• The KIPS Transactions:PartD
• /
• v.13D no.5 s.108
• /
• pp.717-724
• /
• 2006

The cost estimation of software is getting more important as the portion of software is increasing in acquiring weapon systems. However, the cost estimation of embedded software in a weapon system follows the cost estimation method for general purpose softwares and uses the PRICE S model as a tool. However, any validation result of the estimated cost through an evaluated software size is not well known. Hence, we propose an approach to estimate the cost through evaluating the embedded software site in weapon systems. In order to achieve our research goal, we evaluate the software size of using the line of codes and function points which are produced by the PRICE S model. Finally, we compare the estimated cost data the actual cost data provided by the production company. As a result, we propose an approach to estimate the size and the cost of embedded software in weapon systems which are not easy to estimate objectively. We also expect that the Proposed approach is used for the cost validation and negotiation in the acquisition of weapon systems in the future.

• Defense and Technology
• /
• no.8 s.282
• /
• pp.46-55
• /
• 2002

지난 7월호에서는 COCOMO 모델, 기능점수모델, PRICE-S모델, 일반 COSDES 모델 등의 무기체계 S/W 개발비용 산정모델들을 조사 및 분석하여 제시하였다. 이번 8월호에서는 무기체계 소프트웨어 개발비용산저에 영향을 미치는 요소를 기존의 '한소협' 모델, PRICE-S 모델, 기능점수 모델, COCOMO 모델 등 여러 소프트웨어 개발비용 산정모델을 참고 후 무기체계의 특성을 고려하여 식별하였다. 또한 식별된 요소들을 '한소협' 모델의 절차와 방법에 따라 무기체계 소프트웨어의 스텝 수 산정 영향요소, 환경요인 보정계수 영향요소, 제경비 및 기술료 산정 영향요소들을 식별하여 제시하였다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1171-1176
• /
• 2023

In this paper, we predicts the estimated price using the DNBP (Deep learning Network to predict Budget Price) model with bidding data obtained from the bidding websites, ElecNet and OK EMS. We use the DNBP model to predict four lottery preliminary price, calculate their arithmetic mean, and then estimate the expected budget price ratio. We evaluate the model's performance by comparing it with the actual expected budget price ratio. We train the DNBP model by removing some of the 15 input nodes. The prediction results showed the lowest RMSE of 0.75788% when the model had 6 input nodes (a, g, h, i, j, k).

• The KIPS Transactions:PartD
• /
• v.12D no.5 s.101
• /
• pp.737-744
• /
• 2005

As the portion of software cost in construction of the system related to the national defence is getting higher, the required accuracy of cost estimation on defense software in development is also getting higher. The PRICE S is used to estimate the software cost at the first stage in the development of software promptly. However, the PRICE S is appropriate for the American environment not for the Korean circumstances. Thus, we will present a method to compensate the PRICE S with comparing with the model of Korea Software Industry Association. Moreover, we also present another method to estimate software cost based on function point with backfiring approach, which will be used for the software projects planned. Finally, we expect that our works will provide a solution for applying the function point in the future and will increase the accuracy of cost estimation in software development.

• Spatial Information Research
• /
• v.10 no.2
• /
• pp.215-232
• /
• 2002

Variables representing neighborhood quality should be included in hedonic price models to control lfor the influences of negative or positive externalities from the quality of neighborhood on urban housing prices. This study proposes a GIS-based method to effectively measure the neighborhood quality variable when data on the neighborhood quality are aggregated by census sub area. This study also tests the superiority of the proposed neighborhood quality variable created by intensive use of GIS operations to a neighborhood variable not based on GIS operations in explaining the housing price variations by using Seoul＇s apartment sales data. The results from this study show that the neighborhood quality variable based on GIS-based operations shows better performance in explaining the urban housing price variations in Seoul＇s housing market. The implication from the results is that the potentials of GIS-based spatial operations in creating neighborhood quality variables should be well acknowledged by the researchers in the area of urban housing market study and GIS-based spatial operations should be more actively applied to generate better neighborhood quality variables for hedonic price models.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.9
• /
• pp.367-374
• /
• 2021

Stock price prediction is a subject of research in various fields such as economy, statistics, computer engineering, etc. In recent years, researches on predicting the movement of stock prices by learning artificial intelligence models from various indicators such as basic indicators and technical indicators have become active. This study proposes a deep learning model that predicts the ups and downs of KOSPI from overseas indices such as S&P500, past KOSPI indices, and trading trends by KOSPI investors. The proposed model extracts a latent variable using a stacked auto-encoder to predict stock price fluctuations, and predicts the fluctuation of the closing price compared to the market price of the day by learning an LSTM suitable for learning time series data from the extracted latent variable to decide to buy or sell based on the value. As a result of comparing the returns and prediction accuracy of the proposed model and the comparative models, the proposed model showed better performance than the comparative models.

• Spatial Information Research
• /
• v.16 no.4
• /
• pp.489-497
• /
• 2008

Currently, GIS has been widely used in the hedonic analyses of urban apartment housing markets in Korea. In those analyses, the apartment complexes are typically represented as the points or the polygons on the GIS maps and the location variables of the analyses are measured based on the points or the polygons. In this study, the relative performance of the point based approach and the polygon based approach in a GIS based hedonic analysis was compared using the apartment housing market data from the north eastern part of the city of Seoul and Davidson and MacKinnon Test. The results from this study indicate two things. First, two approaches can produce substantially different results in a hedonic price model estimation. Second, the polygon based approach produces a hedonic price model which explains the price variations better than the point based approach. These findings suggest that Korean researchers who are interested in improving quality of hedonic price model estimations and use GIS to measure the location variables for hedonic price models should consider using the polygon based approach with the point based approach. This is because the polygon based approach can produce the location variables with the shortest straight line distances and can explain the housing price variations well.

• KIISE Transactions on Computing Practices
• /
• v.23 no.11
• /
• pp.625-631
• /
• 2017

The stock price prediction for stock markets remains an unsolved problem. Although there have been various overtures and studies to predict the price of stocks scientifically, it is impossible to predict the future precisely. However, stock price predictions have been a subject of interest in a variety of related fields such as economics, mathematics, physics, and computer science. In this paper, we will study fluctuation patterns of stock prices and predict future trends using the Deep learning. Therefore, this study presents the three deep learning models using Tensorflow, an open source framework in which each learning model accepts different input features. We expand the previous study that used simple price data. We measured the performance of three predictive models increasing the number of priced-based input features. Through this experiment, we measured the performance change of the predictive model depending on the price-based input features. Finally, we compared and analyzed the experiment result to evaluate the impact of the price-based input features in stock price prediction.

• The Journal of the Korea Contents Association
• /
• v.13 no.7
• /
• pp.432-439
• /
• 2013

In this study, we evaluate the volatility of housing prices by using literature review and empirical analysis and furthermore we suggest how to improve. In order to diagnose housing market, the KB Bank's House Price Index, Real estate 114;s materials were compared. In addition, to examine the volatility, GARCH (Generalized Autoregressive Conditional Heteroskedasticity) and EGARCH (Exponential GARCH) model are used. By analysis of this research, we found the volatility of housing price also was reduced in the medium and the large houses since 1998, while the volatility of small housing price relatively was large. We proved that the price change rate of small housing was higher than the medium's. On the order hand, the supply of small apartments fell down sharply. The short-term oriented policy should be avoided, and the efficiency and credibility of policy should be increased. Furthermore, the long-term policy system should be established. and rental market's improvement is necessary for stabilization of housing market.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.75-78
• /
• 2014

Discussion of the validity of the software price has been constantly followed in it. For interests friendly relations between the supply provider and consumers, suitable pricing logic is required to convince each other in the market. However, in reality, not only there is no exact calculation standard of the factors that determine the price still, and also lack understanding of the factors. The fact is that by this, each supply company has a software pricing by different criteria, so consumers keep questioning It's a reasonable price. In this paper, it is intended to analyze a variety of factors that influence to the software price and base on this determine a reasonable price formula model of software packages.