• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 하계종합학술대회논문집
• /
• pp.933-935
• /
• 1998

The HMM-Net is an architecture for a neural network that implements a hidden markov model (HMM). The architecture is developed for the purpose of combining the discriminant power of neural networks with the time-domain modeling capability of HMMs. Criteria used for learning HMM-Net classifiers are maximum likelihood(ML) and minimization of mean squared error(MMSE). In this paper we propose an efficient learning method of HMM_Net classifiers using a ML-MMSE hybrid criterion and report the results of an experimental study comparing the performance of HMM_Net classifiers trained by the gradient descent algorithm with the above criteria. Experimental results for the isolated numeric digits from /0/ to /9/ show that the performance of the proposed method is better than the others in the repects of learning and recognition rates.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권1호
• /
• pp.147-165
• /
• 2021

In this work, we empirically evaluated the efficiency of the recent EfficientNetB0 model to identify and diagnose malaria parasite infections in blood smears. The dataset used was collected and classified by relevant experts from the Lister Hill National Centre for Biomedical Communications (LHNCBC). We prepared our samples with minimal image transformations as opposed to others, as we focused more on the feature extraction capability of the EfficientNetB0 baseline model. We applied transfer learning to increase the initial feature sets and reduced the training time to train our model. We then fine-tuned it to work with our proposed layers and re-trained the entire model to learn from our prepared dataset. The highest overall accuracy attained from our evaluated results was 94.70% from fifty epochs and followed by 94.68% within just ten. Additional visualization and analysis using the Gradient-weighted Class Activation Mapping (Grad-CAM) algorithm visualized how effectively our fine-tuned EfficientNetB0 detected infections better than other recent state-of-the-art DCNN models. This study, therefore, concludes that when fine-tuned, the recent EfficientNetB0 will generate highly accurate deep learning solutions for the identification of malaria parasites in blood smears without the need for stringent pre-processing, optimization, or data augmentation of images.

• 대한임베디드공학회논문지
• /
• 제16권5호
• /
• pp.187-193
• /
• 2021

Our final goal is to implement nursing robots that can recognize patient's faces and their medicine on prescription. They can help patients to take medicine on time and prevent its abuse for recovering their health soon. As the first step, we proposed a medicine classifier with a low computational network that is able to run on embedded PCs without GPU in order to be applied to universal nursing robots. We confirm that our proposed model called MedicineNet achieves an 99.99% accuracy performance for classifying 15 kinds of medicines and background images. Moreover, we realize that the calculation time of our MedicineNet is about 8 times faster than EfficientNet-B0 which is well known as ImageNet classification with the high performance and the best computational efficiency.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.1213-1214
• /
• 2023

현재 국내외 CCTV 구축량 증가로 사생활 침해와 높은 설치 비용등이 문제점으로 제기되고 있다. 따라서 본 연구는 Early Fusion을 적용한 위급상황 음향 분류 모델을 제안한다. 음향 데이터에 STFT(Short Time Fourier Transform), Spectrogram, Mel-Spectrogram을 적용해 특징 벡터를 추출하고 3차원으로 Early Fusion하여 ResNet, DenseNet, EfficientNetV2으로 학습한다. 실험 결과 Early Fusion 방법이 가장 좋은 결과를 보였고 DenseNet, EfficientNetV2가 Accuracy, F1-Score 모두 0.972의 성능을 보였다.

• ETRI Journal
• /
• 제36권1호
• /
• pp.31-41
• /
• 2014

The heterogeneous network (HetNet) has been discussed in detail in the Long-Term Evolution (LTE) and LTE Advanced standards. However, the standardization of High-Speed Packet Access HetNet (HSPA HetNet) launched by 3GPP is pushing at full steam. Interference coordination (IC), which is responsible for dealing with the interference in the system, remains a subject worthy of investigation in regard to HSPA HetNet. In this paper, considering the network framework of HSPA HetNet, we propose a quasi-distributed IC (QDIC) scheme to lower the interference level in the co-channel HSPA HetNet. Our QDIC scheme is constructed as slightly different energy-efficient non-cooperative games in the downlink (DL) and uplink (UL) scenarios, respectively. The existence and uniqueness of the equilibrium for these games are first revealed. Then, we derive the closed-form best responses of these games. A feasible implementation is finally developed to achieve our QDIC scheme in the practical DL and UL. Simulation results show the notable benefits of our scheme, which can indeed control the interference level and enhance the system performance.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권5호
• /
• pp.161-168
• /
• 2021

균열은 건물, 교량, 도로, 수송관 등의 기반시설의 안전성에 영향을 주는 요소이다. 본 연구에서는 검사 비용과 시간을 줄일 수 있는 자동화된 균열 탐지 시스템을 다룬다. 환경과 표면에 강건한 시스템을 구성하기 위해서, 본 연구에서는 여러 사전 연구에서 사용된 다양한 표면의 균열 데이터 셋을 수집하여 통합 데이터 셋을 구축하였다. 이후, 컴퓨터 비전 분야에 높은 성능을 발휘하는 VGG, ResNet, WideResNet, ResNeXt, DenseNet, EfficientNet 딥러닝 모델을 적용하였다. 통합 데이터 셋은 훈련 집합(80%)과 테스트 집합(20%)으로 나누어 모델 성능을 검증하기 위해서 사용했다. 실험 결과, DenseNet121 모델이 높은 마라미터 효율성을 가지면서도 테스트 집합에 대해 96.20%의 정확도를 달성하여 가장 높은 성능을 보여주었다. 딥러닝 모델의 균열 검출 성능 검증을 통해, DenseNet121를 활용하여 컴퓨팅 자원이 적은 소형 디바이스에서도 높은 균열 검출 성능을 보이는 탐지 시스템을 구축이 가능함을 확인했다.

• Journal of Semiconductor Engineering
• /
• 제1권1호
• /
• pp.31-37
• /
• 2020

We present an approximate DRAM architecture for energy-efficient deep learning. Our key premise is that by bounding memory errors to non-critical information, we can significantly reduce DRAM refresh energy without compromising recognition accuracy of deep neural networks. To validate the key premise, we make extensive Monte-Carlo simulations for several well-known convolutional neural networks such as LeNet, ConvNet and AlexNet with the input of MINIST, CIFAR-10, and ImageNet, respectively. We assume that the highest-order 8-bits (in single precision) and 4-bits (in half precision) are protected from retention errors under the proposed architecture and then, randomly inject bit-errors to unprotected bits with various bit-error-rates. Here, recognition accuracies of the above convolutional neural networks are successfully maintained up to the 10^-5-order bit-error-rate. We simulate DRAM energy during inference of the above convolutional neural networks, where the proposed architecture shows the possibility of considerable energy saving up to 10 ~ 37.5% of total DRAM energy.

• Journal of Information Processing Systems
• /
• 제18권2호
• /
• pp.197-207
• /
• 2022

The applications and user interfaces (UIs) of smart mobile devices are constantly diversifying. For example, deep learning can be an innovative solution to classify widgets in screen images for increasing convenience. To this end, the present research leverages captured images and the ReDraw dataset to write deep learning datasets for image classification purposes. First, as the validation for datasets using ResNet50 and EfficientNet, the experiments show that the dataset composed in this study is helpful for classification according to a widget's functionality. An implementation for widget detection and classification on RetinaNet and EfficientNet is then executed. Finally, the research suggests the Widg-C and Widg-D datasets-a deep learning dataset for identifying the widgets of smart devices-and implementing them for use with representative convolutional neural network models.

• 한국건설순환자원학회논문집
• /
• 제9권3호
• /
• pp.348-355
• /
• 2021

도로 포장에 널리 사용되는 아스팔트는 도로가 노출되는 환경에 따라 요구되는 물리적 특성이 상이하다. 이에 따라 첨가제의 배합에 따라 아스팔트가 어떤 물리적 특성을 나타내는지 평가하고 도로의 교통, 기후 환경에 맞추어 적절한 배합을 선택하는 것이 아스팔트 도로의 수명을 확보하기 위해 필수적이다. 아스팔트의 다양한 물리적 특성 중 소성변형에 대한 저항성을 측정하기 위해서는 Dynamic shear rheometer(DSR) 테스트를 주로 사용한다. 하지만 DSR 테스트는 실험 세팅에 따라 결과가 상이하고 특정 온도 범위 내에만 측정이 가능한 단점이 있다. 따라서 본 연구에서는 DSR 테스트의 단점을 극복하고자, Atomic force microscopy로부터 수집된 이미지를 학습하여 레올로지적 특성을 예측하고자 했다. 딥러닝 아키텍처 중 하나인 EfficientNet을 통해 이미지를 학습하였고 딥러닝 모델의 한계인 많은 데이터를 요구한다는 점을 극복하기 위해 전이학습을 이용하여 학습을 진행하였다. 학습된 모델은 이종의 첨가제를 사용하였음에도 높은 정확도로 아스팔트 바인더의 레올로지적 특성을 예측하였다. 특히, 전이학습을 사용하지 않았을 때와 비교하여 빠르게 학습이 가능했다.

• International Journal of Computer Science & Network Security
• /
• 제22권10호
• /
• pp.406-412
• /
• 2022

Scene classification of very high-resolution (VHR) imagery can attribute semantics to land cover in a variety of domains. Real-world application requirements have not been addressed by conventional techniques for remote sensing image classification. Recent research has demonstrated that deep convolutional neural networks (CNNs) are effective at extracting features due to their strong feature extraction capabilities. In order to improve classification performance, these approaches rely primarily on semantic information. Since the abstract and global semantic information makes it difficult for the network to correctly classify scene images with similar structures and high interclass similarity, it achieves a low classification accuracy. We propose a VHR remote sensing image classification model that uses extracts the global feature from the original VHR image using an EfficientNet-V2L CNN pre-trained to detect similar classes. The image is then classified using a multilayer perceptron (MLP). This method was evaluated using two benchmark remote sensing datasets: the 21-class UC Merced, and the 38-class PatternNet. As compared to other state-of-the-art models, the proposed model significantly improves performance.