• Journal of Broadcast Engineering
• /
• v.25 no.6
• /
• pp.980-993
• /
• 2020

Deep-learning based style transfer has recently attracted great attention, because it provides high quality transfer results by appropriately reflecting the high level structural characteristics of images. This paper deals with the problem of providing more stable and more diverse style transfer results of such deep-learning based style transfer method. Based on the investigation of the experimental results from the wide range of hyper-parameter settings, this paper defines the problem of the stability and the diversity of the style transfer, and proposes a partial loss normalization method to solve the problem. The style transfer using the proposed normalization method not only gives the stability on the control of the degree of style reflection, regardless of the input image characteristics, but also presents the diversity of style transfer results, unlike the existing method, at controlling the weight of the partial style loss, and provides the stability on the difference in resolution of the input image.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.1
• /
• pp.41-50
• /
• 2023

Recently, as the Coronavirus disease 2019 (COVID-19) prolongs along with the development of artificial intelligence technology, a non-contact society has become commonplace. Many companies are promoting digital transformation and the activation of artificial intelligence introduction to respond to this which leads to dramatic increase of demand for Chatbot. In addition, a Chatbot has reached the point of processing business transactions from responding simple inquiries. However, it is necessary to develop an API to interface with the legacy system and there are many difficulties in connecting. To solve this, it is becoming important to establish a hybrid Chatbot environment through RPA interface. Recently, the combination of RPA and Chatbot is considered an effective tool for handling many business processes. But, there are many difficulties due to the lack of interface cases and the difficulty in finding a method to development them. This study suggests a method for building a hybrid Chatbot which is an interface Chatbot(Conversational UX) and RPA(Task Automation) from the perspective of hyper-automation based on actual development cases and review of literature review is presented, so that the interface method can be understood and develop more easily. Therefore, there are implications for actively using AI Chatbot for digital transformation.

• Journal of the Korean Society of Industry Convergence
• /
• v.15 no.4
• /
• pp.95-101
• /
• 2012

In order to explain observed catalytic reactivity of aminophosphine complexes (seven-membered chelate), total energy, net charge, atomic orbital electron population, HOMO and LUMO energy of free ligands are calculated by PM3 methods of HyperChem 6.0. Free ligands are 1,2-bis{(diphosphino)amino}propane{$H_2PNHCH_2CH(CH_3)NHPH_2$;ligand 1},1,2-bis{(dimenylphosphino)amino}propane{$(CH_3)_2PNHCH_2CH(CH_3)NHP(CH_3)_2$;ligand 2},1,2-bis{(diphenylphosphino)amino}propane{$(C_6H_5)_2PNHCH_2CH(CH_3)NHP(C_6H_5)_2$;ligand 3}. The result showed that ligand 3 is stable than ligand 2 and ligand 1 and ligand 2 is stable than ligand 1 in total energy. Net charge of P atom is changed by H atom, methyl groups and phenyl groups in P atoms. Net charge of N atoms in ligands is nagative. The results of atomic orbital electron population are similar net charge data..

• Journal of Korean Academy of Nursing
• /
• v.33 no.6
• /
• pp.829-838
• /
• 2003

Purpose: In South Korea, as growing the need of psychological support in disaster situation psychological assessment on stress after disaster is important to find out the factors affecting coping, and to plan intervention in the community. Method: The volunteers of Korea Redcross who live around K city, and the research team visited all homes at Jirye town, one of the high-impact area, 4 month after the typhoon. One of the family members who is over 18 years old, answered the self-report questionnaire composed of disaster experience, damage, exposure to traumatic event, and posttraumatic stress with IES-K (Impact of Event Scale-korea) He also, described his family members symptom related to re-experiencing, hyper-arousal, and avoidance. Six hundreds households were surveyed. Result: The prevalence of moderate to severe PTSD symptom was 36% of the subjects. The severity of PTSD was affected by gender, economic status and affected by damaged property, physical injury, worsening existing disease, getting infectious disease, amount of experienced traumatic event before disaster, warning, taking shelter, and subjects revealed differences in somatization as severity of PTSD. According to the description, community members had re-experiencing, hyper-arousal and avoidance. Conclusion: At a rural area, South Korea, community members have suffered from psychological distress after disaster. So psychological interventions are required as affecting factors and also to plan for warning and shelter in disaster situation is needed for preventing PTSD.

• 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.

• The KIPS Transactions:PartB
• /
• v.14B no.2
• /
• pp.107-118
• /
• 2007

This paper proposes a 3D avatar which expresses sign language in a very using lips, facial expression, complexion, pupil motion and body motion as well as hand shape, Hand posture and hand motion to overcome the limitation of conventional sign language avatars from a deaf's viewpoint. To describe motion data of hand and other body components structurally and enhance the performance of databases, we introduce the concept of a hyper sign sentence. We show the superiority of the developed system by a usability test through a questionnaire survey.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.9
• /
• pp.2343-2349
• /
• 1999

The hyper-geometric distribution software reliability growth model (HGDM) was recently developed and successfully applied to real data sets. The HGDM considers the sensitivity factor as a parameter to be estimated. In order to reflect the random behavior of the test-and-debug process, this paper generalizes the HGDM by assuming that the sensitivity factor is a binomial random variable. Such a generalization enables us to easily understand the statistical characteristics of the HGDM. It is shown that the least squares method produces the identical results for both the HGDM and the generalized HGDM. Methods for computing the maximum likelihood estimates and predicting the future outcomes are also presented.

• The Journal of the Convergence on Culture Technology
• /
• v.4 no.4
• /
• pp.343-348
• /
• 2018

Anthocyanin derivatives are an important of natural compounds responsible for the red, purple and blue colors in a large number of plants. This molecules are polymethoxy-derivatives of 2-phenylbenzopyrylium salts. Despite the beneficial properties of anthocyanins, the effectiveness of preventing or treating various diseases depends on bioavailability. Therefore, In this study, in order to investigate the electrical characteristics of anthocyanin derivatives, we investigated the electrochemical properties of derivatives by calculating the total energy, bandgap, net charge of anthocyanin derivatives using HyperChem8.0's PM3 method.

• Journal of the Korean Society of Safety
• /
• v.37 no.6
• /
• pp.81-88
• /
• 2022

It is necessary to better understand the effect of age-related degradation on the performance of reinforced concrete shear walls in nuclear power plants in order to ensure their structural safety in the event of earthquakes. Therefore, this paper studies seismic fragility of the typical shear wall in nuclear power plants under earthquake excitation Reinforced concrete shear wall is composed of wall, horizontal and vertical flanges. Due to characteristics of its geometry, it is difficult to predict the ultimate behavior of shear wall under earthquake excitation. In this study, for more realistic numerical simulation, the Latin Hyper-Cube (LHC) simulation technique was used to generate uncertain variables for the material properties of concrete shear walls. The effects of crack, characteristics of inelastic behavior of concrete, and loss of cross section were considered in the nonlinear finite element analysis. The effects of aging-related deterioration were investigated on the performance of reinforced concrete shear walls through analysis of undegraded concrete shear walls and degraded concrete shear walls. The resulting seismic fragility curves present the change of performance of concrete shear wall due to age-related degradation.

• Journal of the Society of Disaster Information
• /
• v.18 no.3
• /
• pp.542-549
• /
• 2022

Purpose: Pipes are widely used as applied devices in many industrial fields such as machinery, electronics, electricity, and plants, and are also widely used in safety-related fields such as firefighting and chemistry. With the diversification of products, the importance of technology in the piping field is also increasing. In particular, when changing the existing copper pipe to stainless steel, it is necessary to evaluate safety and flow characteristics through structural analysis or flow analysis. Method: This study investigated the structural stability of the 6.35 and 15.88 socket models, which are integrated insert type connectors developed by a company, using FEM. For structural analysis, HyperMesh as pre-processor, HYPER VIEW as post-processor, and LS-DYNA as solver were used. Result: In the case of 6.35 socket, the maximum stresses at hook, holder and hinge were 95.02MPa, 19.59MPa and 44.01MPa, respectively, and in case of 15.88 socket, it was 127.7 MPa, 40.09MPa and 45.23MPa, respectively. Conclusion: Comparing the stress distribution of the two socket models, the stress in the 15.88 socket, which has a relatively large outer diameter, appears to be large overall, but it is significantly lower than the yield stress of each material, indicating that there is no problem in structural safety in both models.