• The Journal of Society for e-Business Studies
• /
• v.26 no.3
• /
• pp.1-20
• /
• 2021

As the Great Reset is discussed at the World Economic Forum due to the COVID-19 pandemic, artificial intelligence, the driving force of the 4th industrial revolution, is also in the spotlight. However, corporate research in the field of artificial intelligence is still scarce. Since 2000, related research has focused on how to create value by applying artificial intelligence to existing companies, and research on how startups seize opportunities and enter among existing businesses to create new value can hardly be found. Therefore, this study analyzed the cases of startups using the comprehensive framework of the multi-level perspective with the research question of how artificial intelligence based startups, a sub-industry of software, have different innovation patterns from the existing software industry. The target firms are gazelle firms that have been certified as venture firms in South Korea, as start-ups within 7 years of age, specializing in machine learning modeling purposively sampled in the medical, finance, marketing/advertising, e-commerce, and manufacturing fields. As a result of the analysis, existing software companies have achieved process innovation from an enterprise-wide integration perspective, in contrast machine learning technology based startups identified unit processes that were difficult to automate or create value by dismantling existing processes, and automate and optimize those processes based on data. The contribution of this study is to analyse the birth of artificial intelligence-based startups and their innovation patterns while validating the framework of an integrated multi-level perspective. In addition, since innovation is driven based on data, the ability to respond to data-related regulations is emphasized even for start-ups, and the government needs to eliminate the uncertainty in related systems to create a predictable and flexible business environment.

• Journal of Industrial Convergence
• /
• v.20 no.4
• /
• pp.23-30
• /
• 2022

Recently, with the development of artificial intelligence (AI) and deep learning, the importance of conversational artificial intelligence chatbots is being highlighted. In addition, chatbot research is being conducted in various fields. To build a chatbot, it is developed using an open source platform or a commercial platform for ease of development. These chatbot platforms mainly use RNN and application algorithms. The RNN algorithm has the advantages of fast learning speed, ease of monitoring and verification, and good inference performance. In this paper, a method for improving the inference performance of RNNs and applied algorithms was studied. The proposed method used the word group expansion learning technique of key words for each sentence when RNN and applied algorithm were applied. As a result of this study, the RNN, GRU, and LSTM three algorithms with a cyclic structure achieved a minimum of 0.37% and a maximum of 1.25% inference performance improvement. The research results obtained through this study can accelerate the adoption of artificial intelligence chatbots in related industries. In addition, it can contribute to utilizing various RNN application algorithms. In future research, it will be necessary to study the effect of various activation functions on the performance improvement of artificial neural network algorithms.

• Journal of Space Technology and Applications
• /
• v.1 no.1
• /
• pp.23-32
• /
• 2021

The high-level Space Situational Awareness (SSA) objective is to provide to the users dependable, accurate and timely information in order to support risk management on orbit and during re-entry and support safe and secure operation of space assets and related services. Therefore the risk assessment for the re-entry of space objects should be managed nationally. In this research, the Software for Re-Entry Prediction of space objects (SREP) was developed for national SSA system. In particular, the rate of change of the drag coefficient is estimated through a newly proposed Drag Scale Factor Estimation (DSFE), and is used for high-precision orbit propagator (HPOP) up to an altitude of 100 km to predict the re-entry time and position of the space object. The effectiveness of this re-entry prediction is shown through the re-entry time window and ground track of space objects falling in real events, Grace-1, Grace-2, Tiangong-1, and Chang Zheng-5B Rocket body. As a result, through analysis 12 hours before the final re-entry time, it is shown that the re-entry time window and crash time can be accurately predicted with an error of less than 20 minutes.

• Korean Journal of Construction Engineering and Management
• /
• v.22 no.4
• /
• pp.29-40
• /
• 2021

Recently, interest in Building Information Modeling (BIM) has increased globally, and 3D modeling is a start for the application of BIM at construction sites. However, while many studies have been conducted on the efficiency of 3D modeling focused on civil facilities, there is a lack of research on the earthwork BIM. In particular, since 3D slope often has complex shapes depending on the ground models, the efficiency method for 3D slope are needed. This study analyzed the interfaces and procedures of other software to find out what functions users need. Then the functions to enter intervals between 3D faces, select multiple ground models, and improve the interface are reflected on the developed system and is able to efficiently perform modeling with only five steps, and reduce the number of clicks and inputs. As a result of conducting the test to verify the efficiency, using the developed system made skilled users complete modeling at least 1.8 times faster and unskilled people at least 2.4 times faster than using other software. This is expected to perform 3D slope modeling more efficiently, as well as to contribute to the activation of future BIM adoption for housing construction projects.

• Smart Media Journal
• /
• v.12 no.2
• /
• pp.56-65
• /
• 2023

In broadcasts such as news and coverage programs, voice is modulated to protect the identity of the informant. Adjusting the pitch is commonly used voice modulation method, which allows easy voice restoration to the original voice by adjusting the pitch. Therefore, since broadcast voice modulation methods cannot properly protect the identity of the speaker and are vulnerable to security, a new voice modulation method is needed to replace them. In this paper, using the Lightweight speech de-identification model as the evaluation target model, we compare speech de-identification performance with broadcast voice modulation method using pitch modulation. Among the six modulation methods in the Lightweight speech de-identification model, we experimented on the de-identification performance of Korean speech as a human test and EER(Equal Error Rate) test compared with broadcast voice modulation using three modulation methods: McAdams, Resampling, and Vocal Tract Length Normalization(VTLN). Experimental results show VTLN modulation methods performed higher de-identification performance in both human tests and EER tests. As a result, the modulation methods of the Lightweight model for Korean speech has sufficient de-identification performance and will be able to replace the security-weak broadcast voice modulation.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.13 no.6
• /
• pp.96-105
• /
• 2017

In this paper, we investigated the age classification from the speaker by analyzing the voice calls of the emergency center. We classified the adult and elderly from the call center calls using behavioral speech utterances and SVM(Support Vector Machine) which is a machine learning classifier. We selected two behavioral speech utterances through analysis of the call data from the emergency center: Silent Pause and Turn-taking latency. First, the criteria for age classification selected through analysis based on the behavioral speech utterances of the emergency call center and then it was significant(p <0.05) through statistical analysis. We analyzed 200 datasets (adult: 100, elderly: 100) by the 5 fold cross-validation using the SVM(Support Vector Machine) classifier. As a result, we achieved 70% accuracy using two behavioral speech utterances. It is higher accuracy than one behavioral speech utterance. These results can be suggested age classification as a new method which is used behavioral speech utterances and will be classified by combining acoustic information(MFCC) with new behavioral speech utterances of the real voice data in the further work. Furthermore, it will contribute to the development of the emergency situation judgment system related to the age classification.

• Informatization Policy
• /
• v.31 no.2
• /
• pp.82-104
• /
• 2024

Smart home services are growing rapidly as the development of the Internet of Things (IoT) opens the era of the so-called "Connected Living." Although personal information leaks through smart home cameras are increasing, however, users-while concerned-tend to take passive measures to protect their personal information. This study theoretically explained and verified how to design effective software update notification messages for smart home cameras to ensure that users comply with the recommended security behavior (i.e., update installation). In a survey experiment participated in by 120 actual users, the effectiveness of both emotional appeals (i.e., security breach warning images for fear appeals) and rational appeals (i.e., loss-framed messages emphasizing the negative consequences of not installing the updates) were confirmed. The results of this study provide theoretical interpretations and practical guidelines on the message design features that are effective for threat appraisals (i.e., severity, vulnerability) of smart home camera users and their protection motivation.

• The Bulletin of The Korean Astronomical Society
• /
• v.40 no.1
• /
• pp.75.4-76
• /
• 2015

우리는 동아시아 각국(대한민국, 중국, 일본)의 VLBI관측망을 통합하고 구성될 동아시아 VLBI 관측망(East Asia VLBI Network; EAVN)의 초기 검증 작업을 진행하고 있다. EAVN은 2 ~ 129 GHz로 관측이 가능하는데, 주로 6.7, 8, 22, 43 GHz로의 관측을 상정하고 있다. 또한 최대 기선장은 약 5,000 km으로 공간분해능은 약 0.3 mas(43 GHz로의 관측의 경우)가 된다. 높은 공간분해능과 고감도의 특징을 활용하고 저광도 활동성은하핵이나 우리 은하의 메이저 천체 등의 연구에 대해서 위력을 나타낼 수가 있다. 우리는 EAVN 시험관측, 상관처리, 자료처리의 실행, 및 그것들을 통한 EAVN 운영의 검증을 하는 EAVN Tiger Team을 2013년에 조직하고 현재까지에 8 GHz 및 22 GHz로 8회의 VLBI 시험관측을 실행하였다. 상관처리는 주로 한국천문연구원에서 운영하고 있는 한일 공동상관기(KJJVC)와 상하이천문대의 소프트웨어 상관기(DiFX)로 실행되어 있다. 현재까지에 8 GHz 및 22 GHz 쌍방에서 프린지검출에 성공하고 있고, 올해는 영상합성을 포함한 과학적인 관측을 진행할 예정이다. 이 발표에서는 EAVN의 개요와 과학목표, 시험관측 현황과 결과, 및 앞으로의 운영 계획 등을 소개하겠다.

• Aerospace Engineering and Technology
• /
• v.13 no.2
• /
• pp.7-17
• /
• 2014

This technical paper deals with development of on-board orbit generation algorithm for GEO Satellite. This paper presents the research analysis results performed in order to improve the accuracy of the existing algorithm used for generating real-time orbit information for GEO satellite. The error impact on orbit accuracy due to the orbit error sources were analyzed with the algorithm suggested by this research. As a result of the analyses, it is found that the initial orbit should be determined with an accuracy of less than 50 m and the reference position angle error for the ground station and the satellite should be maintained within ${\pm}0.0025deg$ in order to meet the orbit accuracy specification. The development of on-board flight software based on the new algorithm was accomplished and the performance verification is ongoing by using a software based performance verification tool.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.42 no.5
• /
• pp.406-414
• /
• 2014

In this paper, it is introduced characteristics of FMCW-type Radar Altimeter for KUH, and its defects occurred during ground/flight test in initial product phase. In addition, it is also described 'data/control flow model' based fault analysis results of S/W and processes of verifying improvement design through flight test as well as aircraft system integration test called MEP SIL. As a result of design improvement and verification, it is validated that settling the defects and improving not only safety but also capability of the KUH.