• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.3
• /
• pp.329-337
• /
• 2017

This paper proposes a search method that explores parameters C and σ values of support vector machines (SVM) to improve performance while maintaining search accuracy. A traditional grid search method requires tremendous computational times because it searches all available combinations of C and σ values to find optimal combinations which provide the best performance of SVM. To address this issue, this paper proposes a deep search method that reduces computational time. In the first stage, it divides C-σ- accurate metrics into four regions, searches a median value of each region, and then selects a point of the highest accurate value as a start point. In the second stage, the selected start points are re-divided into four regions, and then the highest accurate point is assigned as a new search point. In the third stage, after eight points near the search point. are explored and the highest accurate value is assigned as a new search point, corresponding points are divided into four parts and it calculates an accurate value. In the last stage, it is continued until an accurate metric value is the highest compared to the neighborhood point values. If it is not satisfied, it is repeated from the second stage with the input level value. Experimental results using normal and defect bearings show that the proposed deep search algorithm outperforms the conventional algorithms in terms of performance and search time.

• Journal of Korea Society of Industrial Information Systems
• /
• v.9 no.2
• /
• pp.32-43
• /
• 2004

In this paper, a system which can effectively recognize the plate image extracted from camera set on a moving car is proposed. To extract car licence plate from moving vehicles, multiple candidates are maintained based on the strong vertical edges which are found in the region of car licence plate. A candidate region is selected among them based on the ratio of background and characters. We also make a comparative study of recognition performance between support vector machines and modular neural networks. The experimental results lead us to the conclusion that the former is superior to the latter. For a better recognition rate, a simple method combining the support vector machine with modular neural network where the output of the latter is used as the input of the former is suggested and evaluated. As we expected, the hybrid one shows the best result among those three methods we have mentioned.

• IEIE Transactions on Smart Processing and Computing
• /
• v.2 no.5
• /
• pp.277-281
• /
• 2013

Modern speaker verification systems based on support vector machines (SVMs) use Gaussian mixture model (GMM) supervectors as their input feature vectors, and the maximum a posteriori (MAP) adaptation is a conventional method for generating speaker-dependent GMMs by adapting a universal background model (UBM). MAP adaptation requires the appropriate amount of input utterance due to the number of model parameters to be estimated. On the other hand, with limited utterances, unreliable MAP adaptation can be performed, which causes adaptation noise even though the Bayesian priors used in the MAP adaptation smooth the movements between the UBM and speaker dependent GMMs. This paper proposes a sparse MAP adaptation method, which is known to perform well in the automatic speech recognition area. By introducing sparse MAP adaptation to the GMM-SVM-based speaker verification system, the adaptation noise can be mitigated effectively. The proposed method utilizes the L0 norm as a regularizer to induce sparsity. The experimental results on the TIMIT database showed that the sparse MAP-based GMM-SVM speaker verification system yields a 42.6% relative reduction in the equal error rate with few additional computations.

• Journal of Multimedia Information System
• /
• v.3 no.2
• /
• pp.35-42
• /
• 2016

Electrocardiogram (ECG) signal gives a clear indication whether the heart is at a healthy status or not as the early notification of a cardiac problem in the heart could save the patient's life. Several methods were launched to clarify how to diagnose the abnormality over the ECG signal waves. However, some of them face the problem of lack of accuracy at diagnosis phase of their work. In this research, we present an accurate and successive method for the diagnosis of abnormality through Discrete Wavelet Transform (DWT), QRS complex detection and Support Vector Machines (SVM) classification with overall accuracy rate 95.26%. DWT Refers to sampling any kind of discrete wavelet transform, while SVM is known as a model with related learning algorithm, which is based on supervised learning that perform regression analysis and classification over the data sample. We have tested the ECG signals for 10 patients from different file formats collected from PhysioNet database to observe accuracy level for each patient who needs ECG data to be processed. The results will be presented, in terms of accuracy that ranged from 92.1% to 97.6% and diagnosis status that is classified as either normal or abnormal factors.

• Journal of information and communication convergence engineering
• /
• v.20 no.4
• /
• pp.295-302
• /
• 2022

This paper contains the development of a smart power device designed to collect load power data from industrial manufacturing machines, predict future variations in load power data, and detect abnormal data in advance by applying a machine learning-based prediction algorithm. The proposed load power data prediction model is implemented using a Long Short-Term Memory (LSTM) algorithm with high accuracy and relatively low complexity. The Flask and REST API are used to provide prediction results to users in a graphical interface. In addition, we present the results of experiments conducted to evaluate the performance of the proposed approach, which show that our model exhibited the highest accuracy compared with Multilayer Perceptron (MLP), Random Forest (RF), and Support Vector Machine (SVM) models. Moreover, we expect our method's accuracy could be improved by further optimizing the hyperparameter values and training the model for a longer period of time using a larger amount of data.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.22 no.1
• /
• pp.1-12
• /
• 2020

As one of the essential resources in the agricultural process, soil moisture has been carefully managed by predicting future changes and deficits. In recent years, statistics and machine learning based approach to predict soil moisture has been preferred in academia for its generalizability and ease of use in the field. However, little is known that machine learning based soil moisture prediction is applicable in the situation of South Korea. In this sense, this paper aims to examine 1) whether publicly available weather data generated in South Korea has sufficient quality to predict soil moisture, 2) which machine learning algorithm would perform best in the situation of South Korea, and 3) whether a single machine learning model could be generally applicable in various regions. We used various machine learning methods such as Support Vector Machines (SVM), Random Forest (RF), Extremely Randomized Trees (ET), Gradient Boosting Machines (GBM), and Deep Feedforward Network (DFN) to predict future soil moisture in Andong, Boseong, Cheolwon, Suncheon region with open source weather data. As a result, GBM model showed the lowest prediction error in every data set we used (R squared: 0.96, RMSE: 1.8). Furthermore, GBM showed the lowest variance of prediction error between regions which indicates it has the highest generalizability.

• Journal of KIISE:Software and Applications
• /
• v.34 no.1
• /
• pp.30-39
• /
• 2007

The existing content-based spam mail filtering algorithms have difficulties in filtering spam mails when e-mails contain images but little text. In this thesis we propose an efficient spam mail classification algorithm that utilizes the link structure of e-mails. We compute the number of hyperlinks in an e-mail and the in-link frequencies of the web pages hyperlinked in the e-mail. Using these two features we classify spam mails and legitimate mails based on the decision tree trained for spam mail classification. We also suggest a hybrid system combining three different algorithms by majority voting: the link structure analysis algorithm, a modified link structure analysis algorithm, in which only the host part of the hyperlinked pages of an e-mail is used for link structure analysis, and the content-based method using SVM (support vector machines). The experimental results show that the link structure analysis algorithm slightly outperforms the existing content-based method with the accuracy of 94.8%. Moreover, the hybrid system achieves the accuracy of 97.0%, which is a significant performance improvement over the existing method.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2003.10a
• /
• pp.133-138
• /
• 2003

The prediction of protein secondary structure has been an important bioinformatics tool that is an essential component of the template-based protein tertiary structure prediction process. It has been known that the predicted secondary structure information improves both the fold recognition performance and the alignment accuracy. In this paper, we describe several novel ideas that may improve the prediction accuracy. The main idea is motivated by an observation that the protein's structural information, especially when it is combined with the evolutionary information, significantly improves the accuracy of the predicted tertiary structure. From the non-redundant set of protein structures, we derive the 'potential' parameters for the protein secondary structure prediction that contains the structural information of proteins, by following the procedure similar to the way to derive the directional information table of GOR method. Those potential parameters are combined with the frequency matrices obtained by running PSI-BLAST to construct the feature vectors that are used to train the support vector machines (SVM) to build the secondary structure classifiers. Moreover, the problem of huge model file size, which is one of the known shortcomings of SVM, is partially overcome by reducing the size of training data by filtering out the redundancy not only at the protein level but also at the feature vector level. A preliminary result measured by the average three-state prediction accuracy is encouraging.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.3
• /
• pp.297-305
• /
• 2008

Recently, kernel methods have attracted great interests in the areas of pattern classification, function approximation, and anomaly detection. The role of the kernel is particularly important in the methods such as SVM(support vector machine) and KPCA(kernel principal component analysis), for it can generalize the conventional linear machines to be capable of efficiently handling nonlinearities. This paper considers the problem of combining radar and rain gauge observations utilizing the regression approach based on the kernel-based gaussian process and support vector learning. The data-assimilation results of the considered methods are reported for the radar and rain gauge observations collected over the region covering parts of Gangwon, Kyungbuk, and Chungbuk provinces of Korea, along with performance comparison.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.2
• /
• pp.113-130
• /
• 2004

Most multimedia data contain text to emphasize the meaning of the data, to present additional explanations about the situation, or to translate different languages. But, the left makes it difficult to reuse the images, and distorts not only the original images but also their meanings. Accordingly, this paper proposes a support vector machines (SVMs) and spatiotemporal restoration-based approach for automatic text detection and removal in video sequences. Given two consecutive frames, first, text regions in the current frame are detected by an SVM-based texture classifier Second, two stages are performed for the restoration of the regions occluded by the detected text regions: temporal restoration in consecutive frames and spatial restoration in the current frame. Utilizing text motion and background difference, an input video sequence is classified and a different temporal restoration scheme is applied to the sequence. Such a combination of temporal restoration and spatial restoration shows great potential for automatic detection and removal of objects of interest in various kinds of video sequences, and is applicable to many applications such as translation of captions and replacement of indirect advertisements in videos.