• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.8
• /
• pp.2787-2800
• /
• 2022

The aging society increases emergency situations of the elderly living alone and a variety of social crimes. In order to prevent them, techniques to detect emergency situations through voice are actively researched. This study proposes CutPaste-based anomaly detection model using multi-scale feature extraction in time series streaming data. In the proposed method, an audio file is converted into a spectrogram. In this way, it is possible to use an algorithm for image data, such as CNN. After that, mutli-scale feature extraction is applied. Three images drawn from Adaptive Pooling layer that has different-sized kernels are merged. In consideration of various types of anomaly, including point anomaly, contextual anomaly, and collective anomaly, the limitations of a conventional anomaly model are improved. Finally, CutPaste-based anomaly detection is conducted. Since the model is trained through self-supervised learning, it is possible to detect a diversity of emergency situations as anomaly without labeling. Therefore, the proposed model overcomes the limitations of a conventional model that classifies only labelled emergency situations. Also, the proposed model is evaluated to have better performance than a conventional anomaly detection model.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.301-307
• /
• 2024

This study introduces a novel cascade fusion architecture aimed at enhancing thermal images across various scale conditions. The processing of thermal images at multiple scales has been challenging due to the limitations of existing methods that are designed for specific scales. To overcome these limitations, this paper proposes a unified framework that utilizes cascade feature fusion to effectively learn multi-scale representations. Confidence maps from different image scales are fused in a cascaded manner, enabling scale-invariant learning. The architecture comprises end-to-end trained convolutional neural networks to enhance image quality by reinforcing mutual scale dependencies. Experimental results indicate that the proposed technique outperforms existing methods in multi-scale thermal image enhancement. Performance evaluation results are provided, demonstrating consistent improvements in image quality metrics. The cascade fusion design facilitates robust generalization across scales and efficient learning of cross-scale representations.

• Smart Structures and Systems
• /
• v.14 no.5
• /
• pp.831-845
• /
• 2014

This paper proposed a discrete wavelet transform based method for time-varying physical parameter identification of shear type structures. The time-varying physical parameters are dispersed and expanded at multi-scale as profile and detail signal using discrete wavelet basis. To reduce the number of unknown quantity, the wavelet coefficients that reflect the detail signal are ignored by setting as zero value. Consequently, the time-varying parameter can be approximately estimated only using the scale coefficients that reflect the profile signal, and the identification task is transformed to an equivalent time-invariant scale coefficient estimation. The time-invariant scale coefficients can be simply estimated using regular least-squares methods, and then the original time-varying physical parameters can be reconstructed by using the identified time-invariant scale coefficients. To reduce the influence of the ill-posed problem of equation resolving caused by noise, the Tikhonov regularization method instead of regular least-squares method is used in the paper to estimate the scale coefficients. A two-story shear type frame structure with time-varying stiffness and damping are simulated to validate the effectiveness and accuracy of the proposed method. It is demonstrated that the identified time-varying stiffness is with a good accuracy, while the identified damping is sensitive to noise.

• The Journal of Asian Finance, Economics and Business
• /
• v.6 no.1
• /
• pp.149-158
• /
• 2019

Due to the rapid development of IT (information technology) and internet, products become smart and able to collect, process and produce information and can think of themselves to provide better service to consumers. However, research on the characteristics of smart product is still sparse. In this paper, we report the systemic development of a scale to measure the perceived product smartness associated with smart product. To develop product smartness scale, this study follows systemic scale development processes of item generation, item reduction, scale validation, reliability and validity test consequently. And, after acquiring a large amount of qualitative interview data asking the definition of smart product, we add a unique process to reduce the initial items using both a text mining method using 'r' s/w and traditional reliability and validity tests including factor analysis. Based on an initial qualitative inquiry and subsequent quantitative survey, an eight-factor scale of product smartness is developed. The eight factors are multi-functionality, human-like touch, ability to cooperate, autonomy, situatedness, network connectivity, integrity, and learning capability consequently. Results from Korean samples support the proposed measures of product smartness in terms of reliability, validity, and dimensionality. Implications and directions for further study are discussed. The developed scale offers important theoretical and pragmatic implications for researchers and practitioners.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.4 no.2
• /
• pp.189-201
• /
• 2001

For a design of multi-layer armor, the extensive full scale or sub-scale penetration test data are required. In generally, the collection of penetration data is in need of time-consuming and expensive processes. However, the application of numerical or analytical method is very limited due to poor understanding about penetration mechanics. In this paper, we have developed a neural network analyzer which can be used as a design tool for a new armor. Calculation results show that the developed neural network analyzer can predict relatively exact penetration depth of a new armor through the effective analysis of the pre-existing penetration database.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.1-3
• /
• 2001

점차 지리정보시스템(GIS; Geographic Information System)에서 표현의 다양화가 요구되어지며 특히 위성영상의 데이터는 거대하기 때문에, 지라공간의 자세한 연구를 원하는 사용자에게 많은 처리시간과 고가의 비용이 요구된다. 바면 웹에서 성능향상을 위해 공간데이터의 양을 줄인다 보면 공간데이터를 다양하게 표현하지 못하는 경우가 발생하게 된다. 그러므로 본 논문에서는 사용자의 공간데이터에 대한 양적 부담을 줄이고 공간데이터의 정확도를 유지할 수 있는 Multi-Scale에 따른 Multi-Resolution(MS-MR) 기법을 제안하고자 한다. 즉, 서버에서 축척의 정량화를 통해 레이어가 추가될 지점과 다중 해상도의 구간을 정하여 맵을 점차 확대함에 따라 다중해상도의 레스터맵이 클라언트에게 점진적으로 전송된다. 이는 인터넷 연결상태와 GIS 사용목적에 따라 적절한 다중 해상도의 레스터맵을 제공하게 되며, 사용자가 진화적으로 시스템 추구로 빠른 정보습득과 의사결정을 돕는 효과를 기대할 수 있게 한다.

• The KSFM Journal of Fluid Machinery
• /
• v.15 no.1
• /
• pp.52-57
• /
• 2012

Stall inception characteristics are researched to understand stall well. To realize different stall inception patterns, IGV stagger angle was changed. At design IGV stagger angle, spike, which is short length scale, is observed. Decreasing IGV stagger angle, spike changes to mode, which is long length scale, and further decreasing get multi cell. Compressor maps for each IGV stagger are shown to compare different stall inceptions. The characteristics of both spike and mode are confirmed in this experiment. Furthermore, transient from spike to mode is find. multi cell has 4cells and is little bit faster than mode. and multi cell shows 2nd, 3rd characteristics on compressor map.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.3 no.2
• /
• pp.120-125
• /
• 2002

In this paper, we propose a new ordering model for the mixed parts transportation problem with multi-items based on the depot system. Order scale are used as decision parameters instead of order point for ordering multi-items. Finally we test the model with simple example and show computational result that verifies the effectiveness of the model.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.11a
• /
• pp.1383-1386
• /
• 2008

분산된 자원의 실시간 정보교환과 그리드를 통한 효율적인 자원 재구성을 위해서는 기존의 단일 도메인에서 구성되는 네트워크와는 다르게 대규모 가상도메인(Large-Scale Multi-domain)을 위한 네트워크의 성능과 기능 향상이 필요하다. 그리드네트워크를 기반으로 활발히 진행 중인 글로벌한 연구자원을 대상으로 공유된 자원의 성능 개선과 자원 간 데이터전달의 효율 개선을 위해 TDM(Time Division Multiplexing)기반의 Multi-Point Lambda-Path Ring 구현 기술을 제안하고 이를 Multi-Domain 간 Control Plane하에서 최적의 가상도메인으로 구성 할 수 있는 기법을 제안한다.

• Journal of Power System Engineering
• /
• v.11 no.2
• /
• pp.44-50
• /
• 2007

The oxidation behavior of commercial pure titanium is investigated in the temperature range of $727^{\circ}C{\sim}950^{\circ}C$ in mixed gases. The weight change is measured by TGA during oxidation in mixed gases. The oxidation behavior indicated by weight gain or the growth of oxide layer is based on the linear rate law at high temperatures. The structure of the oxide scale formed during oxidation is analysed by optical microscopy, electron probe microanalyzer, scanning electron microscope and x-ray diffraction. Oxide scales have a $TiO_2$ structure, and are constituted with multi-layered or two layered porous external one and a dense internal one. Ti-O solid solution region is formed at the interface of metal and scale layer. The formation of oxide scale is influenced by the oxidation temperature, time, crystal structure and the condition of atmosphere.