• Korean Journal of Remote Sensing
• /
• v.40 no.3
• /
• pp.295-305
• /
• 2024

This study aims to analyze the micro-sedimentary structures of the Hwangdo tidal flats using ultra-high resolution unmanned aerial vehicle (UAV) data. Tidal flats, located in the transitional area between land and sea, constantly change due to tidal activities and provide a unique environment important for understanding sedimentary processes and environmental conditions. Traditional field observation methods are limited in spatial and temporal coverage, and existing satellite imagery does not provide sufficient resolution to study micro-sedimentary structures. To overcome these limitations, high-resolution images of the Hwangdo tidal flats in Chungcheongnam-do were acquired using UAVs. This area has experienced significant changes in its sedimentary environment due to coastal development projects such as sea wall construction. From May 17 to 18, 2022, sediment samples were collected from 91 points during field surveys and 25 in-situ points were intensively analyzed. UAV data with a spatial resolution of approximately 0.9 mm allowed identifying and extracting parameters related to micro-sedimentary structures. For mud cracks, the length of the major axis of the polygons was extracted, and the wavelength and ripple symmetry index were extracted for ripple marks. The results of the study showed that in areas with mud content above 80%, mud cracks formed at an average major axis length of 37.3 cm. In regions with sand content above 60%, ripples with an average wavelength of 8 cm and a ripple symmetry index of 2.0 were formed. This study demonstrated that micro-sedimentary structures of tidal flats can be effectively analyzed using ultra-high resolution UAV data without field surveys. This highlights the potential of UAV technology as an important tool in environmental monitoring and coastal management and shows its usefulness in the study of sedimentary structures. In addition, the results of this study are expected to serve as baseline data for more accurate sedimentary facies classification.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.25 no.6
• /
• pp.583-603
• /
• 2023

Recently, the advancement of mechanical tunnel boring machine (TBM) technology and the characteristics of subsea railway tunnels subjected to hydrostatic pressure have led to the widespread application of shield TBM methods in the design and construction of subsea railway tunnels. Subsea railway tunnels are exposed in a constant pore water pressure and are influenced by the amplification of seismic waves during earthquake. In particular, seismic loads acting on subsea railway tunnels under various ground conditions such as soft ground, soft soil-rock composite ground, and fractured zones can cause significant changes in tunnel displacement and stress, thereby affecting tunnel safety. Additionally, the dynamic response of the ground and tunnel varies based on seismic load parameters such as frequency characteristics, seismic waveform, and peak acceleration, adding complexity to the behavior of the ground-tunnel structure system. In this study, a finite difference method is employed to model the entire ground-tunnel structure system, considering hydrostatic pressure, for the investigation of dynamic behavior of subsea railway tunnel during earthquake. Since the key factors influencing the dynamic behavior during seismic events are ground conditions and seismic waves, six analysis cases are established based on virtual ground conditions: Case-1 with weathered soil, Case-2 with hard rock, Case-3 with a composite ground of soil and hard rock in the tunnel longitudinal direction, Case-4 with the tunnel passing through a narrow fault zone, Case-5 with a composite ground of soft soil and hard rock in the tunnel longitudinal direction, and Case-6 with the tunnel passing through a wide fractured zone. As a result, horizontal displacements due to earthquakes tend to increase with an increase in ground stiffness, however, the displacements tend to be restrained due to the confining effects of the ground and the rigid shield segments. On the contrary, peak compressive stress of segment significantly increases with weaker ground stiffness and the effects of displacement restrain contribute the increase of peak compressive stress of segment.

• Journal of Intelligence and Information Systems
• /
• v.24 no.3
• /
• pp.1-19
• /
• 2018

Large amount of data is now available for research and business sectors to extract knowledge from it. This data can be in the form of unstructured data such as audio, text, and image data and can be analyzed by deep learning methodology. Deep learning is now widely used for various estimation, classification, and prediction problems. Especially, fashion business adopts deep learning techniques for apparel recognition, apparel search and retrieval engine, and automatic product recommendation. The core model of these applications is the image classification using Convolutional Neural Networks (CNN). CNN is made up of neurons which learn parameters such as weights while inputs come through and reach outputs. CNN has layer structure which is best suited for image classification as it is comprised of convolutional layer for generating feature maps, pooling layer for reducing the dimensionality of feature maps, and fully-connected layer for classifying the extracted features. However, most of the classification models have been trained using online product image, which is taken under controlled situation such as apparel image itself or professional model wearing apparel. This image may not be an effective way to train the classification model considering the situation when one might want to classify street fashion image or walking image, which is taken in uncontrolled situation and involves people's movement and unexpected pose. Therefore, we propose to train the model with runway apparel image dataset which captures mobility. This will allow the classification model to be trained with far more variable data and enhance the adaptation with diverse query image. To achieve both convergence and generalization of the model, we apply Transfer Learning on our training network. As Transfer Learning in CNN is composed of pre-training and fine-tuning stages, we divide the training step into two. First, we pre-train our architecture with large-scale dataset, ImageNet dataset, which consists of 1.2 million images with 1000 categories including animals, plants, activities, materials, instrumentations, scenes, and foods. We use GoogLeNet for our main architecture as it has achieved great accuracy with efficiency in ImageNet Large Scale Visual Recognition Challenge (ILSVRC). Second, we fine-tune the network with our own runway image dataset. For the runway image dataset, we could not find any previously and publicly made dataset, so we collect the dataset from Google Image Search attaining 2426 images of 32 major fashion brands including Anna Molinari, Balenciaga, Balmain, Brioni, Burberry, Celine, Chanel, Chloe, Christian Dior, Cividini, Dolce and Gabbana, Emilio Pucci, Ermenegildo, Fendi, Giuliana Teso, Gucci, Issey Miyake, Kenzo, Leonard, Louis Vuitton, Marc Jacobs, Marni, Max Mara, Missoni, Moschino, Ralph Lauren, Roberto Cavalli, Sonia Rykiel, Stella McCartney, Valentino, Versace, and Yve Saint Laurent. We perform 10-folded experiments to consider the random generation of training data, and our proposed model has achieved accuracy of 67.2% on final test. Our research suggests several advantages over previous related studies as to our best knowledge, there haven't been any previous studies which trained the network for apparel image classification based on runway image dataset. We suggest the idea of training model with image capturing all the possible postures, which is denoted as mobility, by using our own runway apparel image dataset. Moreover, by applying Transfer Learning and using checkpoint and parameters provided by Tensorflow Slim, we could save time spent on training the classification model as taking 6 minutes per experiment to train the classifier. This model can be used in many business applications where the query image can be runway image, product image, or street fashion image. To be specific, runway query image can be used for mobile application service during fashion week to facilitate brand search, street style query image can be classified during fashion editorial task to classify and label the brand or style, and website query image can be processed by e-commerce multi-complex service providing item information or recommending similar item.

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.141-154
• /
• 2019

Rapid growth of internet technology and social media is progressing. Data mining technology has evolved to enable unstructured document representations in a variety of applications. Sentiment analysis is an important technology that can distinguish poor or high-quality content through text data of products, and it has proliferated during text mining. Sentiment analysis mainly analyzes people's opinions in text data by assigning predefined data categories as positive and negative. This has been studied in various directions in terms of accuracy from simple rule-based to dictionary-based approaches using predefined labels. In fact, sentiment analysis is one of the most active researches in natural language processing and is widely studied in text mining. When real online reviews aren't available for others, it's not only easy to openly collect information, but it also affects your business. In marketing, real-world information from customers is gathered on websites, not surveys. Depending on whether the website's posts are positive or negative, the customer response is reflected in the sales and tries to identify the information. However, many reviews on a website are not always good, and difficult to identify. The earlier studies in this research area used the reviews data of the Amazon.com shopping mal, but the research data used in the recent studies uses the data for stock market trends, blogs, news articles, weather forecasts, IMDB, and facebook etc. However, the lack of accuracy is recognized because sentiment calculations are changed according to the subject, paragraph, sentiment lexicon direction, and sentence strength. This study aims to classify the polarity analysis of sentiment analysis into positive and negative categories and increase the prediction accuracy of the polarity analysis using the pretrained IMDB review data set. First, the text classification algorithm related to sentiment analysis adopts the popular machine learning algorithms such as NB (naive bayes), SVM (support vector machines), XGboost, RF (random forests), and Gradient Boost as comparative models. Second, deep learning has demonstrated discriminative features that can extract complex features of data. Representative algorithms are CNN (convolution neural networks), RNN (recurrent neural networks), LSTM (long-short term memory). CNN can be used similarly to BoW when processing a sentence in vector format, but does not consider sequential data attributes. RNN can handle well in order because it takes into account the time information of the data, but there is a long-term dependency on memory. To solve the problem of long-term dependence, LSTM is used. For the comparison, CNN and LSTM were chosen as simple deep learning models. In addition to classical machine learning algorithms, CNN, LSTM, and the integrated models were analyzed. Although there are many parameters for the algorithms, we examined the relationship between numerical value and precision to find the optimal combination. And, we tried to figure out how the models work well for sentiment analysis and how these models work. This study proposes integrated CNN and LSTM algorithms to extract the positive and negative features of text analysis. The reasons for mixing these two algorithms are as follows. CNN can extract features for the classification automatically by applying convolution layer and massively parallel processing. LSTM is not capable of highly parallel processing. Like faucets, the LSTM has input, output, and forget gates that can be moved and controlled at a desired time. These gates have the advantage of placing memory blocks on hidden nodes. The memory block of the LSTM may not store all the data, but it can solve the CNN's long-term dependency problem. Furthermore, when LSTM is used in CNN's pooling layer, it has an end-to-end structure, so that spatial and temporal features can be designed simultaneously. In combination with CNN-LSTM, 90.33% accuracy was measured. This is slower than CNN, but faster than LSTM. The presented model was more accurate than other models. In addition, each word embedding layer can be improved when training the kernel step by step. CNN-LSTM can improve the weakness of each model, and there is an advantage of improving the learning by layer using the end-to-end structure of LSTM. Based on these reasons, this study tries to enhance the classification accuracy of movie reviews using the integrated CNN-LSTM model.

• Maxillofacial Plastic and Reconstructive Surgery
• /
• v.31 no.3
• /
• pp.243-248
• /
• 2009

Purpose: Rehabilitation of the edentulous posterior maxilla with dental implants often poses difficulty because of insufficient bone volume caused by pneumatization of the maxillary sinus and by crestal bone resorption. Sinus grafting technique was developed to increase the vertical height to overcome this problem. The present study was designed to evaluate the sinus floor augmentation with anorganic bovine bone (Bio-$cera^{TM}$) using histomorphometric and clinical measures. Patients and methods: Thirteen patients were involved in this study and underwent total 14 sinus lift procedures. Residual bone height was ${\geq}2mm$ and ${\leq}6mm$. Lateral window approach was used, with grafting using Bio-$cera^{TM}$ only(n=1) or mixed with autogenous bone from ramus and/or maxillary tuberosity(n=13). After 6 months of healing, implant sites were created with 3mm diameter trephine and biopsies taken for histomorphometric analysis. The parameters assessed were area fraction of new bone, graft material and connective tissue. Immediate and 6 months after grafting surgery, and 6 months after implantation, computed tomography (CT) was taken and the sinus graft was evaluated morphometric analysis. After implant installation at the grafted area, the clinical outcome was checked. Results: Histomorphometry was done in ten patients.Bio-$cera^{TM}$ particles were surrounded by newly formed bone. The graft particles and newly formed bone were surrounded by connective tissue including small capillaries in some fields. Imaging processing revealed $24.86{\pm}7.59%$ of new bone, $38.20{\pm}13.19%$ connective tissue, and $36.92{\pm}14.51%$ of remaining Bio-$cera^{TM}$ particles. All grafted sites received an implant, and in all cases sufficient bone height was achieved to install implants. The increase in ridge height was about $15.9{\pm}1.8mm$ immediately after operation (from 13mm to 19mm). After 6 months operation, ridge height was reduced about $11.5{\pm}13.5%$. After implant installation, average marginal bone loss after 6 months was $0.3{\pm}0.15mm$. Conclusion: Bio-$cera^{TM}$ showed new bone formation similar with Bio-$Oss^{(R)}$ histomorphometrically and appeared to be an effective bone substitute in maxillary sinus augmentation procedure with the residual bone height from 2 to 6mm.

• Economic and Environmental Geology
• /
• v.50 no.2
• /
• pp.117-128
• /
• 2017

Occurrence characteristics and existing forms of U-Th containing minerals in KURT (KAERI Underground Research Tunnel) granite are investigated to understand long-term behavior of radionuclides in granite considered as a candidate rock for the geological disposal of high-level radioactive waste. KURT granite primarily consists of quartz, feldspar and mica. zircon, REE(Rare Earth Element)-containing monazite and bastnaesite are also identified. Besides, secondary minerals such as sericite, microcline and chlorite including quartz vein and calcite vein are observed. These minerals are presumed to be accompanied by a post-hydrothermal process. U-Th containing minerals are mainly observed at the boundaries of quartz, feldspar and mica, mostly less than $30{\mu}m$ in size. Quantitative analysis results using EPMA (Electron Probe Micro-Analyzer) show that 74.2 ~ 96.5% of the U-Th containing minerals consist of $UO_2$ (3.39 ~ 33.19 wt.%), $ThO_2$ (41.61 ~ 50.24 wt.%) and $SiO_2$ (15.43 ~ 18.60 wt.%). Chemical structure of the minerals calculated using EPMA quantitative analysis shows that the U-Th minerals are silicate minerals determined as thorite and uranothorite. The U-Th containing silicate minerals are formed by a magmatic and hydrothermal process. Therefore, KURT granite formed by a magmatic differentiation is accompanied by an alteration and replacement owing to a hydrothermal process. U-Th containing silicate minerals in KURT granite are estimated to be recrystallized by geochemical factors and parameters such as temperature, pressure and pH owing to the hydrothermal process. By repeated dissolution/precipitation during the recrystallization process, U-Th containing silicate minerals such as thorite and uranothorite are formed according to the variation in the concentrated amount of U and Th.

• Journal of Biomedical Engineering Research
• /
• v.25 no.4
• /
• pp.253-259
• /
• 2004

in this study, we developed a Monte Carlo imaging simulation code written by the visual C$\^$++/ programing language for design optimization of a digital X-ray imaging system. As a digital X-ray imaging system, we considered a Gd$_2$O$_2$S(Tb) scintillator and a photosensor array, and included a 2D parallel grid to simulate general test renditions. The interactions between X-ray beams and the system structure, the behavior of lights generated in the scintillator, and their collection in the photosensor array were simulated by using the Monte Carlo method. The scintillator thickness and the photosensor array pitch were assumed to 66$\mu\textrm{m}$ and 48$\mu\textrm{m}$, respertively, and the pixel format was set to 256 x 256. Using the code, we obtained X-ray images under various simulation conditions, and evaluated their image qualities through the calculations of SNR (signal-to-noise ratio), MTF (modulation transfer function), NPS (noise power spectrum), DQE (detective quantum efficiency). The image simulation code developed in this study can be applied effectively for a variety of digital X-ray imaging systems for their design optimization on various design parameters.

• The Korean Journal of Pesticide Science
• /
• v.6 no.1
• /
• pp.16-24
• /
• 2002

Research trends in the measurement of foliar uptake of pesticides and the recently proposed action mechanism of the surfactant-induced uptake of pesticides were reviewed with the related reports and studies. Major techniques used in those fields are bioassay, radiotracer techniques with leaves or cuticular membrane. Recently, a new method using Congo Red as a tracer was proposed. The limiting factor in the pesticides uptake into leaves is the waxy layer which consists of the epicuticular and cuticular wax. Physico-chemical parameters such as molar volume, water solubility and partition coefficient of pesticides have limited influences on the pesticide uptake into leaves. Polydisperse ethoxylated fatty alcohol surfactants are well known as the good activator for many pesticides. It is now generally agreed that uptake activation is not related to the intrinsic surface active properties of surfactants such as surface activity, solvent property, humectancy and critical micelle concentration. Recent studies using ESR-spectroscopy revealed that the surfactants have an unspecific plasticising effect on the molecular structure of the wax and cuticular matrix, leading to increased mobilities of pesticides. Penetration of surfactants into waxy layer altered the pesticide mobility in wax and the partition coefficient of pesticide, and then the pesticides penetration into leaves was enhanced temporally. The enhancing effect of surfactant could be significantly different depending on the carbon number of aliphatic moiety and the number of ethoxy group in polyoxyethylene chain of surfactants. It is suggested that the rate of penetration of surfactants should have a significant relationship with the rate of penetration of pesticides.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.2
• /
• pp.199-210
• /
• 2002

In this paper, we carried out the study on speech recognition using the KM-Net topology design algorithm based on decision tree state-clustering to improve the performance of acoustic models in speech recognition. The Korean has many allophonic and grammatical rules compared to other languages, so we investigate the allophonic variations, which defined the Korean phonetics, and construct the phoneme question set for phonetic decision tree. The basic idea of the HM-Net topology design algorithm is that it has the basic structure of SSS (Successive State Splitting) algorithm and split again the states of the context-dependent acoustic models pre-constructed. That is, it have generated. the phonetic decision tree using the phoneme question sets each the state of models, and have iteratively trained the state sequence of the context-dependent acoustic models using the PDT-SSS (Phonetic Decision Tree-based SSS) algorithm. To verify the effectiveness of the above algorithm we carried out the speech recognition experiments for 452 words of center for Korean language Engineering (KLE452) and 200 sentences of air flight reservation task (YNU200). Experimental results show that the recognition accuracy has progressively improved according to the number of states variations after perform the splitting of states in the phoneme, word and continuous speech recognition experiments respectively. Through the experiments, we have got the average 71.5%, 99.2% of the phoneme, word recognition accuracy when the state number is 2,000, respectively and the average 91.6% of the continuous speech recognition accuracy when the state number is 800. Also we haute carried out the word recognition experiments using the HTK (HMM Too1kit) which is performed the state tying, compared to share the parameters of the HM-Net topology design algorithm. In word recognition experiments, the HM-Net topology design algorithm has an average of 4.0% higher recognition accuracy than the context-dependent acoustic models generated by the HTK implying the effectiveness of it.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.23-45
• /
• 2020

Big data is creating in a wide variety of fields such as medical care, manufacturing, logistics, sales site, SNS, and the dataset characteristics are also diverse. In order to secure the competitiveness of companies, it is necessary to improve decision-making capacity using a classification algorithm. However, most of them do not have sufficient knowledge on what kind of classification algorithm is appropriate for a specific problem area. In other words, determining which classification algorithm is appropriate depending on the characteristics of the dataset was has been a task that required expertise and effort. This is because the relationship between the characteristics of datasets (called meta-features) and the performance of classification algorithms has not been fully understood. Moreover, there has been little research on meta-features reflecting the characteristics of multi-class. Therefore, the purpose of this study is to empirically analyze whether meta-features of multi-class datasets have a significant effect on the performance of classification algorithms. In this study, meta-features of multi-class datasets were identified into two factors, (the data structure and the data complexity,) and seven representative meta-features were selected. Among those, we included the Herfindahl-Hirschman Index (HHI), originally a market concentration measurement index, in the meta-features to replace IR(Imbalanced Ratio). Also, we developed a new index called Reverse ReLU Silhouette Score into the meta-feature set. Among the UCI Machine Learning Repository data, six representative datasets (Balance Scale, PageBlocks, Car Evaluation, User Knowledge-Modeling, Wine Quality(red), Contraceptive Method Choice) were selected. The class of each dataset was classified by using the classification algorithms (KNN, Logistic Regression, Nave Bayes, Random Forest, and SVM) selected in the study. For each dataset, we applied 10-fold cross validation method. 10% to 100% oversampling method is applied for each fold and meta-features of the dataset is measured. The meta-features selected are HHI, Number of Classes, Number of Features, Entropy, Reverse ReLU Silhouette Score, Nonlinearity of Linear Classifier, Hub Score. F1-score was selected as the dependent variable. As a result, the results of this study showed that the six meta-features including Reverse ReLU Silhouette Score and HHI proposed in this study have a significant effect on the classification performance. (1) The meta-features HHI proposed in this study was significant in the classification performance. (2) The number of variables has a significant effect on the classification performance, unlike the number of classes, but it has a positive effect. (3) The number of classes has a negative effect on the performance of classification. (4) Entropy has a significant effect on the performance of classification. (5) The Reverse ReLU Silhouette Score also significantly affects the classification performance at a significant level of 0.01. (6) The nonlinearity of linear classifiers has a significant negative effect on classification performance. In addition, the results of the analysis by the classification algorithms were also consistent. In the regression analysis by classification algorithm, Naïve Bayes algorithm does not have a significant effect on the number of variables unlike other classification algorithms. This study has two theoretical contributions: (1) two new meta-features (HHI, Reverse ReLU Silhouette score) was proved to be significant. (2) The effects of data characteristics on the performance of classification were investigated using meta-features. The practical contribution points (1) can be utilized in the development of classification algorithm recommendation system according to the characteristics of datasets. (2) Many data scientists are often testing by adjusting the parameters of the algorithm to find the optimal algorithm for the situation because the characteristics of the data are different. In this process, excessive waste of resources occurs due to hardware, cost, time, and manpower. This study is expected to be useful for machine learning, data mining researchers, practitioners, and machine learning-based system developers. The composition of this study consists of introduction, related research, research model, experiment, conclusion and discussion.