• Journal of Institute of Convergence Technology
• /
• v.11 no.1
• /
• pp.1-5
• /
• 2021

Deep learning based methods achieve state-of-the-art accuracy, however, they typically rely on supervised training with large labeled datasets. It is known in many medical applications that labeling medical images requires significant expertise and much time, and typical hand-tuned approaches for data augmentation fail to capture the complex variations in such images. This paper proposes a 3D image augmentation method to overcome these difficulties. It allows us to enrich diversity of training data samples that is essential in medical image segmentation tasks, thus reducing the data overfitting problem caused by the fact the scale of medical image dataset is typically smaller. Our numerical experiments demonstrate that the proposed approach provides significant improvements over state-of-the-art methods for 3D medical image segmentation.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.2 no.4
• /
• pp.295-302
• /
• 1990

The purpose of this study is augmentation of heat transfer without additional power in two-dimensional impinging air jet. The technique of heat transfer augmentation used in this experiment is to place rod bundles in front of the flat heated surface. The effects of rod diameter, nozzle-to-target plate distance and the nozzle exit velocity on heat transfer have been investigated. The main conclusions obtained from this experiment are as follows. High heat transfer augmentation is achieved by means of flow acceleration and thinning of boundary layer by placing rod bundles in front of the flat plate. Average heat transfer coefficient becomes maximum in the case of H/B=10,D=4mm. For H/B=2,D=4mm, maximum heat transfer augmentation has been determined to be about 1.5 times larger than that of the flat plate. Heat transfer augmentation by placing the rod bundles at 12m/s is to be about 2 times more than increasing nozzle exit velocity from 12m/s to 18m/s.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.9
• /
• pp.47-54
• /
• 2023

Infants utilize crying as a non-verbal means of communication [1]. However, deciphering infant cries presents challenges. Extensive research has been conducted to interpret infant cry audios [2,3]. This paper proposes the classification of infant cries using 3D feature vectors augmented with various audio data techniques. A total of 5 classes (belly pain, burping, discomfort, hungry, tired) are employed in the study dataset. The data is augmented using 5 techniques (Pitch, Tempo, Shift, Mixup-noise, CutMix). Tempo, Shift, and CutMix augmentation techniques demonstrated improved performance. Ultimately, applying effective data augmentation techniques simultaneously resulted in a 17.75% performance enhancement compared to models using single feature vectors and original data.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.19 no.1
• /
• pp.9-17
• /
• 2024

It is widely recognized that for 3D human pose estimation (HPE), dataset acquisition is expensive and the effectiveness of augmentation techniques of conventional visual recognition tasks is limited. We address these difficulties by presenting a simple but effective method that augments input images in terms of viewpoints when training a 3D human pose estimation (HPE) model. Our intuition is that meaningful variants of the input images for HPE could be obtained by viewing a human instance in the images from an arbitrary viewpoint different from that in the original images. The core idea is to synthesize new images that have self-occlusion and thus are difficult to predict at different viewpoints even with the same pose of the original example. We incorporate this idea into the training procedure of the 3D HPE model as an augmentation stage of the input samples. We show that a strategy for augmenting the synthesized example should be carefully designed in terms of the frequency of performing the augmentation and the selection of viewpoints for synthesizing the samples. To this end, we propose a new metric to measure the prediction difficulty of input images for 3D HPE in terms of the distance between corresponding keypoints on both sides of a human body. Extensive exploration of the space of augmentation probability choices and example selection according to the proposed distance metric leads to a performance gain of up to 6.2% on Human3.6M, the well-known pose estimation dataset.

• Journal of Korean Neurosurgical Society
• /
• v.47 no.3
• /
• pp.180-184
• /
• 2010

Objective : To prevent temporal depression after the pterional craniotomy, this study was designed to examine the safety and aesthetic efficacy of the brushite calcium phosphate cement (CPC) in the repair and augmentation of bone defects following the pterional craniotomy. Methods : The brushite CPC was used for the repair of surgically induced cranial defects, with or without augmentation, in 17 cases of pterional approach between March, 2005 and December, 2006. The average follow-up month was 20 with range of 12-36 months. In the first 5 cases, bone defects were repaired with only brushite CPC following the contour of the original bone. In the next 12 cases, bone defects were augmented with the brushite CPC rather than original bone contour. For a stability monitoring of the implanted brushite CPC, post-implantation evaluations including serial X-ray, repeated physical examination for aesthetic efficacy, and three-dimensional computed tomography (3D-CT) were taken 1 year after the implantation. Results : The brushite CPC paste provided precise and easy contouring in restoration of the bony defect site. No adverse effects such as infection or inflammation were noticed during the follow-up periods from all patients. 3D-CT was taken 1 year subsequent to implantation showed good preservation of the brushite CPC restoration material. In the cases of the augmentation group, aesthetic outcomes were superior compared to the simple repair group. Conclusion : The results of this clinical study indicate that the brushite CPC is a biocompatible alloplastic material, which is useful for prevention of temporal depression after pterional craniotomy. Additional study is required to determine the long-term stability and effectiveness of the brushite calcium phosphate cement for the replacement of bone.

• Journal of Positioning, Navigation, and Timing
• /
• v.10 no.3
• /
• pp.221-228
• /
• 2021

The Korea Augmentation Satellite System (KASS) is a Korean Satellite Based Augmentation System (SBAS) that has been under development since 2014 with the goal of providing Approach Procedure with Vertical guidance (APV)-I Safety of Life (SoL) services. KASS Control Station (KCS) is a subsystem that controls and monitors KASS systems. It also serves to store data generated by KASS. KCS has now completed detailed design and implementation and verification is in progress. This paper presents verification procedures and verification items for KCS verification activities and presents management measures for defects occurring during the verification phase.

• Journal of Internet Computing and Services
• /
• v.24 no.4
• /
• pp.85-92
• /
• 2023

Deep learning applications are increasingly being leveraged for disease detection tasks in medical imaging modalities such as X-ray, Computed Tomography (CT), and Magnetic Resonance Imaging (MRI). Most data-centric deep learning challenges necessitate the use of supervised learning methodologies to attain high accuracy and to facilitate performance evaluation through comparison with the ground truth. Supervised learning mandates a substantial amount of image and label sets, however, procuring an adequate volume of medical imaging data for training is a formidable task. Various data augmentation strategies can mitigate the underfitting issue inherent in supervised learning-based models that are trained on limited medical image and label sets. This research investigates the enhancement of a deep learning-based rib fracture segmentation model and the efficacy of data augmentation techniques such as left-right flipping, rotation, and scaling. Augmented dataset with L/R flipping and rotations(30°, 60°) increased model performance, however, dataset with rotation(90°) and ⨯0.5 rescaling decreased model performance. This indicates the usage of appropriate data augmentation methods depending on datasets and tasks.

• The Journal of Korea Robotics Society
• /
• v.18 no.3
• /
• pp.346-351
• /
• 2023

With the release of numerous open driving datasets, the demand for domain adaptation in perception tasks has increased, particularly when transferring knowledge from rich datasets to novel domains. However, it is difficult to solve the change 1) in the sensor domain caused by heterogeneous LiDAR sensors and 2) in the environmental domain caused by different environmental factors. We overcome domain differences in the semi-supervised setting with 3-stage model parameter training. First, we pre-train the model with the source dataset with object scaling based on statistics of the object size. Then we fine-tine the partially frozen model weights with copy-and-paste augmentation. The 3D points in the box labels are copied from one scene and pasted to the other scenes. Finally, we use the knowledge distillation method to update the student network with a moving average from the teacher network along with a self-training method with pseudo labels. Test-Time Augmentation with varying z values is employed to predict the final results. Our method achieved 3rd place in ECCV 2022 workshop on the 3D Perception for Autonomous Driving challenge.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.05a
• /
• pp.369-371
• /
• 2011

Since users can experience new type of experiment system using augmentation technology and its data visibility, it is a media that is suited to educational purpose application. This paper developed an augmentation-based experimentation that excludes risks and ehnances immersion in chemical experiment. This virtual chemistry experiment system utilizes users' hands to control 3D objects in experiment through interface that interacts virtual objects without markers that are the cause of losing immersion in existing augmentation system. To maximize immersion effect, we propose a virtual chemistry experiment system that enables collaborative work.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.49-54
• /
• 2024

Data imbalance is a common issue encountered in classification problems, stemming from a significant disparity in the number of samples between classes within the dataset. Such data imbalance typically leads to problems in classification models, including overfitting, underfitting, and misinterpretation of performance metrics. Methods to address this issue include resampling, augmentation, regularization techniques, and adjustment of loss functions. In this paper, we focus on loss function adjustment, particularly comparing the performance of various configurations of loss functions (Cross Entropy, Balanced Cross Entropy, two settings of Focal Loss: 𝛼 = 1 and 𝛼 = Balanced, Asymmetric Loss) on Multi-Class black-box video data with imbalance issues. The comparison is conducted using the I3D, and R3D_18 models.