• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.133-135
• /
• 2020

최근 CNN(Convolutional Neural Network)은 영상 분류, 객체 인식 등 다양한 비전 분야에서 우수한 성능을 보여주고 있으나, CNN 모델의 계산량 및 메모리가 매우 커짐에 따라 모바일 또는 IoT(lnternet of Things) 장치와 같은 저전력 환경에 적용되기에는 제한이 따른다. 따라서, CNN 모델의 임무 성능을 유지하연서 네트워크 모델을 압축하는 기법들이 연구되고 있다. 본 논문에서는 행렬 분해 기술인 저계수행렬 근사(Low-rank approximation)와 CP(Canonical Polyadic) 분해 기법을 결합하여 CNN 모델을 압축하는 기법을 제안한다. 제안하는 기법은 계층의 유형에 상관없이 하나의 행렬분해 기법만을 적용하는 기존의 기법과 달리 압축 성능을 높이기 위하여 CNN의 계층 타입에 따라 두 가지 분해 기법을 선택적으로 적용한다. 제안기법의 성능검증을 위하여 영상 분류 CNN 모델인 VGG-16, ResNet50, 그리고 MobileNetV2 모델 압축에 적용하였고, 모델의 계층 유형에 따라 두 가지의 분해 기법을 선택적으로 적용함으로써 저계수행렬 근사 기법만 적용한 경우 보다 1.5~12.1 배의 동일한 압축율에서 분류 성능이 향상됨을 확인하였다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.155-161
• /
• 2024

In this paper, we propose a new model by adding landmark information as a feature vector to the existing CNN-based facial emotion classification model. Facial emotion classification research using CNN-based models is being studied in various ways, but the recognition rate is very low. In order to improve the CNN-based models, we propose algorithms that improves facial expression classification accuracy by combining the CNN model with a landmark-based fully connected network obtained by ASM. By including landmarks in the CNN model, the recognition rate was improved by several percent, and experiments confirmed that further improved results could be obtained by adding FACS-based action units to the landmarks.

• Journal of Software Engineering Society
• /
• v.29 no.1
• /
• pp.13-21
• /
• 2020

As CNN model is applied to various domains such as image classification and object detection, the performance of CNN model which is used to safety critical system like autonomous vehicles should be reliable. To evaluate that CNN model can sustain the performance in various environments, we developed an image data augmentation apparatus which generates images that is changed background. If an image which contains object is entered into the apparatus, it extracts an object image from the entered image and generate s composed images by synthesizing the object image with collected background images. A s a method to evaluate a CNN model, the apparatus generate s new test images from original test images, and we evaluate the CNN model by the new test image. As a case study, we generated new test images from Pascal VOC2007 and evaluated a YOLOv3 model with the new images. As a result, it was detected that mAP of new test images is almost 0.11 lower than mAP of the original test images.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.6
• /
• pp.245-254
• /
• 2022

Proteins are the basic unit of all life activities, and understanding them is essential for studying life phenomena. Since the emergence of the machine learning methodology using artificial neural networks, many researchers have tried to predict the function of proteins using only protein sequences. Many combinations of deep learning models have been reported to academia, but the methods are different and there is no formal methodology, and they are tailored to different data, so there has never been a direct comparative analysis of which algorithms are more suitable for handling protein data. In this paper, the single model performance of each algorithm was compared and evaluated based on accuracy and speed by applying the same data to CNN, LSTM, and GRU models, which are the most frequently used representative algorithms in the convergence research field of predicting protein functions, and the final evaluation scale is presented as Micro Precision, Recall, and F1-score. The combined models CNN-LSTM and CNN-GRU models also were evaluated in the same way. Through this study, it was confirmed that the performance of LSTM as a single model is good in simple classification problems, overlapping CNN was suitable as a single model in complex classification problems, and the CNN-LSTM was relatively better as a combination model.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.44-45
• /
• 2019

최근 CNN 등 인공신경망은 최근 이미지 분류, 객체 인식, 자연어 처리 등 다양한 분야에서 뛰어난 성능을 보이고 있다. 그러나, 대부분의 분야에서 보다 더 높은 성능을 얻기 위해 사용한 인공신경망 모델들은 파라미터 수 및 연산량 등이 방대하여, 모바일 및 IoT 디바이스 같은 연산량이나 메모리가 제한된 환경에서 추론하기에는 제한적이다. 따라서 연산량 및 모델 파라미터 수를 압축하기 위한 딥러닝 경량화 알고리즘이 연구되고 있다. 본 논문에서는 임베디트 보드에서의 압축된 CNN 모델의 성능을 검증한다. 인공지능 지원 맞춤형 칩인 QCS605 를 내장한 임베디드 보드에서 카메라로 입력한 영상에 대해서 원 CNN 모델과 압축된 CNN 모델의 분류 성능과 동작속도 비교 분석한다. 본 논문의 실험에서는 CNN 모델로 MobileNetV2, VGG16 을 사용했으며, 주어진 모델에서 가지치기(pruning) 기법, 양자화, 행렬 분해 등의 인공신경망 압축 기술을 적용하였을 때 원래의 모델 대비 추론 시간 및 분류의 정확도 성능을 분석하고 인공신경망 압축 기술의 유용성을 확인하였다.

• Journal of Platform Technology
• /
• v.12 no.2
• /
• pp.12-22
• /
• 2024

With the rapid increase in digital data in modern society, digital forensics plays a crucial role, and file type identification is one of its integral components. Research on the development of identification models utilizing artificial intelligence is underway to identify file types swiftly and accurately. However, existing studies do not support the identification of file types with high domestic usage rates, making them unsuitable for use within the country. Therefore, this paper proposes a more accurate file type identification model using Convolutional Neural Networks (CNN) and Gated Recurrent Units (GRU). To overcome limitations of existing methods, the proposed model demonstrates superior performance on the FFT-75 dataset, effectively identifying file types with high domestic usage rates such as HWP, ALZ, and EGG. The model's performance is validated by comparing it with three existing research models (CNN-CO, FiFTy, CNN-LSTM). Ultimately, the CNN and GRU based file type identification and classification model achieved 68.2% accuracy on 512-byte file fragments and 81.4% accuracy on 4096-byte file fragments.

• Journal of Broadcast Engineering
• /
• v.25 no.2
• /
• pp.200-207
• /
• 2020

Recently, deep neural networks such as CNN are showing excellent performance in various fields such as image classification, object recognition, visual quality enhancement, etc. However, as the model size and computational complexity of deep learning models for most applications increases, it is hard to apply neural networks to IoT and mobile environments. Therefore, neural network compression algorithms for reducing the model size while keeping the performance have been being studied. In this paper, we apply few compression methods to CNN models and evaluate their performances in the embedded environment. For evaluate the performance, the classification performance and inference time of the original CNN models and the compressed CNN models on the image inputted by the camera are evaluated in the embedded board equipped with QCS605, which is a customized AI chip. In this paper, a few CNN models of MobileNetV2, ResNet50, and VGG-16 are compressed by applying the methods of pruning and matrix decomposition. The experimental results show that the compressed models give not only the model size reduction of 1.3~11.2 times at a classification performance loss of less than 2% compared to the original model, but also the inference time reduction of 1.2~2.21 times, and the memory reduction of 1.2~3.8 times in the embedded board.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.370-373
• /
• 2022

Recently, various deep learning framework models such as Tensorflow, Pytorch, Keras, etc. have appeared. In addition, CNN (Convolutional Neural Network) is applied to image recognition using frameworks such as Tensorflow, Pytorch, and Keras, and the optimization model in image classification is mainly used. In this paper, based on the results of training the CNN model with the Paitotchi and tensor flow frameworks most often used in the field of deep learning image recognition, the two frameworks are compared and analyzed for image analysis. Derived an optimized framework.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.78-80
• /
• 2019

개체명 인식 연구에서 우수한 성능을 보이고 있는 bi-LSTM-CRFs 모델은 처리 속도가 느린 단점이 있고, CNN-CRFs 모델은 한국어 말뭉치를 사용하여 제대로 분석되지 않았다. 본 논문에서는 한국어 개체명 인식 말뭉치를 이용한 CNN-CRFs 모델의 음절 단위 한국어 개체명 인식 방법을 제안한다. 실험 결과 bi-LSTM-CRFs 모델보다 CNN-CRFs 모델의 F1 score가 0.4% 높았고, 27.5% 빠른 처리 속도를 보였다.

• Journal of Digital Convergence
• /
• v.19 no.10
• /
• pp.295-301
• /
• 2021

Individual mental fatigue not only reduces cognitive ability and work performance, but also becomes a major factor in large and small accidents occurring in daily life. In this paper, a CNN model for EEG-based mental fatigue discrimination was proposed. To this end, EEG in the resting state and task state were collected and applied to the proposed CNN model, and then the model performance was analyzed. All subjects who participated in the experiment were right-handed male students attending university, with and average age of 25.5 years. Spectral analysis was performed on the measured EEG in each state, and the performance of the CNN model was compared and analyzed using the raw EEG, absolute power, and relative power as input data of the CNN model. As a result, the relative power of the occipital lobe position in the alpha band showed the best performance. The model accuracy is 85.6% for training data, 78.5% for validation, and 95.7% for test data. The proposed model can be applied to the development of an automated system for mental fatigue detection.