• Design & Manufacturing
• /
• v.15 no.3
• /
• pp.1-6
• /
• 2021

An artificial neural network model based on a deep learning algorithm is known to be more accurate than humans in image classification, but there is still a limit in the sense that there needs to be a lot of training data that can be called big data. Therefore, various techniques are being studied to build an artificial neural network model with high precision, even with small data. The transfer learning technique is assessed as an excellent alternative. As a result, the purpose of this study is to develop an artificial neural network system that can classify burr images of light guide plate products with 99% accuracy using transfer learning technique. Specifically, for the light guide plate product, 150 images of the normal product and the burr were taken at various angles, heights, positions, etc., respectively. Then, after the preprocessing of images such as thresholding and image augmentation, for a total of 3,300 images were generated. 2,970 images were separated for training, while the remaining 330 images were separated for model accuracy testing. For the transfer learning, a base model was developed using the NASNet-Large model that pre-trained 14 million ImageNet data. According to the final model accuracy test, the 99% accuracy in the image classification for training and test images was confirmed. Consequently, based on the results of this study, it is expected to help develop an integrated AI production management system by training not only the burr but also various defective images.

• International Journal of Advanced Culture Technology
• /
• v.10 no.4
• /
• pp.536-546
• /
• 2022

A society will lose a lot of something in this field when the forest fire broke out. If a forest fire can be detected in advance, damage caused by the spread of forest fires can be prevented early. So, we studied how to detect forest fires using CCTV currently installed. In this paper, we present a deep learning-based model through efficient image data construction for monitoring forest fire smoke, which is unstructured data, based on the deep learning model YOLOv5. Through this study, we conducted a study to accurately detect forest fire smoke, one of the amorphous objects of various forms, in YOLOv5. In this paper, we introduce a method of self-learning by producing insufficient data on its own to increase accuracy for unstructured object recognition. The method presented in this paper constructs a dataset with a fixed labelling position for images containing objects that can be extracted from the original image, through the original image and a model that learned from it. In addition, by training the deep learning model, the performance(mAP) was improved, and the errors occurred by detecting objects other than the learning object were reduced, compared to the model in which only the original image was learned.

• Journal of Industrial Technology
• /
• v.28 no.B
• /
• pp.101-109
• /
• 2008

In general, non-stationary or chaos time series forecasting is very difficult since there exists a drift and/or nonlinearities in them. To overcome this situation, we suggest a new prediction method based on multiple model TS fuzzy predictors combined with preprocessing of time series data, where, instead of time series data, the differences of them are applied to predictors as input. In preprocessing procedure, the candidates of optimal difference interval are determined by using con-elation analysis and corresponding difference data are generated. And then, for each of them, TS fuzzy predictor is constructed by using k-means clustering algorithm and least squares method. Finally, the best predictor which minimizes the performance index is selected and it works on hereafter for prediction. Computer simulation is performed to show the effectiveness and usefulness of our method.

• Spatial Information Research
• /
• v.5 no.1
• /
• pp.77-88
• /
• 1997

This paper presents the design and implementaion of an object-relational geographic information system. This system has been developed on top of a commercial object-relational database management system. It provides flexible spatial data model, spatial query language, visual user interface, and efficient spatial access methods(D0T) in which traditional primary-key access methods can be applied. We report on our design choices and describe the current status of Implementation. The conceptual model of the system is based on SDTS, and is mapped to the intemal obiect-oriented data model. Kevwords : object-oriented data model, GIS, spatial data model, spatial access method.

• Journal of the Korean Statistical Society
• /
• v.30 no.4
• /
• pp.613-635
• /
• 2001

This paper proposes a skewed multivariate probit model for analyzing a correlated binary response data with covariates. The proposed model is formulated by introducing an asymmetric link based upon a skewed multivariate normal distribution. The model connected to the asymmetric multivariate link, allows for flexible modeling of the correlation structure among binary responses and straightforward interpretation of the parameters. However, complex likelihood function of the model prevents us from fitting and analyzing the model analytically. Simulation-based Bayesian inference methodologies are provided to overcome the problem. We examine the suggested methods through two data sets in order to demonstrate their performances.

• International Journal of Advanced Culture Technology
• /
• v.11 no.4
• /
• pp.464-469
• /
• 2023

As modern society develops, the number of diseases caused by bad smells is increasing. As it can harm people's health, it is important to predict in advance the extent to which bad smells may occur, inform the public about this, and take preventive measures. In this paper, we propose a hybrid neural network structure of CNN and LSTM that can be used to detect or predict the occurrence of odors, which are most required in manufacturing or real life, using odor complex sensors. In addition, the proposed learning model uses a complex odor sensor to receive four types of data, including hydrogen sulfide, ammonia, benzene, and toluene, in real time, and applies this data to the inference model to detect and predict the odor state. The proposed model evaluated the prediction accuracy of the training model through performance indicators based on accuracy, and the evaluation results showed an average performance of more than 94%.

• KOREAN JOURNAL OF PACKAGING SCIENCE & TECHNOLOGY
• /
• v.29 no.3
• /
• pp.163-174
• /
• 2023

Though box compression strength (BCS) is commonly used as a performance criterion for shipping containers, estimating BCS remains a challenge. In this study, artificial neural networks (ANN) are implemented as a new tool, with a focus on building up ANN architectures for BCS estimation. An Artificial Neural Network (ANN) model can be constructed by adjusting four modeling factors: hidden neuron numbers, epochs, number of modeling cycles, and number of data points. The four factors interact with each other to influence model accuracy and can be optimized by minimizing model's Mean Squared Error (MSE). Using both data from the literature and "synthetic" data based on the McKee equation, we find that model estimation accuracy remains limited due to the uncertainty in both the input parameters and the ANN process itself. The population size to build an ANN model has been identified based on different data sets. This study provides a methodology guide for future research exploring the applicability of ANN to address problems and answer questions in the corrugated industry.

• ETRI Journal
• /
• v.34 no.5
• /
• pp.783-786
• /
• 2012

This letter proposes a more advanced joint maximum a posteriori (MAP) adaptation using a prior model based on a probabilistic scheme utilizing the bilinear transformation (BIT) concept. The proposed method not only has scalable parameters but is also based on a single prior distribution without the heuristic parameters of the previous joint BIT-MAP method. Experiment results, irrespective of the amount of adaptation data, show that the proposed method leads to a consistent improvement over the previous method.

• Journal of Korean Society for Geospatial Information Science
• /
• v.11 no.4 s.27
• /
• pp.35-43
• /
• 2003

Currently, the government has been driving numerous projects to build the e-government which can enable limitless access and utilization of the information through the accomplishment of the real time based various administrative services. In water resource field, a project to generate digital river thematic maps has been undergoing as a part of the computerization projects. As a partial results, the RIMGIS project has been completed and generation of the various river thematic maps has been required to fully utilize the DB built from RIMGIS project. For the effective generation of the thematic maps, a data model needs to be developed. A data model has been developed in this study to provide more efficient method to generate the thematic maps utilizing existing DB. The data model proposed from this study has defined the relationships between core feature data and framework Data along with relationships among data elements to represent the rivers in the real world more accurately. The core feature data and framework layers have been defined based on the survey of the domestic and foreign case studies along with requirement analysis of the users in the water resource field. The proposed core feature data has been defined based on the minimum unit of 'class', and the relationship between classes has been established based on the ArcGIS Hydro Data Model for the integrated processing of the river information. The proposed spatial data model can be judged to contribute establishing more efficient generation methodology of the river thematic maps.

• Spatial Information Research
• /
• v.17 no.4
• /
• pp.469-481
• /
• 2009

Due to the increasing demands on the efficient use of land and the fast growth of construction technologies, human living space is expanded from on the surface to above and under the surface. By recognizing that the current cadastre system based on 2D was not appropriate to reflect the trend, the researchers are interested in a 3D cadastre. This paper proposed the 3D cadastre data model that is appropriate to protect ownership effectively in Korea. The 3D cadastre data model consists of a 3D cadastre feature model and a 3D cadastre geometry model, and the data are produced by a 3D cadastre data structure. A 3D cadastre feature model is based on 3D rights and features derived from case studies. A 3D cadastre geometry model based on ISO19107 Spatial Schema is modified to be good for 3D cadastre in Korea. A 3D cadastre data structure consists of point, line, polygon and solid primitives. This study finally purposes 1) serving and managing land information effectively, 2) creating rights and displaying ranges about infrastructures above and under surface, 3) serving ubiquitous-based geoinformation, 4) adapting ubiquitous-based GIS to urban development, and 5) regulating relationships between rights of land and registration and management systems.