• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.4
• /
• pp.1246-1262
• /
• 2021

Recent studies have demonstrated the strong ability of deep convolutional neural networks (CNNs) to significantly boost the performance in single image super-resolution (SISR). The key concern is how to efficiently recover and utilize diverse information frequencies across multiple network layers, which is crucial to satisfying super-resolution image reconstructions. Hence, previous work made great efforts to potently incorporate hierarchical frequencies through various sophisticated architectures. Nevertheless, economical SISR also requires a capable structure design to balance between restoration accuracy and computational complexity, which is still a challenge for existing techniques. In this paper, we tackle this problem by proposing a competent architecture called Enhanced U-Net Network (EUN), which can yield ready-to-use features in miscellaneous frequencies and combine them comprehensively. In particular, the proposed building block for EUN is enhanced from U-Net, which can extract abundant information via multiple skip concatenations. The network configuration allows the pipeline to propagate information from lower layers to higher ones. Meanwhile, the block itself is committed to growing quite deep in layers, which empowers different types of information to spring from a single block. Furthermore, due to its strong advantage in distilling effective information, promising results are guaranteed with comparatively fewer filters. Comprehensive experiments manifest our model can achieve favorable performance over that of state-of-the-art methods, especially in terms of computational efficiency.

• Transactions of Materials Processing
• /
• v.31 no.4
• /
• pp.229-239
• /
• 2022

Convolution Neural Network(CNN) is a class of deep learning algorithms and can be used for image analysis. In particular, it has excellent performance in finding the pattern of images. Therefore, CNN is commonly applied for recognizing, learning and classifying images. In this study, the surface defect classification performance of Al 6061 extruded material using CNN-based algorithms were compared and evaluated. First, the data collection criteria were suggested and a total of 2,024 datasets were prepared. And they were randomly classified into 1,417 learning data and 607 evaluation data. After that, the size and quality of the training data set were improved using data augmentation techniques to increase the performance of deep learning. The CNN-based algorithms used in this study were VGGNet-16, VGGNet-19, ResNet-50 and DenseNet-121. The evaluation of the defect classification performance was made by comparing the accuracy, loss, and learning speed using verification data. The DenseNet-121 algorithm showed better performance than other algorithms with an accuracy of 99.13% and a loss value of 0.037. This was due to the structural characteristics of the DenseNet model, and the information loss was reduced by acquiring information from all previous layers for image identification in this algorithm. Based on the above results, the possibility of machine vision application of CNN-based model for the surface defect classification of Al extruded materials was also discussed.

• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.301-307
• /
• 2022

Energy consumption has grown alongside dramatic population increases. Statistics show that buildings in particular utilize a significant amount of energy, worldwide. Because of this, building energy prediction is crucial to best optimize utilities' energy plans and also create a predictive model for consumers. To improve energy prediction performance, this paper proposes a ResNet-LSTM model that combines residual networks (ResNets) and long short-term memory (LSTM) for energy consumption prediction. ResNets are utilized to extract complex and rich features, while LSTM has the ability to learn temporal correlation; the dense layer is used as a regression to forecast energy consumption. To make our model more robust, we employed Huber loss during the optimization process. Huber loss obtains high efficiency by handling minor errors quadratically. It also takes the absolute error for large errors to increase robustness. This makes our model less sensitive to outlier data. Our proposed system was trained on historical data to forecast energy consumption for different time series. To evaluate our proposed model, we compared our model's performance with several popular machine learning and deep learning methods such as linear regression, neural networks, decision tree, and convolutional neural networks, etc. The results show that our proposed model predicted energy consumption most accurately.

• International Journal of Computer Science & Network Security
• /
• v.22 no.10
• /
• 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.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.8-11
• /
• 2020

4 차 산업혁명 시대의 도래와 함께 AI, ICT 기술의 융합이 진행됨에 따라, 유저 레벨의 디바이스에서도 AI 서비스의 요청이 실현되었다. 이미지 처리와 관련된 AI 서비스는 피사체 판별, 불량품 검사, 자율주행 등에 이용되고 있으며, 특히 Deep Convolutional Neural Network (DCNN)은 이미지의 특색을 파악하는 데 뛰어난 성능을 보여준다. 하지만, 이미지의 크기가 커지고, 신경망이 깊어짐에 따라 연산 처리에 있어 낮은 데이터 지역성과 빈번한 메모리 참조를 야기했다. 이에 따라, 기존의 계층적 시스템 구조는 DCNN 을 scalable 하고 빠르게 처리하는 데 한계를 보인다. 본 연구에서는 DCNN 의 scalable 하고 빠른 처리를 위해 3 차원 메모리 구조의 Processing-In-Memory (PIM) 가속기를 제안한다. 이를 위해 기존 3 차원 메모리인 Hybrid Memory Cube (HMC)에 하드웨어 및 소프트웨어 모듈을 추가로 구성하였다. 구체적으로, Processing Element (PE)간 데이터를 공유할 수 있는 공유 캐시 및 소프트웨어 스택, 파이프라인화된 곱셈기 및 듀얼 프리페치 버퍼를 구성하였다. 이를 유명 DCNN 알고리즘 LeNet, AlexNet, ZFNet, VGGNet, GoogleNet, RestNet 에 대해 성능 평가를 진행한 결과 기존 HMC 대비 40.3%의 속도 향상을 29.4%의 대역폭 향상을 보였다.

• International Journal of Computer Science & Network Security
• /
• v.24 no.1
• /
• pp.119-126
• /
• 2024

Disease caused by the coronavirus (COVID-19) is sweeping the globe. There are numerous methods for identifying this disease using a chest imaging. Computerized Tomography (CT) chest scans are used in this study to detect COVID-19 disease using a pretrain Convolutional Neural Network (CNN) ResNet50. This model is based on image dataset taken from two hospitals and used to identify Covid-19 illnesses. The pre-train CNN (ResNet50) architecture was used for feature extraction, and then fully connected layers were used for classification, yielding 97%, 96%, 96%, 96% for accuracy, precision, recall, and F1-score, respectively. When combining the feature extraction techniques with the Back Propagation Neural Network (BPNN), it produced accuracy, precision, recall, and F1-scores of 92.5%, 83%, 92%, and 87.3%. In our suggested approach, we use a preprocessing phase to improve accuracy. The image was enhanced using the Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm, which was followed by cropping the image before feature extraction with ResNet50. Finally, a fully connected layer was added for classification, with results of 99.1%, 98.7%, 99%, 98.8% in terms of accuracy, precision, recall, and F1-score.

• Proceedings of the KIEE Conference
• /
• 1997.11a
• /
• pp.600-602
• /
• 1997

In this study, a hybrid neural net consisting of an Adaptive LVQ(ALVQ) algorithm and MLP is proposed to perform speaker identification task. ALVQ is a new learning procedure using adaptively feature vector sequence instead of only one feature vector in training codebooks initialized by LBG algorithm and the optimization criterion of this method is consistent with the speaker classification decision rule. ALVQ aims at providing a compressed, geometrically consistent data representation. It is fit to cover irregular data distributions and computes the distance of the input vector sequence from its nodes. On the other hand, MLP aim at a data representation to fit to discriminate patterns belonging to different classes. It has been shown that MLP nets can approximate Bayesian "optimal" classifiers with high precision, and their output values can be related a-posteriori class probabilities. The different characteristics of these neural models make it possible to devise hybrid neural net systems, consisting of classification modules based on these two different philosophies. The proposed method is compared with LBG algorithm, LVQ algorithm and MLP for performance.

• Journal of the Society of Naval Architects of Korea
• /
• v.58 no.3
• /
• pp.129-136
• /
• 2021

Cavitation erosion is one of the major factors causing damage by lowering the structural strength of the marine propeller and the risk of it has been qualitatively evaluated by each institution with their own criteria based on the experiences. In this study, in order to quantitatively evaluate the risk of cavitation erosion on the propeller, we implement a deep learning algorithm based on a convolutional neural network. We train and verify it using the model tests results, including cavitation characteristics of various ship types. Here, we adopt the validated well-known networks such as VGG, GoogLeNet, and ResNet, and the results are compared with the expert's qualitative prediction results to confirm the feasibility of the prediction algorithm using a convolutional neural network.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.4
• /
• pp.217-228
• /
• 2022

Currently, there are increasing demands for applying deep neural networks (DNNs) in the embedded domain such as classification and object detection. The DNN processing in embedded domain often requires custom hardware such as NPU for acceleration due to the constraints in power, performance, and area. Processing DNN models requires a large amount of data, and its seamless transfer to NPU is crucial for performance. In this paper, we developed a cycle-accurate NPU simulator to evaluate diverse NPU microarchitectures. In addition, we propose a novel technique for reducing the number of memory accesses when processing convolutional layers in convolutional neural networks (CNNs) on the NPU. The main idea is to reuse data with memory interleaving, which recycles the overlapping data between previous and current input windows. Data memory interleaving makes it possible to quickly read consecutive data in unaligned locations. We implemented the proposed technique to the cycle-accurate NPU simulator and measured the performance with LeNet-5, VGGNet-16, and ResNet-50. The experiment shows up to 2.08x speedup in processing one convolutional layer, compared to the baseline.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.6
• /
• pp.44-51
• /
• 1999

The HMM-Net is a neural network architecture that implements the computation of output probabilities of 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 of maximum likehood(ML) and minimization of mean squared error(MMSE) are used for learning HMM-Net classifiers. The criterion MMSE is better than ML when initial learning condition is well established. However Ml is more useful one when the condition is incomplete[3]. Therefore we propose an efficient learning method of HMM-Net classifiers using a hybrid criterion(ML/MMSE). In the method, we begin a learning with ML in order to get a stable start-point. After then, we continue the learning with MMSE to search an optimal or near-optimal solution. Experimental results for the isolated numeric digits from /0/ to /9/, a training and testing time-series pattern set, show that the performance of the proposed method is better than the others in the respects of learning and recognition rates.