• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.11
• /
• pp.75-83
• /
• 1999

We propose a PfSGA(parameter-free species genetic algorithm) to learn the topological structure of MLP classifiers being adequate to given applications. The PfSGA is a combinational method of SGA(species genetic algorithm) and PfGA(parameter-free genetic algorithm). In SGA, we divide the total search space into several subspaces(species) according to the number of hidden units, and reduce the unnecessary search by eliminating the low promising species from the evolutionary process. However the performances of SGA classifiers are readily affected by the values of parameters such as mutation ratio and crossover ratio. In this paper, therefore, we combine SGA with PfGA, for which it is not necessary to determine the learning parameters. Experimental results on benchmark data and sign language words show that PfSGA can reduce the learning time of SGA and is not affected by the selection parameter values on structural learning. The results also show that PfSGA is more efficient than the exisiting methods in the aspect of misclassification ratio, learning rate, and complexity of MLP structure.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.9
• /
• pp.117-123
• /
• 1996

In this paper, we present a new learning method for the fuzzy ARTMAP which is effective for the noisy input patterns. Conventional fuzzy ARTMAP employs only fuzzy AND operation between input vector and weight vector in learning both top-down and bottom-up weight vectors. This fuzzy AND operation causes excessive update of the weight vector in the noisy input environment. As a result, the number of spurious categories are increased and the recognition ratio is reduced. To solve these problems, we propose a new method in updating the weight vectors: the top-down weight vectors of the fuzzy ART system are updated using weighted average of the input vector and the weight vector itself, and the bottom-up weight vectors are updated using fuzzy AND operation between the updated top-down weitht vector and bottom-up weight vector itself. The weighted average prevents the excessive update of the weight vectors and the fuzzy AND operation renders the learning fast and stble. Simulation results show that the proposed method reduces the generation of spurious categories and increases the recognition ratio in the noisy input environment.

• International Journal of High-Rise Buildings
• /
• v.9 no.4
• /
• pp.335-342
• /
• 2020

This article comes up with a new method which is based on the visual characteristic of the objects and machine learning technology to achieve semi-automated recognition of the personnel, machine & materials of the construction sites. Balancing the real-time performance and accuracy, using Faster RCNN (Faster Region-based Convolutional Neural Networks) with transfer learning method appears to be a rational choice. After fine-tuning an ImageNet pre-trained Faster RCNN and testing with it, the result shows that the precision ratio (mAP) has so far reached 67.62%, while the recall ratio (AR) has reached 56.23%. In other word, this recognizing method has achieved rational performance. Further inference with the video of the construction of Huoshenshan Hospital also indicates preliminary success.

• Computers and Concrete
• /
• v.30 no.1
• /
• pp.33-42
• /
• 2022

Experimentally predicting the compressive strength (CS) of concrete (for a mix design) is a time-consuming and laborious process. The present study aims to propose surrogate models based on Support Vector Machine (SVM) and Gaussian Process Regression (GPR) machine learning techniques, which can predict the CS of concrete containing nano-silica. Content of cement, aggregates, nano-silica and its fineness, water-binder ratio, and the days at which strength has to be predicted are the input variables. The efficiency of the models is compared in terms of Correlation Coefficient (CC), Root Mean Square Error (RMSE), Variance Account For (VAF), Nash-Sutcliffe Efficiency (NSE), and RMSE to observation's standard deviation ratio (RSR). It has been observed that the SVM outperforms GPR in predicting the CS of the concrete containing nano-silica.

• Communications for Statistical Applications and Methods
• /
• v.31 no.3
• /
• pp.279-289
• /
• 2024

Familial searching is a useful technique in a forensic investigation. Using genetic information, it is possible to identify individuals, determine familial relationships, and obtain racial/ethnic information. The total number of shared alleles (TNSA) and likelihood ratio (LR) methods have traditionally been used, and novel data-mining classification methods have recently been applied here as well. However, it is difficult to apply these methods to identify familial relationships above the third degree (e.g., uncle-nephew and first cousins). Therefore, we propose to apply a stacking ensemble machine learning algorithm to improve the accuracy of familial relationship identification. Using real data analysis, we obtain superior relationship identification results when applying meta-classifiers with a stacking algorithm rather than applying traditional TNSA or LR methods and data mining techniques.

• The Mathematical Education
• /
• v.51 no.4
• /
• pp.395-413
• /
• 2012

National Assessment of Educational Achievement(NAEA) is important standard reference to become the basic data for confirming the effect of the curriculum administrated and the educational policies put in force presently and preparing the new curriculum and educational policies. In this paper, we looked into the mean and standard deviation of the calibrated score of whole group and male/female students, the correct answer ratio of each performance level and the correct answer ratio of each content domain, etc. in the results of NAEA at 6th elementary school. The analytic objects are 2010 and 2011 NAEA that are changed into complete enumeration survey and the standard reference prepared on the basis of the new calibrated score is applied to. And we analysed and compared correct answer ratio of the each content domain and each item to conform the difference between male and female students. On the basis of the these informations, we investigated that here is what kind of characteristics and trends to the whole group and what kind of suggestions to the teaching-learning. And we were going to provide the information of the needs to understand which content of mathematics is needed and which thinking methods are needed.

• Convergence Security Journal
• /
• v.20 no.3
• /
• pp.53-60
• /
• 2020

At the present stage of the fourth industrial revolution, machine learning and artificial intelligence technologies are rapidly developing, and there is a movement to apply machine learning technology in the security field. Malicious code, including new and transformed, generates an average of 390,000 a day worldwide. Statistics show that security companies ignore or miss 31 percent of alarms. As many malicious codes are generated, it is becoming difficult for humans to detect all malicious codes. As a result, research on the detection of malware and network intrusion events through machine learning is being actively conducted in academia and industry. In international conferences and journals, research on security data analysis using deep learning, a field of machine learning, is presented. have. However, these papers focus on detection accuracy and modify several parameters to improve detection accuracy but do not consider the ratio of dataset. Therefore, this paper aims to reduce the cost and resources of many machine learning research by finding the ratio of dataset that can derive the highest detection accuracy in CNN Mobile net-based malware detection model.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1007-1014
• /
• 2022

Compact Advanced Satellite 500 (CAS500) can be used for various purposes, including vegetation, forestry, and agriculture fields. It is expected that it will be possible to acquire satellite images of various areas quickly. In order to use satellite images acquired through CAS500 in the agricultural field, it is necessary to develop a satellite image-based extraction technique for crop-cultivated areas.In particular, as research in the field of deep learning has become active in recent years, research on developing a deep learning model for extracting crop cultivation areas and generating training data is necessary. This manuscript classified the onion and garlic cultivation areas in Hapcheon-gun using PlanetScope satellite images and farm maps. In particular, for effective model learning, the model performance was analyzed according to the proportion of crop-cultivated areas. For the deep learning model used in the experiment, Fully Convolutional Densely Connected Convolutional Network (FC-DenseNet) was reconstructed to fit the purpose of crop cultivation area classification and utilized. As a result of the experiment, the ratio of crop cultivation areas in the training data affected the performance of the deep learning model.

• Journal of the Korean Society of Radiology
• /
• v.17 no.5
• /
• pp.709-715
• /
• 2023

In this study, the performance evaluation of image quality for noise reduction was implemented using the U-net deep learning architecture in computed tomography (CT) images. In order to generate input data, the Gaussian noise was applied to ground truth (GT) data, and datasets were consisted of 8:1:1 ratio of train, validation, and test sets among 1300 CT images. The Adagrad, Adam, and AdamW were used as optimizer function, and 10, 50 and 100 times for number of epochs were applied. In addition, learning rates of 0.01, 0.001, and 0.0001 were applied using the U-net deep learning model to compare the output image quality. To analyze the quantitative values, the peak signal to noise ratio (PSNR) and coefficient of variation (COV) were calculated. Based on the results, deep learning model was useful for noise reduction. We suggested that optimized hyper parameters for noise reduction in CT images were AdamW optimizer function, 100 times number of epochs and 0.0001 learning rates.

• Journal of Information Processing Systems
• /
• v.18 no.6
• /
• pp.803-812
• /
• 2022

With the increasing number of mobile device users worldwide, utilizing mobile edge computing (MEC) devices close to users for content caching can reduce transmission latency than receiving content from a server or cloud. However, because MEC has limited storage capacity, it is necessary to determine the content types and sizes to be cached. In this study, we investigate a caching strategy that increases the hit ratio from small base stations (SBSs) for mobile users in a heterogeneous network consisting of one macro base station (MBS) and multiple SBSs. If there are several SBSs that users can access, the hit ratio can be improved by reducing duplicate content and increasing the diversity of content in SBSs. We propose a Deep Q-Network (DQN)-based caching strategy that considers time-varying content popularity and content redundancy in multiple SBSs. Content is stored in the SBS in a divided form using maximum distance separable (MDS) codes to enhance the diversity of the content. Experiments in various environments show that the proposed caching strategy outperforms the other methods in terms of hit ratio.