• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2004.11a
• /
• pp.755-762
• /
• 2004

In our country, when the replacement for individual components of equipment in nuclear power plants is required, establishment of individual criteria i.e. Required Response Spectra(RRS) of seismic test/analysis for the component is very difficult because of the absence of Test Response Spectra(TRS) for the individual component to be replaced, from the existing qualification documents. In this case, it is required to perform the structural analysis for the nuclear equipment including the components to be replaced. After the structural analysis, Analysis Response Spectra(ARS) at the point of the component shall be generated and used for seismic test of the component. However, as of today, no standard program authorized for the response spectra generation by using the structural analysis exists in korea. Because of above reason, the STAR-Egs computer program was developed by using the method which calculates directly the expected response spectrum(frequency vs. acceleration type) of the selected points in the nuclear equipment with input spectrum(Required Response Spectra, RRS), based on the dynamic characteristics of the Finite Element(FE) model that is equivalent to the nuclear equipment. The STAR-Egs controls ANSYS/I-DEAS commercial software and automatically extract modal parameters of the FE model. The STAR-Egs calculates response spectrum using the established algorithm based on the extracted modal parameters, too. Reliance on the calculation result of the STAR-Egs was verified through comparison output with the result of MATLAB commercial software based on the identical algorithm. Moreover, actual seismic testing was performed as per IEEE344-1987 for the purpose of program verification by comparison of the FE analysis results.

• Smart Structures and Systems
• /
• v.6 no.5_6
• /
• pp.561-578
• /
• 2010

This study proposes a multi-level damage localization strategy to achieve an effective damage detection system for civil infrastructure systems based on wireless sensors. The proposed system is designed for use of distributed computation in a wireless sensor network (WSN). Modal identification is achieved using the frequency-domain decomposition (FDD) method and the peak-picking technique. The ASH (angle-between-string-and-horizon) and AS (axial strain) flexibility-based methods are employed for identifying and localizing damage. Fundamentally, the multi-level damage localization strategy does not activate all of the sensor nodes in the network at once. Instead, relatively few sensors are used to perform coarse-grained damage localization; if damage is detected, only those sensors in the potentially damaged regions are incrementally added to the network to perform finer-grained damage localization. In this way, many nodes are able to remain asleep for part or all of the multi-level interrogations, and thus the total energy cost is reduced considerably. In addition, a novel distributed computing strategy is also proposed to reduce the energy consumed in a sensor node, which distributes modal identification and damage detection tasks across a WSN and only allows small amount of useful intermediate results to be transmitted wirelessly. Computations are first performed on each leaf node independently, and the aggregated information is transmitted to one cluster head in each cluster. A second stage of computations are performed on each cluster head, and the identified operational deflection shapes and natural frequencies are transmitted to the base station of the WSN. The damage indicators are extracted at the base station. The proposed strategy yields a WSN-based SHM system which can effectively and automatically identify and localize damage, and is efficient in energy usage. The proposed strategy is validated using two illustrative numerical simulations and experimental validation is performed using a cantilevered beam.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.1
• /
• pp.27-32
• /
• 2019

Research that implements the classification process through Deep Learning algorithm, one of the outstanding human abilities, includes a unimodal model, a multi-modal model, and a multi-modal method using music videos. In this study, the results were better by suggesting a system to analyze each song's spectrum into short samples and vote for the results. Among Deep Learning algorithms, CNN showed superior performance in the category of music genre compared to RNN, and improved performance when CNN and RNN were applied together. The system of voting for each CNN result by Deep Learning a short sample of music showed better results than the previous model and the model with Softmax layer added to the model performed best. The need for the explosive growth of digital media and the automatic classification of music genres in numerous streaming services is increasing. Future research will need to reduce the proportion of undifferentiated songs and develop algorithms for the last category classification of undivided songs.

• Journal of Convergence for Information Technology
• /
• v.10 no.12
• /
• pp.216-225
• /
• 2020

This study was conducted to qualitatively analyze the selected research through a systematic review to find out application method, outcome measures, and intervention effects of dual task. We searched for published studies from January 2010 to December 2019. Electrical database were PubMed and ProQuest. Search terms were 'dual task' OR 'multi modal' AND 'mild cognitive impairment' OR 'dementia' OR 'Alzheimer's disease'AND 'intervention' OR 'rehabilitation. There were 8 studies selected finally. The dual task was applied not as a single intervention but as a combined intervention with other exercises. The contents of dual task were consisted of motor and cognitive tasks to be independent each other. The outcome measures included general cognitive function such as MMSE and CERAD, executive function, and memory. Additionally the dual task cost was also used to identify the direct improvement of the dual task. This study could provide informations of dual task application on elderly with cognitive impairment.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.1
• /
• pp.57-67
• /
• 2021

Recently, multi-modal deep learning techniques that combine heterogeneous data for deep learning analysis have been utilized a lot. In particular, studies on the synthesis of Text to Image that automatically generate images from text are being actively conducted. Deep learning for image synthesis requires a vast amount of data consisting of pairs of images and text describing the image. Therefore, various data augmentation techniques have been devised to generate a large amount of data from small data. A number of text augmentation techniques based on synonym replacement have been proposed so far. However, these techniques have a common limitation in that there is a possibility of generating a incorrect text from the content of an image when replacing the synonym for a noun word. In this study, we propose a text augmentation method to replace words using word hierarchy information for noun words. Additionally, we performed experiments using MSCOCO data in order to evaluate the performance of the proposed methodology.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.1
• /
• pp.157-166
• /
• 2022

In this study, The goal is to analyze the feasibility of introducing a Piggyback system that can reduce the time and cost incurred by transshipment work and improve the transportation speed when transporting complex cargo by rail. To this end, the feasibility analysis methodology is reviewed through domestic and international literature review. In order to quantitatively derive the feasibility analysis values, a transportation database was applied to develop a freight transport simulation model and a freight demand prediction model for major freight transport O-D routes with a transportation distance of 200 km or more. As a result of analyzing economic feasibility by setting the analysis period to 15 years on the premise that the Piggyback System will be introduced on major cargo transport O-D routes in 2025, the NPV value was positive and the B/C value was 1.18, indicating that the Piggyback system was economical. The proposed research method can be meaningful data for establishing transportation policies that can improve the competitiveness of railroad transportation.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.5
• /
• pp.388-394
• /
• 2023

When the vibration of the thin panel by exciting single point is used to radiate sound, the inherent vibration characteristic of the plate itself causes influence on the radiated sound. A conventional panel speaker system usually uses the single or double point excitations for generating the sound through the panel itself. The radiated sound can be easily distorted due to the modal characteristics of the plate so it is difficult to expect sufficient sound power or high radiation efficiency. In this paper, to achieve an immersive sound field, the multiple speaker zones on a thin panel are created with the limited number of actuators. The designated vibration field which can generates directional sound is realized by employing the vibro-acoustic inverse rendering methods. Actuators are arranged from the positions which have the advantage of implementing with multi-modal excitations. The location and number of actuators are compared with the location and number of controllable speaker zones by conducting numerical simulations.

• Smart Structures and Systems
• /
• v.31 no.3
• /
• pp.247-257
• /
• 2023

In structural health monitoring of large-scale structures, optimal sensor placement plays an important role because of the high cost of sensors and their supporting instruments, as well as the burden of data transmission and storage. In this study, a vibration sensor placement algorithm based on deep reinforcement learning (DRL) is proposed, which can effectively solve non-convex, high-dimensional, and discrete combinatorial sensor placement optimization problems. An objective function is constructed to estimate the quality of a specific vibration sensor placement scheme according to the modal assurance criterion (MAC). Using this objective function, a DRL-based algorithm is presented to determine the optimal vibration sensor placement scheme. Subsequently, we transform the sensor optimal placement process into a Markov decision process and employ a DRL-based optimization algorithm to maximize the objective function for optimal sensor placement. To illustrate the applicability of the proposed method, two examples are presented: a 10-story braced frame and a sea-crossing bridge model. A comparison study is also performed with a genetic algorithm and particle swarm algorithm. The proposed DRL-based algorithm can effectively solve the discrete combinatorial optimization problem for vibration sensor placements and can produce superior performance compared with the other two existing methods.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.3A
• /
• pp.257-264
• /
• 2010

Generally, estimations on the displacement as an important factor in evaluating the safety of large structures could be a barometer assessing whether the condition of the structure is deteriorating. Practically, it is not easy how to measure the displacement response to large structures like suspension bridges. In this study, as a method for estimation displacement response from strain signals, mode decomposition technique is proposed. Total displacement response is estimated by superposing quasistatic displacement response and modal displacement responses in dominant modes with larger contributions after estimating the modal displacement responses. If foiled strain gauges are used to measure strain signals, there would likely to generate electric noise, what's more, the more measuring points there are the more economic burden it could be. In order to solve such problems, fiber optic bragg-grating(FBG) sensors were used, which have multi-point measurements with no effect on electric noises. Therefore, the experiment was performed through dynamic load test of suspension bridge and plate-girder bridge to review the possibility for using mode decomposition technique.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.10
• /
• pp.2768-2787
• /
• 2023

As an important research direction of the application of computer science in the medical field, the automatic generation technology of radiology report has attracted wide attention in the academic community. Because the proportion of normal regions in radiology images is much larger than that of abnormal regions, words describing diseases are often masked by other words, resulting in significant feature loss during the calculation process, which affects the quality of generated reports. In addition, the huge difference between visual features and semantic features causes traditional multi-modal fusion method to fail to generate long narrative structures consisting of multiple sentences, which are required for medical reports. To address these challenges, we propose a multi-feature optimization Transformer (MFOT) for generating radiology reports. In detail, a multi-dimensional mapping attention (MDMA) module is designed to encode the visual grid features from different dimensions to reduce the loss of primary features in the encoding process; a feature pre-fusion (FP) module is constructed to enhance the interaction ability between multi-modal features, so as to generate a reasonably structured radiology report; a detail enhanced attention (DEA) module is proposed to enhance the extraction and utilization of key features and reduce the loss of key features. In conclusion, we evaluate the performance of our proposed model against prevailing mainstream models by utilizing widely-recognized radiology report datasets, namely IU X-Ray and MIMIC-CXR. The experimental outcomes demonstrate that our model achieves SOTA performance on both datasets, compared with the base model, the average improvement of six key indicators is 19.9% and 18.0% respectively. These findings substantiate the efficacy of our model in the domain of automated radiology report generation.