• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2019년도 춘계학술대회
• /
• pp.211-213
• /
• 2019

본 논문은 머쉰비전기반 자동검사를 위한 대상 이미지영상 검출에 관한 연구결과로서, 영상카메라에 의한 자동 비전검사의 과정에서 요구되는 시험대상물의 위치와 방향에 상관없이 검사대상의 영상을 검출하는 방법을 제안한다. 본 연구에서는 검사대상으로서 와이어 하네스 제조과정에서 실제 적용할 수 있는 기술과 방법을 개발하여 실제 시스템으로 구현한 결과를 제시한다.

• International Journal of Computer Science & Network Security
• /
• 제22권6호
• /
• pp.364-373
• /
• 2022

Image morphing methods make seamless transition changes in the image and mask the meaningful information attached to it. This can be detected by traditional machine learning algorithms and new emerging deep learning algorithms. In this research work, scope of different Hybrid learning approaches having combination of Deep learning and Machine learning are being analyzed with the public dataset CASIA V1.0, CASIA V2.0 and DVMM to find the most efficient algorithm. The simulated results with CNN (Convolution Neural Network), Hybrid approach of CNN along with SVM (Support Vector Machine) and Hybrid approach of CNN along with Random Forest algorithm produced 96.92 %, 95.98 and 99.18 % accuracy respectively with the CASIA V2.0 dataset having 9555 images. The accuracy pattern of applied algorithms changes with CASIA V1.0 data and DVMM data having 1721 and 1845 set of images presenting minimal accuracy with Hybrid approach of CNN and Random Forest algorithm. It is confirmed that the choice of best algorithm to find image forgery depends on input data type. This paper presents the combination of best suited algorithm to detect image morphing with different input datasets.

• International journal of advanced smart convergence
• /
• 제12권4호
• /
• pp.464-469
• /
• 2023

The government has set the mechanization of paddy agriculture as a national task, aiming to achieve over 70% by 2025. The main objective is to stabilize the farming costs of rural households due to the aging and feminization of rural areas, as well as the shortage of agricultural labor. In response to this, the Korea Rural Economic Institute operates a farm machinery rental business. However, there are challenges in selecting and managing rental machinery, including issues related to labor, costs, verification, and time. Additionally, there is a limit to upgrades, and overseas models are being imported and used for transplanters and rice planters, which do not conform to domestic standards and face maintenance difficulties. In order to solve the difficulties of the agricultural machine rental business, we intend to develop an application that shares domestic and foreign machines purchased and used by individuals at a low cost and use them in gun-level administrative districts.

• 융합정보논문지
• /
• 제10권11호
• /
• pp.185-194
• /
• 2020

제 4차 산업혁명 시대에 포스트휴먼적 존재들의 등장은 인간중심적인 근대 휴머니즘에서 탈피하여 인간 아닌 존재들과의 새로운 관계에 대한 성찰의 필요하다는 인식론적 변화를 야기했다. 이러한 성찰을 위해서 주변 세계를 공감하고 이해할 수 있는 포스트휴먼 감수성이 요구되며, 이러한 감수성 함양을 위해 포스트휴먼 시대를 사유하고 경험할 수 있는 미술작품 사례를 포스트휴머니즘 연구자인 브라이도티가 제시한 '동물-되기', '지구-되기', '기계-되기' 기준을 바탕으로 분석하여 제시하였다. 미술작품은 시대정신을 반영하고 있기에 포스트휴먼 시대를 성찰하고 체험해 볼 수 있는 텍스트라는 긍정적인 측면을 확인하였다. 본 연구는 포스트휴먼 감수성 함양을 위해 미술교육에서 활용할 수 있는 미술작품들을 제시하여 기초연구로서 의의가 있다.

• 한국정보기술학회논문지
• /
• 제17권5호
• /
• pp.47-55
• /
• 2019

최근 GPS 재밍으로 인한 피해가 증가되면서 GPS 재밍을 탐지하고 대비하기 위한 연구가 활발히 진행되고 있다. 본 논문은 다중 GPS 수신채널과 3가지 기계학습을 이용한 GPS 재밍 탐지 방법을 다루고 있다. 제안된 다중 GPS 채널은 항재밍 기능이 없는 상용 GPS 수신기와 항잡음 재밍능력만 있는 수신기, 항잡음/항기만 재밍능력이 있는 수신기로 구성되고 운용자는 각각의 수신기에 수신된 좌표를 비교하여 재밍신호의 특성을 식별할 수 있다. 본 논문에서는 신호특성이 다른 각각의 5개 재밍신호를 입력하고, 3가지 기계학습방법(AB: Adaptive Boosting, SVM: Support Vector Machine, DT: Decision Tree)을 이용하여 재밍탐지 시험을 수행하였다. 시험 결과 머신러닝 기법을 단독으로 사용하였을 때 DT 기법이 96.9% 탐지율로 가장 우수한 성능을 보였으며 이진분류기 기법에 비해 모호성 낮고 하드웨어가 단순하여 GPS 재밍탐지에 효과적임을 확인하였다. 또한, 모호성을 해결해주는 추가기법을 적용할 경우 SVM 기법을 활용할 수 있음을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권2호
• /
• pp.742-756
• /
• 2022

A flood of information has occurred with the rise of the internet and digital devices in the fourth industrial revolution era. Every millisecond, massive amounts of structured and unstructured data are generated; smartphones, wearable devices, sensors, and self-driving cars are just a few examples of devices that currently generate massive amounts of data in our daily. Machine learning has been considered an approach to support and recognize patterns in data in many areas to provide a convenient way to other sectors, including the healthcare sector, government sector, banks, military sector, and more. However, the conventional machine learning model requires the data owner to upload their information to train the model in one central location to perform the model training. This classical model has caused data owners to worry about the risks of transferring private information because traditional machine learning is required to push their data to the cloud to process the model training. Furthermore, the training of machine learning and deep learning models requires massive computing resources. Thus, many researchers have jumped to a new model known as "Federated Learning". Federated learning is emerging to train Artificial Intelligence models over distributed clients, and it provides secure privacy information to the data owner. Hence, this paper implements Federated Averaging with a Deep Neural Network to classify the handwriting image and protect the sensitive data. Moreover, we compare the centralized machine learning model with federated averaging. The result shows the centralized machine learning model outperforms federated learning in terms of accuracy, but this classical model produces another risk, like privacy concern, due to the data being stored in the data center. The MNIST dataset was used in this experiment.

• 한국주거학회논문집
• /
• 제18권1호
• /
• pp.61-72
• /
• 2007

The purposes of this study were to summarize the concept of well-being and well-being apartment, to grasp the present condition of apartments which were introduced with well-being elements, and to find out the consumer preferences on well-being elements for apartment planning. Library and internet surveys were performed to summarize the concept of well-being and well-being apartment and to grasp the present condition of apartments which were introduced with well-being elements. Questionnaire survey was carried out from 2nd to 22nd of June 2005, to investigate the preferences on well-being elements for apartment planning. The respondents were 250 residents who are from thirties to fifties and living in urban area. As results, respondents think that 'living for health of body and mind' about concept of well-being and 'certificated apartments by green building rating system' or 'apartments introduced ecological factor' about concept of well-being apartment. They answered that 'yes' about 'Do you have intention to buy well-being apartment?'. The elements in aspect of complex planning having the preference were revealed that promenade for complex design, ecological garden or walking space for landscape design, outdoor exercise space for outdoor design, and security system for foundation equipment. The elements having the preference in aspect of public facilities were fitness room for sports & health facility and study room for cultural facility. The preferred elements in aspect of building and unit design were roof garden for building design, multi-functional room for unit floor plan, natural surface material for interior surface, ventilation system for indoor environment, control system for home automation, and food waste machine for home electronics.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1986년도 하계학술대회논문집
• /
• pp.286-289
• /
• 1986

Power plants are being met by integrating more functions into fewer displays and control devices. The trend toward more efficient man/machine interface, together with developments in distributed type systems, could lead to simplicity of the control benchboard.

• 전기의세계
• /
• 제30권12호
• /
• pp.817-821
• /
• 1981

A simple scheme using the single equivalent machine representation, equivalent loss reprsentation and direct hydro-MW representation are applied to economic dispatch for practical applications. A,simple approach to calculation of incremental transmission losses is proposed from the fast decoupled load flow algorithm. This program is presently being tested on KECO system.

• 한국의류산업학회지
• /
• 제9권6호
• /
• pp.671-678
• /
• 2007

Formulations of compact and supercompact heavy-duty detergents, which are being used widely around the world, differ from those of conventional heavy-duty detergents. Significant differences in composition exist between the compact detergents and the conventional detergents. The compact detergents have a higher content of surfactants, oxygen bleach and enzymes than the conventional detergents. We have studied to find the most effective washing conditions of artificially soiled cloths with a commercial, supercompact, heavy-duty detergent and a drum type washing machine which is becoming the preferred type in Korea. Moreover, we have studied the washing performance with an impeller type washing machine, which has heretofore been the most popular type in East Asia. With the drum-type washing machine, washing performances improved as the washing temperatures went up and the washing times were lengthened. Though the rate of soil removal with a double recommended dosage was higher than with the recommended amount at $20^{\circ}C$, the effects of the higher dosage decreased as the washing temperatures increased. Finally, the washing performances with the two different dosages were the same at $60^{\circ}C$. The washing performances at $40^{\circ}C$ with the recommended dosage for 90 minutes were the same as with the double recommended dosage for 45 minutes. The soil removal efficiencies with the impeller-type washing machine were much lower than those of the drum-type washing machine. The reasons for this were the higher bath ratio that led to the lower concentration of wash liquor, the shorter washing time, and the lower washing temperature.