• The Journal of the Acoustical Society of Korea
• /
• v.28 no.2
• /
• pp.135-140
• /
• 2009

In this paper, we synthesized active sonar target signals based on highlights model, and then carried out target classification using the synthesized signals. If the target aspect angle is changed, the different signals are synthesized. To know the result, two different experiments are done. First, The classification results with respect to each aspect angle are shown. Second, the results in two group in aspect angle are acquired. Time domain feature extraction is done using matched filter and envelope detection. It shows the pattern of each highlights. Artificial neural networks and multi-class SVM are used for classifying target signals.

• Korean Journal of Cognitive Science
• /
• v.23 no.3
• /
• pp.295-322
• /
• 2012

In this paper, we cluster similar word senses applying vector space model and HAL (Hyperspace Analog to Language). HAL measures corelation among words through a certain size of context (Lund and Burgess 1996). The similarity measurement between a word pair is cosine similarity based on the vector space model, which reduces distortion of space between high frequency words and low frequency words (Salton et al. 1975, Widdows 2004). We use PCA (Principal Component Analysis) and SVD (Singular Value Decomposition) to reduce a large amount of dimensions caused by similarity matrix. For sense similarity clustering, we adopt supervised and non-supervised learning methods. For non-supervised method, we use clustering. For supervised method, we use SVM (Support Vector Machine), Naive Bayes Classifier, and Maximum Entropy Method.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.3
• /
• pp.513-520
• /
• 2020

Recently, the development of a vision inspection system using machine learning has become more active. This study seeks to develop a defect inspection model using machine learning. Defect detection problems for images correspond to classification problems, which are the method of supervised learning in machine learning. In this study, defect detection models are developed based on algorithms that automatically extract features and algorithms that do not extract features. One-dimensional CNN and two-dimensional CNN are used as algorithms for automatic extraction of features, and MLP and SVM are used as algorithms for non-extracting features. A defect detection model is developed based on four models and their accuracy and AUC compare based on AUC. Although image classification is common in the development of models using CNN, high accuracy and AUC is achieved when developing SVM models by converting pixels from images into RGB values in this study.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.9
• /
• pp.615-620
• /
• 2013

With the development of smartphones, the number of applications for smartphone increases sharply. As a result, users need to try several times to find their favorite apps. In order to solve this problem, we propose a recommendation system to provide an appropriate app list based on the user's log information including time stamp, location, application list, and so on. The proposed approach learns three recommendation models including Naive-Bayesian model, SVM model, and Most-Frequent Usage model using temporal and spatial attributes. In order to figure out the best model, we compared the performance of these models with variant features, and suggest an hybrid method to improve the performance of single models.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.1
• /
• pp.56-62
• /
• 2021

High forecast accuracy is required as social issues on particulate matter increase. Therefore, many attempts are being made using machine learning to increase the accuracy of particulate matter prediction. However, due to problems with the distribution of imbalance in the concentration and various characteristics of particulate matter, the learning of prediction models is not well done. In this paper, to solve these problems, a binary classification model was proposed to predict the concentration of particulate matter needed for prediction by dividing it into two classes based on the value of 80㎍/㎥. Four classification algorithms were utilized for the binary classification of PM10. Classification algorithms used logistic regression, decision tree, SVM, and MLP. As a result of performance evaluation through confusion matrix, the MLP model showed the highest binary classification performance with 89.98% accuracy among the four models.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.333-340
• /
• 2023

Efficient prediction of corporate bankruptcy is an important part of making appropriate lending decisions for financial institutions and reducing loan default rates. In many studies, classification models using artificial intelligence technology have been used. In the financial industry, even if the performance of the new predictive models is excellent, it should be accompanied by an intuitive explanation of the basis on which the result was determined. Recently, the US, EU, and South Korea have commonly presented the right to request explanations of algorithms, so transparency in the use of AI in the financial sector must be secured. In this paper, an artificial intelligence-based interpretable classification prediction model was proposed using corporate bankruptcy data that was open to the outside world. First, data preprocessing, 5-fold cross-validation, etc. were performed, and classification performance was compared through optimization of 10 supervised learning classification models such as logistic regression, SVM, XGBoost, and LightGBM. As a result, LightGBM was confirmed as the best performance model, and SHAP, an explainable artificial intelligence technique, was applied to provide a post-explanation of the bankruptcy prediction process.

• Journal of Digital Convergence
• /
• v.16 no.5
• /
• pp.399-406
• /
• 2018

Much research has been done using the KDDCup99 data set to study intrusion detection using artificial intelligence. Previous studies have shown that the performance of the SMO (SVM) algorithm is superior. However, intrusion detection studies of new intrusion types not used in training are insufficient. In this paper, a model was created using the instances of weka's SMO and KDDCup99 training data set, kddcup.data.gz. We tested existing instances(292,300) of the corrected.gz file and new intrusions(18,729). In general, intrusion labels not used in training are not tested, so new intrusion labels were changed to normal. Of the 18,729 new intrusions, 1,827 were classified as intrusions. 1,827 instances classified as new intrusions are buffer_overflow. Three, neptune. 392, portsweep. 164, ipsweep. 9, back. 511, imap. 1, satan. Dogs, 645, nmap. 102.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.8
• /
• pp.958-964
• /
• 2016

In this paper, we propose an i-vector based language recognition system to identify the spoken language of the speaker, which uses multiple discriminative deep neural network (DNN) models analogous to the multi-class support vector machine (SVM) classification system. The proposed model was trained and tested using the i-vectors included in the NIST 2015 i-vector Machine Learning Challenge database, and shown to outperform the conventional language recognition methods such as cosine distance, SVM and softmax NN classifier in open-set experiments.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.28 no.1
• /
• pp.33-41
• /
• 2017

This paper suggests a hand gesture recognition technology to control smart devices using multiple Doppler radars and a support vector machine(SVM), which is one of the machine learning algorithms. Whereas single Doppler radar can recognize only simple hand gestures, multiple Doppler radar can recognize various and complex hand gestures by using various Doppler patterns as a function of time and each device. In addition, machine learning technology can enhance recognition accuracy. In order to determine the feasibility of the suggested technology, we implemented a test-bed using two Doppler radars, NI DAQ USB-6008, and MATLAB. Using this test-bed, we can successfully classify four hand gestures, which are Push, Pull, Right Slide, and Left Slide. Applying SVM machine learning algorithm, it was confirmed the high accuracy of the hand gesture recognition.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.6
• /
• pp.414-423
• /
• 2009

Folksonomy, which is collaborative classification created by freely selected keywords, is one of the driving factors of the web 2.0. Folksonomy has advantage of being built at low cost while its weakness is lack of hierarchical or systematic structure in comparison with taxonomy. If we can build classifier that is able to classify web resources from collective intelligence in taxonomy, we can build taxonomy at low cost. In this paper, targeting folksonomy in Slashdot.org, we define a general model and show that collective intelligence, which can build classifier, really exists in folksonomy using a stability value. We suggest method that builds SVM classifier using stability that is result from this collective intelligence. The experiment shows that our proposed method managed to build taxonomy from folksonomy with high accuracy.