• Journal of the Korea Computer Graphics Society
• /
• v.29 no.3
• /
• pp.79-84
• /
• 2023

Image generation models have been applied in various fields to overcome data sparsity, time and cost issues. However, it has limitations in generating images from regular pattern images and detecting defects in such data. In this paper, we verified the feasibility of the image generation model to generate pattern images and applied it to data augmentation for defect detection of OLED panels. The data required to train an OLED defect detection model is difficult to obtain due to the high cost of OLED panels. Therefore, even if the data set is obtained, it is necessary to define and classify various defect types. This paper introduces an OLED panel defect data acquisition system that acquires a hypothetical data set and augments the data with an image generation model. In addition, the difficulty of generating pattern images in the diffusion model is identified and a possibility is proposed, and the limitations of data augmentation and defect detection data augmentation using the image generation model are improved.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.6
• /
• pp.261-268
• /
• 2015

In spoken chatting systems, users'spoken queries are converted to text queries using automatic speech recognition (ASR) engines. If the top-1 results of the ASR engines are incorrect, these errors are propagated to the spoken chatting systems. To improve the top-1 accuracies of ASR engines, we propose a post-processing model to rearrange the top-n outputs of ASR engines using a ranking support vector machine (RankSVM). On the other hand, a number of chatting sentences are needed to train chatting systems. If new chatting sentences are not frequently added to training data, responses of the chatting systems will be old-fashioned soon. To resolve this problem, we propose a data collection model to automatically select chatting sentences from TV and movie scenarios using a support vector machine (SVM). In the experiments, the post-processing model showed a higher precision of 4.4% and a higher recall rate of 6.4% compared to the baseline model (without post-processing). Then, the data collection model showed the high precision of 98.95% and the recall rate of 57.14%.

• Journal of Korea Multimedia Society
• /
• v.23 no.10
• /
• pp.1270-1285
• /
• 2020

As a representative concept of the fourth industrial revolution era where everything is digitized, digital twin means analyzing and optimizing a complex system using a simulation model synchronized with the system. In this paper, we propose a digital twin simulation model for the efficient operation of urban railways in Busan. Due to the geopolitical nature of Busan, where there are many mountains and narrow roads, the railways are more useful than other public transportation. However, this inversely results in a high level of congestion, which is an inconvenience to citizens and may be fatal to the spread of the virus, such as COVID19. Considering these characteristics, the proposed model analyzes the congestion level of the railways in Busan. The model is developed based on a mathematical formalism called discrete-event system specification and deduces the congestion level and the average waiting time of passengers depending on the train schedule. In addition, a new schedule to reduce the congestion level is derived through particle swarm optimization, which helps the efficient operation of the railways. Although the model is developed for the railways in Busan, it can also be used for railways in other cities where a high level of congestion is a problem.

• Journal of the Korean GEO-environmental Society
• /
• v.14 no.12
• /
• pp.61-69
• /
• 2013

As construction for road and train tunnel is increasing, various geotechnical conditions can be faced during the construction stage. Especially, if the tunnel is located in limestone area, the cavity is mostly to locate in tunnel planning location. One or some cavities which can be harmful for tunnel safety are predicted. Hence, this study was fulfilled to confirm the influence between tunnel and cavity using laboratory scale down model test and numerical analysis. The scale down model test was carried out to confirm the failure load of the model ground about the interval length of cavity and tunnel and to analyze behaviour characteristics of the model ground on the cavity shape. From the model test result, the failure load decrease in accordance with decreasing of interval length between cavity and tunnel within 0.5D. The numerical analyses were carried out for verification about scale down model test. From the numerical analysis result, tunnel safety decreases in the case of the interval between cavity and tunnel within 0.5D.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.10
• /
• pp.1300-1306
• /
• 2018

The purpose of this study is to see possibility of Char2Vec as alternative of Word2Vec that most famous word embedding model in Sentence Similarity Measure Problem by Deep-Learning. In experiment, we used the Siamese Ma-LSTM recurrent neural network architecture for measure similarity two random sentences. Siamese Ma-LSTM model was implemented with tensorflow. We train each model with 200 epoch on gpu environment and it took about 20 hours. Then we compared Word2Vec based model training result with Char2Vec based model training result. as a result, model of based with Char2Vec that initialized random weight record 75.1% validation dataset accuracy and model of based with Word2Vec that pretrained with 3 million words and phrase record 71.6% validation dataset accuracy. so Char2Vec is suitable alternate of Word2Vec to optimize high system memory requirements problem.

• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.34 no.12
• /
• pp.85-94
• /
• 2018

The purpose of this paper was to propose a model that recognizes potential users' emotional response toward design by classifying Electroencephalography(EEG). Studies in neuroscience and psychology have made an effort to recognize subjects' emotional response by analyzing EEG data. And this approach has been adopted in design since it is critical to monitor users' subjective response in the preface of design. Moreover, the building design process cannot be reversed after construction, recognizing clients' affection toward design alternatives plays important role. An experiment was conducted to record subjects' EEG data while they view their most/least liked images of small-house designs selected by them among the eight given images. After the recording, a subjective questionnaire, PANAS, was distributed to the subjects in order to describe their own affection score in quantitative way. Google TensorFlow was used to build and train the model. Dataset for model training and testing consist of feature columns for recorded EEG data and labels for the questionnaire results. After training and testing, the measured accuracy of the model was 0.975 which was higher than the other machine learning based classification methods. The proposed model may suggest one quantitative way of evaluating design alternatives. In addition, this method may support designer while designing the facilities for people like disabled or children who are not able to express their own feelings toward alternatives.

• Journal of Convergence for Information Technology
• /
• v.11 no.7
• /
• pp.14-20
• /
• 2021

Most accidents caused by road icing in winter lead to major accidents. Because it is difficult for the driver to detect the road icing in advance. In this work, we study how to accurately detect road traffic emerging risk using AutoML and CNN's ensemble model that use both structured and unstructured data. We train CNN-based road traffic emerging risk classification model using images that are unstructured data and AutoML-based road traffic emerging risk classification model using weather data that is structured data, respectively. After that the ensemble model is designed to complement the CNN-based classification model by inputting probability values derived from of each models. Through this, improves road traffic emerging risk classification performance and alerts drivers more accurately and quickly to enable safe driving.

• Journal of Broadcast Engineering
• /
• v.27 no.2
• /
• pp.174-184
• /
• 2022

3D human pose estimation models can be classified into a multi-view model and a single-view model. In general, the multi-view model shows superior pose estimation performance compared to the single-view model. In the case of the single-view model, the improvement of the 3D pose estimation performance requires a large amount of training data. However, it is not easy to obtain annotations for training 3D pose estimation models. To address this problem, we propose a method to generate pseudo ground-truths of multi-view human pose data from a multi-view model and exploit the resultant pseudo ground-truths to train a single-view model. In addition, we propose a multi-view consistency loss function that considers the consistency of poses estimated from multi-view images, showing that the proposed loss helps the effective training of single-view models. Experiments using Human3.6M and MPI-INF-3DHP datasets show that the proposed method is effective for training single-view 3D human pose estimation models.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.8
• /
• pp.263-269
• /
• 2022

This study is to propose a FOCUS Teaching & Learning model to educate pre-service early childhood teachers and in the era of convergence and integration and the Fourth Industrial Revolution. In an era where the use of digital technology is maximized due to COVID-19, boundaries of each fields are blurred and convergence is emphasized, a teaching and learning model is needed to strengthen capabilities of freshmen at colleges that train specialists. This study proposes ways to vitalize ICT education in early childhood education and proposes an integrated teaching and learning model. Through this model, pre-service early childhood teachers will be able to enhance their digital capabilities and contribute to the field of early childhood education by producing video content, activities and teaching aids to be provided to early childhood education institutions. In addition, the model can be applied to areas other than early childhood education to improve digital capabilities through video production and utilization.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.12
• /
• pp.3330-3344
• /
• 2023

This paper proposes an antenna performance prediction model in the autonomous driving radar manufacturing process. Our research work is based upon a challenge dataset, Driving Radar Manufacturing Process Dataset, and a typical AutoML machine learning workflow engine, Pycaret open-source Python library. Note that the dataset contains the total 70 data-items, out of which 54 used as input features and 16 used as output features, and the dataset is properly built into resolving the multi-output regression problem. During the data regression analysis and preprocessing phase, we identified several input features having similar correlations and so detached some of those input features, which may become a serious cause of the multicollinearity problem that affect the overall model performance. In the training phase, we train each of output-feature regression models by using the AutoML approach. Next, we selected the top 5 models showing the higher performances in the AutoML result reports and applied the ensemble method so as for the selected models' performances to be improved. In performing the experimental performance evaluation of the regression prediction model, we particularly used two metrics, MAE and RMSE, and the results of which were 0.6928 and 1.2065, respectively. Additionally, we carried out a series of experiments to verify the proposed model's performance by comparing with other existing models' performances. In conclusion, we enhance accuracy for safer autonomous vehicles, reduces manufacturing costs through AutoML-Pycaret and machine learning ensembled model, and prevents the production of faulty radar systems, conserving resources. Ultimately, the proposed model holds significant promise not only for antenna performance but also for improving manufacturing quality and advancing radar systems in autonomous vehicles.