• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.34-36
• /
• 2022

In the existing text sentiment analysis models, the entire text is usually directly modeled as a whole, and the hierarchical relationship between text contents is less considered. However, in the practice of sentiment analysis, many texts are mixed with multiple emotions. If the semantic modeling of the whole is directly performed, it may increase the difficulty of the sentiment analysis model to judge the sentiment, making the model difficult to apply to the classification of mixed-sentiment sentences. Therefore, this paper proposes a sentiment analysis model BHGCN that considers the text hierarchy. In this model, the output of hidden states of each layer of BERT is used as a node, and a directed connection is made between the upper and lower layers to construct a graph network with a semantic hierarchy. The model not only pays attention to layer-by-layer semantics, but also pays attention to hierarchical relationships. Suitable for handling mixed sentiment classification tasks. The comparative experimental results show that the BHGCN model exhibits obvious competitive advantages.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.3
• /
• pp.845-850
• /
• 2023

In this paper, we propose a method for diagnosing ball bearing vibration using transfer learning. STFT, which can analyze vibration signals in time-frequency, was used as input to CNN to diagnose failures. In order to rapidly learn CNN-based deep artificial neural networks and improve diagnostic performance, we proposed a transfer learning-based deep learning learning technique. For transfer learning, the feature extractor and classifier were selectively learned using a VGG-based image classification model, the data set for learning was publicly available ball bearing vibration data provided by Case Western Reserve University, and performance was evaluated by comparing the proposed method with the existing CNN model. Experimental results not only prove that transfer learning is useful for condition diagnosis in ball bearing vibration data, but also allow other industries to use transfer learning to improve condition diagnosis.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.27 no.2
• /
• pp.289-297
• /
• 2009

In the paper, we propose the methodology to extract training dataset automatically for supervised classification of road networks. For the preprocessing, we co-register the airborne photos, LIDAR data and large-scale digital maps and then, create orthophotos and intensity images. By overlaying the large-scale digital maps onto generated images, we can extract the initial training dataset for the supervised classification of road networks. However, the initial training information is distorted because there are errors propagated from registration process and, also, there are generally various objects in the road networks such as asphalt, road marks, vegetation, cars and so on. As such, to generate the training information only for the road surface, we apply the Expectation Maximization technique and finally, extract the training dataset of the road surface. For the accuracy test, we compare the training dataset with manually extracted ones. Through the statistical tests, we can identify that the developed method is valid.

• Journal of Energy Engineering
• /
• v.23 no.1
• /
• pp.75-80
• /
• 2014

The past several years have seen a substantial growth in mathematical modeling activities whose interests are to describe the performance, efficiency and emissions characteristics of various types of internal combustion engines. The key element in these simulations of various aspects of engine operation is the model of the engine combustion process. Combustion models are then classified into three categories: zero-dimensional, quasi-dimensional and multidimensional models. zero-dimensional models are built around the first law of thermodynamics, and time is the only independent variable. This paper presents a introduction to the combustion characteristics of a spark ignition combustion modeling by zero-dimensional model.

• Animal Systematics, Evolution and Diversity
• /
• v.19 no.2
• /
• pp.237-244
• /
• 2003

Two epistylid peritrichous ciliates collected from the littoral aquatic plants at pond in a suburb of Ulsan, Korea were identified as Epistylis plicatilis Ehrenberg, 1831 and E. hentscheli Kahl, 1935. The description was based on the observation of living specimens and protargol impregnated specimens. This study is about redescription compared with original description. These species have not been reported in Korea and their characteristics are as follows: E. plicatilis is thin, long funnel form and has compact stalk, while E. hentscheli is unsymmetrical bell form and has hollow stalk.

• Journal of Korea Technology Innovation Society
• /
• v.16 no.1
• /
• pp.176-198
• /
• 2013

Preliminary feasibility study(PFS) was introduced in 1999 by financial authority to encourage a cautious approach to new large-scale public investment project. As it applied cost-benefit analysis as prime measure for decision-making, various issues have been arisen concerning feasibility analysis on R&D programs. This work is intended to suggest standard approaches to be established in PFS on R&D program as follows: 1. The issue questions can be induced in a standard way by 15 representative questions and their correlation with evaluation criteria. 2. The analyzing strategy can be standardized by establishing standards for classification of R&D effects and R&D logic analysis.

• Journal of Internet Computing and Services
• /
• v.21 no.2
• /
• pp.121-130
• /
• 2020

This paper suggests evaluating the military closed network data as an image which is generated by Generative Adversarial Network (GAN), applying an image evaluation method such as the InceptionV3 model-based Inception Score (IS) and Frechet Inception Distance (FID). We employed the famous image classification models instead of the InceptionV3, added layers to those models, and converted the network data to an image in diverse ways. Experimental results show that the Densenet121 model with one added Dense Layer achieves the best performance in data converted using the arctangent algorithm and 8 * 8 size of the image.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.18 no.2
• /
• pp.170-177
• /
• 2009

The objective of this study is to evaluate an acoustic emission (AE) source characterization and fracture behavior of the SM45C steel by using back-propagation neural network (BPN). In previous research Ref. [8] about k-nearest neighbor classifier (k-NNC) continuity, we used K-means clustering method as an unsupervised learning method for obtaining multi-variate AE main data sets, such as AE counts, energy, amplitude, risetime, duration and counts to peak. Similarly, we applied k-NNC and BPN as a supervised learning method for obtaining multi-variate AE working data sets. According to the error of convergence for determinant criterion Wilk's ${\lambda}$, heuristic criteria D&B(Rij) and Tou values are discussed. As a result, in k-NNC before fracture signal is detected or when fracture signal is detected, showed that produce some empty classes in BPN. And we confirmed that could save trouble in AE signal processing if suitable error of convergence or acceptable encoding error give to BPN.

• Journal of Korea Multimedia Society
• /
• v.18 no.3
• /
• pp.298-311
• /
• 2015

Vector data represents a map by its coordinate and Raster data represents a map by its pixel. Since these data types have very large data size, data compression procedure is a compulsory process. This paper compare the results from three different methodologies; GIS (Geographic Information System) vector map data compression using DP(Douglas-Peucker) Simplification algorithm, vector data compression based on Bin classification and the combination between two previous methods. The results shows that the combination between the two methods have the best performance among the three tested methods. The proposed method can achieve 4-9% compression ratio while the other methods show a lower performance.

• Environmental Analysis Health and Toxicology
• /
• v.18 no.4
• /
• pp.249-254
• /
• 2003

본 연구는 환경호르몬(endocrine disruptors)으로 분류되었으며, 에스트로젠 화합물의 특성을 지닌 4-Nonylphenol (NP)이 설치류 Pituitary 세포 중 성장호르몬을 분비하는 GH3 세포의 Nitric oxide(NO)을 증가시키는 작용기전을 규명코자 수행되었다 먼저 GH3세포에 NP처리 농도에 따른 NO의 생성을 측정한 결과 NP처리농도 의존적으로 증가시켰다. 이러한 NO의 증가가 genomic action인지를 확인하기 위해 GH3세포의 NO를 증가시키는 효소인 neuronal oxide synthase의 단백질량을 측정한 결과 GH3세포에서 NP에 의한 nNOS의 단백질의 변화는 없었다. 에스트로젠 화합물인 NP가 에스트로젠 리셉터 (ER)와의 관계를 조사하기 위해 ER억제제(ICI 168,780)클 처리한 경우 NP에 의해 증가한 NO가 감소하였다. 또한 유전자 전사억제제인 actinomycin D 및 단백질 발현 억제제인 cycloheximide을 처리한 경우는 NP에 의한 NO 증가억제효과가 없었다. 이러한 결과를 종합해 볼 때 GH3 세포에서 NP는 ER을 매개한 non-genomic action에 의해 NO를 증가키는 것으로 사료된다.