• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.949-950
• /
• 2008

The intra prediction technique is the one of the key factors to the success of H.264. There are nine optional prediction modes for each $4{\times}4$ luma block and 4 modes for each $16{\times}16$ luma block. To reduce the intra mode bits efficiently, the most probable mode (MPM) is estimated by using the intra modes of the adjacent blocks, since intra modes for neighboring $4{\times}4$ luma blocks are correlated. In this paper, a new method for estimating the MPM is proposed by using the statistical distribution of intra modes of adjacent intra blocks. Experimental results show that the proposed method can achieve a coding gain of about 0.1dB.

• The Journal of the Korea Contents Association
• /
• v.14 no.10
• /
• pp.527-538
• /
• 2014

The demand prediction is a critical issue for the film industry. As the social media, such as Twitter and Facebook, gains momentum of late, considerable efforts are being dedicated to prediction and analysis of hit movies based on unstructured text data. For prediction of trends found in commercially successful films, the correlations between the amount of data and hit movies may be analyzed by estimating the data variation by period while opinion mining that assigns sentiment polarity score to data may be employed. However, it is not possible to understand why the audience chooses a certain movie or which attribute of a movie is preferred by using such a quantitative approach. This has limited the efforts to identify factors driving a movie's commercial success. In this regard, this study aims to investigate a movie's attributes that reflect the interests of the audience. This would be done by extracting topic keywords that represent the contents of Twits through frequency measurement based on the collected Twitter data while analyzing responses displayed by the audience. The objective is to propose factors driving a movie's commercial success.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.55 no.4
• /
• pp.181-188
• /
• 2006

The purpose of this study is to predict the defibrillation success of a ventricular Fibrillation ECG signal using time-frequency analysis. During CPR, coronary perfusion pressure and electrocardiogram were measured. Parameters extracted from time-frequency domain were served as predictor of resuscitation success. Time frequency distribution(TFD) of ECG signals was estimated from the smoothed pseudo Wigner-Ville distribution(SPWVD). Median frequency, peak frequency, 1/f slope, frequency band ratios$(2{\sim}4Hz,\;4{\sim}6Hz,\;6{\sim}8Hz,\;8{\sim}10Hz,\;10{\sim}12Hz,\;12{\sim}15Hz)$ were extracted from each TFD as function of time. Paired t-test was used to determine the differences in ROSC and non-ROSC groups. In the statistical results, we selected four significant parameters - median frequency, 1/f slope, $2{\sim}4Hz$ band ratio, $8{\sim}10Hz$ band ratio. We made an attempt to predict defibrillation success by combining features extracted from time frequency distribution. Independent t-test was used to determine the differences ROSC and non-ROSC groups. Consequently, we selected four significant parameters-median frequency, 1/f slope, $2{\sim}4Hz$ band ratio, $8{\sim}10Hz$ band ratio. The relationship between coronary perfusion pressure and ECG parameters was analyzed with linear regression analysis. R-square value was 55%. 1/f slope and $8{\sim}10Hz$ band ratio had the significant relationship with coronary perfusion pressure.

• The Journal of Society for e-Business Studies
• /
• v.26 no.2
• /
• pp.19-43
• /
• 2021

The prediction of box office performance in performing arts institutions is an important issue in the performing arts industry and institutions. For this, traditional prediction methodology and data mining methodology using standardized data such as cast members, performance venues, and ticket prices have been proposed. However, although it is evident that audiences tend to seek out their intentions by the performance guide poster, few attempts were made to predict box office performance by analyzing poster images. Hence, the purpose of this study is to propose a deep learning application method that can predict box office success through performance-related poster images. Prediction was performed using deep learning algorithms such as Pure CNN, VGG-16, Inception-v3, and ResNet50 using poster images published on the KOPIS as learning data set. In addition, an ensemble with traditional regression analysis methodology was also attempted. As a result, it showed high discrimination performance exceeding 85% of box office prediction accuracy. This study is the first attempt to predict box office success using image data in the performing arts field, and the method proposed in this study can be applied to the areas of poster-based advertisements such as institutional promotions and corporate product advertisements.

• The Journal of the Korea Contents Association
• /
• v.7 no.7
• /
• pp.161-170
• /
• 2007

E-Business has, nowadays, become a common commerce transaction. In the beginning, e-Biz has known as Electronic Commerce and has expanded its territory to department store's shopping mall, travel, finance, stock, and even luxury goods as car sales market. Considering these trends, this paper researched the environment of korean e-Biz market and suggested the picture of the matured and sound e-Biz market in Korea. We surveyed matured level of Critical Success Factors of e-Biz in terms of management. We also surveyed time based Critical Success Factors to analyze level of the Korean e-Biz market. These study's may provide us the knowledge about the prediction and preparation for changes in e-Biz market in the future.

• The Journal of Information Technology
• /
• v.3 no.3
• /
• pp.11-26
• /
• 2000

This is to study that effects in a company's success with using the new information technology. Here It was confirmed that an existing information technology resulted in a positive bias in managers' thought of new technology had been effected in success. This is more stronger among managers who had greater amounts of experience with the existing technology and among managers whose companies did not engage in proactive information seeking about new information technologies. Even though it has demonstrated that manager's understanding of a strategic issue have and important impact on organizational actions, the research on strategic issue has gotten little attention to the determinants of those interpretations. This suggests that an prior experience of information technology will be affected in manager's strategic issue about applying new IT.

• International conference on construction engineering and project management
• /
• 2015.10a
• /
• pp.523-526
• /
• 2015

In recent years, building commissioning has often been part of a standard delivery practice in construction, particularly in the high-performance green building market, to ensure the building is designed and constructed per owner's requirements. Commissioning, therefore, intends to provide quality assurance that buildings perform as intended by the design and often helps achieve energy savings. Commissioning, however, is not as widely adopted as its potential benefits are perceived. Owners are still skeptical of the cost-effectiveness claims by energy management and commissioning professionals. One of the issues in the current commissioning practice is that not every project is guaranteed to benefit from the commissioning services. This, coupled with its added cost, the commissioning service is not acquired with great acceptance and confidence by building owners. To overcome this issue, this paper presents a unique methodology to enhance owner's predicting capability of the degree of success of commissioning service using the Bayesian theorem. The paper analyzes a situation where a future building owner wants to use a pre-commissioning in an attempt to refine the success rate of the future commissioned building performance. The author proposes the Bayesian theorem based framework to improve the current commissioning practice where building owners are not given accurate information how much successful their projects are going to be in terms of energy savings from the commissioning service. What should be provided to the building owners who consider their buildings to be commissioned is that they need some indicators how likely their projects benefit from the commissioning process. Based on this, the owners can make better informed decisions whether or not they acquire a commissioning service.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.1
• /
• pp.63-69
• /
• 2010

Ensemble is one of widely used methods for improving the performance of classification and prediction models. Two popular ensemble methods, Bagging and Boosting, have been applied with great success to various machine learning problems using mostly decision trees as base classifiers. This paper performs an empirical comparison of Boosted neural networks and traditional neural networks on bankruptcy prediction tasks. Experimental results on Korean firms indicated that the boosted neural networks showed the improved performance over traditional neural networks.

• Educational Technology International
• /
• v.15 no.2
• /
• pp.71-88
• /
• 2014

A variety of studies to predict students' performance have been conducted since educational data such as web-log files traced from Learning Management System (LMS) are increasingly used to analyze students' learning behaviors. However, it is still challenging to predict students' learning achievement in blended learning environment where online and offline learning are combined. In higher education, diverse cases of blended learning can be formed from simple use of LMS for administrative purposes to full usages of functions in LMS for online distance learning class. As a result, a generalized model to predict students' academic success does not fulfill diverse cases of blended learning. This study compares two blended learning classes with each prediction model. The first blended class which involves online discussion-based learning revealed a linear regression model, which explained 70% of the variance in total score through six variables including total log-in time, log-in frequencies, log-in regularities, visits on boards, visits on repositories, and the number of postings. However, the second case, a lecture-based class providing regular basis online lecture notes in Moodle show weaker results from the same linear regression model mainly due to non-linearity of variables. To investigate the non-linear relations between online activities and total score, RF (Random Forest) was utilized. The results indicate that there are different set of important variables for the two distinctive types of blended learning cases. Results suggest that the prediction models and data-mining technique should be based on the considerations of diverse pedagogical characteristics of blended learning classes.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.28 no.10
• /
• pp.1255-1263
• /
• 2004

An a priori test has been conducted for the dynamic mixed model which was generalized for the prediction of passive scalar field in a turbulent channel flow The results from a priori tests indicated that dynamic mixed model is capable of predicting both subgrid-scale heat flux and dissipation rather accurately. The success is attributed to the explicitly calculated resolved term incorporated into the model. The actual test of the model in a LES a posteriori showed that dynamic mixed model is superior to the widely used dynamic Smagorinsky model in the prediction of temperature statistics.