• Journal of Korean Society of Forest Science
• /
• v.110 no.2
• /
• pp.155-164
• /
• 2021

Many studies have been conducted on developing automatic plant identification algorithms using machine learning to various plant features, such as leaves and flowers. Unlike other plant characteristics, barks show only little change regardless of the season and are maintained for a long period. Nevertheless, barks show a complex shape with a large variation depending on the environment, and there are insufficient materials that can be utilized to train algorithms. Here, in addition to the previously published bark image dataset, BarkNet v.1.0, images of barks were collected, and a dataset consisting of 53 tree species that can be easily observed in Korea was presented. A convolutional neural network (CNN) was trained and tested on the dataset, and the factors that interfere with the model's performance were identified. For CNN architecture, VGG-16 and 19 were utilized. As a result, VGG-16 achieved 90.41% and VGG-19 achieved 92.62% accuracy. When tested on new tree images that do not exist in the original dataset but belong to the same genus or family, it was confirmed that more than 80% of cases were successfully identified as the same genus or family. Meanwhile, it was found that the model tended to misclassify when there were distracting features in the image, including leaves, mosses, and knots. In these cases, we propose that random cropping and classification by majority votes are valid for improving possible errors in training and inferences.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.1
• /
• pp.581-586
• /
• 2023

Recently a drama that features a lawyer with autism spectrum disorder has attracted a lot of attention, raising interest in the difficulties faced by people with autism spectrum disorders. If the Autism spectrum gets detected early and proper education and treatment, the prognosis can be improved, so the development of the treatment is urgently needed. Drugs currently used to treat autism spectrum often have side effects, so Digital Therapeutics that have no side effects and can be supplied in large quantities are drawing attention. In this paper, we introduce 'AEmotion', an application and a Digital Therapeutic that provides emotion and facial expression learning for toddlers with an autism spectrum disorder. This system is developed as an application for smartphones to increase interest in training autistic children and to test easily. Using machine learning, this system consists of three main stages: an 'emotion learning' step to learn emotions with facial expression cards, an 'emotion identification' step to check if the user understood emotions and facial expressions properly, and an 'expression training' step to make appropriate facial expressions. Through this system, it is expected that it will help autistic toddlers who have difficulties with social interactions by having problems recognizing facial expressions and emotions.

• Journal of Internet of Things and Convergence
• /
• v.6 no.1
• /
• pp.83-95
• /
• 2020

Being a dense and complex task of precisely detecting the weeds in practical crop field environment, previous approaches lack in terms of speed of processing image frames with accuracy. Although much of the attention has been given to classify the plants diseases but detecting crop weed issue remained in limelight. Previous approaches report to use fast algorithms but inference time is not even closer to real time, making them impractical solutions to be used in uncontrolled conditions. Therefore, we propose a detection model for the complex rice weed detection task. Experimental results show that inference time in our approach is reduced with a significant margin in weed detection task, making it practically deployable application in real conditions. The samples are collected at two different growth stages of rice and annotated manually

• Journal of the Korea Convergence Society
• /
• v.9 no.5
• /
• pp.1-6
• /
• 2018

In smart grid an accurate load forecasting is crucial in planning resources, which aids in improving its operation efficiency and reducing the dynamic uncertainties of energy systems. Research in this area has included the use of shallow neural networks and other machine learning techniques to solve this problem. Recent researches in the field of computer vision and speech recognition, have shown great promise for Deep Neural Networks (DNN). To improve the performance of daily electric peak load forecasting the paper presents a new deep neural network model which has the architecture of two multi-layer neural networks being serially connected. The proposed network model is progressively pre-learned layer by layer ahead of learning the whole network. For both one day and two day ahead peak load forecasting the proposed models are trained and tested using four years of hourly load data obtained from the Korea Power Exchange (KPX).

• The Journal of the Korea Contents Association
• /
• v.11 no.11
• /
• pp.514-520
• /
• 2011

Technological development, a diverse range of media adapting to new technology has been developing. Augmented Reality Technology provides realistic information through the stereoscopic 3D images and it has been riding a wave of learner interest as an educational media which can broaden their learning experience through direct operating activity. The biggest reason why the Augmented Reality has gained such attention is because of its unique way of suggesting learning information that unlike the existing educational media, the Augmented Reality provides additional digitalized information while its users are looking at the actual object. Based on the domestic and foreign cases of development for educational contents using the Augmented Reality Technology, this thesis suggests the utilization of Pop-up books and multi-augmented Digilog Books that are ways to maximize the educational effects of the Augmented Reality. Through the development of smartphone applications that are propagating lately at a rapid rate, users can now use the Augmented Reality educational contents in a way that is easier than ever.

• Journal of Digital Convergence
• /
• v.14 no.3
• /
• pp.55-62
• /
• 2016

Today, demand for job training of married immigrants is increasing. This research aims to propose developmental Edu-Tech based on the demand for education contents and the characteristics of multicultural family. Based on analysis such as FGI(focus group interview) and expert interview, this paper presents a four methods for development of EduTech for multicultural people, such as language skills, the recommendation technology of customized training contents, contents design based on gamification and user experience design. This research contributes to the direction of the method to use EduTech as a tool for gaps in education and welfare state.

• Journal of Digital Convergence
• /
• v.16 no.10
• /
• pp.59-67
• /
• 2018

There are not that many m-health related services limited to the elderly. Many of the elderly who are at risk of dementia are unfamiliar to smart devices, so it is required to design an user-customized App. Therefore, I design and embody a mobile voice alert integrated app, which enables voice input to increase the accessibility of the elderly, so as to prevent diseases caused by declined cognitive function such as dementia. I conducted interviews and questionnaire after having the students use the app in Lifelong Education Center in H region of Gyeongbuk, and the analysis result has showed the high satisfaction. It is expected that it will be able to play a key role for M-Health service for the elderly since it is possible to prevent dementia through the voice health care alert app. I would like to learn deep learning in the future to predict the life patterns and the possibility of dementia of the elderly.

• Journal of KIISE
• /
• v.43 no.1
• /
• pp.47-53
• /
• 2016

While the Internet develops rapidly, a huge amount of image data collected from smart phones, digital cameras and black boxes are being shared through social media sites. Generally, social images are handled by tagging them with information. Due to the ease of sharing multimedia and the explosive increase in the amount of tag information, it may be considered too much hassle by some users to put the tags on images. Image retrieval is likely to be less accurate when tags are absent or mislabeled. In this paper, we suggest a method of extracting tags from social images by using image content. In this method, CNN(Convolutional Neural Network) is trained using ImageNet images with labels in the training set, and it extracts labels from instagram images. We use the extracted labels for automatic image tagging. The experimental results show that the accuracy is higher than that of instagram retrievals.

• Journal of the Korean Geotechnical Society
• /
• v.37 no.12
• /
• pp.117-125
• /
• 2021

The occurrence of ground subsidence and sinkhole in downtown areas, which threatens the safety of citizens, has been frequently reported. Among the various mechanisms of a sinkhole, soil erosion through the damaged part of the sewer pipe was found to be the main cause in Seoul. In this study, a random forest model for predicting the occurrence of sinkholes caused by damaged sewer pipes based on sewage pipe information was trained using the information on the sewage pipe and the locations of the sinkhole occurrence case in Seoul. The random forest model showed excellent performance in the prediction of sinkhole occurrence after the optimization of its hyperparameters. In addition, it was confirmed that the sewage pipe length, elevation above sea level, slope, depth of landfill, and the risk of ground subsidence were affected in the order of sewage pipe information used as input variables. The results of this study are expected to be used as basic data for the preparation of a sinkhole susceptibility map and the establishment of an underground cavity exploration plan and a sewage pipe maintenance plan.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.4
• /
• pp.161-167
• /
• 2019

Recently, demand forecasting techniques have been actively studied due to interest in stable power supply with surging power demand, and increase in spread of smart meters that enable real-time power measurement. In this study, we proceeded the deep learning prediction model experiments which learns actual measured power usage data of home and outputs the forecasting result. And we proceeded pre-processing with moving average method. The predicted value made by the model is evaluated with the actual measured data. Through this forecasting, it is possible to lower the power supply reserve ratio and reduce the waste of the unused power. In this paper, we conducted experiments on three types of networks: Multi Layer Perceptron (MLP), Recurrent Neural Network (RNN), and Long Short Term Memory (LSTM) and we evaluate the results of each scheme. Evaluation is conducted with following method: MSE(Mean Squared Error) method and MAE(Mean Absolute Error).