• Annual Conference of KIPS
• /
• 2023.05a
• /
• pp.522-524
• /
• 2023

위치 기반 서비스(LBS)의 확산으로 다양한 분야에서 활용할 수 있는 많은 양의 경로 데이터가 생성되고 있다. 하지만 공격자가 경로 데이터를 통해 잠재적으로 사용자의 개인정보를 유추할 수 있다는 문제점이 존재한다. 따라서 경로 데이터의 프라이버시를 보존하며 유용성을 유지할 수 있는 GAN(Generative Adversarial Network)을 사용한 많은 연구가 진행되고 있다. 그러나 GAN은 생성된 결과물을 제어하지 못한다는 한계점을 가지고 있다. 본 논문에서는 ACGAN(Auxiliary classifier GAN)을 통해 생성된 결과물을 제어함으로써 경로 데이터의 민감한 정점을 숨기고, Attention mechanism을 결합하여 높은 유용성과 익명성을 제공하는 합성 경로 생성 모델인 TAP-GAN(Trajectory attention and protection-GAN)을 제안한다. 또한 모델의 성능을 입증하기 위해 유용성 및 익명성 실험을 진행하고, 선행 연구 모델과의 비교를 통해 TAP-GAN이 경로 데이터의 유용성을 보장하면서 사용자의 프라이버시를 효과적으로 보호할 수 있음을 확인하였다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.2 no.1
• /
• pp.12-18
• /
• 2001

SAR radar and FLIR images, which are taken from sensors on aircrafts or satellites, are compressed prior to transmission to facilitate rapid transfer through the limited bandwidth channels. In this case, it is important that it achieves compression ratio as high as possible as well as high target detection rate. In this paper a joint ATR-compression system based on the subband coding and VQ is proposed, which utilizes the encoder as a predictor or classifier for target detection. Simulation result shows that the proposed system achieves a relatively high level of target detection performance as well as a high compression ratio over 200:1.

• Journal of Broadcast Engineering
• /
• v.13 no.2
• /
• pp.236-244
• /
• 2008

We propose a new building detection and description algorithm for Lidar data and photogrammetric imagery using color segmentation, line segments matching, perceptual grouping. Our algorithm consists of two steps. In the first step, from the initial building regions extracted from Lidar data and the color segmentation results from the photogrammetric imagery, we extract coarse building boundaries based on the Lidar results with split and merge technique from aerial imagery. In the secondstep, we extract precise building boundaries based on coarse building boundaries and edges from aerial imagery using line segments matching and perceptual grouping. The contribution of this algorithm is that color information in photogrammetric imagery is used to complement collapsed building boundaries obtained by Lidar. Moreover, linearity of the edges and construction of closed roof form are used to reflect the characteristic of man-made object. Experimental results on multisensor data demonstrate that the proposed algorithm produces more accurate and reliable results than Lidar sensor.

• Convergence Security Journal
• /
• v.20 no.2
• /
• pp.123-135
• /
• 2020

Since AlphaGo's Match in 2016, there has been a growing calls for artificial intelligence applications in various industries, and research related to it has been actively conducted. The same is true in the military field, and since there has been no weapon system with artificial intelligence so far, effort to implement it are posing a challenge. Meanwhile, AlphaGo Zero, which beat AlphaGo, showed that artificial intelligence's self-training data-based approach can lead to better results than the knowledge-based approach by humans. Taking this point into consideration, this paper proposes to apply Reinforcement Learning, which is the basis of AlphaGo Zero, to the Shipboard Combat System or Combat Management System. This is how an artificial intelligence application to the Shipboard Combat System or Combat Management System that allows the optimal tactical assist with a constant win rate to be recommended to the user, that is, the commanding officer and operation personnel. To this end, the definition of the combat performance of the system, the design plan for the Shipboard Combat System, the mapping with the real system, and the training system are presented to smoothly apply the current operations.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.27 no.5
• /
• pp.130-138
• /
• 2023

In this study, experimental and analytical studies were conducted on the structural performance of permanent steel formed wide beams in construction stage. Four specimens were fabricated with different rib spacings of the side steel formwork and fixing plate depths, and experimental tests were performed to investigate the effects of variables on the structural performance. Also, an finite element analysis model of the steel permanent formwork wide beam was proposed based on the test results. Using the proposed model, parametric studies were performed with variables including rib spacing of the bottom and side steel formwork, spacing, depth, and thickness of the fixing plate to derive optimized details. Furthermore, an artificial neural network model was developed to easily estimate the deformation of the steel permanent formwork wide beam with various details.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.5
• /
• pp.715-723
• /
• 2024

The purpose of this study was to identify research trends related to future education through keyword network analysis. To this end, 308 academic papers and master's and doctoral dissertations published from 2000 to 2023 in Korea, and 146 keywords were selected for analysis, divided into 5 periods, and used and analyzed with the Microsoft Excel 365 program and NetMiner 4 program. The results of the study are as follows. First, the publication of future education research has steadily increased since 2000, but has increased significantly since the second half of the 2010s, and the number has exploded in 2021. Second, the number of new keywords that emerged in future education research has increased in recent times, but the frequency of 'future society' keywords appearing in all periods has been high. Third, in future education research results, the number of keywords that simultaneously appear among keywords has increased as time passes, and the contents of keywords that simultaneously have changed in various ways. This study is meaningful in that it suggested the direction of future education by analyzing the past and present of future education with artificial intelligence more than 20 years later.

• Journal of Wetlands Research
• /
• v.17 no.4
• /
• pp.428-435
• /
• 2015

Constructed wetlands (CWs) have been accepted as an attractive and economic alternative to a variety of pollution control and provided potentially valuable wildlife habitat in urban and suburban areas, as well as esthetic value within the local natural environment. CWs are known eco-friendly technology to solve the problem of the climate change and urbanization issues. Numerous studies have been published on the various aspects of a CW. However, there are current limitations about the CW operations such as few design guidelines, poor performance results regarding the simple construction. Therefore, the objective of this research was to suggest an appropriate design and maintenance guidelines for a CW by thorough investigation of site monitoring results. The research also concentrated in redefining and reclassifying CWs, based on literatures made by the Ministry of Environment (MOE) and other organizations. Investigation at 43 CWs in Korea was performed by using collected data and by performing site survey from 2013 to 2014. Based on the results, the best practices among the investigated CWs provided water treatment, wildlife habitat, environmental education, and leisure. Also these CWs conducted a regular maintenance such as vegetation, sediment dredging and cleaning of facilities. Results obtained are intended for use by academics and any organizations involved in CW management.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.4
• /
• pp.309-314
• /
• 2023

This study examines the development and limitations of current artificial intelligence (AI) music composition programs. AI music composition programs have progressed significantly owing to deep learning technology. However, they possess limitations pertaining to the creative aspects of music. In this study, we collect, compare, and analyze information on existing AI-based music composition programs and explore their technical orientation, musical concept, and drawbacks to delineate future directions for AI music composition programs. Furthermore, this study emphasizes the importance of developing AI music composition programs that create "personalized" music, aligning with the era of personalization. Ultimately, for AI-based composition programs, it is critical to extensively research how music, as an output, can touch the listeners and implement appropriate changes. By doing so, AI-based music composition programs are expected to form a new structure in and advance the music industry.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.6 no.12
• /
• pp.587-594
• /
• 2016

Autonomous A.I. vehicles are seemingly soon ready for our life. One of the critical problems with autonomous vehicles is how one could assign responsibility for accidents to them. We can envisage that autonomous vehicles may confront an ethical dilemma. Then a question arises of how we are able to assign legal responsibility to autonomous vehicles. In this paper, I first introduce what the ethical dilemma of autonomous vehicles is about. Second, I show how we could be able to assign legal responsibility for autonomous vehicles. Legal probability is the received criteria for causal responsibility most of the legal theorists consider. But it remains vague. I articulate the concept of legal probability in terms of the probabilitstic theory of individual level causality while considering how one can assign causal responsibility for autonomous vehicles. My theory of causal responsibility may help one to assign legal responsibility not just for autonomous vehicles but also for people.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.533-535
• /
• 2021

The differences between this study and previous studies are as follows. First, by building a cloud-based system using IoT technology, the system was built to monitor the status of buildings in real time from anywhere with an internet connection. Second, a model for predicting the future was developed using artificial intelligence (LSTM) and statistical (ARIMA) methods for the measured time series sensor data, and the effectiveness of the proposed prediction model was experimentally verified using a scaled-down building model. Third, a method to analyze the condition of a building more three-dimensionally by visualizing the structural deformation of a building by convergence of multiple sensor data was proposed, and the effectiveness of the proposed method was demonstrated through the case of an actual earthquake-damaged building.