• KEPCO Journal on Electric Power and Energy
• /
• v.2 no.4
• /
• pp.619-625
• /
• 2016

In this paper, we propose a new fault diagnosis monitoring system using gyro sensor-based angular velocity calculation for blades of the wind turbine system. First, the proposed system generates the angular velocity dataset for the rotation speed of the normal blade. Using the dataset, we estimate and evaluate the state of blades for the wind turbine by comparing the current state with the pre-calculated normal state. In the experimental results, the angular velocity of the normal state was higher than $360^{\circ}/s$ while that of the damaged blades was lower than $360^{\circ}/s$ and the standard deviation of the angular velocity was significantly increased.

• International Journal of Contents
• /
• v.10 no.1
• /
• pp.1-11
• /
• 2014

In the current generation of smart mobile devices, object tracking is one of the most important research topics for computer vision. Because human face tracking can be widely used for many applications, collecting a dataset of face videos is necessary for evaluating the performance of a tracker and for comparing different approaches. Unfortunately, the well-known benchmark datasets of face videos are not sufficiently diverse. As a result, it is difficult to compare the accuracy between different tracking algorithms in various conditions, namely illumination, background complexity, and subject movement. In this paper, we propose a new dataset that includes 91 face video clips that were recorded in different conditions. We also provide a semi-automatic ground-truth generation tool that can easily be used to evaluate the performance of face tracking systems. This tool helps to maintain the consistency of the definitions for the ground-truth in each frame. The resulting video data set is used to evaluate well-known approaches and test their efficiency.

• Journal of the Korean Society for Library and Information Science
• /
• v.54 no.2
• /
• pp.419-434
• /
• 2020

The purpose of the study is to design and propose metadata standard for building AI training dataset of landmark images. In order to achieve the purpose, we first examined and analyzed the state of art of the types of image retrieval systems and their indexing methods, comprehensively. We then investigated open training dataset and machine learning tools for image object recognition. Sequentially, we selected metadata elements optimized for the AI training dataset of landmark images and defined the input data for each element. We then concluded the study with implications and suggestions for the development of application services using the results of the study.

• The Journal of the Korea Contents Association
• /
• v.18 no.6
• /
• pp.27-37
• /
• 2018

Streamline generation is one of the most representative visualization methods to analyze the flow stream of fluid dynamics dataset. It is a challenging problem, however, to determine the seed locations for effective streamline visualization. Meanwhile, it needs much time to compute effective seed locations and streamlines on the massive flow dataset. In this paper, we propose not only an importance based method to determine seed locations for the effective streamline placements but also a parallel streamline visualization method on the distributed visualization system. Moreover, we introduce case studies on the real fluid dynamics dataset using GLOVE visualization system to evaluate the proposed method.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.10
• /
• pp.45-55
• /
• 2018

R2RML is a W3C standard language that defines how to expose the relational data as RDF triples. The output from an R2RML mapping is only an RDF dataset. By definition, the dataset has no schema. The lack of schema makes the dataset in linked data portal impractical for integrating and analyzing data. To address this issue, we propose an approach for generating automatically schemas for RDF graphs populated by R2RML mappings. More precisely, we represent the schema using ShEx, which is a language for validating and describing RDF. Our approach allows to generate ShEx schemas as well as RDF datasets from R2RML mappings. Our ShEx schema can provide benefits for both data providers and ordinary users. Data providers can verify and guarantee the structural integrity of the dataset against the schema. Users can write SPARQL queries efficiently by referring to the schema. In this paper, we describe data structures and algorithms of the system to derive ShEx documents from R2RML documents and presents a brief demonstration regarding its proper use.

• Journal of IKEEE
• /
• v.21 no.3
• /
• pp.244-247
• /
• 2017

In this paper, we implemented a convolution neural network using GP-GPU. After defining the structure, CNN performed inferencing using the GP-GPU with 256 threads, which was the previous study, using the weight obtained from the training. Training used Intel i7-4470 CPU and Matlab. Dataset used Daimler Pedestrian Dataset. The GP-GPU is controlled by the PC using PCIe and operates as an FPGA. We assigned a thread according to the depth and size of each layer. In the case of the pooling layer, we used over warpping pooling to perform additional operations on the horizontal and vertical regions. One inferencing takes about 12 ms.

• Journal of Korea Multimedia Society
• /
• v.25 no.11
• /
• pp.1643-1652
• /
• 2022

Most of the existing machine reading research has used Recurrent Neural Network (RNN) and Convolutional Neural Network (CNN) algorithms as networks. Among them, RNN was slow in training, and Question Answering Network (QANet) was announced to improve training speed. QANet is a model composed of CNN and self-attention. CNN extracts semantic and syntactic information well from the local corpus, but there is a limit to extracting the corresponding information from the global corpus. Graph Convolutional Networks (GCN) extracts semantic and syntactic information relatively well from the global corpus. In this paper, to take advantage of this strength of GCN, we propose I-QANet, which changed the CNN of QANet to GCN. The proposed model performed 1.2 times faster than the baseline in the Stanford Question Answering Dataset (SQuAD) dataset and showed 0.2% higher performance in Exact Match (EM) and 0.7% higher in F1. Furthermore, in the Korean Question Answering Dataset (KorQuAD) dataset consisting only of Korean, the learning time was 1.1 times faster than the baseline, and the EM and F1 performance were also 0.9% and 0.7% higher, respectively.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.22 no.1
• /
• pp.49-59
• /
• 2019

Generative adversarial networks(GANs) have received great attention in the machine learning field for their capacity to model high-dimensional and complex data distribution implicitly and generate new data samples from the model distribution. This paper investigates the model training methodology, architecture, and various applications of generative adversarial networks. Experimental evaluation is also conducted for generating synthetic image dataset for defense using two types of GANs. The first one is for military image generation utilizing the deep convolutional generative adversarial networks(DCGAN). The other is for visible-to-infrared image translation utilizing the cycle-consistent generative adversarial networks(CycleGAN). Each model can yield a great diversity of high-fidelity synthetic images compared to training ones. This result opens up the possibility of using inexpensive synthetic images for training neural networks while avoiding the enormous expense of collecting large amounts of hand-annotated real dataset.

• Journal of the Korea Convergence Society
• /
• v.12 no.1
• /
• pp.57-63
• /
• 2021

Spoken language understanding, which aims to understand utterance as naturally as human would, are mostly focused on English language. In this paper, we construct a Korean language dataset for spoken language understanding, which is based on a conversational corpus between reservation system and its user. The domain of conversation is limited to restaurant reservation. There are 7 types of slot tags and 5 types of intent tags in 6857 sentences. When a model proposed in English-based research is trained with our dataset, intent classification accuracy decreased a little, while slot filling F1 score decreased significantly.

• Journal of Korea Multimedia Society
• /
• v.25 no.3
• /
• pp.451-460
• /
• 2022

Recently, several deep learning studies have been reported to automatically identify the location of diagnostic devices using endoscopic data. In previous studies, there was no design to determine whether the configuration of the dataset resulted in differences in the accuracy in which artificial intelligence models perform image classification. Studies that are based on large amounts of data are likely to have different results depending on the composition of the dataset or its proportion. In this study, we intended to determine the existence and extent of accuracy according to the composition of the dataset by compiling it into three main types using larynx, esophagus, gastroscopy, and laryngeal endoscopy images.