• Journal of the Korean Society for information Management
• /
• v.25 no.4
• /
• pp.115-129
• /
• 2008

Recently, as its growth and popularization, the Web is changed into the place where people express, share and debate their opinions rather than the space of information seeking. Accordingly, the needs for searching opinions expressed in the Web are also increasing. However, it is difficult to meet these needs by using a classical information retrieval system that only concerns the relevance between the user's query and documents. Instead, a more advanced system that captures subjective information through documents is required. The proposed system effectively retrieves opinionated documents by utilizing an existing information retrieval system. This paper proposes a kind of hybrid method which can utilize both a dictionary-based opinion analysis technique and a machine learning based opinion analysis technique. Experimental results show that the proposed method is effective in improving the performance.

• Journal of Broadcast Engineering
• /
• v.21 no.2
• /
• pp.252-260
• /
• 2016

The performance of human detection system is affected by camera location and view angle. In 2D image acquired from such camera settings, humans are displayed in different sizes. Detecting all the humans with diverse sizes poses a difficulty in realizing a real-time system. However, if the size of a human in an image can be predicted, the processing time of human detection would be greatly reduced. In this paper, we propose a method that estimates human size by constructing an indoor scene in 3D space. Since the human has constant size everywhere in 3D space, it is possible to estimate accurate human size in 2D image by projecting 3D human into the image space. Experimental results validate that a human size can be predicted from the proposed method and that machine-learning based detection methods can yield the reduction of the processing time.

• Journal of IKEEE
• /
• v.20 no.3
• /
• pp.209-219
• /
• 2016

SVM is a machine learning method used for image processing. It is well known for its high classification performance. We have to perform multiple MAC operations in order to use SVM for image classification. However, if the resolution of the target image or the number of classification cases increases, the execution time of SVM also increases, which makes it difficult to be performed in real-time applications. In this paper, we propose an hardware architecture which enables real-time applications using SVM classification. We used parallel architecture to simultaneously calculate MAC operations, and also designed the system for several feature extractors for compatibility. RBF kernel was used for hardware implemenation, and the exponent calculation formular included in the kernel was modified to enable fixed point modelling. Experimental results for the system, when implemented in Xilinx ZC-706 evaluation board, show that it can process 60.46 fps for $1360{\times}800$ resolution at 100MHz clock frequency.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.4
• /
• pp.292-302
• /
• 2020

Machine learning algorithms have made immense contributions in various fields including sonar and radar applications. Recently developed Cycle-Consistency Generative Adversarial Network (CycleGAN), a variant of GAN has been successfully used for unpaired image-to-image translation. We present a modified CycleGAN for translation of underwater ship engine sounds with high perceptual quality. The proposed network is composed of an improved generator model trained to translate underwater audio from one vessel type to other, an improved discriminator to identify the data as real or fake and a modified cycle-consistency loss function. The quantitative and qualitative analysis of the proposed CycleGAN are performed on publicly available underwater dataset ShipsEar by evaluating and comparing Mel-cepstral distortion, pitch contour matching, nearest neighbor comparison and mean opinion score with existing algorithms. The analysis results of the proposed network demonstrate the effectiveness of the proposed network.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.5
• /
• pp.279-284
• /
• 2017

Currenty, in the era of big data, text mining and opinion mining have been used in many domains, and one of their most important research issues is to extract significant information from social media. Thus in this paper, we propose a logistic regression ensemble method of finding the main body text from blog HTML. First, we extract structural features and text features from blog HTML tags. Then we construct a classification model with logistic regression and ensemble that can decide whether any given tags involve main body text or not. One of our important findings is that the main body text can be found through 'depth' features extracted from HTML tags. In our experiment using diverse topics of blog data collected from the web, our tag classification model achieved 99% in terms of accuracy, and it recalled 80.5% of documents that have tags involving the main body text.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.23 no.1
• /
• pp.49-62
• /
• 2018

Net community production (NCP), defined as the difference between net primary production and respiration of heterotrophs, has been used as a measure of oceanic biological carbon pump. This paper summarizes the theoretical background and experimental methods for the estimation of NCP based on $O_2/Ar$ measurements ($O_2/Ar-NCP$). The high frequency measurements of $O_2/Ar-NCP$ (<1 min) is a significant enhancement over the conventional measures of biological pump, such as new production and export production. This paper also introduces some of important works as to the comparison between $O_2/Ar-NCP$ and other measures of biological pump, the distributions of $O_2/Ar-NCP$ in the oceans, and the correlation of $O_2/Ar-NCP$ with various oceanic parameters, including community structures.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.5
• /
• pp.859-866
• /
• 2021

Agricultural Photovoltaic power generation is a new model that installs solar power generation facilities on top of farmland. Through this, it is possible to increase farm household income by producing crops and electricity at the same time. Recently, various attempts have been made to utilize agricultural solar power generation. Agricultural photovoltaic power generation has a disadvantage in that maintenance is relatively difficult because it is installed on a relatively high structure unlike conventional photovoltaic power generation. To solve these problems, intelligent and efficient operation and diagnostic functions are required. In this paper, we discuss the design and implementation of a prediction and diagnosis system to collect and store the power output of agricultural solar power generation facilities and implement an intelligent prediction model. The proposed system predicts the amount of power generation based on the amount of solar power generation and environmental sensor data, determines whether there is an abnormality in the facility, calculates the aging degree of the facility and provides it to the user.

• Journal of the Architectural Institute of Korea Structure & Construction
• /
• v.35 no.11
• /
• pp.155-162
• /
• 2019

The construction industry is the highest safety accident causing industry as 28.55% portion of all industries' accidents in Korea. In particular, falling is the highest accidents type composed of 60.16% among the construction field accidents. Therefore, we analyzed the factors of major disaster affecting the fall accident and then derived feature importances by considering various variables. We used data collected from Korea Occupational Safety & Health Agency (KOSHA) for learning and predicting in the proposed model. We have an effort to predict the degree of occupational fall accidents by using the machine learning model, i.e., Adaboost, short for Adaptive Boosting. Adaboost is a machine learning meta-algorithm which can be used in conjunction with many other types of learning algorithms to improve performance. Decision trees were combined with AdaBoost in this model to predict and classify the degree of occupational fall accidents. HyOperpt was also used to optimize hyperparameters and to combine k-fold cross validation by hierarchy. We extracted and analyzed feature importances and affecting fall disaster by permutation technique. In this study, we verified the degree of fall accidents with predictive accuracy. The machine learning model was also confirmed to be applicable to the safety accident analysis in construction site. In the future, if the safety accident data is accumulated automatically in the network system using IoT(Internet of things) technology in real time in the construction site, it will be possible to analyze the factors and types of accidents according to the site conditions from the real time data.

• Journal of Internet Computing and Services
• /
• v.23 no.6
• /
• pp.87-96
• /
• 2022

This paper is an empirical analysis as a reference model that can predict up to the maximum number of elementary school student care needs in local governments across the country. This study analyzed and predicted the characteristics of the region based on machine learning to predict the demand for elementary care in a new apartment complex. For this purpose, a total of 292 variables were used, including data related to apartment structure, such as number of parking spaces per household, and building-to-land ratio, environmental data around apartments such as distance to elementary schools, and population data of administrative districts. The use of various variables is of great significance, and it is meaningful in complex analysis. It is also an empirical case study that increased the reliability of the model through comparison with the actual value of the basic local government.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.10
• /
• pp.75-80
• /
• 2017

In this paper, we describe the effect of the regularization method and the network with identity mapping on the performance of the activation functions in deep convolutional neural networks. The activation functions act as nonlinear transformation. In early convolutional neural networks, a sigmoid function was used. To overcome the problem of the existing activation functions such as gradient vanishing, various activation functions were developed such as ReLU, Leaky ReLU, parametric ReLU, and ELU. To solve the overfitting problem, regularization methods such as dropout and batch normalization were developed on the sidelines of the activation functions. Additionally, data augmentation is usually applied to deep learning to avoid overfitting. The activation functions mentioned above have different characteristics, but the new regularization method and the network with identity mapping were validated only using ReLU. Therefore, we have experimentally shown the effect of the regularization method and the network with identity mapping on the performance of the activation functions. Through this analysis, we have presented the tendency of the performance of activation functions according to regularization and identity mapping. These results will reduce the number of training trials to find the best activation function.