• Journal of IKEEE
• /
• v.24 no.3
• /
• pp.743-753
• /
• 2020

In this paper, we propose a set of robustness indicators for immersive 360-degree video. With the full-fledged service of mobile carriers' 5G networks, it is possible to use large-capacity, immersive 360-degree videos at high speed anytime, anywhere. Since it can be illegally distributed in web-hard and torrents through DRM dismantling and various video modifications, however, evaluation indicators that can objectively evaluate the filtering performance for copyright protection are required. In this paper, a robustness indicators is proposed that applies the existing 2D Video robustness indicators and considers the projection method and reproduction method, which are the characteristics of Immersive 360-degree Video. The performance evaluation experiment has been carried out for a sample filtering system and it is verified that an excellent recognition rate of 95% or more has been achieved in about 3 second execution time.

• Structural Engineering and Mechanics
• /
• v.65 no.6
• /
• pp.689-698
• /
• 2018

This study focuses on a novel procedure for the robustness assessment of reinforced concrete (RC) framed structures under threat-independent damage scenarios. The procedure is derived from coupled dynamic and non-linear static analyses. Two robustness indicators are defined and the method is applied to two RC frame buildings. The first building was designed for gravity load and earthquake resistance in accordance with Eurocode 8. The second was designed according to the tie force (TF) method, one of the design quantitative procedures for enhancing resistance to progressive collapse. In addition, in order to demonstrate the suitability and applicability of the TF method, the structural robustness and resistance to progressive collapse of the two designs is compared.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.5
• /
• pp.997-1008
• /
• 2022

Today, AI(Artificial Intelligence) technology is being extensively researched in various fields, including the field of malware detection. To introduce AI systems into roles that protect important decisions and resources, it must be a reliable AI model. AI model that dependent on training dataset should be verified to be robust against new attacks. Rather than generating new malware detection, attackers find malware detection that succeed in attacking by mass-producing strains of previously detected malware detection. Most of the attacks, such as adversarial attacks, that lead to misclassification of AI models, are made by slightly modifying past attacks. Robust models that can be defended against these variants is needed, and the Robustness level of the model cannot be evaluated with accuracy and recall, which are widely used as AI evaluation indicators. In this paper, we experiment a framework to evaluate robustness level by generating an adversarial sample based on one of the adversarial attacks, C&W attack, and to improve robustness level through adversarial training. Through experiments based on malware dataset in this study, the limitations and possibilities of the proposed method in the field of malware detection were confirmed.

• Ocean and Polar Research
• /
• v.32 no.2
• /
• pp.137-144
• /
• 2010

There is a host of habitat assessment systems available to evaluate and grade tidal flat ecosystems in Korea. Nevertheless, we recognize the need to develop a better ecological scheme to improve reliability and accuracy given the importance of using an empirical approach in assigning grades to indicators and the limitation of current systems which evaluate tidal flats on a regional basis. A preferable system would be one that enables habitat mapping within a tidal flat, provides a diagnosis of ecological stress/health, has a high level of ecological relevance, communicability, and statistical robustness, and enables evaluation of diverse habitats within a tidal flat. The following points should be considered in framing such a system. Indicators should discriminate habitat quality into five to seven grades accomodating diverse characteristics and conservation value of a habitat, and the grading should be made from frequency distribution of indicators based on nationwide data.We suggest the following tasks in crafting such a system: i) The decision on selection of indicators should be made based on accuracy of assessment and practical application; ii) effects of physical habitat conditions on variability of indicators should be reflected; and, iii) further works on stress/health indicators should be addressed for adopting a multiple-indicator approach which reduces misdiagnosis.

• International Journal of Computer Science & Network Security
• /
• v.23 no.7
• /
• pp.210-218
• /
• 2023

The author presents a simple data-driven intraday technical indicator trading approach based on Genetic Programming (GP) for return forecasting in the Bitcoin market. We use five trend-following technical indicators as input to GP for developing trading rules. Using data on daily Bitcoin historical prices from January 2017 to February 2020, our principal results show that the combination of technical analysis indicators and Artificial Intelligence (AI) techniques, primarily GP, is a potential forecasting tool for Bitcoin prices, even outperforming the buy-and-hold strategy. Sensitivity analysis is employed to adjust the number and values of variables, activation functions, and fitness functions of the GP-based system to verify our approach's robustness.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.437-438
• /
• 2020

국내 실감형 콘텐츠 시장은 전년도비 42.9%의 연평균 성장률을 보이며 2020년에는 약 5조 7,271억원의 규모에 이를 것으로 전망된다. 특히 2018년 기점으로 하드웨어보다는 콘텐츠 시장이 확대되었다. 최근 실감형 콘텐츠의 유통이 본격적으로 시작됨에 따라 저작권 침해 사례들이 나타나고 있으나 시장의 저변확대 측면에서 그렇게 주목받지 못하고 있다. 실감형 저작물을 제작하는 업체가 주로 소기업이고, 제작하는 비용이 고비용인 점을 고려할 때 저작권 보호 기술인 필터링 기술이 절대적으로 요구되고 있다. 필터링 기술의 성능 평가할 기준인 강인성 지표가 미정립 된 상태이다. 따라서 본 논문에서는 특정 기술에 종속되지 않는 실감형 360도 영상 콘텐츠 강인성 지표를 제안한다.

• Journal of Korea Water Resources Association
• /
• v.49 no.2
• /
• pp.95-106
• /
• 2016

Water Management Resilience Index (WMRI) was developed as a policy measure of adaptability to withstand water stresses and to set up water management strategies mainly in mid-small scale tributaries, and then evaluated on 117 sub-basins in South Korea. The index consists of 3 sub-indices such as vulnerability, robustness and redundancy sub-indices, each including indicators of 3 sectors: water use, flood mitigation, and river environment. Total number of indicators selected for the index was 31. Taking into account the stream order and control capability of river flow discharge, sub-basins were categorized into 3: 1 for mainstreams of lower large dams, 2 and 3 for tributaries, respectively without and with flow discharge regulation. As a result of the evaluation, resilience index scores in Category 2 and 3 are much lower than that of Category 1, especially with very poor score of redundancy. Although there was no significant difference between mainstream and tributaries in vulnerability and robustness sub-indices, results of redundancy sub-index in tributaries were lower than those in mainstream. Thus, it is conceived that the variety of water management schemes should be considered to improve their resilience in the face of future uncertainty. Addressing comprehensive stability of river basin against internal and external impacts, WMRI in this study can also be used for the prioritization of water management plans.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.2
• /
• pp.156-160
• /
• 2008

A localization system to estimate the position as well as movement direction of mobile robots is proposed in this paper. This system implements a camera fixed on a robot and color patches evenly distributed and mounted on the planar ceiling. Different permutations of patch colors code information about robot localization. Thus, extraction of color information from patch images leads to estimation of robot position. Additionally, simple geometric indicators are combined with patch colors to estimate robot's movement direction. Since only the distribution of patch colors has to be known, the analysis of patch images to is relatively fast and simple. The proposed robot localization system has been successfully tested for navigation of sample mobile robot. Obtained test results indicate the robustness and reliability of proposed technique for robot navigation.

• Journal of Positioning, Navigation, and Timing
• /
• v.11 no.2
• /
• pp.135-146
• /
• 2022

In GNSS, the structure of the navigation message has been improved to increase the flexibility of data addition and transmission, and the robustness of message reception in a low SNR environment. GNSS signals currently being broadcast have a different message structure from each other, and the structure can be largely classified into the fixed structure, the packetized structure, and the packetized and fixed pattern structure. This paper analyzes the features of these three types of structures and compares the performance using the indicators. It can be seen that the performance after adopting the packetized structure is superior to those of other structures. In particular, there has been remarkable improvement in terms of the message management and transmission efficiency.

• Smart Structures and Systems
• /
• v.9 no.1
• /
• pp.1-20
• /
• 2012

In bridge engineering, maintenance strategies and thus budgetary demands are highly influenced by construction type and quality of design. Nowadays bridge owners and planners tend to include life-cycle cost analyses in their decision processes regarding the overall design trying to optimize structural reliability and durability within financial constraints. Smart permanent and short term monitoring can reduce the associated risk of new design concepts by observing the performance of structural components during prescribed time periods. The objectives of this paper are the discussion and analysis of influence line or influence field approaches in terms of (a) an efficient incorporation of monitoring information in the structural performance assessment, (b) an efficient characterization of performance indicators for the assessment of structures, (c) the ability of optimizing the positions of sensors of a monitoring system, and (d) the ability of checking the robustness of the monitoring systems applied to a structure. The proposed influence line- model correction approach has been applied to an integrative monitoring system that has been installed for the performance assessment of an existing three-span jointless bridge.