• Journal of KIBIM
• /
• v.11 no.2
• /
• pp.54-59
• /
• 2021

In the process of designing a building, the process of expressing the designer's ideas through images is essential. However, it is expensive and time consuming for a designer to analyze every individual case image to generate a hypothetical design. This study aims to visualize the basic design draft sketch made by the designer as a real image using the Generative Adversarial Network (GAN) based on the continuously accumulated architectural case images. Through this, we proposed a method to build an automated visualization environment using artificial intelligence and to visualize the architectural idea conceived by the designer in the architectural planning stage faster and cheaper than in the past. This study was conducted using approximately 20,000 images. In our study, the GAN algorithm allowed us to represent primary materials and shades within 2 seconds, but lacked accuracy in material and shading representation. We plan to add image data in the future to address this in a follow-up study.

• The Journal of Industrial Distribution & Business
• /
• v.13 no.9
• /
• pp.37-50
• /
• 2022

Purpose: The purpose of this study is to explore and compare research trends in Korea and overseas academic papers on social media marketing, and to present new academic perspectives for the future direction in Korea. Research design, data and methodology: We used English abstract of research paper (Korea's: 1,349, overseas': 5,036) for word frequency analysis, topic modeling, and trend analysis for each topic. Results: The results of word frequency and co-occurrence frequency analysis showed that Korea researches focused on the experiential values of users, and overseas researches focused on platforms and content. Next, 13 topics and 12 topics for Korea and overseas researches were derived from topic modeling. And, trend analysis showed that Korean studies were different from overseas in applying marketing methods to specific industries and they were interested in the short-term performance of social media marketing. Conclusions: We found that the long-term strategies of social media marketing and academic interest in the overall industry will necessary in the future researches. Also, data mining techniques will necessary to generate more general results by quantifying various phenomena in reality. Finally, we expected that continuous and various academic approaches for volatile social media is effective to derive practical implications.

• Korean Journal of Artificial Intelligence
• /
• v.9 no.1
• /
• pp.9-14
• /
• 2021

This paper predicted a model that indicates whether to buy a car based on primary health insurance customer data. Currently, automobiles are being used to land transportation and living, and the scope of use and equipment is expanding. This rapid increase in automobiles has caused automobile insurance to emerge as an essential business target for insurance companies. Therefore, if the car insurance sales are predicted and sold using the information of existing health insurance customers, it can generate continuous profits in the insurance company's operating performance. Therefore, this paper aims to analyze existing customer characteristics and implement a predictive model to activate advertisements for customers interested in such auto insurance. The goal of this study is to maximize the profits of insurance companies by devising communication strategies that can optimize business models and profits for customers. This study was conducted through the Microsoft Azure program, and an automobile insurance purchase prediction model was implemented using Health Insurance Cross-sell Prediction data. The program algorithm uses Two-Class Logistic Regression and Two-Class Boosted Decision Tree at the same time to compare two models and predict and compare the results. According to the results of this study, when the Threshold is 0.3, the AUC is 0.837, and the accuracy is 0.833, which has high accuracy. Therefore, the result was that customers with health insurance could induce a positive reaction to auto insurance purchases.

• International Journal of Contents
• /
• v.17 no.4
• /
• pp.1-15
• /
• 2021

Named entity recognition (NER) is a crucial task for NLP, which aims to extract information from texts. To build NER systems, deep learning (DL) models are learned with dictionary features by mapping each word in the dataset to dictionary features and generating a unique index. However, this technique might generate noisy labels, which pose significant challenges for the NER task. In this paper, we proposed DL-dictionary features, and evaluated them on two datasets, including the OntoNotes 5.0 dataset and our new infectious disease outbreak dataset named GFID. We used (1) a Bidirectional Long Short-Term Memory (BiLSTM) character and (2) pre-trained embedding to concatenate with (3) our proposed features, named the Convolutional Neural Network (CNN), BiLSTM, and self-attention dictionaries, respectively. The combined features (1-3) were fed through BiLSTM - Conditional Random Field (CRF) to predict named entity classes as outputs. We compared these outputs with other predictions of the BiLSTM character, pre-trained embedding, and dictionary features from previous research, which used the exact matching and partial matching dictionary technique. The findings showed that the model employing our dictionary features outperformed other models that used existing dictionary features. We also computed the F1 score with the GFID dataset to apply this technique to extract medical or healthcare information.

• Journal of information and communication convergence engineering
• /
• v.20 no.4
• /
• pp.288-294
• /
• 2022

The media content market has been growing, as various types of content are being mass-produced owing to the recent proliferation of the Internet and digital media. In addition, platforms that provide personalized services for content consumption are emerging and competing with each other to recommend personalized content. Existing platforms use a method in which a user directly inputs video metadata. Consequently, significant amounts of time and cost are consumed in processing large amounts of data. In this study, keyframes and audio spectra based on the YCbCr color model of a movie trailer were extracted for the automatic generation of metadata. The extracted audio spectra and image keyframes were used as learning data for genre recognition in deep learning. Deep learning was implemented to determine genres among the video metadata, and suggestions for utilization were proposed. A system that can automatically generate metadata established through the results of this study will be helpful for studying recommendation systems for media super-personalization.

• Journal of Fashion Business
• /
• v.26 no.6
• /
• pp.32-46
• /
• 2022

The purpose of this study is to explore a three-dimensional (3D) simulation of skirt shape concepts by manipulating circumferences and lengths via parametric design in the fashion design concept stage. This study also intends to propose a modeling method that can judge and transform the shape through immediate parameter adjustment. We looked at cases that utilized parametric design in other fields of fashion design, reviewed and analyzed the variables used in each study, and constructed parameters suitable to implement skirt fashion design. The traditional design elements required for skirt design, namely waist and hip circumferences, were set as variables in this study. The parametric design was developed to generate ideas of two skirt silhouettes (tight and flared) and three lengths (mini, knee-length, and maxi). To apply the skirt design implemented through variables to the actual 3D human shape, the shape data of women in their 20s and 30s were randomly selected from the 5th human data of Size Korea. Skirt design silhouette modeling was performed by adjusting the variable values according to body type. Parametric design has the potential to help develop design ideas in the field of fashion design, considering the method and characteristics of parameters of the variety of variables and rapid modification. Furthermore, if systematic research on variables and options among fashion design elements is conducted, the possibility of converging them into customization or co-design fashion design processes could be confirmed.

• International Journal of Knowledge Content Development & Technology
• /
• v.12 no.2
• /
• pp.29-40
• /
• 2022

The study investigated the challenges of recruitment and selection process of librarians in federal university libraries in South-South, Nigeria. The study adopted a descriptive survey. The population of the study consists of 108 librarians. 95 copies of the questionnaire were filled and returned. The questionnaire was used in collecting data. The overall reliability of the instrument yielded 0.95 with the use of Cronbach Alpha Coefficient. Standard deviation and mean was used to generate the data that was gathered. The rating scale of 4 points was subjected to an estimation procedure using SPSS version 17.0. A mean score of 2.5 and above on any item was accepted. The findings revealed that the librarians identified the challenges to include ethnicity influence; favouritisms; recruitment based on godfatherism; dwindling budgetary allocation. The librarians also identified some of the strategies to include performance at interview as benchmark; equity and fairness as benchmark; recruitment should be done according to relevant discipline; and having channels for reporting cases of corruption during recruitment. Based on the above findings the study recommended among others that recruitment and selection of qualified librarians should be done according to the laid down procedures.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.5
• /
• pp.476-486
• /
• 2022

Synthetic dynamic infrared image generation from the given virtual environment is being the primary goal to simulate the output of the infra-red(IR) camera installed on a vehicle to evaluate the control algorithm for various search & reconnaissance missions. Due to the difficulty to obtain actual IR data in complex environments, Artificial intelligence(AI) has been used recently in the field of image data generation. In this paper, CycleGAN technique is applied to obtain a more realistic synthetic IR image. We added the Structural Similarity Index Measure(SSIM) loss function to the L1 loss function to generate a more realistic synthetic IR image when the CycleGAN image is generated. From the simulation, it is applicable to the guided-missile flight simulation tests by using the synthetic infrared image generated by the proposed technique.

• International conference on construction engineering and project management
• /
• 2005.10a
• /
• pp.662-666
• /
• 2005

Using data gathered from expert opinion of plant and equipment professionals; this paper presents the key variables that may constitute a maintenance proficient plant operator. The Multivariate Discriminant Analysis (MDA) was applied to generate data and was tested for sensitivity analysis. Results showed that the MDA model was able to classify plant operators' proficiency at 94.10 percent accuracy and determined nine (9) key variables of a maintenance proficient plant operator. The key variables included: i) number of years of experience as equipment operator (PQ1); ii) eye-hand coordination (PQ9); iii) eye-hand-foot coordination (PQ10); iv) planning skills (TE16); v) pay/wage (MQ1); vi) work satisfaction (MQ4); vii) operator responsibilities as defined by management (MF1); viii) clear management policies (MF4); and ix) management pay scheme (MF5). The classification procedure of nine variables formed the general model with the equation viz: OMP (general) = 0.516PQ1 + 0.309PQ9 + 0.557PQ10 + 0.831TE16 + 0.8MQ1 + 0.0216MQ4 + 0.136MF1 + 0.28MF4 + 0.332MF5 - 4.387

• The Bulletin of The Korean Astronomical Society
• /
• v.45 no.1
• /
• pp.68.3-69
• /
• 2020

We develop a series of N-body data challenges, functional to the final analysis of the extended Baryon Oscillation Spectroscopic Survey (eBOSS) Data Release 16 (DR16) galaxy sample, primarily based on high-fidelity catalogs constructed from the Outer Rim simulation. We generate synthetic galaxy mocks by populating Outer Rim halos with a variety of halo occupation distribution (HOD) schemes of increasing complexity, spanning different redshift intervals. We then assess the performance of three complementary redshift space distortion (RSD) models in configuration and Fourier space, adopted for the analysis of the complete DR16 eBOSS sample of Luminous Red Galaxies (LRGs). We find that all the methods are mutually consistent, with comparable systematic errors on the Alcock-Paczynski parameters and the growth of structure, and robust to different HOD prescriptions - thus validating the robustness of the models and the pipelines used for the baryon acoustic oscillation (BAO) and full shape clustering analysis. Our study is relevant for the final eBOSS DR16 'consensus cosmology', as the systematic error budget is informed by testing the results of analyses against these high-resolution mocks. In addition, it is also useful for future large-volume surveys, since similar mock-making techniques and systematic corrections can be readily extended to model for instance the DESI galaxy sample.