclable resources.

• Journal of information and communication convergence engineering
• /
• 제20권2호
• /
• pp.96-102
• /
• 2022

We aim to build predictive models for Airbnb's prices using a GPU-accelerated RAPIDS in a big data cluster. The Airbnb Listings datasets are used for the predictive analysis. Several machine-learning algorithms have been adopted to build models that predict the price of Airbnb listings. We compare the results of traditional and big data approaches to machine learning for price prediction and discuss the performance of the models. We built big data models using Databricks Spark Cluster, a distributed parallel computing system. Furthermore, we implemented models using multiple GPUs using RAPIDS in the spark cluster. The model was developed using the XGBoost algorithm, whereas other models were developed using traditional central processing unit (CPU)-based algorithms. This study compared all models in terms of accuracy metrics and computing time. We observed that the XGBoost model with RAPIDS using GPUs had the highest accuracy and computing time.

• 정보학연구
• /
• 제2권2호
• /
• pp.139-144
• /
• 1999

본 논문은 음성인식 시스템에서 정확도를 높이기 위해 후처리 단계에서 후보 단어들의 엔트로피 정보를 이용하였다. 기존의 우도비 검출방법은 음성 데이터에 따라 음성인식 시스템의 성능이 변하고 N개의 후보단어들의 우도값이 비슷하여 오인식 발생확률이 높았다. 그러나 본 눈문에서는 각 후보 단어들의 엔트로피 값보다 인식대상 단어 외의 단어들의 엔트로피 값이 상대적으로 낮은 후보를 거절하는 후처리 방법을 사용하여 음성 데이터에 독립적이면서도 변별력을 높인 정확한 음성인식 시스템을 얻을 수 있었다. 실험 결과 본 논문에서 제안하는 엔트로피에 의한 후처리 방법은 우도비에 의한 방법보다 인식 시스템의 성능을 false alarm이 20%일 때 최대 3.6% 향상시킬 수 있었다.