• Journal of Platform Technology
• /
• v.10 no.4
• /
• pp.47-55
• /
• 2022

Recently, diverse devices using different wireless technologies are gradually increasing in the IoT environment. In particular, it is essential to design an efficient feature extraction approach and detect the exact types of radio signals in order to accurately identify various radio signal modulation techniques. However, it is difficult to gather labeled wireless signal in a real environment due to the complexity of the process. In addition, various learning techniques based on deep learning have been proposed for wireless signal classification. In the case of deep learning, if the training dataset is not enough, it frequently meets the overfitting problem, which causes performance degradation of wireless signal classification techniques using deep learning models. In this paper, we propose a generative adversarial network(GAN) based on data augmentation techniques to improve classification performance when various wireless signals exist. When there are various types of wireless signals to be classified, if the amount of data representing a specific radio signal is small or unbalanced, the proposed solution is used to increase the amount of data related to the required wireless signal. In order to verify the validity of the proposed data augmentation algorithm, we generated the additional data for the specific wireless signal and implemented a CNN and LSTM-based wireless signal classifier based on the result of balancing. The experimental results show that the classification accuracy of the proposed solution is higher than when the data is unbalanced.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.165-184
• /
• 2023

Recently, Deep learning analysis of unstructured text data using language models, such as Google's BERT and OpenAI's GPT has shown remarkable results in various applications. Most language models are used to learn generalized linguistic information from pre-training data and then update their weights for downstream tasks through a fine-tuning process. However, some concerns have been raised that privacy may be violated in the process of using these language models, i.e., data privacy may be violated when data owner provides large amounts of data to the model owner to perform fine-tuning of the language model. Conversely, when the model owner discloses the entire model to the data owner, the structure and weights of the model are disclosed, which may violate the privacy of the model. The concept of offsite tuning has been recently proposed to perform fine-tuning of language models while protecting privacy in such situations. But the study has a limitation that it does not provide a concrete way to apply the proposed methodology to text classification models. In this study, we propose a concrete method to apply offsite tuning with an additional classifier to protect the privacy of the model and data when performing multi-classification fine-tuning on Korean documents. To evaluate the performance of the proposed methodology, we conducted experiments on about 200,000 Korean documents from five major fields, ICT, electrical, electronic, mechanical, and medical, provided by AIHub, and found that the proposed plug-in model outperforms the zero-shot model and the offsite model in terms of classification accuracy.

• Korean Journal of Remote Sensing
• /
• v.36 no.2_2
• /
• pp.293-307
• /
• 2020

Every year, the floating macroalgae, green and golden tide, are massively detected at the Yellow Sea and East China Sea. After influx of them to the aquaculture facility or beach, it occurs enormous economic losses to remove them. Currently, remote sensing is used effectively to detect the floating macroalgae flowed into the coast. But it has difficulties to detect the floating macroalgae exactly because of the wavelength overlapped with other targets in the ocean. Also, it is difficult to distinguish between green and golden tide because they have similar spectral characteristics. Therefore, we tried to distinguish between green and golden tide applying the Deep learning method to the satellite images. To determine the network, the optimal training conditions were searched to train the AlexNet. Also, Gaofen-1 WFV images were used as a dataset to train and validate the network. Under these conditions, the network was determined after training, and used to confirm the test data. As a result, the accuracy of test data is 88.89%, and it can be possible to distinguish between green and golden tide with precision of 66.67% and 100%, respectively. It is interpreted that the AlexNet can be pick up on the subtle differences between green and golden tide. Through this study, it is expected that the green and golden tide can be effectively classified from various objects in the ocean and distinguished each other.

• International Commerce and Information Review
• /
• v.17 no.2
• /
• pp.307-327
• /
• 2015

Trade education methods that combine practical knowledge and on-site job training have significantly contributed in improving abilities of trade experts. For instance, GTEP and LINC have contributed to a substantial expansion of SME export performane. Moreover, students' cooperation experience have led to employment outcomes as SMEs can employ customized trade workers. I have conducted a survey to 100 students about university-industry collaboration. Results show that ICT skills and foreign language ability are the highest required conditions of employment while production and technology knowledge are the lowest. Furthermore, 50 companies operating in foreign markets responded that through industry-university cooperation, capabilities of university graduates have improved and trade education cooperation scheme is a success.

• Journal of Korea Multimedia Society
• /
• v.23 no.8
• /
• pp.953-964
• /
• 2020

Ever since media contents took over the world, the importance of typography has increased, and the influence of fonts has be n recognized. Nevertheless, the current Hangul font system is very poor and is provided passively, so it is practically impossible to understand and utilize all the shape characteristics of more than six thousand Hangul fonts. In this paper, the characteristics of Hangul font shapes were selected based on the Hangul structure of similar fonts. The stroke element detection training was performed by fine tuning Faster R-CNN Inception v2, one of the deep learning object detection models. We also propose a system that automatically extracts the stroke element characteristics from characters by introducing an automatic extraction algorithm. In comparison to the previous research which showed poor accuracy while using SVM(Support Vector Machine) and Sliding Window Algorithm, the proposed system in this paper has shown the result of 10 % accuracy to properly detect and extract stroke elements from various fonts. In conclusion, if the stroke element characteristics based on the Hangul structural information extracted through the system are used for similar classification, problems such as copyright will be solved in an era when typography's competitiveness becomes stronger, and an automated process will be provided to users for more convenience.

• Journal of Environmental Health Sciences
• /
• v.46 no.5
• /
• pp.588-598
• /
• 2020

Objectives: Human indices were developed to determine returning point of residents and damage restoration after the chemical accident Methods: To determine the returning point of residents after the chemical accident, a new concept, the standard man model was introduced as a human index, in which both H-code and its acute effects were main idea. To evaluate the applicability, a hydrogen fluoride leakage accident in Gumi was applied. The returning point were suggested as the conservative remission period of acute effects among relevant hazard effects and compared with actual returning point. The coverage of each age group were considered with reflecting average daily dose expected for actual residents. In addition, a relief-index as a social-scientific approach was reflected as well to apply the damage restoration Results: Actual returning point of residents in Gumi was 88 days; and that of standard man model suggested was 84 days. The expected amount of exposure at aged 12 or under was at least 2.35 times greater than that of this model, 40s, theoretically. However, their population ratio was less than 1%, so 99% of residents could be applied when the standard man model was applied. The relief-index was as an objective and quantitative methodology to apply the qualitative aspect. Conclusions: Although evaluated as a relatively positive result, there was a limitation such as the number of accident applied to the verification of standard man model. The relief index was also considered, but further research should be carried out to find threshold level for the relief.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.26 no.2
• /
• pp.475-487
• /
• 2016

Recently, various risks of smartphone hacking are emerging. Smishing crime techniques become more cunning and its damage has been increasing, thereby requiring effective ways of preventing and coping with smishing. Especially, it is emphasized the need for smartphone users' security awareness and training besides technological approach. This study investigates the effective method for providing news messages in order to improve the perception of risk from smishing. This research empirically examines that the degree of optimistic bias on risk perception can vary depending on news frame, topic type, and involvement regarding smishing. Based on the findings, it identifies the factors influencing risk perception and verifies effective ways of promoting individual security awareness on smishing. The results of this study provide implications that assist in educating, campaigning and promoting information security awareness for smart device users.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.6
• /
• pp.855-860
• /
• 2018

The IT technologies applying to IoT(Internet of Things), Big Data, and AI(Artificial Intelligence) are needed in the era of 4th industrial revolution. So, the IT convergence courses of computer science major which will be required in the companies in order to prepare the crises of 4th industry revolution are necessary. And, one approach to cope with this problem is the training of IT convergence man power based on NCS(National Competency Standard) education. In this paper, we propose and analyze the NCS education courses for computer science major in order to teach the students who are needed in the Korean domestic companies preparing the 4th industrial revolution. The skills and applications of Chatbot, Blockchain, and CPS(Cyber Physical System) for the post mobile and post Internet technologies are included in the proposed courses.

• The Journal of the Korea Contents Association
• /
• v.6 no.12
• /
• pp.216-225
• /
• 2006

Teaching methods should focus on enabling the students to adopt an open mind towards new experiences and to be flexible to change. Moreover, their purpose lies in encouraging the students to build their ability to discern values so that they can make the right decisions when they are at a crossroad. However, traditional teaching methods were centered on textbooks and on the teachers. This type of teaching method needs to change so that the new teaching method will focus on the students themselves, taking levels of individual students into consideration to enable development of their creativity in line with the demands made during the 21st century, an era of information and globalization. Projected learning method is appropriate for the Physical Education (PE) classes where various activities aim to increase the level of cooperation among students and their investigative skills. Moreover, PE classes pay special attention to the practical aspect. Accordingly, this research makes recommendations for the class execution methods based on projected learning by improving the curriculum for the PE classes, and the effect of these methods are subject to verification.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.55 no.4
• /
• pp.378-391
• /
• 2019

The objective of this study is to establish a direction for smart aquaculture technology development in the Republic of Korea through patent analysis and a demand survey of experts and fishermen. The patent analysis was conducted using Wisdomain for patents in the Republic of Korea, the United States of America, Europe, Japan, and China from 2005 to 2016. This study conducted an analytic hierarchy process (AHP) survey of experts in the fields of fishery, marine, and ICT among others. Furthermore, it carried out a demand survey of 85 fishermen in Jeonnam and Jeju. The smart aquaculture technology market has moderately grown in the Republic of Korea until recently, and it is expected to expand further because of the expansion of national investment in the smart aquaculture field. The priority evaluation results for developing smart aquaculture technology show that land-based aquaculture has a higher priority than sea-based aquaculture. Of the fishermen that responded, 84% said that they need to introduce smart aquaculture technology to solve problems in the supply and demand of manpower, labor cost, and maintenance expenses. The direction of development should lie in developing biological and environment-based standard aquaculture models to spread high-tech systems and vitalize the aquaculture industry. This requires continual training of human resources in the smart aquaculture field.