• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.516-518
• /
• 2022

In this paper, we introduce a dependence of number of nodes of hidden-layer in fall detection system using Long Short-Term Memory that can detect falls. Its training is carried out using the parameter theta(θ), which indicates the angle formed by the x, y, and z-axis data for the direction of gravity using a 3-axis acceleration sensor. In its learning, validation is performed and divided into training data and test data in a ratio of 8:2, and training is performed by changing the number of nodes in the hidden layer to increase efficiency. When the number of nodes is 128, the best accuracy is shown with Accuracy = 99.82%, Specificity = 99.58%, and Sensitivity = 100%.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.481-483
• /
• 2023

본 논문에서는 다중 카메라환경에서의 안면인식 기반 영유아 활동 사진 자동 생성 시스템을 개발했다. 개발한 시스템은 어린이집에서 알림장 작성을 위한 촬영하는 동안 보육에 부주의하여 안전사고가 발생하는 것을 방지 할 수 있다. 시스템은 이동식 수집기와 분류 서버로 나뉘어 작동하게 된다. 이동식 수집기는 Raspberry Pi를 이용하였고 초당 1장 내외의 사진을 촬영하여 SAMBA를 사용 공유폴더에 저장한다. 분류 서버에서는 YOLOv5를 사용해 안면을 인식해 분류한다. OpenCV와 TensorFlow-Keras를 통해 분류된 사진에서의 표정을 파악하여 부모에게 전송할 웃는사진만을 분류하여 남겨둔다. 이외의 사진은 /dev/null로 이동하여 삭제된다.

• Journal of Digital Convergence
• /
• v.16 no.5
• /
• pp.221-229
• /
• 2018

Machine learning and artificial intelligence are core technologies for the 4th industrial revolution. However, it is difficult for the general public to get familiar with those technologies because most people lack programming ability. Thus, we developed a Graphic User Interface(GUI) to overcome this obstacle. We adopted TensorFlow and used .Net of Microsoft for the develop. With this new GUI, users can manage data, apply algorithms, and run machine learning without coding ability. We hope that this development will be used as a basis for developing artificial intelligence in various fields.

• The Journal of the Korea Contents Association
• /
• v.20 no.6
• /
• pp.695-704
• /
• 2020

Recently, There has been an increasing of utilization IT, and studies have been conducted on predicting learning results. In this study, Learning activity data were collected that could affect learning outcomes by using learning analysis. The survey was conducted at a university in South Chung-Cheong Province from October to December 2018, with 1,062 students taking part in the survey. First, A Hierarchical regression analysis was conducted by organizing a model of individual, academic, and behavioral factors for learning results to ensure the validity of predictors in machine learning. The model of hierarchical regression was significant, and the explanatory power (R²) was shown to increase step by step, so the variables injected were appropriate. In addition, The linear regression analysis method of machine learning was used to determine how predictable learning outcomes are, and its error rate was collected at about 8.4%.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2017.04a
• /
• pp.166-166
• /
• 2017

모돈의 건강 상태를 정량 지수화 하기 위한 연구를 수행 중이다. 지제이상, 섭식 불량, 수면 패턴 등의 운동 특성 분석을 위하여 복수의 초음파 센서를 이용하였다. 시계열 계측 신호를 분석하여 정량 지수화를 수행하는 과정에서 주파수 도메인 분석을 시도하였다. 이 과정에서 주파수 도메인의 분해능에 따른 편차 극복을 위한 비선형 모델링을 수행하였다. 또한 인접한 시계열 데이터 구간 간의 상관성 분석이 가능하면 대용량 데이터의 실시간 처리로 인한 지연 시간 극복 및 기대되는 예후에 대한 조기 진단이 가능할 것이다. 본 연구에서는 구글에서 제공하는 Tensorflow와 NVIDIA에서 제공하는 CUDA 엔진을 동시 적용한 심층 학습 시스템을 이용하였다. 전 처리를 위하여 주파수 분해능 (2분, 3분, 5분, 7분, 11분, 13분, 17분, 19분)에 따른 데이터 집합을 1단계로 두고, 상위 10 순위 안에 드는 파워 스펙트럼 밀도의 크기를 2단계로 하여, 총 2~10개의 입력 노드를 순차적으로 선정하였고, 동일한 방식으로 인접한 시계열의 파워 스펙터럼 밀도를 순위를 변화시켜 지정하였다. 대표적인 심층학습 모델인 Softmax regression with a multilayer convolutional network를 이용하여 Recursive feature selection 경우의 수를 $8{\times}9{\times}9$로 총 648 가지 선정하고, Epoch는 10,000회로 지정하였다. Calibration 모델링의 경우 Cost function이 10% 이하인 경우 해당 경우의 학습을 중단하였으며, 모델 간 상호 교차 검증을 수행하기 위하여 $_8C_2{\times}_8C_2{\times}_8C_2$ 경우의 수에 대한 Verification test를 수행하였다. Calibration 과정 상 모든 경우에 대하여 10% 이하의 Cost function 값을 보였으나, 검증 테스트 과정에서 모든 경우에 대하여 $r^2$ < 0.5 인 결정 계수 값이 나타났다. 단적으로 심층학습 모델의 과도한 적합(Over fitting) 방식의 한계를 보인 것이라 판단할 수 있다. 적합한 Feature selection 및 심층 학습 모델에 대한 지속적이고 추가적인 고려를 통해 과도적합을 해소함과 동시에 실효적이고 활용 가능한 Classification을 위한 입, 출력 노드 단의 전후 Indexing, Quantization에 대한 고려가 필요할 것이다. 이를 통해 모돈 생체 정보 정량화를 위한 지능형 현장 진단 기술 연구를 지속할 것이다.

• Korean Journal of Remote Sensing
• /
• v.33 no.4
• /
• pp.423-436
• /
• 2017

This paper presents a deep learning-based road segmentation framework from very high-resolution orthophotos. The proposed method uses Deep Convolutional Autoencoders for end-to-end mapping of orthophotos to road segmentations. In addition, a set of post-processing steps were applied to make the model outputs GIS-ready data that could be useful for various applications. The optimization of the model's parameters is explained which was conducted via grid search method. The model was trained and implemented in Keras, a high-level deep learning framework run on top of Tensorflow. The results show that the proposed model with the best-obtained hyperparameters could segment road objects from orthophotos at an average accuracy of 88.5%. The results of optimization revealed that the best optimization algorithm and activation function for the studied task are Stochastic Gradient Descent (SGD) and Exponential Linear Unit (ELU), respectively. In addition, the best numbers of convolutional filters were found to be 8 for the first and second layers and 128 for the third and fourth layers of the proposed network architecture. Moreover, the analysis on the time complexity of the model showed that the model could be trained in 4 hours and 50 minutes on 1024 high-resolution images of size $106{\times}106pixels$, and segment road objects from similar size and resolution images in around 14 minutes. The results show that the deep learning models such as Convolutional Autoencoders could be a best alternative to traditional machine learning models for road segmentation from aerial photographs.

• International Journal of Highway Engineering
• /
• v.20 no.2
• /
• pp.57-65
• /
• 2018

PURPOSES : The study aims to predict the service life of national highway asphalt pavements through deep learning methods by using maintenance history data of the National Highway Pavement Management System. METHODS : For the configuration of a deep learning network, this study used Tensorflow 1.5, an open source program which has excellent usability among deep learning frameworks. For the analysis, nine variables of cumulative annual average daily traffic, cumulative equivalent single axle loads, maintenance layer, surface, base, subbase, anti-frost layer, structural number of pavement, and region were selected as input data, while service life was chosen to construct the input layer and output layers as output data. Additionally, for scenario analysis, in this study, a model was formed with four different numbers of 1, 2, 4, and 8 hidden layers and a simulation analysis was performed according to the applicability of the over fitting resolution algorithm. RESULTS : The results of the analysis have shown that regardless of the number of hidden layers, when an over fitting resolution algorithm, such as dropout, is applied, the prediction capability is improved as the coefficient of determination ($R^2$) of the test data increases. Furthermore, the result of the sensitivity analysis of the applicability of region variables demonstrates that estimating service life requires sufficient consideration of regional characteristics as $R^2$ had a maximum of between 0.73 and 0.84, when regional variables where taken into consideration. CONCLUSIONS : As a result, this study proposes that it is possible to precisely predict the service life of national highway pavement sections with the consideration of traffic, pavement thickness, and regional factors and concludes that the use of the prediction of service life is fundamental data in decision making within pavement management systems.

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.1
• /
• pp.9-16
• /
• 2020

The k-anonymity scheme has been widely used to protect private information when Big Data are distributed to a third party for research purposes. When the scheme is applied, an optimal k value determination is one of difficult problems to be resolved because many factors should be considered. Currently, the determination has been done almost manually by human experts with their intuition. This leads to degrade performance of the anonymization, and it takes much time and cost for them to do a task. To overcome this problem, a simple idea has been proposed that is based on machine learning. This paper describes implementations and experiments to realize the proposed idea. In thi work, a deep neural network (DNN) is implemented using tensorflow libraries, and it is trained and tested using input dataset. The experiment results show that a trend of training errors follows a typical pattern in DNN, but for validation errors, our model represents a different pattern from one shown in typical training process. The advantage of the proposed approach is that it can reduce time and cost for experts to determine k value because it can be done semi-automatically.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.10
• /
• pp.323-328
• /
• 2020

Recently, new approaches that significantly improve performance in object detection and recognition using deep learning technology have been proposed quickly. Of the various techniques for object detection, especially facial object detection (Faster R-CNN, R-CNN, YOLO, SSD, etc), SSD is superior in accuracy and speed to other techniques. At the same time, multiple object detection networks are also readily available. In this paper, among object detection networks, Mobilenet v2 network is used, models combined with SSDs are trained, and methods for detecting objects at a rate of four times or more than conventional performance are proposed using TensorRT engine, and the performance is verified through experiments. Facial object detector was created as an application to verify the performance of the proposed method, and its behavior and performance were tested in various situations.

• Journal of radiological science and technology
• /
• v.43 no.2
• /
• pp.65-70
• /
• 2020

PA(postero-anterior) and AP(antero-posterior) chest projections are the most sought-after types of all kinds of projections. But if a radiological technologist puts wrong information about the position in the computer, the orientation of left and right side of an image would be reversed. In order to solve this problem, we utilized CNN(convolutional neural network) which has recently utilized a lot for studies of medical imaging technology and rule-based system. 70% of 111,622 chest images were used for training, 20% of them were used for testing and 10% of them were used for validation set in the CNN experiment. The same amount of images which were used for testing in the CNN experiment were used in rule-based system. Python 3.7 version and Tensorflow r1.14 were utilized for data environment. As a result, rule-based system had 66% accuracy on evaluating whether the orientation reversal on chest x-ray image. But the CNN had 97.9% accuracy on that. Being overcome limitations by CNN which had been shown on rule-based system and shown the high accuracy can be considered as a meaningful result. If some problems which can occur for tasks of the radiological technologist can be separated by utilizing CNN, It can contribute a lot to optimize workflow.