• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.6
• /
• pp.605-610
• /
• 2020

Software Defined Networking (SDN) is setting the standard for the management of networks due to its scalability, flexibility and functionality to program the network. The Distributed Denial of Service (DDoS) attack is most widely used to attack the SDN controller to bring down the network. Different methodologies have been utilized to detect DDoS attack previously. In this paper, first the dataset is obtained by Kaggle with 84 features, and then according to the rank, the 20 highest rank features are selected using Permutation Importance Algorithm. Then, the datasets are trained and tested with Convolution Neural Network (CNN) classifier model by utilizing deep learning techniques. Our proposed solution has achieved the best results, which will allow the critical systems which need more security to adopt and take full advantage of the SDN paradigm without compromising their security.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.39-46
• /
• 2021

This study is about a method of extracting a summary from a news article in consideration of the importance of each sentence constituting the article. We propose a method of calculating sentence importance by extracting the probabilities of topic sentence, similarity with article title and other sentences, and sentence position as characteristics that affect sentence importance. At this time, a hypothesis is established that the Topic Sentence will have a characteristic distinct from the general sentence, and a deep learning-based classification model is trained to obtain a topic sentence probability value for the input sentence. Also, using the pre-learned ELMo language model, the similarity between sentences is calculated based on the sentence vector value reflecting the context information and extracted as sentence characteristics. The topic sentence classification performance of the LSTM and BERT models was 93% accurate, 96.22% recall, and 89.5% precision, resulting in high analysis results. As a result of calculating the importance of each sentence by combining the extracted sentence characteristics, it was confirmed that the performance of extracting the topic sentence was improved by about 10% compared to the existing TextRank algorithm.

• Geomechanics and Engineering
• /
• v.31 no.2
• /
• pp.129-147
• /
• 2022

The properties of soil are naturally highly variable and thus, to ensure proper safety and reliability, we need to test a large number of samples across the length and depth. In pile foundations, conducting field tests are highly expensive and the traditional empirical relations too have been proven to be poor in performance. The study proposes a state-of-art Particle Swarm Optimization (PSO) hybridized Artificial Neural Network (ANN), Extreme Learning Machine (ELM) and Adaptive Neuro Fuzzy Inference System (ANFIS); and comparative analysis of metaheuristic models (ANN-PSO, ELM-PSO, ANFIS-PSO) for prediction of bearing capacity of pile foundation trained and tested on dataset of nearly 300 dynamic pile tests from the literature. A novel ensemble model of three hybrid models is constructed to combine and enhance the predictions of the individual models effectively. The authenticity of the dataset is confirmed using descriptive statistics, correlation matrix and sensitivity analysis. Ram weight and diameter of pile are found to be most influential input parameter. The comparative analysis reveals that ANFIS-PSO is the best performing model in testing phase (R² = 0.85, RMSE = 0.01) while ELM-PSO performs best in training phase (R² = 0.88, RMSE = 0.08); while the ensemble provided overall best performance based on the rank score. The performance of ANN-PSO is least satisfactory compared to the other two models. The findings were confirmed using Taylor diagram, error matrix and uncertainty analysis. Based on the results ELM-PSO and ANFIS-PSO is proposed to be used for the prediction of bearing capacity of piles and ensemble learning method of joining the outputs of individual models should be encouraged. The study possesses the potential to assist geotechnical engineers in the design phase of civil engineering projects.

• Journal of Korea Water Resources Association
• /
• v.49 no.5
• /
• pp.361-372
• /
• 2016

Reliable long-term dam inflow prediction is necessary for efficient multi-purpose dam operation in changing climate. Since 2000s the teleconnection between global climate indices (e.g., ENSO) and local hydroclimate regimes have been widely recognized throughout the world. To date many hydrologists focus on predicting future hydrologic conditions using lag teleconnection between streamflow and climate indices. This study investigated the utility of teleconneciton for predicting dam inflow with 1-month lead time at Andong dam basin. To this end 40 global climate indices from NOAA were employed to identify potential predictors of dam inflow, areal averaged precipitation, temperature of Andong dam basin. This study compared three different approaches; 1) dam inflow prediction using SWAT model based on teleconneciton-based precipitation and temperature forecast (SWAT-Forecasted), 2) dam inflow prediction using teleconneciton between dam inflow and climate indices (CIR-Forecasted), and 3) dam inflow prediction based on the rank of current observation in the historical dam inflow (Rank-Observed). Our results demonstrated that CIR-Forecasted showed better predictability than the other approaches, except in December. This is because uncertainties attributed to temporal downscaling from monthly to daily for precipitation and temperature forecasts and hydrologic modeling using SWAT can be ignored from dam inflow forecast through CIR-Forecasted approach. This study indicates that 1-month lead dam inflow forecast based on teleconneciton could provide useful information on Andong dam operation.

• Journal of Broadcast Engineering
• /
• v.26 no.2
• /
• pp.125-131
• /
• 2021

In recent years, Convolutional Neural Networks (CNNs) have achieved outstanding performance in the fields of computer vision such as image classification, object detection, visual quality enhancement, etc. However, as huge amount of computation and memory are required in CNN models, there is a limitation in the application of CNN to low-power environments such as mobile or IoT devices. Therefore, the need for neural network compression to reduce the model size while keeping the task performance as much as possible has been emerging. In this paper, we propose a method to compress CNN models by combining matrix decomposition methods of LR (Low-Rank) approximation and CP (Canonical Polyadic) decomposition. Unlike conventional methods that apply one matrix decomposition method to CNN models, we selectively apply two decomposition methods depending on the layer types of CNN to enhance the compression performance. To evaluate the performance of the proposed method, we use the models for image classification such as VGG-16, RestNet50 and MobileNetV2 models. The experimental results show that the proposed method gives improved classification performance at the same range of 1.5 to 12.1 times compression ratio than the existing method that applies only the LR approximation.

• The Korean Journal of Applied Statistics
• /
• v.27 no.4
• /
• pp.553-560
• /
• 2014

This paper deals with estimable functions of parameters of less than full rank linear model. In general, the parameters of an overspecified model are not uniquely determined by least squares solutions. It discusses how to formulate linear estimable functions as functions of parameters in the model and shows how to use projection matrices to check out whether a parameter or function of the pamameters is estimable. It also presents a method to form a basis set of estimable functions using linearly independent characteristic vectors generating the row space of the model matrix.

• English Language & Literature Teaching
• /
• v.16 no.4
• /
• pp.153-184
• /
• 2010

On the bases of the 5 principles and the 4 criteria for designing and developing of the listening and the reading test of National English Ability Test (NEAT), this study presents Item-Types Decision-Making Model as a blueprint for designing and constructing the two tests. It sets up the criteria for validating item types, designs a modular type of test specifications, constructs an item-types bank, and specifies a complementary type of test specifications of the two tests. To gather all these threads up, it constructs Item-Types Decision-Making Model which consists of such components as the item-type pool, the validity criteria and the procedures of testing item types, the item-types bank, the modular and the complementary type test specification. Thus, it shows how the Model works in developing and constructing the two level-differentiated listening and reading tests (the 2nd and the 3rd rank) of NEAT. Finally, it discusses some implications and applications of the Model to the two level-differentiated tests (the A and the B type) of 2014 CSAT (College Scholastic Ability Test) systems, National Assessment of Educational Achievement (NAEA), and classroom testing. In conclusion, Item-Types Decision-Making Model functions as a testing template in an item development system and as a matrix in an item-types bank system.

• Journal of the Korea Institute of Building Construction
• /
• v.13 no.1
• /
• pp.66-74
• /
• 2013

In the early stages of a construction project, the most important thing is to predict construction costs in a rational way. For this reason, many studies have been performed on the estimation of construction costs for apartment housing and office buildings at early stage using artificial intelligence, statistics, and the like. In this study, cost data held by a provincial Office of Education on elementary schools constructed from 2004 to 2007 were used to compare the multiple regression model with an artificial neural network model. A total of 96 historical data were classified into 76 historical data for constructing models and 20 historical data for comparing the constructed regression model with the artificial neural network model. The results of an analysis of predicted construction costs were that the error rate of the artificial neural network model is lower than that of the multiple regression model.

• Journal of the Korean Home Economics Association
• /
• v.39 no.12
• /
• pp.51-63
• /
• 2001

With the development of information technology, more and more internet sites are available to consumers. Increasing on the interests of diet and health in modem society, there are numerous internet sites dealing with food, nutrition and health. Considering the importance and expected roles of internet sites in information dissemination in the future world, it is important to put more efforts to encourage internet sites with more accurate an useful information. Up to present, not much work has been done on quality analysis and evaluation of the internet information. This study aimed to develop a model to evaluate and rank the internet information according to its quality so that consumers can be guided toward correct information source. Three models were adapted from the literature for pilot study to develop a model suitable for evaluation of contents of sites related to food and nutrition information. From the pilot study, a evaluation model was developed with criteria more relevant to Korean internet site by expert panel. Evaluation criteria of the model is authority, accuracy, objectivity, coverage, and user-friendliness. For the objective and systematic evaluation, scores were assigned totaling maximum 100 point to each evaluation criteria factors. The model developed in this study could be used as one for other internet sites in area other than food and nutrition.

• Journal of Animal Science and Technology
• /
• v.50 no.5
• /
• pp.601-612
• /
• 2008

This study was conducted to figure out how the shape of Hanwoo changes over time, examine the rank correlations between the carcass traits which are the selection traits and parameters of growth curve, and determine the correlation between body shape and carcass. Body weight, body measurements and carcass traits were measured from 161 castrated Hanwoo, and 12 growth traits and 5 carcass traits were investigated in total. The logistic model(Nelder, 1961) used for the estimation of growth curve parameters and growth characteristics at inflection point were calculated by these growth curve parameters. The value of this parameter was greatest for pinbone width, which suggests that it is an early ripening trait, while it was lowest for chest girth, suggesting it to be a late ripening trait. The rank correlations of chest depth, chest width, and hip width with backfat thickness steadily increased from 6 to 24 months, while the rank correlations of other traits decreased after 18 months until 24 months of age. Only phenotypic records were analyzed in this study, but for examine the genetic changes over growth phase in Hanwoo, if another additional genetic analysis like as estimation of genetic parameters should achieve, body measurements may be useful traits in proven bull selection.