• Journal of Practical Engineering Education
• /
• v.14 no.2
• /
• pp.305-312
• /
• 2022

In this paper, we focused on training to create and optimize a basic data prediction model. And we proposed a gradient descent training method of machine learning that is widely used to optimize data prediction models. It visually shows the entire operation process of gradient descent used in the process of optimizing parameter values required for data prediction models by applying the differential method and teaches the effective use of mathematical differentiation in machine learning. In order to visually explain the entire operation process of gradient descent, we implement gradient descent SW in a spreadsheet. In this paper, first, a two-variable gradient descent training method is presented, and the accuracy of the two-variable data prediction model is verified by comparison with the error least squares method. Second, a three-variable gradient descent training method is presented and the accuracy of a three-variable data prediction model is verified. Afterwards, the direction of the optimization practice for gradient descent was presented, and the educational effect of the proposed gradient descent method was analyzed through the results of satisfaction with education for non-majors.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.5
• /
• pp.482-488
• /
• 2014

This paper aims to analyze user's emotion automatically by analyzing Twitter, a representative social network service (SNS). In order to create sentiment analysis models by using machine learning techniques, sentiment labels that represent positive/negative emotions are required. However it is very expensive to obtain sentiment labels of tweets. So, in this paper, we propose a sentiment analysis model by using self-training technique in order to utilize "data without sentiment labels" as well as "data with sentiment labels". Self-training technique is that labels of "data without sentiment labels" is determined by utilizing "data with sentiment labels", and then updates models using together with "data with sentiment labels" and newly labeled data. This technique improves the sentiment analysis performance gradually. However, it has a problem that misclassifications of unlabeled data in an early stage affect the model updating through the whole learning process because labels of unlabeled data never changes once those are determined. Thus, labels of "data without sentiment labels" needs to be carefully determined. In this paper, in order to get high performance using self-training technique, we propose 3 policies for updating "data with sentiment labels" and conduct a comparative analysis. The first policy is to select data of which confidence is higher than a given threshold among newly labeled data. The second policy is to choose the same number of the positive and negative data in the newly labeled data in order to avoid the imbalanced class learning problem. The third policy is to choose newly labeled data less than a given maximum number in order to avoid the updates of large amount of data at a time for gradual model updates. Experiments are conducted using Stanford data set and the data set is classified into positive and negative. As a result, the learned model has a high performance than the learned models by using "data with sentiment labels" only and the self-training with a regular model update policy.

• Journal of Korean Academy of Fundamentals of Nursing
• /
• v.11 no.2
• /
• pp.213-219
• /
• 2004

Purpose: This study was done for the purpose of comparing death orientation scores of nurses before and after a hospice training program. Method: The participants were 56 nurses who completed the hospice training program at C university in Kwang Ju city. The data were gathered from October 2001 to December 2002 by questionnaire. The data were analyzed by using frequency, paired t-test, ANOVA and Pearson's correlation coefficients. Results: The mean scores for death orientation before and after hospice training were mid range scores of 57.2 and 57.0 respectively and this difference was not significant. The death orientation score before hospice training was significantly different according to the 'work place (F=3.16, p=.033)' of nurses but after the hospice training there was no significant difference for any of the general characteristics. The death orientation scores before and after hospice training showed no correlation with the religiosity score either. Conclusion: Considering the mid range scores and the lack of significant difference after the intervention, this study shows that there is a need to analyze the content of hospice education programs and the need to change death orientation. This is especially true when the participants are professional hospice nurses who are being prepared to give care to people who are dying. In order to develop more appropriate programs there is a need to examine the process by which nurses come to view death more positively.

• Journal of Korean Academy of Nursing
• /
• v.33 no.5
• /
• pp.643-650
• /
• 2003

Purpose: This study was conducted to examine the effect of a posture training program, including posture education and spinal exercise as implemented on the elementary school students with scoliosis. Method: The design of this study is nonequivalent sample control group pretest-posttest design. The study subjects were elementary school students attending 7 elementary schools located in G city in Gyungsangbuk-Do. Among them, those who had the Cobb angle between 4～10$^{\circ}$ in spine x-ray who agreed to participate in the study program were selected as the study subjects. The research instruments included the degree of spinal scoliosis(cobb angle), the level of knowledge on posture, and an evaluation following the posture training program. The data were collected from March 1, 2002 to July 30, 2002. The collected data were analyzed by frequency, percentile, mean, standard deviation, t-test, i test and Mann-Whitney U test were using SPSS WIN10.0 program. Result: The elementary school students with scoliosis who received the posture training program have a lower Cobb angle and higher level of knowledge of posture than the elementary school students with scoliosis who did not receive the posture training program. Conclusion: The posture training program was effective on the on Cobb angle and Knowledge of posture in the elementary school students with scoliosis in this study. Therefore, the program training program can be usefully utilized for the students with mild scoliosis in the field of school health.

• Journal of Technologic Dentistry
• /
• v.38 no.4
• /
• pp.343-352
• /
• 2016

Purpose: The intention of the study is to reveal the factors that influence the safety-behavior and safety-accident of the students of dental laboratory science. We intend to use the study as a basic data of searching effective ways to heighten the safety-behavior of clinical training and to prevent safety-accident. Methods: The survey was conducted on dental technology students. The collected data was analyzed by the statistical program SPSS 21.0. The results were analyzed by reliability, frequency, t-test, correlation, multiple regression. To test for significance on each item, p<0.05 has been decided as a standard. Results: The results of the study showed that the safety of the students was influenced by the school year, the leader of clinical training, clinical training environment and the experience of safety education. The safety-accident turned out to be influenced by the school year of the student and the safety behavior. Conclusion: Active leader of clinical training, clinical training environment that enables the safety-behavior, and the offering of the systematic safety education were the most important factors to heighten the safety behavior of the students and prevent the safety-accident. These factors were expected to not only induce the safety-behavior but also prevent the safety-accident as well.

• The Journal of Korea Robotics Society
• /
• v.14 no.2
• /
• pp.122-130
• /
• 2019

Collecting a rich but meaningful training data plays a key role in machine learning and deep learning researches for a self-driving vehicle. This paper introduces a detailed overview of existing open-source simulators which could be used for training self-driving vehicles. After reviewing the simulators, we propose a new effective approach to make a synthetic autonomous vehicle simulation platform suitable for learning and training artificial intelligence algorithms. Specially, we develop a synthetic simulator with various realistic situations and weather conditions which make the autonomous shuttle to learn more realistic situations and handle some unexpected events. The virtual environment is the mimics of the activity of a genuine shuttle vehicle on a physical world. Instead of doing the whole experiment of training in the real physical world, scenarios in 3D virtual worlds are made to calculate the parameters and training the model. From the simulator, the user can obtain data for the various situation and utilize it for the training purpose. Flexible options are available to choose sensors, monitor the output and implement any autonomous driving algorithm. Finally, we verify the effectiveness of the developed simulator by implementing an end-to-end CNN algorithm for training a self-driving shuttle.

• Korean Journal of Artificial Intelligence
• /
• v.5 no.1
• /
• pp.29-37
• /
• 2017

The range of problems that can be handled by the activation of big data and the development of hardware has been rapidly expanded and machine learning such as deep learning has become a very versatile technology. In this paper, mnist data set is used as experimental data, and the Cross Entropy function is used as a loss model for evaluating the efficiency of machine learning, and the value of the loss function in the steepest descent method is We applied the Gradient Descent Optimize algorithm to minimize and updated weight and bias via backpropagation. In this way we analyze optimal reliability value corresponding to the number of exercises and optimal reliability value without overfitting. And comparing the overfitting time according to the number of data changes based on the number of training times, when the training frequency was 1110 times, we obtained the result of 92%, which is the optimal reliability value without overfitting.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.637-639
• /
• 2003

As the number of spectral bands of high spectral resolution data increases, the capability to detect more detailed classes should also increase, and the classification accuracy should increase as well. Often, it is impossible to access enough training pixels for supervise classification. For this reason, the performance of traditional classification methods isn't useful. In this paper, we propose a new model for classification that operates based on decision fusion. In this classifier, learning is performed at two steps. In first step, only training samples are used and in second step, this classifier utilizes semilabeled samples in addition to original training samples. At the beginning of this method, spectral bands are categorized in several small groups. Information of each group is used as a new source and classified. Each of this primary classifier has special characteristics and discriminates the spectral space particularly. With using of the benefits of all primary classifiers, it is made sure that the results of the fused local decisions are accurate enough. In decision fusion center, some rules are used to determine the final class of pixels. This method is applied to real remote sensing data. Results show classification performance is improved, and this method may solve the limitation of training samples in the high dimensional data and the Hughes phenomenon may be mitigated.

• Knowledge Management Research
• /
• v.18 no.4
• /
• pp.261-286
• /
• 2017

Key factors enhancing transfer behavior of training and knowledge sharing are of great interest to researchers and executives because training transfer and knowledge sharing activities are remarkable predictors of organizational growth. This study investigates the core motivations for boosting transfer behavior of training and knowledge sharing. To empirically test the impacts of employee training, servant leadership and self-efficacy, a survey was conducted in small-medium sized companies. The data (N=292) were analyzed using structural equation modeling analysis. The results indicate that higher employee training positively leads to self-efficacy and transfer behavior of training. Servant leadership is positively leads to self-efficacy, transfer behavior of training, and knowledge sharing. Self-efficacy of employees induces greater transfer behavior of training and knowledge sharing. Finally, transfer behavior of training encourages workers to increase knowledge sharing. This study represents an initial step to examine the psychological mechanism of improving employees' transfer behavior of training and knowledge sharing activities based on the employee training qualities and servant leaderships.

• Computers and Concrete
• /
• v.17 no.4
• /
• pp.489-498
• /
• 2016

In this paper, the flexural strength ($f_{fs}$) and splitting tensile strength ($f_{sts}$) of concrete containing different proportions of fly ash have been modeled by using gene expression programming (GEP). Two GEP models called GEP-I and GEP-II are constituted to predict the $f_{fs}$ and $f_{sts}$ values, respectively. In these models, the age of specimen, cement, water, sand, aggregate, superplasticizer and fly ash are used as independent input parameters. GEP-I model is constructed by 292 experimental data and trisected into 170, 86 and 36 data for training, testing and validating sets, respectively. Similarly, GEP-II model is constructed by 278 experimental data and trisected into 142, 70 and 66 data for training, testing and validating sets, respectively. The experimental data used in the validating set of these models are independent from the training and testing sets. The results of the statistical parameters obtained from the models indicate that the proposed empirical models have good prediction and generalization capability.