• Journal of IKEEE
• /
• v.26 no.4
• /
• pp.647-652
• /
• 2022

In this paper, we propose a prediction system for skin pore labeling based on a CNN(Convolution Neural Network) model, where a data set is constructed by processing skin images taken by users, and a pore feature image is generated by the proposed image processing algorithm. The skin image data set was labeled for pore characteristics based on the visual classification criteria of skin beauty experts. The proposed image processing algorithm was applied to generate pore feature images from skin images and to train a CNN model that predicts pore feature ratings. The prediction results with pore features by the proposed CNN model is similar to experts visual classification results, where less learning time and higher prediction results were obtained than the results by the comparison model (Resnet-50). In this paper, we describe the proposed image processing algorithm and CNN model, the results of the prediction system and future research plans.

• Journal of Internet Computing and Services
• /
• v.21 no.1
• /
• pp.45-55
• /
• 2020

Due to the development of information and communication technology, the number of new / variant malicious codes is increasing rapidly every year, and various types of malicious codes are spreading due to the development of Internet of things and cloud computing technology. In this paper, we propose a malware analysis method based on string information that can be used regardless of operating system environment and represents library call information related to malicious behavior. Attackers can easily create malware using existing code or by using automated authoring tools, and the generated malware operates in a similar way to existing malware. Since most of the strings that can be extracted from malicious code are composed of information closely related to malicious behavior, it is processed by weighting data features using text mining based method to extract them as effective features for malware analysis. Based on the processed data, a model is constructed using various machine learning algorithms to perform experiments on detection of malicious status and classification of malicious groups. Data has been compared and verified against all files used on Windows and Linux operating systems. The accuracy of malicious detection is about 93.5%, the accuracy of group classification is about 90%. The proposed technique has a wide range of applications because it is relatively simple, fast, and operating system independent as a single model because it is not necessary to build a model for each group when classifying malicious groups. In addition, since the string information is extracted through static analysis, it can be processed faster than the analysis method that directly executes the code.

• The Journal of Society for e-Business Studies
• /
• v.23 no.3
• /
• pp.159-171
• /
• 2018

The imported foods, which are imported and sold domestically, are on the rise every year, and the scale is expected to be larger, including processing the imported raw materials. However, the origin of raw materials is indicated when declaring cargo for finished products of agricultural products, but the standardization of inspection information management system for raw materials is insufficient. In addition, there is a growing concern about the presence of residual pesticides or radioactivity in raw materials or products, and customer want to know production history information when purchasing agrifoods. It manages the hazard analysis of imported agricultural products, but most of them are global issues such as microorganisms, residual pesticides, food additives, and allergy components, etc. Therefore, it is necessary to share among the logistics entities in the entire transportation process the related data. Additionally, to do this, it needs to design an architecture and standardize business model. In this paper, it defines the architecture and the work-flow that occurs between the business process for collecting, processing, and processing information for tracking the status of imported agricultural products by steps, and develops XML message with UBL and the extracted conceptual information model. It will be easy to exchange and share information among the logistics entities through the defined standard model and it will be possible to establish visibility, reliability, safety, and freshness system for transportation of agricultural products requiring real-time management.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.5
• /
• pp.449-456
• /
• 2022

This study proposes a deep learning algorithm to predict crop yield using GIS (Geographic Information System) to extract soil properties from Soilgrids and soil suitability class maps. The proposed model modified the structure of a published CNN-RNN (Convolutional Neural Network-Recurrent Neural Network) based crop yield prediction model suitable for the domestic crop environment. The existing model has two characteristics. The first is that it replaces the original yield with the average yield of the year, and the second is that it trains the data of the predicted year. The new model uses the original field value to ensure accuracy, and the network structure has been improved so that it can train only with data prior to the year to be predicted. The proposed model predicted the yield per unit area of autumn cabbage for kimchi by region based on weather, soil, soil suitability classes, and yield data from 1980 to 2020. As a result of computing and predicting data for each of the four years from 2018 to 2021, the error amount for the test data set was about 10%, enabling accurate yield prediction, especially in regions with a large proportion of total yield. In addition, both the proposed model and the existing model show that the error gradually decreases as the number of years of training data increases, resulting in improved general-purpose performance as the number of training data increases.

• Journal of the Korean Society of Safety
• /
• v.19 no.4 s.68
• /
• pp.135-140
• /
• 2004

Wear mechanisms may be briefly classified by mechanical, chemical and thermal wear. A plane strain finite element method is used with a new material stress and temperature fields to simulate orthogonal machining with continuous chip formation. Deformation of the workpiece material is healed as elastic-viscoplastic with isotropic strain hardening and the numerical solution accounts for coupling between plastic deformation and the temperature field, including treatment of temperature-dependent material properties. Effect of the uncertainty in the constitutive model on the distributions of strait stress and temperature around the shear zone are presented, and the model is validated by comparing average values of the predicted stress, strain, and temperature at the shear zone with experimental results.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.3
• /
• pp.1014-1020
• /
• 2012

This paper focuses on the development of a supporting S/W tool that can minimize designer's manual operations and errors in metal mold design based on a 3D solid model. The scope in this work includes the offset surface modeling, the computation of the padding force, the generation of material table, the decision of hole position, the estimation of the size of raw material, which are the essential parts of press die and mold design in automotive industry. The proposed system has been developed as a plug-in type using Pro/E API and Visual C++ in order to put the system into the menu functions of Pro/E which is one major 3D CAD systems in the manufacturing industry.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06d
• /
• pp.140-142
• /
• 2012

최근 상황인지에 관한 연구가 활발히 진행되고 있으며 스마트폰의 각종 센서를 통해 사용자의 컨텍스트 파악이 가능해졌다. 이에 따라서 스마트폰의 컨텍스트 파악을 통해서 사용자에게 각종 친화적 서비스 모델이 많이 생겨 나고 있다. 사용자의 경로 추론, 실내에서의 사용자의 위치파악, 사용자 위치기반 편의시설 추천 등이 그 예이며, 그 중 애플리케이션 추천은 대표적인 서비스라 할 수 있다. 애플리케이션 추천은 사용자의 컨텍스트에 따라서 애플리케이션 사용내역을 로그 데이터로 만들고, 로그 데이터를 기반으로 컨텍스트에 따라서 사용자의 애플리케이션 추천을 해주는 시스템이다. 여기서 로그 데이터를 가공하지 않고 통계를 통해 추천이 가능하지만, 로그 데이터를 사용하여 의사 결정 트리를 만들게 되면 보다 정확하고, 빠르게 추천이 가능하며 적은 로그 데이터로 더 많은 컨텍스트에 적용하여 추천 할 수 있다는 이점이 있다. 본 논문에서는 사용자의 컨텍스트 추출하고 이 데이터를 기반으로 의사결정트리를 만들어 앱을 추천하는 시스템을 제안한다. 이러한 컨텍스트 수집 방법과 추론모델을 이용한 애플리케이션 추천 시스템은 추후 사용자 친화적 서비스 연구에 많은 도움이 될 것이다.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2011.11a
• /
• pp.654-657
• /
• 2011

For the successful development of korean exploraton program, KARI started development of ground test model for lunar lander from last year. In order to secure core technology for space propulsion system, Koreanization of propellant tank is proceeding and it will be used for final assembly and test for ground test model. In this paper, the development result of titanum tank shell and verification test result was presented.

• Journal of KIISE:Software and Applications
• /
• v.26 no.9
• /
• pp.1125-1131
• /
• 1999

정보자원의 변화에 따라 학습의 유형도 점차 변화되고 있으며 그에 따라서 컴퓨터를 이용하는 학습 형태도 변화할 필요가 있다. 그것은 학생이 중심이 되는 학습형태이며 그 중의 하나가 문제해결학습형태이다. 컴퓨터와 정보통신기술을 이용하는 문제해결능력은 구체적인 수준에서의 컴퓨터 관련 지식과 기술에 대한 체계적인 조직이 필요하다. 본 연구에서는 정보소양의 단계를 문제인식, 전략수립, 정보수집, 정보가공, 정보출력, 반성단계로 제시하고 그에 따른 컴퓨터관련 지식과 기술을 조직하여 문제해결능력 신장을 위한 컴퓨터 교육과정의 한 모델을 제시하였다.Abstract Learning styles have got to vary gradually according to the change of information resources. Thus We need to change learning styles with a computer. It's a student-oriented learning types. One of them is called a problem solving learning type. The problem solving ability with a computer and information communication technology require the systematic organization of concrete knowledges and the technology about computer. In this study we found the steps of information literacy as problem cognition, strategies establish, information collection, information processing, information presentation, reflection and proposed a model of computer curriculum to improve the problem solving ability.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.7
• /
• pp.1594-1600
• /
• 2005

Recently many researches have been studied in the human vision model to solve the Wblem of the machine vision. Starting from research on the human visual system, first, we investigate the mechanisms of retina through physiological and biological evidence. In retina, input data was processed information processing that was data reduction edge detection, and emphasizing region. The processed image was recognized by region. In this paper, we proposed retinal algorithms that process data reduction and edge detection by the wavelet transform and emphasize region contrast. In experiments, the proposed model simulates processing the retina outputs in the levels and compares with outputs.