• The Korean Journal of Applied Statistics
• /
• v.35 no.2
• /
• pp.189-201
• /
• 2022

In this study, we propose factor augmentation to improve forecasting power of cryptocurrency return. We consider financial and economic variables as well as psychological aspect for possible factors. To be more specific, financial and economic factors are obtained by applying principal factor analysis. Psychological factor is summarized by news sentiment analysis. We also visualize such factors through impulse response analysis. In the modeling perspective, we consider ARIMAX as the classical model, and random forest and deep learning to accommodate nonlinear features. As a result, we show that factor augmentation reduces prediction error and the GRU performed the best amongst all models considered.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.12 no.1
• /
• pp.1-5
• /
• 2012

Data reduction has been used widely in data mining for convenient analysis. Principal component analysis (PCA) and factor analysis (FA) methods are popular techniques. The PCA and FA reduce the number of variables to avoid the curse of dimensionality. The curse of dimensionality is to increase the computing time exponentially in proportion to the number of variables. So, many methods have been published for dimension reduction. Also, data augmentation is another approach to analyze data efficiently. Support vector machine (SVM) algorithm is a representative technique for dimension augmentation. The SVM maps original data to a feature space with high dimension to get the optimal decision plane. Both data reduction and augmentation have been used to solve diverse problems in data analysis. In this paper, we compare the strengths and weaknesses of dimension reduction and augmentation for classification and propose a classification method using data reduction for classification. We will carry out experiments for comparative studies to verify the performance of this research.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.6
• /
• pp.1383-1392
• /
• 2019

Adversarial attack, which geneartes adversarial data to make target model misclassify the input data, is able to confuse real life applications of classification models and cause severe damage to the classification system. An Black-box adversarial attack learns a substitute model, which have similar decision boundary to the target model, and then generates adversarial data with the substitute model. Jacobian-based data augmentation is used to synthesize the training data to learn substitutes, but has a drawback that the data synthesized by the augmentation get distorted more and more as the training loop proceeds. We suggest data augmentation with 'decay factor' to alleviate this problem. The result shows that attack success rate of our method is higher(around 8.5%) than the existing method.

• Archives of Plastic Surgery
• /
• v.42 no.2
• /
• pp.131-142
• /
• 2015

Literature indicates an increased risk of suicide among women who have had cosmetic breast implants. An explanatory model for this association has not been established. Some studies conclude that women with cosmetic breast implants demonstrate some characteristics that are associated with increased suicide risk while others support that the breast augmentation protects from suicide. A systematic review including data collection from January 1961 up to February 2014 was conducted. The results were incorporated to pre-existing suicide risk models of the general population. A modified suicide risk model was created for the female cosmetic augmentation mammaplasty candidate. A 2-3 times increased suicide risk among women that undergo cosmetic breast augmentation has been identified. Breast augmentation patients show some characteristics that are associated with increased suicide risk. The majority of women reported high postoperative satisfaction. Recent research indicates that the Autoimmune syndrome induced by adjuvants and fibromyalgia syndrome are associated with silicone implantation. A thorough surgical, medical and psycho-social (psychiatric, family, reproductive, and occupational) history should be included in the preoperative assessment of women seeking to undergo cosmetic breast augmentation. Breast augmentation surgery can stimulate a systematic stress response and increase the risk of suicide. Each risk factor of suicide has poor predictive value when considered independently and can result in prediction errors. A clinical management model has been proposed considering the overlapping risk factors of women that undergo cosmetic breast augmentation with suicide.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.14 no.1
• /
• pp.55-62
• /
• 2006

Ionospheric signal delay is a critical factor for precision differential GNSS(Global Navigation Satellite Systems) applications such as GBAS(Ground-Based Augmentation System) and SBAS (Satellite-Based Augmentation System). Most concern is the impact of the ionospheric storm caused by the interaction between Solar and geomagnetic activities. After brief description of the ionosphere and ionospheric storm, ionospheric models for SBAS are discussed. History of recent ionospheric storms is reviewed and their impact on GNSS is discussed. In order to support Korean GNSS augmentation system development, a preliminary study on the regional ionosphere performed. A software tool for computing regional ionospheric maps is being developed, and initial results during a recent storm period is analyzed.

• Korean Journal of Clinical Laboratory Science
• /
• v.47 no.1
• /
• pp.28-34
• /
• 2015

Pulse wave velocity (PWV) is used to non-invasively estimate the severity of arteriosclerosis by measuring arterial stiffness. Increased arterial stiffness measured by PWV stands for progressive arteriosclerosis and is caused by atherosclerotic risk factors. This study is focused on how brachial-ankle pulse wave velocity (baPWV) is related to the leading risk factors for arteriosclerosis or atherosclerosis. Subjects were 114, 69 males and 45 females who are in 60's and had baPWV test for acute stroke. The results are as follows: the group with increased arterial stiffness showed significant increase in HbA1c, total cholesterol, BSBP (brachial artery systolic blood pressure), BDBP (brachial artery diastolic blood pressure), CSBP (central artery systolic blood pressure), CDBP (central artery diastolic blood pressure), augmentation index (AIx) and diabetes mellitus. Correlation analysis between baPWV and atherosclerotic risk factor showed significant relationship in age, HbA1c, LDL cholesterol, BSBP, BDBP, CSBP, CDBP and augmentation index. baPWV was independently related to age and BSBP in multiple linear regression analysis. The group with increased arterial stiffness was independently related to BDBP in multiple logistic regression analysis. This study might be meaningful in evaluating the relationship between arterial stiffness and atherosclerotic risk factor in a new way, and be helped to make various studies for cardiovascular disease.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.41 no.6
• /
• pp.1141-1153
• /
• 2017

The wearing of the correction bra is very important to stabilize the shape of an implant after breast enlargement surgery; however, the verification of the wearing effect is insufficient. This study surveyed women who experienced breast augmentation surgery, to investigate wearing condition and satisfaction with bras worn immediately after surgery and during the recovery period as well as to collect basic data for the development of an improved patient bra. The study results are as follows. More than half of the respondents stated that they wear a cupless brassiere. As a result of the satisfaction by brassiere types, the cupless bra showed the highest satisfaction. The most important factor in choosing a patient's bra after breast augmentation surgery was the "degree of breast compression". Through the application of the results of this study, the necessity of development of the brassiere for breast enlargement patients with improved function and comfort was understood. It is therefore necessary to improve the function of holding the shape of the breast and applying appropriate pressure as well as designing the ventilated material without skin irritation that is superior to the existing brassieres.

• Journal of Korean Dental Science
• /
• v.6 no.2
• /
• pp.50-57
• /
• 2013

Purpose: Autogenous tooth bone graft is proven to be efficient. We evaluated the bone healing effect and clinical capabilities of autogenous tooth bone materials as a scaffold when growth factor is used together with this material. Materials and Methods: Subjects were those who needed implant placement and bone graft because of missing tooth or alveolar bone defect and who kept their autogenous tooth or needed extraction of other tooth. Group I included autogenous tooth bone graft with growth factor, whereas Group II had only autogenous tooth bone graft. We investigated the bone healing state through computed tomography taken just before surgery and 3 to 4 months after surgery to evaluate the effectiveness of bone graft. Group I had 9 patients, whereas Group II had 5 patients. We compared the pre- and post-operative increase of the Hounsfield unit and bone height by analyzing the computed tomography images. Result: Sinus bone grafts numbered 8 cases, and vertical ridge augmentation was performed together with 3 cases of these. Vertical ridge augmentation was performed in 2 cases, and horizontal ridge augmentation in 1 case alone. Socket graft was done in 3 cases. The post-operative mean value of the Hounsfield unit was 960 in Group I and 836.7 in Group II, but the increase was almost similar, i.e., 636.9 in Group I and 634.7 in Group II on the average. Increase of bone height was 7.6 mm in Group I and 11.1 mm in Group II on the average. This difference was attributable to the fact that most of the cases were sinus bone graft in Group II. Conclusion: In this study, we suggest the possibility of autogenous tooth bone graft materials as a scaffold besides their bone healing ability.

• Journal of Information Technology Services
• /
• v.19 no.5
• /
• pp.83-91
• /
• 2020

Language Models such as BERT has been an important factor of deep learning-based natural language processing. Pre-training the transformer-based language models would be computationally expensive since they are consist of deep and broad architecture and layers using an attention mechanism and also require huge amount of data to train. Hence, it became mandatory to do fine-tuning large pre-trained language models which are trained by Google or some companies can afford the resources and cost. There are various techniques for fine tuning the language models and this paper examines three techniques, which are data augmentation, tuning the hyper paramters and partly re-constructing the neural networks. For data augmentation, we use no-answer augmentation and back-translation method. Also, some useful combinations of hyper parameters are observed by conducting a number of experiments. Finally, we have GRU, LSTM networks to boost our model performance with adding those networks to BERT pre-trained model. We do fine-tuning the pre-trained korean-based language model through the methods mentioned above and push the F1 score from baseline up to 89.66. Moreover, some failure attempts give us important lessons and tell us the further direction in a good way.

• Journal of the Korean Society of Combustion
• /
• v.4 no.1
• /
• pp.117-129
• /
• 1999

A method for the mixing augmentation of the transverse injection of fuel in a Scramjet combustor is suggested. Based on the fact that the main factor controlling the mixing characteristics in transverse injection is the effective back-pressure (the pressure around the injection hole) it is tried to make a flow expansion near the injection port in order to reduce effective back-pressure. A three dimensional Navier-Stokes code adopting the upwind method of Roe#s flux difference splitting scheme is used. The k-w SST turbulence model turbulence model is used to calculate the turbulent viscosity. It is shown that the reducing of the effective back-pressure make it possible to increase the penetration distance and to increase the mixing rate without excessive losses of stagnation pressure. Also, it is shown that the streamwise vorticity generated by baroclinic torque has great influences on the mixing process.