• Journal of the Earthquake Engineering Society of Korea
• /
• v.7 no.2
• /
• pp.49-58
• /
• 2003

The linear motor has not only no backlash and less friction, resulting in very high accuracy, but also mechanical simplicity, higher reliability, and longer lifetime. In this study, a large-capacity hybrid mass damper using linear motor principle has been developed to suppress vibration of large structures. It is designated linear motor damper in this paper. The LMD has been designed to be able to move the auxiliary damper mass of 155kg up to $\pm$250mm stroke. A series of performance tests for LMD control system with $H_{winfty}$ robust controller have been carried out on the full-scale steel frame structure. Through the performance tests, it is confirmed that vibration response levels are reduced down 10dB for the first and second modes of the test structure.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.27 no.2
• /
• pp.1-7
• /
• 2023

Durability was evaluated by performing a full-scale vertical load fatigue test and a wheel load performance test on the HRS, which reduces the replacement time of the existing expansion joint and improves serviceability to allow partial replacement by lane. As a result of the vertical load fatigue test, the maximum stress of the rail-type expansion joint is 170 MPa, which is about 47.8% of the yield strength of the HRS expansion joint rail 355 MPa. The vertical load fatigue test of the HRS expansion joint with improved serviceability set the size and load of the load plate according to the road bridge design standards, did not show any fracture behavior in the vertical load fatigue test and the wheel load performance test 2 million times, and its durability and safety were verified.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.26 no.5
• /
• pp.506-513
• /
• 2020

Due to climate change, there is an increasing risk of complex (hybrid) disasters, comprising rising sea-levels, typhoons, and torrential rains. This study focuses on Marine City, Busan, a new residential city built on a former landfill site in Suyeong Bay, which recently suffered massive flood damage following a combination of typhoons, storm surges, and wave overtopping and run-up. Preparations for similar complex disasters in future will depend on risk impact assessment and prioritization to establish appropriate countermeasures. A framework was first developed for this study, followed by the collection of data on flood prediction and socioeconomic risk factors. Five socioeconomic risk factors were identified: (1) population density, (2) basement accommodation, (3) building density and design, (4) design of sidewalks, and (5) design of roads. For each factor, absolute criteria were determined with which to assess their level of risk, while expert surveys were consulted to weight each factor. The results were classified into four levels and the risk level was calculated according to the sea-level rise predictions for the year 2100 and a 100-year return period for storm surge and rainfall: Attention 43 %, Caution 24 %, Alert 21 %, and Danger 11 %. Finally, each level, indicated by a different color, was depicted on a complex disaster risk map.

• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.55-71
• /
• 2013

The prediction model is the main factor affecting the performance of a knowledge-based system for bankruptcy prediction. Earlier studies on prediction modeling have focused on the building of a single best model using statistical and artificial intelligence techniques. However, since the mid-1980s, integration of multiple techniques (hybrid techniques) and, by extension, combinations of the outputs of several models (ensemble techniques) have, according to the experimental results, generally outperformed individual models. An ensemble is a technique that constructs a set of multiple models, combines their outputs, and produces one final prediction. The way in which the outputs of ensemble members are combined is one of the important issues affecting prediction accuracy. A variety of combination schemes have been proposed in order to improve prediction performance in ensembles. Each combination scheme has advantages and limitations, and can be influenced by domain and circumstance. Accordingly, decisions on the most appropriate combination scheme in a given domain and contingency are very difficult. This paper proposes a confidence-based selection approach as part of an ensemble bankruptcy-prediction scheme that can measure unified confidence, even if ensemble members produce different types of continuous-valued outputs. The present experimental results show that when varying the number of models to combine, according to the creation type of ensemble members, the proposed combination method offers the best performance in the ensemble having the largest number of models, even when compared with the methods most often employed in bankruptcy prediction.

• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.34 no.11
• /
• pp.113-123
• /
• 2018

First of all, the multi-story Housing applying resident's participation in europe was classified by the menu selection method, the two-step supply method and the cooperative method. And then I analyzed flexible unit plan of cases for deriving the planning methode and the characteristics of flexibility. First, I analyzed the area and form of the unit plan, structure and Installation, fixed and variable elements to derive the planning method. The area of units are distributed from a minimum of $35m^2$ to a maximum of $150m^2$, and many of the unit planes have a narrow front and a deep depth. The structure is a long-span wall-structure or a skeleton structure, and is designed without any columns and bearing walls in the interior space for flexibility in spatial composition. The vertical shafts are located in the center of the unit in a box-form or in the corner at the unit dividing wall for free placement of interior wall. Fixed elements are framework and facility systems. Most of the future residents in the two-steps supply method and the cooperative method were able to freely design the internal space within the zoning concept proposed by the architect and change the location of the facade element within module system proposed by the architect. Second, the characteristics of the flexibility applied to the unit plan were divided in integrated flexibility, functional flexibility, construction flexibility, and supply flexibility. The integrated flexibility enables residents to give the variable space combination based on the complex structure of the inner space for providing various living experiences. Regarding functional flexibility, the three-dimensional spatial structure with neutral space has multi-functionality according to the needs of residents and easily accepts mixing of hybrid programs such as work and residence. Constructive flexibility allows residents to create identity by freely planning interior space and changing the size or location of facade components in a determined system of architects. Finally, various types of size and space composition are proposed and realized in the whole building applying menu selection method, so that flexibility in the offer can accommodate and integrate various types of living.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.36 no.2
• /
• pp.105-112
• /
• 2018

To determine the position of receiver, the GPS (Global Positioning System) uses position information of satellites and pseudo ranges based on signals. These are reflected by surrounding structures and multipath errors occur. This paper proposes a method for multipath error reduction using digital images to enhance the accuracy. The goal of the study is to calculate the shielding environment of receiver using image processing and apply it to GPS positioning. The proposed method, firstly, performs a preprocessing to reduce the effect of noise on images. Next, it uses hough transform to detect the outline of building roofs and determines mask angles and permissible azimuth range. Then, it classifies the satellites according to the condition using the image processing results. Finally, base on point positioning, it computes the receiver position by applying a weight model that assigns different weights to the classified satellites. We confirmed that the RMSE (Root Mean Square Error) was reduced by 2.29m in the horizontal direction and by 15.62m in the vertical direction. This paper showed the potential for the hybrid of GPS positioning and image processing technology.

• Phonetics and Speech Sciences
• /
• v.12 no.2
• /
• pp.63-72
• /
• 2020

This study aims to develop a video-based smart utterance deep analyser (SUDA) application that analyzes semiautomatically the utterances that child and mother produce during interactions over time. SUDA runs on the platform of Android, iPhones, and tablet PCs, and allows video recording and uploading to server. In this device, user modes are divided into three modes: expert mode, general mode and manager mode. In the expert mode which is useful for speech and language evaluation, the subject's utterances are analyzed semi-automatically by measuring speech and language factors such as disfluency, morpheme, syllable, word, articulation rate and response time, etc. In the general mode, the outcome of utterance analysis is provided in a graph form, and the manger mode is accessed only to the administrator controlling the entire system, such as utterance analysis and video deletion. SUDA helps to reduce clinicians' and researchers' work burden by saving time for utterance analysis. It also helps parents to receive detailed information about speech and language development of their child easily. Further, this device will contribute to building a big longitudinal data enough to explore predictors of stuttering recovery and persistence.

• International Journal of Computer Science & Network Security
• /
• v.24 no.9
• /
• pp.30-40
• /
• 2024

Building an accurate 3-D spatial road network model has become an active area of research now-a-days that profess to be a new paradigm in developing Smart roads and intelligent transportation system (ITS) which will help the public and private road impresario for better road mobility and eco-routing so that better road traffic, less carbon emission and road safety may be ensured. Dealing with such a large scale 3-D road network data poses challenges in getting accurate elevation information of a road network to better estimate the CO₂ emission and accurate routing for the vehicles in Internet of Vehicle (IoV) scenario. Clustering and regression techniques are found suitable in discovering the missing elevation information in 3-D spatial road network dataset for some points in the road network which is envisaged of helping the public a better eco-routing experience. Further, recently Explainable Artificial Intelligence (xAI) draws attention of the researchers to better interprete, transparent and comprehensible, thus enabling to design efficient choice based models choices depending upon users requirements. The 3-D road network dataset, comprising of spatial attributes (longitude, latitude, altitude) of North Jutland, Denmark, collected from publicly available UCI repositories is preprocessed through feature engineering and scaling to ensure optimal accuracy for clustering and regression tasks. K-Means clustering and regression using Support Vector Machine (SVM) with radial basis function (RBF) kernel are employed for 3-D road network analysis. Silhouette scores and number of clusters are chosen for measuring cluster quality whereas error metric such as MAE ( Mean Absolute Error) and RMSE (Root Mean Square Error) are considered for evaluating the regression method. To have better interpretability of the Clustering and regression models, SHAP (Shapley Additive Explanations), a powerful xAI technique is employed in this research. From extensive experiments , it is observed that SHAP analysis validated the importance of latitude and altitude in predicting longitude, particularly in the four-cluster setup, providing critical insights into model behavior and feature contributions SHAP analysis validated the importance of latitude and altitude in predicting longitude, particularly in the four-cluster setup, providing critical insights into model behavior and feature contributions with an accuracy of 97.22% and strong performance metrics across all classes having MAE of 0.0346, and MSE of 0.0018. On the other hand, the ten-cluster setup, while faster in SHAP analysis, presented challenges in interpretability due to increased clustering complexity. Hence, K-Means clustering with K=4 and SVM hybrid models demonstrated superior performance and interpretability, highlighting the importance of careful cluster selection to balance model complexity and predictive accuracy.