• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.528-530
• /
• 2022

심층강화학습에 완전 연결 신경망과 합성곱 신경망은 잘 활용되는 것에 반해 순환 신경망은 잘 활용되지 않는다. 이는 강화학습이 마르코프 속성을 전제로 하기 때문이다. 지금까지의 강화학습은 환경이 마르코프 속성을 만족하도록 사전 작업이 필요했다, 본 논문에서는 마르코프 속성을 따르지 않는 환경에서 이러한 사전 작업 없이도 순환 신경망의 은닉 상태를 통해 마르코프 속성을 학습함으로써 학습 성능을 개선할 수 있다는 것을 소개한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.550-551
• /
• 2021

Positioning technology is performing important functions in augmented reality, smart factory, and autonomous driving. Among the positioning techniques, the positioning method using beacons has been considered a challenging task due to the deviation of the RSSI value. In this study, the position of a moving object is predicted by training a neural network that takes the RSSI value of the receiver as an input and the distance as the target value. To do this, the measured distance versus RSSI was collected.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.555-558
• /
• 2020

본 논문에서는 입력 영상에 담긴 다양한 물체들과 그들 간의 관계를 효과적으로 탐지하여, 하나의 장면 그래프로 표현해내는 새로운 심층 신경망 모델을 제안한다. 제안 모델에서는 물체와 관계의 효과적인 탐지를 위해, 합성 곱 신경망 기반의 시각 맥락 특징들뿐만 아니라 언어 맥락 특징들을 포함하는 다양한 멀티 모달 맥락 정보들을 활용한다. 또한, 제안 모델에서는 관계를 맺는 두 물체 간의 상호 의존성이 그래프 노드 특징값들에 충분히 반영되도록, 그래프 신경망을 이용해 맥락 정보를 임베딩한다. 본 논문에서는 Visual Genome 벤치마크 데이터 집합을 이용한 비교 실험들을 통해, 제안 모델의 효과와 성능을 입증한다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.6
• /
• pp.435-444
• /
• 2019

Recently, DL (Deep Learning) has been rapidly applied in various fields. In particular, classification and object recognition from images are major tasks in computer vision. Most of the DL utilizing imagery is primarily based on the CNN (Convolutional Neural Network) and improving performance of the DL model is main issue. While most CNNs are involve with images for training data, this paper aims to classify and recognize objects using DSM (Digital Surface Model), and slope and aspect information derived from the DSM instead of images. The DSM data sets used in the experiment were established by DGPF (German Society for Photogrammetry, Remote Sensing and Geoinformatics) and provided by ISPRS (International Society for Photogrammetry and Remote Sensing). The CNN-based SegNet model, that is evaluated as having excellent efficiency and performance, was used to train the data sets. In addition, this paper proposed a scheme for training data generation efficiently from the limited number of data. The results demonstrated DSM and derived data could be feasible for semantic classification with desirable accuracy using DL.

• Journal of Internet Computing and Services
• /
• v.19 no.5
• /
• pp.33-41
• /
• 2018

Recently, Internet technology has developed, various programs are being created and therefore various codes are being made through many authors. On this aspect, some author deceive a program or code written by other particular author as they make it themselves and use other writers' code indiscriminately, or not indicating the exact code which has been used. Due to this makes it more and more difficult to protect the code. In this paper, we propose author identification framework using Authorship Analysis theory and Natural Language Processing(NLP) based on Convolutional Neural Network(CNN). We apply Authorship Analysis theory to extract features for author identification in the source code, and combine them with the features being used text mining to perform author identification using machine learning. In addition, applying CNN based natural language processing method to source code for code author classification. Therefore, we propose a framework for the identification of authors using the Authorship Analysis theory and the CNN. In order to identify the author, we need special features for identifying the authors only, and the NLP method based on the CNN is able to apply language with a special system such as source code and identify the author. identification accuracy based on Authorship Analysis theory is 95.1% and identification accuracy applied to CNN is 98%.

• Journal of the Institute of Convergence Signal Processing
• /
• v.21 no.3
• /
• pp.148-153
• /
• 2020

In order to obtain high accuracy with an convolutional neural network(CNN), it is necessary to set the optimal hyperparameters. However, the exact value of the hyperparameter that can make high performance is not known, and the optimal hyperparameter value is different based on the type of the dataset, therefore, it is necessary to find it through various experiments. In addition, since the range of hyperparameter values is wide and the number of combinations is large, it is necessary to find the optimal values of the hyperparameters after the experimental design in order to save time and computational costs. In this paper, we suggest an algorithm that use the design of experiments and grid search algorithm to determine the optimal hyperparameters for a classification problem. This algorithm determines the optima values of the hyperparameters that yields high performance using the factorial design of experiments. It is shown that the amount of computational time can be efficiently reduced and the accuracy can be improved by performing a grid search after reducing the search range of each hyperparameter through the experimental design. Moreover, Based on the experimental results, it was shown that the learning rate is the only hyperparameter that has the greatest effect on the performance of the model.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.2
• /
• pp.276-284
• /
• 2020

This paper proposes a new convolutional neural network (CNN) based spectrum sensing technique for cognitive radio communications. The proposed technique determines the existence of the primary user (PU) by using energy detection without any prior knowledge of the PU's signal. In the proposed method, the received signal is high-rate sampled to sense the entire spectrum bands of interest. After that, fast Fourier transform (FFT) of the signal converts the time domain signal to frequency domain spectrum and by stacking those consecutive spectrums, a 2 dimensional signal is made. The 2 dimensional signal is cut by the sensing channel bandwidth and inputted to the CNN. The CNN determines the existence of the primary user. Since there are only two states (existence or non-existence), binary classification CNN is used. The performance of the proposed method is examined through computer simulation and indoor experiment. According to the results, the proposed method outperforms the conventional threshold-based method by over 2 dB.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.4
• /
• pp.221-232
• /
• 2023

This paper presents a novel convolutional neural network (CNN)-based approach for predicting bolt clamping force in the early bolt loosening state of bolted structures. The approach entails tightening eight bolts with different clamping forces and generating frequency responses, which are then used to create a similarity map. This map quantifies the magnitude and shape similarity between the frequency responses and the initial model in a fully fastened state. Krylov subspace-based model order reduction is employed to efficiently handle the large amount of frequency response data. The CNN model incorporates a regression output layer to predict the clamping forces of the bolts. Its performance is evaluated by training the network by using various amounts of training data and convolutional layers. The input data for the model are derived from the magnitude and shape similarity map obtained from the frequency responses. The results demonstrate the diagnostic potential and effectiveness of the proposed approach in detecting early bolt loosening. Accurate bolt clamping force predictions in the early loosening state can thus be achieved by utilizing the frequency response data and CNN model. The findings afford valuable insights into the application of CNNs for assessing the integrity of bolted structures.

• The Journal of the Convergence on Culture Technology
• /
• v.3 no.4
• /
• pp.171-175
• /
• 2017

Recently, Training of the convolutional neural network (CNN) entails many iterative computations. Therefore, a method of accelerating the training speed through parallel processing using the hardware specifications of GPGPU is actively researched. In this paper, the operations of the feature extraction unit and the classification unit are divided into blocks and threads of GPGPU and processed in parallel. Convolution and Pooling operations of the feature extraction unit are processed in parallel at once without sequentially processing. As a result, proposed method improved the training time about 314%.

• Journal of Broadcast Engineering
• /
• v.24 no.6
• /
• pp.1113-1121
• /
• 2019

In this paper, we propose the face anti-spoofing method based on combination of luminance and chrominance with convolutional neural networks. The proposed method extracts luminance and chrominance features independently from live and fake faces by using stacked convolutional neural networks and auxiliary networks. Unlike previous methods, an attention module has been adopted to adaptively combine extracted features instead of simply concatenating them. In addition, we propose a new loss function, called the contrast loss, to learn the classifier more efficiently. Specifically, the contrast loss improves the discriminative power of the features by maximizing the distance of the inter-class features while minimizing that of the intra-class features. Experimental results demonstrate that our method achieves the significant improvement for face anti-spoofing compared to existing methods.