• Journal of Broadcast Engineering
• /
• v.26 no.6
• /
• pp.680-691
• /
• 2021

Due to the recent developments of attaining 3D contents by using devices such as 3D scanners, the diversity of the contents being used in AR(Augmented Reality)/VR(Virutal Reality) fields is significantly increasing. There are several ways to represent 3D data, and using point clouds is one of them. A point cloud is a cluster of points, having the advantage of being able to attain actual 3D data with high precision. However, in order to express 3D contents, much more data is required compared to that of 2D images. The size of data needed to represent dynamic 3D point cloud objects that consists of multiple frames is especially big, and that is why an efficient compression technology for this kind of data must be developed. In this paper, a motion estimation and compensation method for dynamic point cloud objects using 3D DCT is proposed. This will lead to switching the 3D video frames into I frames and P frames, which ensures higher compression ratio. Then, we confirm the compression efficiency of the proposed technology by comparing it with the anchor technology, an Intra-frame based compression method, and 2D-DCT based V-PCC.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.11
• /
• pp.435-442
• /
• 2018

Outlier detection means to detect data samples that deviate significantly from the distribution of normal data. Most outlier detection methods calculate an outlier score that indicates the extent to which a data sample is out of normal state and determine it to be an outlier when its outlier score is above a given threshold. However, since the range of an outlier score is different for each data and the outliers exist at a smaller ratio than the normal data, it is very difficult to determine the threshold value for an outlier score. Further, in an actual situation, it is not easy to acquire data including a sufficient amount of outliers available for learning. In this paper, we propose a clustering-based outlier detection method by constructing a model representing a normal data region using only normal data and performing binary classification of outliers and normal data for new data samples. Then, by dividing the given normal data into chunks, and constructing a clustering model for each chunk, we expand it to the ensemble method combining the decision by the models and apply it to the streaming data with dynamic changes. Experimental results using real data and artificial data show high performance of the proposed method.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.31 no.6
• /
• pp.347-352
• /
• 2018

This study proposes seismic response analysis technique of a two-mass rack system which sustains heavy loads with frictional behavioral characteristics. In order to deal with the nonlinear frictional characteristics of the mass on the rack system, the equations of motion of the system has been derived and the appropriate numerical simulation technique has been developed. In order to examine the seismic performance of the proposed system, we consider two parameters that are expected to have great influence on the seismic performance of the system. One is the ratio of the two masses of the load and the rack structure, and the other is the friction coefficient between rack and loaded mass. A number of numerical simulations of the seismic response of structures with various natural frequencies for both parameters have been performed in order to investigate the seismic safety of the rack structures. From the simulated results. it is observed that the maximum displacement of the rack system tends to decrease drastically as the natural frequency of the structure increases regardless of the two parameters of mass ratio and friction coefficient. The proposed study provides important reference data to guarantee the seismic safety of the rack system by considering nonlinear frictional behavior of the loaded mass.

• Journal of the Korean Geotechnical Society
• /
• v.34 no.11
• /
• pp.57-70
• /
• 2018

In this study, verification of the nonlinear effective stress analysis is performed for introducing performance based earthquake resistance design of port and harbor structures. Seismic response of gravitational caisson quay wall in numerical analysis is compared directly with dynamic centrifuge test results in prototype scale. Inside of the rigid box, model of the gravitational quay wall is placed above the saturated sand layer which can show the increase of excess pore water pressure. The model represents caisson quay wall with a height of 10 m, width of 6 m under centrifugal acceleration of 60 g. The numerical model is made in the same dimension with the prototype scale of the test in two dimensional plane strain condition. Byrne's liquefaction model is adopted together with a nonlinear constitutive model. Interface element is used for sliding and tensional separation between quay wall and the adjacent soils. Verification results show good agreement for permanent displacement of the quay wall, horizontal acceleration at quay wall and soil layer, and excess pore water pressure increment beneath the quay wall foundation.

• Journal of Broadcast Engineering
• /
• v.24 no.3
• /
• pp.472-484
• /
• 2019

This paper proposes a time-domain sound event detection algorithm using DNN (Deep Neural Network). In this system, time domain sound waveform data which is not converted into the frequency domain is used as input to the DNN. The overall structure uses CRNN structure, and GLU, ResNet, and Squeeze-and-excitation blocks are applied. And proposed structure uses structure that considers features extracted from several layers together. In addition, under the assumption that it is practically difficult to obtain training data with strong labels, this study conducted training using a small number of weakly labeled training data and a large number of unlabeled training data. To efficiently use a small number of training data, the training data applied data augmentation methods such as time stretching, pitch change, DRC (dynamic range compression), and block mixing. Unlabeled data was supplemented with insufficient training data by attaching a pseudo-label. In the case of using the neural network and the data augmentation method proposed in this paper, the sound event detection performance is improved by about 6 %(based on the f-score), compared with the case where the neural network of the CRNN structure is used by training in the conventional method.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.12
• /
• pp.910-917
• /
• 2018

This paper describes the developments to improve the feeling and safety of the remote control system of unmanned vehicles. Generally, in the case of the remote control systems, a joystick-type device or a simple steering-wheel are used. There are many cases, in which there are operations without considering the feedback to users and driving feel. Recently, as the application area of the unmanned vehicles has been extended, the problems caused by not considering the feedback are emphasized. Therefore, the need for a force feedback-haptic control arises to solve these problems. In this study, the force feedback-haptic control algorithm considering the vehicle parameters is proposed. The vehicle parameters include first the state variables of dynamics, such as the body side-slip angle (${\beta}$) and yawrate (${\gamma}$), and second, the parameters representing the driving situations. Force feedback-haptic control technology consists of the algorithms for general and specific situations, and considers the situation transition process. To verify the algorithms, a simulator was constructed using the vehicle dynamics simulation tool with CAN communication environment. Using the simulator, the feasibility of the algorithms was verified in various scenarios.

• Journal of the Korea Convergence Society
• /
• v.12 no.1
• /
• pp.99-104
• /
• 2021

In this paper, we propose health risk management using feature extraction and cluster analysis considering time flow. The proposed method proceeds in three steps. The first is the pre-processing and feature extraction step. It collects user's lifelog using a wearable device, removes incomplete data, errors, noise, and contradictory data, and processes missing values. Then, for feature extraction, important variables are selected through principal component analysis, and data similar to the relationship between the data are classified through correlation coefficient and covariance. In order to analyze the features extracted from the lifelog, dynamic clustering is performed through the K-means algorithm in consideration of the passage of time. The new data is clustered through the similarity distance measurement method based on the increment of the sum of squared errors. Next is to extract information about the cluster by considering the passage of time. Therefore, using the health decision-making system through feature clusters, risks able to managed through factors such as physical characteristics, lifestyle habits, disease status, health care event occurrence risk, and predictability. The performance evaluation compares the proposed method using Precision, Recall, and F-measure with the fuzzy and kernel-based clustering. As a result of the evaluation, the proposed method is excellently evaluated. Therefore, through the proposed method, it is possible to accurately predict and appropriately manage the user's potential health risk by using the similarity with the patient.

• The Korean Journal of Applied Statistics
• /
• v.34 no.3
• /
• pp.309-327
• /
• 2021

Dynamic treatment regimes (DTRs) are decision-making rules designed to provide personalized treatment to individuals in multi-stage randomized trials. Unlike classical methods, in which all individuals are prescribed the same type of treatment, DTRs prescribe patient-tailored treatments which take into account individual characteristics that may change over time. The Q-learning method, one of regression-based algorithms to figure out optimal treatment rules, becomes more popular as it can be easily implemented. However, the performance of the Q-learning algorithm heavily relies on the correct specification of the Q-function for response, especially in observational studies. In this article, we examine a number of double-robust weighted least-squares estimating methods for Q-learning in high-dimensional settings, where treatment models for propensity score and penalization for sparse estimation are also investigated. We further consider flexible ensemble machine learning methods for the treatment model to achieve double-robustness, so that optimal decision rule can be correctly estimated as long as at least one of the outcome model or treatment model is correct. Extensive simulation studies show that the proposed methods work well with practical sample sizes. The practical utility of the proposed methods is proven with real data example.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.25 no.1
• /
• pp.41-50
• /
• 2021

In this study, the flow path width (Gap Size), which is the flow path of fluid, was selected differently among various factors that determine the Ccontrol Force of MR damper, and the change of Control Force was confirmed accordingly. For this purpose, two MR dampers with a Gap Size of 1.0mm and 1.5mm were fabricated, respectively, and dynamic load experiments were conducted according to changes in applied current and vibration conditions The experimental results showed that the minimum Control Force was 3.2 times higher than 1.5mm in the case of 1.0mm Gap Size, and the maximum Control Force was 2.3 times higher than 1.5mm in the case of 1.0mm Gap Size. In addition, the increased width of the Control Force according to applied current was 34N for Gap Size 1.0mm, and 12.7N for Gap Size 1.5mm. As the gap Size increased, the overall Control Force and the increase in the Control Force by the applied current decreased. Next, the dynamic range, which is a performance evaluation index of the semi-active Control device, was 2.3 on average under 1.0mm condition and 2.8 on average under 1.5mm condition, confirming the possibility of utilization as a semi-active Control device.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.9 no.1
• /
• pp.109-116
• /
• 2021

In order to replace mineral aggregate used as road pavement materials with steel slag aggregate, this present study evaluated mechanical properties of SMA Concrete mixtures using steel slag aggregate as oxidized slag from electric furnace in iron works. The variables of this experiment are the aggregate type of mineral and steel slag and the sieve sized of 10mm and 13mm. The physical properties inclu ding the specific gravity and absorption rate etc. of the slag aggregate mixtu res satisfied the KS standard as asphalt mixtu re. As a resu lt of evalu ating the mechanical properties of the asphalt mixtures, the optimum asphalt content of the slag aggregate mixtures were lower than that of the mineral aggregate mixtures, but other quality standards were all satisfied. In the deformation strength evaluation, the slag aggregate mixtures were measu red slightly higher than that of the mineral aggregate mixtu res, and the dynamic stability test satisfied the 2,000pass/mm standard value in all specimens. And, the moduli of resilient of the slag aggregate mixtures showed an improved value compared with the mineral aggregate mixtures. Therefore, as the resilient rate of the slag aggregate mixtures improved, it is speculated that there will be an effect of improving public performance according to the repeated traffic load of the vehicle.