• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.42 no.3
• /
• pp.109-115
• /
• 2019

Most demand forecasting studies for telecommunication services have focused on estimating market size at the introductory stage of new products or services, or on suggesting improvement methods of forecasting models. Although such studies forecast business growth and market sizes through demand forecasting for new technologies and overall demands in markets, they have not suggested more specific information like relative market share, customers' preferences on technologies or service, and potential sales power. This study focuses on the telecommunication service industry and explores ways to calculate the relative market shares between competitors, considering competitive situations at the introductory stage of a new mobile telecommunication service provider. To reflect the competitive characteristics of the telecommunication markets, suggested is an extended conjoint analysis using service coverage and service switching rates as modification variables. This study is considered to be able to provide strategic implications to businesses offering existing service and ones planning to launch new services. The result of analysis shows that the new service provider has the greatest market share at the competitive situation where the new service covers the whole country, offers about 50% of existing service price, and allows all cellphones except a few while the existing service carrier maintains its price and service and has no response to the new service introduction. This means that the market share of the new service provider soars when it is highly competitive with fast network speed and low price.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.2
• /
• pp.139-148
• /
• 2019

The paper proposes an analytical framework for the impact of technical change on business model innovation. Based upon the examination of the relationship between the mission of business and technology, it introduces classification of technology-based business models such as problem-solving model, production model and network model, respectively employing intensive technology, interlinked technology and mediating technology as a key technology. The discussion of various cases of business model innovation shows that the impact of digital technology is first translated into the value generation in terms of efficiency or effectiveness. These new values then enable a new business model which is based on a different key technology through business model shift, expansion, unbundling, or platform. Quite often those business model changes involves system-wide innovation. The framework for the analysis of the impact of technical change on business model innovation is presented with directions for future research.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.1
• /
• pp.121-128
• /
• 2019

An Internet of Things(IoT) technology which provides intelligent services by combining context-awareness based intelligences, inter-communication is made of between things and things or between things and person through the network connected with intelligent things is spreading rapidly. Especially as this technology is converged into smart device, mobile, cloud, big data technologies, it is applied into various domains. Therefore, this is different from existing Web or Mobile Application. New types of IoT applications are emerging by adapting IoT into Web or mobile. Because IoT application is not only focused on software but also considering hardware or things aspect, there are limitations existing development process. Existing development processes don't consider analysis and design techniques considering both hardware and things. We propose not only a meta-model for development process which can support IoT application's development but also meta-models for main activities in this paper. Especially we define modeling elements by using UML's extension mechanisms, provide development process, and suggest design techniques how to apply those elements into IoT application's modeling phase. Because there are many types of IoT application's type, we propose an Android and Arduino-based on IoT application as a case study. We expect that proposed technique can be applied into many of various IoT application development and design with a form of flexible and extensible as well as main functionalities or elements are more concretely described. As a result, it brings IoT application's flexibility and the effect of quality improvement.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.1
• /
• pp.80.1-80.1
• /
• 2019

Photometric investigations of asteroids allow us to determine their rotation states and shape models (Apostolovska et al. 2014). Our main target, asteroid (2078) Nanking's perihelion distance (q) is 1.480 AU, which belongs to the Mars-crossing asteroid (1.3 < q < 1.66 AU). Mars-crossing asteroids are objects that cross the orbit of Mars and regarded as one of the primary sources of near-Earth asteroids due to the unstable nature of their orbits. We present the analysis of the spin parameters and 3D shape model of (2078) Nanking. We conducted Cousins_R-band time-series photometry of this asteroid from November 26, 2014 to January 17, 2015 at the Sobaeksan Optical Astronomy Observatory (SOAO) and for 25 nights from March to April 2016 using the Korea Microlensing Telescope Network (KMTNet) to reconstruct its physical model with our dense photometric datasets. Using the lightcurve inversion method (Kaasalainen & Torppa 2001; Kaasalainen et al. 2001), we determine the pole orientation and shape model of this object based on our lightcurves along with the archival data obtained from the literatures. We derived rotational period of 6.461 h, the preliminary ecliptic longitude (${\lambda}_p$) and latitude (${\beta}_p$) of its pole as ${\lambda}_p{\sim}8^{\circ}$ and ${\beta}_p{\sim}-52^{\circ}$ which indicates a retrograde rotation of the body. From the apparent W UMa-shaped lightcurve and its location in the rotation frequency-amplitude plot of Sheppard and Jewitt (2004), we suspect the contact binary nature of the body (Choi 2016).

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.1
• /
• pp.123-130
• /
• 2021

With the recent developments in computer technology, there has been an increasing interest in the field of machine learning. This also has led to a significant increase in real business cases of machine learning theory in various sectors. In finance, it has been a major challenge to predict the future value of financial products. Since the 1980s, the finance industry has relied on technical and fundamental analysis for this prediction. For future value prediction models using machine learning, model design is of paramount importance to respond to market variables. Therefore, this paper quantitatively predicts the stock price movements of individual stocks listed on the KOSPI market using machine learning techniques; specifically, the reinforcement learning model. The DQN and A2C algorithms proposed by Google Deep Mind in 2013 are used for the reinforcement learning and they are applied to the stock trading strategies. In addition, through experiments, an input value to increase the cumulative profit is selected and its superiority is verified by comparison with comparative algorithms.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.3
• /
• pp.175-181
• /
• 2021

This paper analyzes the artificial intelligence-based approach for short-term energy consumption prediction. In this paper, we employ the reinforcement learning algorithms to improve the limitation of the supervised learning algorithms which usually utilize to the short-term energy consumption prediction technologies. The supervised learning algorithm-based approaches have high complexity because the approaches require contextual information as well as energy consumption data for sufficient performance. We propose a deep reinforcement learning algorithm based on multi-agent to predict energy consumption only with energy consumption data for improving the complexity of data and learning models. The proposed scheme is simulated using public energy consumption data and confirmed the performance. The proposed scheme can predict a similar value to the actual value except for the outlier data.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.12 no.3
• /
• pp.103-118
• /
• 2002

To provide the privacy of transmitted message over network the use of cryptographic system is increasing gradually. Because the security and reliability of the cryptographic system is totally rely on the key, the key management is the most important part of the cryptographic system. Although there are a lot of security products providing encryption, the security of the key exchange protocols used in the product are not mostly proved yet. Therefore, we have to study properties and operation of key agreement protocols based on elliptic curve in ANSI X9.63. furthermore, we analyze the security of their protocols under passive and active attacker models and propose the most suitable application field taking the feature of the protocols into account.

• Journal of Convergence for Information Technology
• /
• v.11 no.6
• /
• pp.270-281
• /
• 2021

With the development of information technology, the size of insurance fraud is increasing rapidly every year, and the method is being organized and advanced in conspiracy. Although various forms of prediction models are being studied to predict and detect this, insurance-related information is highly sensitive, which poses a high risk of sharing and access and has many legal or technical constraints. In this paper, we propose a machine learning insurance fraud prediction model based on blockchain, one of the most popular technologies with the recent advent of the Fourth Industrial Revolution. We utilize blockchain technology to realize a safe and trusted insurance information sharing system, apply the theory of social relationship analysis for more efficient and accurate fraud prediction, and propose machine learning fraud prediction patterns in four stages. Claims with high probability of fraud have the effect of being detected at a higher prediction rate at an earlier stage, and claims with low probability are applied differentially for post-reference management. The core mechanism of the proposed model has been verified by constructing an Ethereum local network, requiring more sophisticated performance evaluations in the future.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.8
• /
• pp.1-9
• /
• 2019

With the development of imaging information communication technology in modern society, imaging acquisition and mass production technology have developed rapidly. However, crime rates using these technology are increased and forensic studies are conducted to prevent it. Identification techniques for image acquisition devices are studied a lot, but the field is limited to images. In this paper, camera model identification technique for video, not image is proposed. We analyzed video frames using the trained model with images. Through training and analysis by considering the frame characteristics of video, we showed the superiority of the model using the P frame. Then, we presented a video camera model identification system by applying a majority-based decision algorithm. In the experiment using 5 video camera models, we obtained maximum 96.18% accuracy for each frame identification and the proposed video camera model identification system achieved 100% identification rate for each camera model.

• Journal of the Institute of Convergence Signal Processing
• /
• v.21 no.3
• /
• pp.121-126
• /
• 2020

Sound-based machine fault diagnosis is the automatic detection of abnormal sound in the acoustic emission signals of the machines. Conventional methods of using mathematical models were difficult to diagnose machine failure due to the complexity of the industry machinery system and the existence of nonlinear factors such as noises. Therefore, we want to solve the problem of machine fault diagnosis as a deep learning-based image classification problem. In the paper, we propose a CNN-based automatic machine fault diagnosis method using Spectrogram images. The proposed method uses STFT to effectively extract feature vectors from frequencies generated by machine defects, and the feature vectors detected by STFT were converted into spectrogram images and classified by CNN by machine status. The results show that the proposed method can be effectively used not only to detect defects but also to various automatic diagnosis system based on sound.