• Journal of Korea Multimedia Society
• /
• v.22 no.1
• /
• pp.44-54
• /
• 2019

Recently, image-based object detection has made great progress with the introduction of Convolutional Neural Network (CNN). Many trials such as Region-based CNN, Fast R-CNN, and Faster R-CNN, have been proposed for achieving better performance in object detection. YOLO has showed the best performance under consideration of both accuracy and computational complexity. However, these data-driven detection methods including YOLO have the fundamental problem is that they can not guarantee the good performance without a large number of training database. In this paper, we propose a data sampling method using CycleGAN to solve this problem, which can convert styles while retaining the characteristics of a given input image. We will generate the insufficient data samples for training more robust object detection without efforts of collecting more database. We make extensive experimental results using the day-time and night-time road images and we validate the proposed method can improve the object detection accuracy of the night-time without training night-time object databases, because we converts the day-time training images into the synthesized night-time images and we train the detection model with the real day-time images and the synthesized night-time images.

• Journal of the Korea Convergence Society
• /
• v.10 no.4
• /
• pp.17-23
• /
• 2019

In this paper, quality control (QC) is applied to each meteorological element of weather data collected from seven IoT sensors such as temperature. In addition, we propose a method for estimating the data regarded as error by means of machine learning. The collected meteorological data was linearly interpolated based on the basic QC results, and then machine learning-based QC was performed. Support vector regression, decision table, and multilayer perceptron were used as machine learning techniques. We confirmed that the mean absolute error (MAE) of the machine learning models through the basic QC is 21% lower than that of models without basic QC. In addition, when the support vector regression model was compared with other machine learning methods, it was found that the MAE is 24% lower than that of the multilayer neural network and 58% lower than that of the decision table on average.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.4
• /
• pp.163-170
• /
• 2019

Korea language has postpositions such as eul, reul, yi, ga, wa, and gwa, which are attached to nouns and add meaning to the sentence. When foreign notations or abbreviations are included in sentences, the appropriate postposition for the pronunciation of the foreign words may not be used. Sometimes, for natural expression of the sentence, two postpositions are used with one in parentheses as in "eul(reul)" so that both postpositions can be acceptable. This study finds examples of using unnatural postpositions when foreign words are included in Korean sentences and proposes a method for using natural postpositions by learning the final consonant pronunciation of nouns. The proposed method uses a recurrent neural network model to naturally express postpositions connected to foreign words. Furthermore, the proposed method is proven by learning and testing with the proposed method. It will be useful for composing perfect sentences for machine translation by using natural postpositions for English abbreviations or new foreign words included in Korean sentences in the future.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.20-20
• /
• 2017

최근 기후변화 영향에 따라 전 세계적으로 인명피해 및 재산피해를 유발하는 자연재난이 지속적으로 증가하고 있으며, 그로 인한 자연재해의 규모가 점점 더 커지고 있다. 실제로 우리나라에서도 지난 1994 년에서 2013 년까지 지난 20 년간 자연재해에 의한 피해액은 12조 3천억 원으로 집계되었으며, 이 중 강우와 태풍에 의한 피해가 85 % 이고, 대설에 의한 피해는 약 13 % 로 자연재해 중 대부분의 피해는 강우 및 태풍에서 발생하지만, 폭설에 의한 피해도 적지 않은 것으로 나타났다. 이에 따라, 정확한 예측을 위해 신뢰도 높은 자료 구축을 통한 대설피해 예측에 관한 연구가 필요한 시점이다. 본 연구에서는 대설피해액 예측을 위해 우리나라의 63개 기상 관측소에서 관측한 적설심 자료 및 기상관측 자료와 사회 경제 자료 총 11개를 대설피해 예측을 위한 입력변수로 선정하고, 이를 기상관측소가 속한 도시의 면적에 따라 3개의 지역으로 구분하였다. 주성분분석을 활용하여 선정된 입력변수들을 4개의 주성분으로 구분하고, 인공신경망 및 다중선형 회귀 모형을 구성하여 각 지역별 대설피해 예측의 오차를 분석하였다. 적용결과, 인공신경망 모형을 이용한 대설피해 예측의 수정결정계수는 22.8 %~48.2 %를 나타냈고, 다중선형회귀 모형의 수정결정 계수는 9.2 %~39.7% 로 나타났다. 그러므로 인공신경망 모형이 다중회귀 모형보다 선택된 입력자료를 활용하여 대설피해를 예측하는 목적으로 조금 더 우수한 결과를 나타내었다. 향후 자료를 보완 및 모형의 고도화를 통해 보다 정확한 대설피해 예측 함수 개발이 가능할 것으로 기대된다.

• Journal of dental hygiene science
• /
• v.20 no.4
• /
• pp.206-212
• /
• 2020

Background: A Teachable Machine is a kind of machine learning web-based tool for general persons. In this paper, the feasibility of Google's Teachable Machine (ver. 2.0) was studied in the diagnosis of the tooth-marked tongue. Methods: For machine learning of tooth-marked tongue diagnosis, a total of 1,250 tongue images were used on Kaggle's web site. Ninety percent of the images were used for the training data set, and the remaining 10% were used for the test data set. Using Google's Teachable Machine (ver. 2.0), machine learning was performed using separated images. To optimize the machine learning parameters, I measured the diagnosis accuracies according to the value of epoch, batch size, and learning rate. After hyper-parameter tuning, the ROC (receiver operating characteristic) analysis method determined the sensitivity (true positive rate, TPR) and specificity (false positive rate, FPR) of the machine learning model to diagnose the tooth-marked tongue. Results: To evaluate the usefulness of the Teachable Machine in clinical application, I used 634 tooth-marked tongue images and 491 no-marked tongue images for machine learning. When the epoch, batch size, and learning rate as hyper-parameters were 75, 0.0001, and 128, respectively, the accuracy of the tooth-marked tongue's diagnosis was best. The accuracies for the tooth-marked tongue and the no-marked tongue were 92.1% and 72.6%, respectively. And, the sensitivity (TPR) and specificity (FPR) were 0.92 and 0.28, respectively. Conclusion: These results are more accurate than Li's experimental results calculated with convolution neural network. Google's Teachable Machines show good performance by hyper-parameters tuning in the diagnosis of the tooth-marked tongue. We confirmed that the tool is useful for several clinical applications.

• Journal of Platform Technology
• /
• v.8 no.1
• /
• pp.16-23
• /
• 2020

For protecting copyright for trademark, convolutional neural network can be used to confirm genuine of trademark image. For this, repeated training one trademark image degrades the performance of machine learning because of overfitting problem. Therefore, this type of machine learning application generates training data in various way. But if genuine trademark image is rotated, this image is classified as not genuine trademark. In this paper, we propose the way for extending training data to confirm genuine of trademark image which is rotated. Our proposed way generates rotated image from genuine trademark image as training data. To show effectiveness of our proposed way, we use CNN machine learning model, and evaluate the accuracy with test image. From evaluation result, our way can be used to generate training data for machine learning application which confirms genuine of rotated trademark image.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.32 no.1
• /
• pp.133-150
• /
• 2021

The purpose of this study is to identify the applicability of machine learning targeting titles in the classification of books in public libraries. Data analysis was performed using Python's scikit-learn library through the Jupiter notebook of the Anaconda platform. KoNLPy analyzer and Okt class were used for Hangul morpheme analysis. The units of analysis were 2,000 title fields and KDC classification class numbers (300 and 600) extracted from the KORMARC records of public libraries. As a result of analyzing the data using six machine learning models, it showed a possibility of applying machine learning to book classification. Among the models used, the neural network model has the highest accuracy of title classification. The study suggested the need for improving the accuracy of title classification, the need for research on book titles, tokenization of titles, and stop words.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.2
• /
• pp.115-123
• /
• 2021

A lot of sensor and control signals is generated by an industrial controller and related internet-of-things in discrete manufacturing system. The acquired signals are such records indicating whether several process operations have been correctly conducted or not in the system, therefore they are usually composed of binary numbers. For example, once a certain sensor turns on, the corresponding value is changed from 0 to 1, and it means the process is finished the previous operation and ready to conduct next operation. If an actuator starts to move, the corresponding value is changed from 0 to 1 and it indicates the corresponding operation is been conducting. Because traditional fault detection approaches are generally conducted with analog sensor signals and the signals show stationary during normal operation states, it is not simple to identify whether the manufacturing process works properly via conventional fault detection methods. However, digital control signals collected from a programmable logic controller continuously vary during normal process operation in order to show inherent sequence information which indicates the conducting operation tasks. Therefore, in this research, it is proposed to a recurrent neural network-based fault detection approach for considering sequential patterns in normal states of the manufacturing process. Using the constructed long short-term memory based fault detection, it is possible to predict the next control signals and detect faulty states by compared the predicted and real control signals in real-time. We validated and verified the proposed fault detection methods using digital control signals which are collected from a laser marking process, and the method provide good detection performance only using binary values.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.9
• /
• pp.1202-1208
• /
• 2020

In line with the current era of the 4th Industrial Revolution, it is necessary to prepare for the future by integrating AI elements in the ship sector. In addition, it is necessary to respond to this in the field of power management for the appearance of autonomous ships. In this study, we propose a battery-linked electric propulsion system (BLEPS) algorithm using machine learning's DNN. For the experiment, we learned the pattern of ship power consumption for each operation mode based on the ship data through LabView and derived the battery status through Python to check the flexibility of the generator and battery interlocking. As a result of the experiment, the low load operation of the generator was reduced through charging and discharging of the battery, and economic efficiency and reliability were confirmed by reducing the fuel consumption of 1% of LNG.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.1
• /
• pp.22-27
• /
• 2020

Recently, as the number of households raising pets increases due to the increase of single households, there is a need for a system for monitoring the status or behavior of pets. There are regional limitations in the monitoring of pets using domestic CCTVs, which requires a large number of CCTVs or restricts the behavior of pets. In this paper, we propose a mobile system for detecting and tracking cats using deep learning to solve the regional limitations of pet monitoring. We use YOLO (You Look Only Once), an object detection neural network model, to learn the characteristics of pets and apply them to Raspberry Pi to track objects detected in an image. We have designed a mobile monitoring system that connects Raspberry Pi and a laptop via wireless LAN and can check the movement and condition of cats in real time.