• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.10a
• /
• pp.208-209
• /
• 2011

In this paper, we introduce a Naive Bayes learning algorithm for learning and reasoning in Map-Reduce model based environment. For this purpose, we use Apache Mahout to execute Distributed Naive Bayes on University of California, Irvine (UCI) benchmark data sets. From the experimental results, we see that Apache Mahout' s Distributed Naive Bayes algorithm is comparable to WEKA' s Naive Bayes algorithm in terms of performance. These results indicates that in the future Big Data environment, Map-Reduce model based systems such as Apache Mahout can be promising for machine learning usage.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2017.10a
• /
• pp.166-169
• /
• 2017

Currently, studies using Deep Learning are actively carried out showing good results in many fields. A template matching method is mainly used to recognize parts mounted on PCB(Printed Circuit Board). However, template matching should have multiple templates depending on the shape, orientation and brightness. And it takes long time to perform matching because it searches for the entire image. And there is also a disadvantage that the recognition rate is considerably low. In this paper, we use the Faster-RCNN method for recognizing PCB components as machine learning for classifying several objects in one image. This method performs better than the template matching method, execution time and recognition.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3685-3707
• /
• 2021

In recent years, facial attribute editing has been successfully used to effectively change face images of various attributes based on generative adversarial networks and encoder-decoder models. However, existing models have a limitation in that they may change an unintended part in the process of changing an attribute or may generate an unnatural result. In this paper, we propose a model that improves the learning of the attention mask by adding a spatial attention mechanism based on the unified selective transfer network (referred to as STGAN) using semi-supervised learning. The proposed model can edit multiple attributes while preserving details independent of the attributes being edited. This study makes two main contributions to the literature. First, we propose an encoder-decoder model structure that learns and edits multiple facial attributes and suppresses distortion using an attention mask. Second, we define guide masks and propose a method and an objective function that use the guide masks for multiple facial attribute editing through semi-supervised learning. Through qualitative and quantitative evaluations of the experimental results, the proposed method was proven to yield improved results that preserve the image details by suppressing unintended changes than existing methods.

• ETRI Journal
• /
• v.43 no.2
• /
• pp.299-312
• /
• 2021

It is necessary to achieve high performance in the task of zero anaphora resolution (ZAR) for completely understanding the texts in Korean, Japanese, Chinese, and various other languages. Deep-learning-based models are being employed for building ZAR systems, owing to the success of deep learning in the recent years. However, the objective of building a high-quality ZAR system is far from being achieved even using these models. To enhance the current ZAR techniques, we fine-tuned a pretrained bidirectional encoder representations from transformers (BERT). Notably, BERT is a general language representation model that enables systems to utilize deep bidirectional contextual information in a natural language text. It extensively exploits the attention mechanism based upon the sequence-transduction model Transformer. In our model, classification is simultaneously performed for all the words in the input word sequence to decide whether each word can be an antecedent. We seek end-to-end learning by disallowing any use of hand-crafted or dependency-parsing features. Experimental results show that compared with other models, our approach can significantly improve the performance of ZAR.

• Journal of the Semiconductor & Display Technology
• /
• v.18 no.2
• /
• pp.48-52
• /
• 2019

Virtual metrology, which is one of APC techniques, is a method to predict characteristics of manufactured films using machine learning with saving time and resources. As the photoresist is no longer a mask material for use in high aspect ratios as the CD is reduced, hard mask is introduced to solve such problems. Among many types of hard mask materials, amorphous carbon layer(ACL) is widely investigated due to its advantages of high etch selectivity than conventional photoresist, high optical transmittance, easy deposition process, and removability by oxygen plasma. In this study, VM using different machine learning algorithms is applied to predict the thickness of ACL and trained models are evaluated which model shows best prediction performance. ACL specimens are deposited by plasma enhanced chemical vapor deposition(PECVD) with four different process parameters(Pressure, RF power, $C_3H_6$ gas flow, $N_2$ gas flow). Gradient boosting regression(GBR) algorithm, random forest regression(RFR) algorithm, and neural network(NN) are selected for modeling. The model using gradient boosting algorithm shows most proper performance with higher R-squared value. A model for predicting the thickness of the ACL film within the abovementioned conditions has been successfully constructed.

• PNF and Movement
• /
• v.9 no.1
• /
• pp.11-19
• /
• 2011

The purpose of this study was to investigate whether it makes difference to use of the Augmented Feedback Type(Verbal Feedback, VTR Feedback and Verbal & VTR Feedback) to hemiplegic adults on learning of motor skill. For the purpose 15 hemiplegic adults who are received rehabilitation program at H hospital in Hong-Sung, Choong-Nam Province. Subjects were classified into three groups by random assignment; the Verbal Feedback group, the VTR Feedback group and Verbal & VTR Feedback group. Each groups received 5 subjects from hemiplegic adults. Subjects were tested by Timed Up and Go test for 9 weeks. And to find out the improvement measured by Pre-Test, Acquisition Test and Retention Test. To find out the improvement of each group's measures took average and standard deviation. To probate the significance of difference between the improvement conducted the one-way ANOVA and to probate the significance of difference of Acquisition Test and Retention test conducted paired t-test. The results of this study were as follows; First, All of Augmented Feedback Types had a positive effect on hemiplegic adults to learning of motor skill. Second, The Verbal Feedback group and the VTR Feedback group had no significantly difference at Acquisition Test, But They had the most improvement at Retention Test. Third, In hemiplegic adults, the Verbal & VTR Feedback group had the highest Retention Effect.

• Nuclear Engineering and Technology
• /
• v.53 no.12
• /
• pp.3944-3951
• /
• 2021

Several reasons such as no free lunch theorem indicate that there is not a universal Feature selection (FS) technique that outperforms other ones. Moreover, some approaches such as using synthetic dataset, in presence of large number of FS techniques, are very tedious and time consuming task. In this study to tackle the issue of dependency of estimation accuracy on the selected FS technique, a methodology based on the heterogeneous ensemble is proposed. The performance of the major learning algorithms of neural network (i.e. the FFNN-BR, the FFNN-LM) in combination with the diverse FS techniques (i.e. the NCA, the F-test, the Kendall's tau, the Pearson, the Spearman, and the Relief) and different combination techniques of the heterogeneous ensemble (i.e. the Min, the Median, the Arithmetic mean, and the Geometric mean) are considered. The target parameters/transients of Bushehr nuclear power plant (BNPP) are examined as the case study. The results show that the Min combination technique gives the more accurate estimation. Therefore, if the number of FS techniques is m and the number of learning algorithms is n, by the heterogeneous ensemble, the search space for acceptable estimation of the target parameters may be reduced from n × m to n × 1. The proposed methodology gives a simple and practical approach for more reliable and more accurate estimation of the target parameters compared to the methods such as the use of synthetic dataset or trial and error methods.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.21 no.2
• /
• pp.137-143
• /
• 2022

Composite materials, being light-weight and of high mechanical strength, are increasingly used in various industries such as the aerospace, automobile, sporting-goods manufacturing, and ship-building industries. Recently, manufacturing of composite materials using 3D printers has increased. 3D-printed composite materials are made in free-form and adapted for end-use by adjusting the fiber content and orientation. However, research on the machining of 3D printed composite materials is limited. The aim of this study is to develop a machine learning method to select machining conditions for machining of 3D-printed composite materials. The composite material was composed of Onyx and carbon fibers and stacked sequentially. The experiments were performed using the following machining conditions: spindle speed, feed rate, depth of cut, and machining direction. Cutting forces of the different machining conditions were measured by milling the composite materials. PCA, a method of machine learning, was developed to select the machining conditions and will be used in subsequent experiments under various machining conditions.

• International Journal of Computer Science & Network Security
• /
• v.23 no.11
• /
• pp.183-189
• /
• 2023

A stroke is a medical disease where a blood vessel in the brain ruptures, causes damage to the brain. If the flow of blood and different nutrients to the brain is intermittent, symptoms may occur. Stroke is other reason for loss of life and widespread disorder. The prevalence of stroke is high in growing countries, with ischemic stroke being the high usual category. Many of the forewarning signs of stroke can be recognized the seriousness of a stroke can be reduced. Most of the earlier stroke detections and prediction models uses image examination tools like CT (Computed Tomography) scan or MRI (Magnetic Resonance Imaging) which are costly and difficult to use for actual-time recognition. Machine learning (ML) is a part of artificial intelligence (AI) that makes software applications to gain the exact accuracy to predict the end results not having to be directly involved to get the work done. In recent times ML algorithms have gained lot of attention due to their accurate results in medical fields. Hence in this work, Stroke disease identification system by using Machine Learning algorithm is presented. The ML algorithm used in this work is Artificial Neural Network (ANN). The result analysis of presented ML algorithm is compared with different ML algorithms. The performance of the presented approach is compared to find the better algorithm for stroke identification.

• Journal of Digital Convergence
• /
• v.14 no.4
• /
• pp.69-78
• /
• 2016

The purpose of this study is to analyze convergent effects of team interaction and team metacognition of participants on a continuous participation in the university learning community. We developed 19 items of team interaction and 17 items of team metacognition through literature review. The subjects were 113 students who participated in learning community in A university. The results are as follows. First, team interaction level and team metacognition level can affect a continuous participation in learning community. The higher team interaction is and the lower team metacognition is, the higher continuous participation is. Second, among team interaction factors that affect a continuous participation in learning community, the more number of learning is and the more encouragement of one another is, the higher continuous participation is. But the less participation of members is, the less flow to learning is, and the less learning time is, the lower a continuous participation is. Third, among team metacognition factors that affect a continuous participation in learning community, the more number of learning is, the higher continuous participation is. But the more use of various learning tools is and the more learning time is, the lower continuous participation is. Based on these results, the convergent ways of support for continuous participation in the university learning community are as follows. First, supporting system is needed to induce students to experience the positive atmosphere of learning community by increasing number of learning to facilitate team interaction and urging them to encourage one another. Second, providing the effective utilization method is necessary for students to fully acknowledge the necessity and value of team metacognition activity.