• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.889-892
• /
• 2020

현재 식품의약품안전처에서 공공데이터 포털에 제공하는 정보에 의하면 국내에는 20,000종 이상의 약이 유통되고 있다. 식약처와 여러 제약회사에서 기본적인 약 정보를 제공하고는 있지만 정확한 처방전이나 설명서가 없는 경우에 무분별한 약 복용의 위험성을 안고 있다. 일부 약 검색을 지원하는 사이트가 있으나 세부 사항을 사용자가 일일이 선택하고 입력해야 정확한 정보를 얻을 수 있다. 본 논문에서는 사용자의 스마트폰을 이용하여 알약을 촬영하면 해당 약을 인식하고 상세 정보를 알려주는 딥러닝 모델을 설계하였다. CNN 신경망을 사용하여 약의 모양, 색상, 마크, 분할선 등을 기준으로 분류하고 인식된 약의 세부 정보는 공공데이터로부터 받아온다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.78-81
• /
• 2021

Through the smart factory construction project, sensors can be installed in manufacturing production facilities and various process data can be collected in real time. Through this, research on real-time facility anomaly detection is being actively conducted to reduce production interruption due to facility abnormality in the manufacturing process. In this paper, to detect abnormalities in production facilities, the manufacturing data was applied to deep learning models Autoencoder(AE), VAE(Variational Autoencoder), and AAE(Adversarial Autoencoder) to derive the results. Manufacturing data was used as input data through a simple moving average technique and preprocessing process, and performance analysis was conducted according to the window size of the simple movement average technique and the feature vector size of the AE model.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.10
• /
• pp.135-149
• /
• 2014

This study proposed the ubiquitous learning system by finding the difficulties which students have in learning the course of science and analyzing the current learning applications that are used commercially. Through case studies, we found 4 problems. First, the request of long learning time by most of the existing video-based learning applications. Second, it is impossible to know their level of learning due to the lack of open learning contents. Third, it is difficult for learners to participate in interactive learning. Fourth, there are educational contents without considerations on the level of learners. To refine the difficulties due to these problems, we designed and implemented a new ubiquitous learning system which applies the small learning contents for short-term learning, open learning system and enhanced hierarchical learning contents. The system was implemented based on Android. It provides learners with useful science education. We conducted a questionnaire for third grade middle school students in order to show that the proposed system has a good educational effects. The questionnaire asks for the differences between the proposed ubiquitous learning system and the existing learning application. We concluded that the proposed system is better than the existing application by using t-test for improvement of learning effects using feedback with which students participate in interactive learning but not in unidirectional learning, and share the learning result.

• Smart Media Journal
• /
• v.10 no.1
• /
• pp.63-69
• /
• 2021

When a person sees a sentence and understands the sentence, the person understands the sentence by reminiscent of the main word in the sentence as an image. Text-to-image is what allows computers to do this associative process. The previous deep learning-based text-to-image model extracts text features using Convolutional Neural Network (CNN)-Long Short Term Memory (LSTM) and bi-directional LSTM, and generates an image by inputting it to the GAN. The previous text-to-image model uses basic embedding in text feature extraction, and it takes a long time to train because images are generated using several modules. Therefore, in this research, we propose a method of extracting features by using the attention mechanism, which has improved performance in the natural language processing field, for sentence embedding, and generating an image by inputting the extracted features into the GAN. As a result of the experiment, the inception score was higher than that of the model used in the previous study, and when judged with the naked eye, an image that expresses the features well in the input sentence was created. In addition, even when a long sentence is input, an image that expresses the sentence well was created.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.7
• /
• pp.191-198
• /
• 2021

Since the size of training dataset become large and the model is getting deeper to achieve high accuracy in deep learning, the deep neural network training requires a lot of computation and it takes too much time with a single node. Therefore, distributed deep learning is proposed to reduce the training time by distributing computation across multiple nodes. In this study, we propose hybrid allreduce strategy that considers the characteristics of each layer and communication and computational overlapping technique for synchronization of distributed deep learning. Since the convolution layer has fewer parameters than the fully-connected layer as well as it is located at the upper, only short overlapping time is allowed. Thus, butterfly allreduce is used to synchronize the convolution layer. On the other hand, fully-connecter layer is synchronized using ring all-reduce. The empirical experiment results on PyTorch with our proposed scheme shows that the proposed method reduced the training time by up to 33% compared to the baseline PyTorch.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.906-909
• /
• 2015

The smart educational environment using the IWB(Interactive White Board) system has been built and developed since e-learning industry was developed significantly in the early 2000's. Basically the IWB system includes the board writing software, and instructors can further increase the training effect by handwriting on the IWB. In this paper we propose new menu layout mechanism of board writing software that only a few menu buttons are displayed based on the frequency of menu usage and the position of menu layout is dynamically moved according to user's writing position. The implementation of our proposed mechanism shows that it is simple and easy to use without user's unnecessary movement. Therefore it is expected to contribute greatly to the development of a future smart education.

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.12
• /
• pp.321-332
• /
• 2020

Decentralized approaches are extensively researched by academia and industry in order to cover up the flaws of existing systems in terms of data privacy. Blockchain and decentralized learning are prominent representatives of a deconcentrated approach. Blockchain is secure by design since the data record is irrevocable, tamper-resistant, consensus-based decision making, and inexpensive of overall transactions. On the other hand, decentralized learning empowers a number of devices collectively in improving a deep learning model without exposing the dataset publicly. To motivate participants to use their resources in building models, a decent and proportional incentive system is a necessity. A centralized incentive mechanism is likely inconvenient to be adopted in decentralized learning since it relies on the middleman that still suffers from bottleneck issues. Therefore, we design an incentive model for decentralized learning applications by leveraging the Ethereum smart contract. The simulation results satisfy the design goals. We also outline the concerns in implementing the presented scheme for sensitive data regarding privacy and data leakage.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.6
• /
• pp.672-680
• /
• 2019

This paper proposes "A Smart Farm Environment Optimization and Yield Prediction Platform based on IoT and Deep Learning" which gathers bio-sensor data from farms, diagnoses the diseases of growing crops, and predicts the year's harvest. The platform collects all the information currently available such as weather and soil microbes, optimizes the farm environment so that the crops can grow well, diagnoses the crop's diseases by using the leaves of the crops being grown on the farm, and predicts this year's harvest by using all the information on the farm. The result shows that the average accuracy of the AEOM is about 15% higher than that of the RF and about 8% higher than the GBD. Although data increases, the accuracy is reduced less than that of the RF or GBD. The linear regression shows that the slope of accuracy is -3.641E-4 for the ReLU, -4.0710E-4 for the Sigmoid, and -7.4534E-4 for the step function. Therefore, as the amount of test data increases, the ReLU is more accurate than the other two activation functions. This paper is a platform for managing the entire farm and, if introduced to actual farms, will greatly contribute to the development of smart farms in Korea.

• Culinary science and hospitality research
• /
• v.19 no.2
• /
• pp.176-189
• /
• 2013

This study has been conducted on 213 students in 4-year universities located in the regions of Daejeon and Chungnam in order to investigate a method to develop a smart device based culinary education application and the results and development method were as follows. First, the most often used smart device was a smart phone, which is used for over 5 hours a day and mainly used for SNS. Second, they utilized a smart device for language and major study during their spare time, wanted educational contents most and thought them useful for learning. Third, most of the students were positively aware of the necessity and learning effects of culinary education applications, and the response rate to utilize the application once a week was highest. Also, they hoped various recipes and simple cuisine and craftsman cooking. Therefore, the functions of SNS mostly often used by students should be added to promote interaction between teachers and students. And more contents should be made for students to use easily in moving or in their spare time. Furthermore, various videos of teaching and theoretical information should be included. And the applications focused on recipes and simple and craftsman cooking should be developed and uploaded on a school homepage and on popular portal sites so that students can easily utilize them.

• Journal of Convergence for Information Technology
• /
• v.10 no.6
• /
• pp.19-27
• /
• 2020

In this study, Developing high resolution camera and Social Network Service sharing image can be easily getting images, it cause about taking fingerprints to easy from images. So I present solution about prevent to taking fingerprints. this technology is develop python using to opencv, blur libraries. First of all 'Hand Key point Detection' algorithm is used to locate the hand in the image. Using this algorithm can be find finger joints that can be protected while minimizing damage in the original image by using the coordinates of separate blurring the area of fingerprints in the image. from now on the development of accurate finger tracking algorithms, fingerprints will be protected by using technology as an internal option for smartphone camera apps from high resolution images.