• Korean Journal of Artificial Intelligence
• /
• v.5 no.2
• /
• pp.15-25
• /
• 2017

Recently, technologies are being developed to recognize and authenticate users using bioinformatics to solve information security issues. Biometric information includes face, fingerprint, iris, voice, and vein. Among them, face recognition technology occupies a large part. Face recognition technology is applied in various fields. For example, it can be used for identity verification, such as a personal identification card, passport, credit card, security system, and personnel data. In addition, it can be used for security, including crime suspect search, unsafe zone monitoring, vehicle tracking crime.In this thesis, we conducted a study to recognize faces by detecting the areas of the face through a computer webcam. The purpose of this study was to contribute to the improvement in the accuracy of Recognition of Face Based on CNN Algorithms. For this purpose, We used data files provided by github to build a face recognition model. We also created data using CNN algorithms, which are widely used for image recognition. Various photos were learned by CNN algorithm. The study found that the accuracy of face recognition based on CNN algorithms was 77%. Based on the results of the study, We carried out recognition of the face according to the distance. Research findings may be useful if face recognition is required in a variety of situations. Research based on this study is also expected to improve the accuracy of face recognition.

• International Journal of Advanced Culture Technology
• /
• v.5 no.2
• /
• pp.82-89
• /
• 2017

The range of problems that can be handled by the activation of big data and the development of hardware has been rapidly expanded and machine learning such as deep learning has become a very versatile technology. In this paper, mnist data set is used as experimental data, and the Cross Entropy function is used as a loss model for evaluating the efficiency of machine learning, and the value of the loss function in the steepest descent method is We applied the GradientDescentOptimize algorithm to minimize and updated weight and bias via backpropagation. In this way we analyze optimal reliability value corresponding to the number of exercises and optimal reliability value without overfitting. And comparing the overfitting time according to the number of data changes based on the number of training times, when the training frequency was 1110 times, we obtained the result of 92%, which is the optimal reliability value without overfitting.

• ETRI Journal
• /
• v.41 no.6
• /
• pp.760-770
• /
• 2019

Based on the growing demand for neural network technologies, various neural network inference engines are being developed. However, each inference engine has its own neural network storage format. There is a growing demand for standardization to solve this problem. This study presents interworking techniques for ensuring the compatibility of neural networks and data among the various deep learning frameworks. The proposed technique standardizes the graphic expression grammar and learning data storage format using the Neural Network Exchange Format (NNEF) of Khronos. The proposed converter includes a lexical, syntax, and parser. This NNEF parser converts neural network information into a parsing tree and quantizes data. To validate the proposed system, we verified that MNIST is immediately executed by importing AlexNet's neural network and learned data. Therefore, this study contributes an efficient design technique for a converter that can execute a neural network and learned data in various frameworks regardless of the storage format of each framework.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.2
• /
• pp.63-70
• /
• 2018

Safety management agent manages the risk behavior of the worker with the naked eye, but there is a real difficulty for one the agent to manage all the workers. In this paper, IoT device is attached to a harness safety belt that a worker wears to solve this problem, and behavior data is upload to the cloud in real time. We analyze the upload data through the deep learning and analyze the risk behavior of the worker. When the analysis result is judged to be dangerous behavior, we designed and implemented a system that informs the manager through monitoring application. In order to confirm that the risk behavior analysis through the deep learning is normally performed, the data values of 4 behaviors (walking, running, standing and sitting) were collected from IMU sensor for 60 minutes and learned through Tensorflow, Inception model. In order to verify the accuracy of the proposed system, we conducted inference experiments five times for each of the four behaviors, and confirmed the accuracy of the inference result to be 96.0%.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.147-147
• /
• 2018

In this article, we use an open source software library: TensorFlow, developed for the purposes of conducting very complex machine learning and deep neural network applications. However, the system is general enough to be applicable in a wide variety of other domains as well. The proposed model based on a deep neural network model, LSTM (Long Short-Term Memory) to predict the river water level at Okcheon Station of the Guem River without utilization of rainfall - forecast information. For LSTM modeling, the input data is hourly water level data for 15 years from 2002 to 2016 at 4 stations includes 3 upstream stations (Sutong, Hotan, and Songcheon) and the forecasting-target station (Okcheon). The data are subdivided into three purposes: a training data set, a testing data set and a validation data set. The model was formulated to predict Okcheon Station water level for many cases from 3 hours to 12 hours of lead time. Although the model does not require many input data such as climate, geography, land-use for rainfall-runoff simulation, the prediction is very stable and reliable up to 9 hours of lead time with the Nash - Sutcliffe efficiency (NSE) is higher than 0.90 and the root mean square error (RMSE) is lower than 12cm. The result indicated that the method is able to produce the river water level time series and be applicable to the practical flood forecasting instead of hydrologic modeling approaches.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.1
• /
• pp.117-125
• /
• 2019

Deep Learning, which is being used in various fields recently, is being threatened with Adversarial Attack. In this paper, we experimentally verify that the classification accuracy is lowered by adversarial samples generated by malicious attackers in image classification models. We used MNIST dataset and measured the detection accuracy by injecting adversarial samples into the Autoencoder classification model and the CNN (Convolution neural network) classification model, which are created using the Tensorflow library and the Pytorch library. Adversarial samples were generated by transforming MNIST test dataset with JSMA(Jacobian-based Saliency Map Attack) and FGSM(Fast Gradient Sign Method). When injected into the classification model, detection accuracy decreased by at least 21.82% up to 39.08%.

• Journal of Biomedical Engineering Research
• /
• v.43 no.3
• /
• pp.131-135
• /
• 2022

Due to COVID-19, Correct method of wearing mask is important to prevent COVID-19 and the other respiratory tract infections. And the deep learning technology in the image processing has been developed. The purpose of this study is to create the type of mask wearing dataset for deep learning models and select the deep learning model to detect the wearing mask correctly. The Image dataset is the 2,296 images acquired using a web crawler. Deep learning classification models provided by tensorflow are used to validate the dataset. And Object detection deep learning model YOLOs are used to select the detection deep learning model to detect the wearing mask correctly. In this process, this paper proposes to validate the type of mask wearing datasets and YOLOv5 is the effective model to detect the type of mask wearing. The experimental results show that reliable dataset is acquired and the YOLOv5 model effectively recognize type of mask wearing.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.328-328
• /
• 2021

최근 전 지구적인 기후변화의 영향은 강우량의 집중을 야기하며 홍수피해의 규모를 증가시키는 영향을 끼친다. 특히, 아세안 국가들은 해수면 상승, 태풍 및 집중호우에 의한 침수피해 빈발로 최소 2,000만명이 영향을 받고 있다. 국내의 홍수예보모형을 수출하여 아세안 국가에 구축하고 있으나 통신 시설이 불안정하여 중앙제어 방식의 기존의 홍수예보시스템만으로는 긴급상황에 대한 대처가 부족할 수 있다. 따라서 본 연구에서는 하나의 관측소에서 수위, 강우의 관측과 홍수예측, 경보까지 한번에 가능한 관측소를 개발하기 위해 관측된 수위와 강우자료를 활용하여 인공지능기반의 하천수위예측 모형을 개발하였다. 목표 리드타임은 30분에서 6시간으로 설정하였으며 모형은 Tensorflow로 구축하였다. 시계열 자료의 예측에 적합한 LSTM 기법을 적용하였다. 연구의 대상지역은 건설연의 계측시험유역인 설마천유역으로 하였으며 학습에는 2009년부터 2020년까지의 10분 단위 수위 및 강우량자료를 활용하였다. 연구결과 설마천 유역은 규모가 작고 도달시간이 짧아 1시간 후 예측까지는 높은 정확도를 나타냈으나 3시간 이상의 예측결과는 다소 낮게 평가되었다. 다만, 비상상황에서 통신이 두절된 상황에서 위급하게 대피를 위해 홍수경보를 발령하는데는 활용이 가능 할 것으로 판단된다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.349-349
• /
• 2021

일반적인 도시홍수모형은 수리-수문모형을 기반으로 한 홍수위 모형을 사용하고 있으나 강우사상이나 물리적 조건에 따라 모의시간의 변화가 있으며 경우에 따라서는 긴 모의시간이 소요된다. 알파고 이후 큰 관심을 갖게된 딥러닝을 이용한 데이터기반의 모의를 통해 수자원 부분에 적용하여 수위 예측을 진행하였다. 본 연구에서는 딥러닝을 이용하여 관측자료기반의 수위예측 연구를 수행하였다. 대상유역은 중랑천 유역으로 선정하였으며 2015년 ~ 2020년 사이의 10분단위 강우, 수위자료를 이용하였다. 지방자치단체에서 제공하는 강우, 수위자료의 경우 결측자료 또는 이상자료에 대한 보정이 미흡하여 기계학습을 통합 분석자료로 활용하는데 어려움이 있다. 이에, 결측 및 이상자료가 포함된 자료로부터 인위적으로 교란된 데이터 및 결측구간을 삭제한 데이터를 생성하여 자료의 시계열성을 제거하고, 딥러닝을 통한 수위 예측 결과를 정상 데이터를 적용한 결과와 비교하였다. 사용된 딥러닝 모형은 시계열 데이터 예측에 우수한성능을 보이는 LSTM모형과 GRU모형을 이용하였으며 RMSE, NSE를 이용하여 평가하였다. 본 연구에서는 결측자료 및 이상자료가 포함된 수문자료를 자료의 시계열성 제거를 통해 딥러닝 분석 입력자료 구성하기 위한 방안을 제시하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.391-393
• /
• 2021

In this paper, we introduce a long short-term memory (LSTM)-based fall detection system using TensorFlow that can detect falls occurring in the elderly in daily living. 3-axis accelerometer data are aggregated for fall detection, and then three types of parameter are calculated. 4 types of activity of daily living (ADL) and 3 types of fall situation patterns are classified. The parameterized data applied to LSTM. Learning proceeds until the Loss value becomes 0.5 or less. The results are calculated for each parameter θ, SVM, and GSVM. The best result was GSVM, which showed Sensitivity 98.75%, Specificity 99.68%, and Accuracy 99.28%.