• International Journal of Computer Science & Network Security
• /
• v.22 no.6
• /
• 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
• /
• v.12 no.4
• /
• 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.

• Journal of Convergence for Information Technology
• /
• v.10 no.11
• /
• pp.185-194
• /
• 2020

The emergence of post-human beings in the 4th Industrial Revolution era led to an epistemological shift in the need for reflection on new relationships with non-human beings, away from human-centered modern humanism. For this reflection, post-human sensibility to empathize and understand the surrounding world is required. In order to cultivate this sensibility, we analyzed the case of art works that can think about and experience the post-human era based on the criteria of 'animal-becoming', 'earth-becoming', and 'machine-being' presented by post-humanist researcher Bridotti. Since the work of art reflects the spirit of the era, we confirmed the positive aspect of the text that can reflect and experience the post-human era. This study is meaningful as a basic study by presenting art works that can be used in art education to improve post-human sensitivity.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.5
• /
• pp.47-55
• /
• 2019

As the damage caused by GPS jamming has been increased, researches for detecting and preventing GPS jamming is being actively studied. This paper deals with a GPS jamming detection method using multiple GPS receiving channels and three-types machine learning techniques. Proposed multiple GPS channels consist of commercial GPS receiver with no anti-jamming function, receiver with just anti-noise jamming function and receiver with anti-noise and anti-spoofing jamming function. This system enables user to identify the characteristics of the jamming signals by comparing the coordinates received at each receiver. In this paper, The five types of jamming signals with different signal characteristics were entered to the system and three kinds of machine learning methods(AB: Adaptive Boosting, SVM: Support Vector Machine, DT: Decision Tree) were applied to perform jamming detection test. The results showed that the DT technique has the best performance with a detection rate of 96.9% when the single machine learning technique was applied. And it is confirmed that DT technique is more effective for GPS jamming detection than the binary classifier techniques because it has low ambiguity and simple hardware. It was also confirmed that SVM could be used only if additional solutions to ambiguity problem are applied.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.2
• /
• 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.

• Journal of the Korean housing association
• /
• v.18 no.1
• /
• 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.

• Proceedings of the KIEE Conference
• /
• 1986.07a
• /
• 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
• /
• v.30 no.12
• /
• 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.

• Fashion & Textile Research Journal
• /
• v.9 no.6
• /
• 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.

• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1393-1399
• /
• 2019

With the rapid growth of the Internet, millions of indiscriminate advertising SMS are sent every day because of the convenience of sending and receiving data. Although we still use methods to block spam words manually, we have been actively researching how to filter spam in a various ways as machine learning emerged. However, spam words and patterns are constantly changing to avoid being filtered, so existing machine learning mechanisms cannot detect or adapt to new words and patterns. Recently, the concept of Lifelong Learning emerged to overcome these limitations, using existing knowledge to keep learning new knowledge continuously. In this paper, we propose a method of spam filtering system using ensemble techniques of naive bayesian which is most commonly used in document classification and LLML(Lifelong Machine Learning). We validate the performance of lifelong learning by applying the model ELLA and the Naive Bayes most commonly used in existing spam filters.