• ETRI Journal
• /
• v.39 no.4
• /
• pp.455-466
• /
• 2017

This study focuses on a method for sequential data augmentation in order to alleviate data sparseness problems. Specifically, we present corpus expansion techniques for enhancing the coverage of a language model. Recent recurrent neural network studies show that a seq2seq model can be applied for addressing language generation issues; it has the ability to generate new sentences from given input sentences. We present a method of corpus expansion using a sentence-chain based seq2seq model. For training the seq2seq model, sentence chains are used as triples. The first two sentences in a triple are used for the encoder of the seq2seq model, while the last sentence becomes a target sequence for the decoder. Using only internal resources, evaluation results show an improvement of approximately 7.6% relative perplexity over a baseline language model of Korean text. Additionally, from a comparison with a previous study, the sentence chain approach reduces the size of the training data by 38.4% while generating 1.4-times the number of n-grams with superior performance for English text.

• Journal of the Korean Statistical Society
• /
• v.25 no.3
• /
• pp.433-444
• /
• 1996

In contrast to the multiplicative risk model, the additive risk model specifies that the hazard function with covariates is the sum of, rather than product of, the baseline hazard function and the regression function of covariates. We, in this paper, propose a method for checking the adequacy of the additive risk model based on partial-sum of matingale residuals. Under the assumed model, the asymptotic properties of the proposed test statistic and approximation method to find the critical values of the limiting distribution are studied. Several real examples are illustrated.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.30 no.6
• /
• pp.527-538
• /
• 2010

This paper presents a nondestructive evaluation approach for system identification (SID) of real railway bridges using field vibration test results. First, a multi-phase SID scheme designed on the basis of eigenvalue sensitivity concept is presented. Next, the proposed multi-phase approach is evaluated from field vibration tests on a real railway bridge (Wondongcheon bridge) located in Yangsan, Korea. On the steel girder bridge, a few natural frequencies and mode shapes are experimentally measured under the ambient vibration condition. The corresponding modal parameters are numerically calculated from a three-dimensional finite element (FE) model established for the target bridge. Eigenvalue sensitivities are analyzed for potential model-updating parameters of the FE model. Then, structural subsystems are identified phase-by-phase using the proposed model-updating procedure. Based on model-updating results, a baseline model and a nondestructive evaluation of test bridge are identified.

• ETRI Journal
• /
• v.43 no.2
• /
• pp.272-287
• /
• 2021

This article presents a multi-dimensional spatial pattern analysis of crime events in San Francisco. Our analysis includes the impact of spatial resolution on hotspot identification, temporal effects in crime spatial patterns, and relationships between various crime categories. In this work, crime prediction is viewed as a classification problem. When predictions for a particular category are made, a binary classification-based model is framed, and when all categories are considered for analysis, a multiclass model is formulated. The proposed crime-prediction model (HotBlock) utilizes spatiotemporal analysis for predicting crime in a fixed spatial region over a period of time. It is robust under variation of model parameters. HotBlock's results are compared with baseline real-world crime datasets. It is found that the proposed model outperforms the standard DeepCrime model in most cases.

• Journal of the Society of Disaster Information
• /
• v.12 no.1
• /
• pp.10-18
• /
• 2016

This study presented a new NOS model through the following suggestions to apply the construction work planing and management to NOS(Network Operating System). First, This study presented CIMS(construction information classification system) reflected the characteristics of facility classification - functional component classification - functional component classification - work classification - resource classification. Based on this system. this study presented how to establish PMMB(performance measurement management baseline) with proposed master target equation which analyzed the trend of performance measurement management baseline and proposed work target equation which analyzed the execution results. Finally, this study presented NOS model that can be applied to fixed price method and cost plus fee method through the theoretical verification of executive performance analysis method.

• Journal of Aerospace System Engineering
• /
• v.11 no.4
• /
• pp.36-43
• /
• 2017

Blade design optimization of QTP-UAV prop-rotor was conducted using ModelCenter(R). Performance efficiency of the blade in hover and forward flight were adopted as the multi-objective function. Required power and pitch link force applied to constraint in each flight mode and limited lower than the value of the baseline blade. Design variables of root chord length of the blade, taper ratio, twist slope, twist angle at 0.5R of the blade, anhedral angle, parabolic coefficient of a tip shape and location of airfoil were used to generate the blade planform. CAMRAD-II, the comprehensive analysis program of rotorcraft, was used for performance analysis of prop-rotor blade in design process. Performance of the optimized blade improved 1.6% of figure of merit in hover and 13.6% of propulsive efficiency in forward flight. Pitch link force also reduced approximately 30% less than that of the baseline blade.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.8
• /
• pp.1976-1995
• /
• 2023

The anchor-free object detector CenterNet regards the object as a center point and predicts it based on the Gaussian circle region. For each object's center point, CenterNet directly regresses the width and height of the objects and finally gets the boundary range of the objects. However, the critical range of the object's center point can not be accurately limited by using the Gaussian circle region to constrain the prediction region, resulting in many low-quality centers' predicted values. In addition, because of the large difference between the width and height of different objects, directly regressing the width and height will make the model difficult to converge and lose the intrinsic relationship between them, thereby reducing the stability and consistency of accuracy. For these problems, we proposed a center point prediction method based on the Gaussian elliptic region and a size component regression method based on the small solution space. First, we constructed a Gaussian ellipse region that can accurately predict the object's center point. Second, we recode the width and height of the objects, which significantly reduces the regression solution space and improves the convergence speed of the model. Finally, we jointly decode the predicted components, enhancing the internal relationship between the size components and improving the accuracy consistency. Experiments show that when using CenterNet as the improved baseline and Hourglass-104 as the backbone, on the MS COCO dataset, our improved model achieved 44.7%, which is 2.6% higher than the baseline.

• Smart Media Journal
• /
• v.13 no.7
• /
• pp.36-44
• /
• 2024

Identifying plant species and diseases is crucial for maintaining biodiversity and achieving optimal crop yields, making it a topic of significant practical importance. Recent studies have extended plant disease recognition from traditional closed-set scenarios to open-set environments, where the goal is to reject samples that do not belong to known categories. However, in open-world tasks, it is essential not only to define unknown samples as "unknown" but also to classify them further. This task assumes that images and labels of known categories are available and that samples of unknown categories can be accessed. The model classifies unknown samples by learning the prior knowledge of known categories. To the best of our knowledge, there is no existing research on this topic in plant-related recognition tasks. To address this gap, this paper utilizes knowledge distillation to model the category space relationships between known and unknown categories. Specifically, we identify similarities between different species or diseases. By leveraging a fine-tuned model on known categories, we generate pseudo-labels for unknown categories. Additionally, we enhance the baseline method's performance by using a larger pre-trained model, dino-v2. We evaluate the effectiveness of our method on the large plant specimen dataset Herbarium 19 and the disease dataset Plant Village. Notably, our method outperforms the baseline by 1% to 20% in terms of accuracy for novel category classification. We believe this study will contribute to the community.

• ETRI Journal
• /
• v.32 no.5
• /
• pp.795-800
• /
• 2010

Embedding a large vocabulary speech recognition system in mobile devices requires a reduced acoustic model obtained by eliminating redundant model parameters. In conventional optimization methods based on the minimum description length (MDL) criterion, a binary Gaussian tree is built at each state of a hidden Markov model by iteratively finding and merging similar mixture components. An optimal subset of the tree nodes is then selected to generate a downsized acoustic model. To obtain a better binary Gaussian tree by improving the process of finding the most similar Gaussian components, this paper proposes a new distance measure that exploits the difference in likelihood values for cases before and after two components are combined. The mixture weight of Gaussian components is also introduced in the component merging step. Experimental results show that the proposed method outperforms MDL-based optimization using either a Kullback-Leibler (KL) divergence or weighted KL divergence measure. The proposed method could also reduce the acoustic model size by 50% with less than a 1.5% increase in error rate compared to a baseline system.

• Journal of Advanced Marine Engineering and Technology
• /
• v.38 no.2
• /
• pp.154-161
• /
• 2014

This research presents results of structural designs and evaluations for 3MW Wind Turbine Blade by FEM analysis. After the GFRP model was designed as a baseline model, failure check by Puck's failure criterion and buckling analysis were accomplished to verify safety of wind turbine blade in the critical design load case. Moreover, applicability of two kinds of carbon spar cap model, was studied by comparing total mass, price and tip deflection to the GFRP model. The results showed that the GFRP model had sufficient structural integrity in the critical design load case, and the carbon spar cap model could be a reasonable solution to reduce weights, tip deflections.