• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.12
• /
• pp.5765-5781
• /
• 2018

Extreme learning machine (ELM) is emerging as a powerful machine learning method in a variety of application scenarios due to its promising advantages of high accuracy, fast learning speed and easy of implementation. However, how to select the optimal hidden layer of ELM is still an open question in the ELM community. Basically, the number of hidden layer nodes is a sensitive hyperparameter that significantly affects the performance of ELM. To address this challenging problem, we propose to adopt multiple kernel learning (MKL) to design a multi-hidden-layer-kernel ELM (MHLK-ELM). Specifically, we first integrate kernel functions with random feature mapping of ELM to design a hidden-layer-kernel ELM (HLK-ELM), which serves as the base of MHLK-ELM. Then, we utilize the MKL method to propose two versions of MHLK-ELMs, called sparse and non-sparse MHLK-ELMs. Both two types of MHLK-ELMs can effectively find out the optimal linear combination of multiple HLK-ELMs for different classification and regression problems. Experimental results on seven data sets, among which three data sets are relevant to classification and four ones are relevant to regression, demonstrate that the proposed MHLK-ELM achieves superior performance compared with conventional ELM and basic HLK-ELM.

• International Journal of Contents
• /
• v.17 no.4
• /
• pp.1-15
• /
• 2021

Named entity recognition (NER) is a crucial task for NLP, which aims to extract information from texts. To build NER systems, deep learning (DL) models are learned with dictionary features by mapping each word in the dataset to dictionary features and generating a unique index. However, this technique might generate noisy labels, which pose significant challenges for the NER task. In this paper, we proposed DL-dictionary features, and evaluated them on two datasets, including the OntoNotes 5.0 dataset and our new infectious disease outbreak dataset named GFID. We used (1) a Bidirectional Long Short-Term Memory (BiLSTM) character and (2) pre-trained embedding to concatenate with (3) our proposed features, named the Convolutional Neural Network (CNN), BiLSTM, and self-attention dictionaries, respectively. The combined features (1-3) were fed through BiLSTM - Conditional Random Field (CRF) to predict named entity classes as outputs. We compared these outputs with other predictions of the BiLSTM character, pre-trained embedding, and dictionary features from previous research, which used the exact matching and partial matching dictionary technique. The findings showed that the model employing our dictionary features outperformed other models that used existing dictionary features. We also computed the F1 score with the GFID dataset to apply this technique to extract medical or healthcare information.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.8
• /
• pp.2473-2489
• /
• 2022

Urban development has brought about the increasing saturation of urban traffic demand, and traffic congestion has become the primary problem in transportation. Roads are in a state of waiting in line or even congestion, which seriously affects people's enthusiasm and efficiency of travel. This paper mainly studies the discrete domain path planning method based on the flow data. Taking the traffic flow data based on the highway network structure as the research object, this paper uses the deep learning theory technology to complete the path weight determination process, optimizes the path planning algorithm, realizes the vehicle path planning application for the expressway, and carries on the deployment operation in the highway company. The path topology is constructed to transform the actual road information into abstract space that the machine can understand. An appropriate data structure is used for storage, and a path topology based on the modeling background of expressway is constructed to realize the mutual mapping between the two. Experiments show that the proposed method can further reduce the interpolation error, and the interpolation error in the case of random missing is smaller than that in the other two missing modes. In order to improve the real-time performance of vehicle path planning, the association features are selected, the path weights are calculated comprehensively, and the traditional path planning algorithm structure is optimized. It is of great significance for the sustainable development of cities.

• Korean Journal of Remote Sensing
• /
• v.35 no.6_2
• /
• pp.1037-1052
• /
• 2019

We had developed in preceding study a classification model for the Korean pine and Larch with an accuracy of 98 percent using Hyperion and Sentinel-2 satellite images, texture information, and geometric information as the first step for tree species mapping in the inaccessible North Korea. Considering a share of major tree species in North Korea, the classification model needs to be expanded as it has a large share of Oak(29.5%), Pine (12.7%), Fir (8.2%), and as well as Larch (17.5%) and Korean pine (5.8%). In order to classify 5 major tree species, national forest type map of South Korea was used to build 11,039 training and 2,330 validation data. Sentinel-2 data was used to derive spectral information, and PlanetScope data was used to generate texture information. Geometric information was built from SRTM DEM data. As a machine learning algorithm, Random forest was used. As a result, the overall accuracy of classification was 80% with 0.80 kappa statistics. Based on the training data and the classification model constructed through this study, we will extend the application to Mt. Baekdu and North and South Goseong areas to confirm the applicability of tree species classification on the Korean Peninsula.

• Korean Journal of Breeding Science
• /
• v.43 no.4
• /
• pp.282-287
• /
• 2011

Bacterial pustule (BP) is a leaf disease of soybean that is most common in Korea. Inoculation of 8ra, pathogen strain, to resistant and susceptible cultivars for finding the BP resistance gene (rxp) was much tried but the sequence of the exact gene is not found. This research performed in order to confirm the rxp gene near molecular marker by using the resistant and susceptible cultivars. Soybean BP resistance gene which related to region of near molecular marker could select the resistant cultivar. For the near molecular marker of rxp, reference genomics data available at sequenced Phytozome was used for designing molecular markers. The rxp was mapped between Satt372 and Satt486 on chromosome 17. According to previous study, rxp released in find mapping 7.2 Mbp to 7.3 Mbp on chromosome 17. In this study, we developed 3 random markers near from 6.6 Mbp to 7.3 Mbp on chromosome 17 identified to increase the genetic resolution of the rxp gene region using resistant and susceptible cultivars. Particularly, Rxp17-700 marker was mostly coincided resistance and susceptible genotype to rxp. This result suggests that Rxp17-700 marker will be more tightly linked to rxp gene.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_1
• /
• pp.1367-1377
• /
• 2020

The purpose of this study is to assess the seismic vulnerability of buildings in Gyeongju city starting with the earthquake that occurred in the city on September 12, 2016, and produce a seismic vulnerability map. 11 influence factors related to geotechnical, physical, and structural indicators were selected to assess the seismic vulnerability, and these were applied as independent variables. For a dependent variable, location data of the buildings that were actually damaged in the 9.12 Gyeongju Earthquake was used. The assessment model was constructed based on random forest (RF) as a mechanic study method and support vector machine (SVM), and the training and test dataset were randomly selected with a ratio of 70:30. For accuracy verification, the receiver operating characteristic (ROC) curve was used to select an optimum model, and the accuracy of each model appeared to be 1.000 for RF and 0.998 for SVM, respectively. In addition, the prediction accuracy was shown as 0.947 and 0.926 for RF and SVM, respectively. The prediction values of the entire buildings in Gyeongju were derived on the basis of the RF model, and these were graded and used to produce the seismic vulnerability map. As a result of reviewing the distribution of building classes as an administrative unit, Hwangnam, Wolseong, Seondo, and Naenam turned out to be highly vulnerable regions, and Yangbuk, Gangdong, Yangnam, and Gampo turned out to be relatively safer regions.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.48 no.4
• /
• pp.297-302
• /
• 2003

Genetic linkage maps serve the plant geneticist in a number of ways, from marker assisted selection in plant improvement to map-based cloning in molecular genetic research. Genetic map based upon DNA polymorphism is a powerful tool for the study of qualitative and quantitative traits in crops. The objective of this study was to develop genetic linkage map of soybean using the population derived from the cross of Korean soybean cultivar 'Kwangkyo, and wild accession 'IT182305'. Total 1,000 Operon random primers for RAPD marker, 49 combinations of primer for AFLP marker, and 100 Satt primers for SSR marker were used to screen parental polymorphism. Total 341 markers (242 RAPD, 83 AFLP, and 16 SSR markers) was segregated in 85 $\textrm{F}_2$ population. Forty two markers that shown significantly distorted segregation ratio (1:2:1 for codominant or 3:1 for domimant marker) were not used in mapping procedure. A linkage map was constructed by applying the computer program MAPMAKER/EXP 3.0 to the 299 marker data with LOD 4.0 and maximum distance 50 cM. 176 markers were found to be genetically linked and formed 25 linkage groups. Linkage map spanned 2,292.7 cM across all 25 linkage groups. The average linkage distance between pair of markers among all linkage groups was 13.0 cM. The number of markers per linkage group ranged from 2 to 55. The longest linkage group 3 spanned 967.4 cM with 55 makers. This map requires further saturation with more markers and agronomically important traits will be joined over it.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2010.09a
• /
• pp.790-799
• /
• 2010

The Upper Devonian Grossmont Formation in Alberta, Canada reserves an estimated 50 billion cubic meters of bitumen and possess about 1/6 of the total bitumen resources in northern Alberta. However, unlike the overlying Athabasca oil sands, non conventional bitumen resources has not been developed as yet. The carbonate rocks of Grosmont Formation have been subject to various stages of diagenesis, including dolomatization and karstification with a strong effect on the distribution of porosity and permeability, which resulted in highly heterogeneous reservoirs. An extensive fracture logging and mapping was performed on total of six boreholes located in the study area to explore the characteristics of fracture geometry system and the subsurface structures of carbonates reservoir that holds bitumen. Fractal dimension was used as a measure of the statistical homogeneity of the fractured rock masses. The applicability of random Cantor dust, Dc, as a fractal parameter was examined systematically. The statistical homogeneity of fractured carbonates rock masses was investigated in the study area. The structural domains of the rock masses were delineated depthwise according to estimated Dc. The major fracture orientation was dominated by horizontal beddings having dip of $0-20^{\circ}$. Also, fractures having high dip angles existed with relatively low frequency. Three dimensional fracture network modeling for each structural domain has been performed based on fracture orientation and intensity, and some representative conceptual models for carbonates reservoir in the study area has been proposed. The developed subsurface conceptual models will be used to capture the geomechanical characteristics of the carbonates reservoir.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.12
• /
• pp.55-62
• /
• 1998

Matching two images is an essential step for many computer vision applications. A new approach to the scale and rotation invariant scene matching, using linear features, is presented. Scene or model images are described by a set of linear features approximating edge information, which can be obtained by the conventional edge detection, thinning, and piecewise linear approximation. A set of candidate parameters are hypothesized by mapping the angular difference and a new distance measure to the Hough space and by detecting maximally consistent points. These hypotheses are verified by a fast linear feature matching algorithm composed of a single-step relaxation and a Hough technique. The proposed method is shown to be much faster than the conventional one where the relaxation process is repeated until convergence, while providing matching performance robust to the random alteration of the linear features, without a priori information on the geometrical transformation parameters.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.23 no.12
• /
• pp.1035-1044
• /
• 2013

Because of the high specific stiffness and strength inherent in the sandwich structure composed of facesheet that resists in-plane loads and a core that resists out-of-plane loads, it is often used for large and light-weighted structures. However, inevitably the increased flexibility allows greater deformation-based disturbances in the structures. Thus, it is necessary to analyze the structural safety. To obtain more accurate analytical results, the input disturbances must more closely simulate real load conditions; to improve accuracy, non-linear elements such as gust effects were considered. In addition, the structural safety was analyzed for the iso-grid sandwich panel structure using fluid-structure interactions. For a more realistic simulation, flow velocity fields, which consider the effects of irregular gust fluctuation, were generated and the coupled field was analyzed by mapping the pressure and displacement.