• Journal of IKEEE
• /
• v.25 no.1
• /
• pp.180-192
• /
• 2021

One widely used algorithm for image recognition and pattern detection is the convolution neural network (CNN). To efficiently handle convolution operations, which account for the majority of computations in the CNN, we use hardware accelerators to improve the performance of CNN applications. In using these hardware accelerators, the CNN fetches data from the off-chip DRAM, as the massive computational volume of data makes it difficult to derive performance improvements only from memory inside the hardware accelerator. In other words, data communication between off-chip DRAM and memory inside the accelerator has a significant impact on the performance of CNN applications. In this paper, a simulator for the CNN is developed to analyze the main memory or DRAM access with respect to the size of the on-chip memory or global buffer inside the CNN accelerator. For AlexNet, one of the CNN architectures, when simulated with increasing the size of the global buffer, we found that the global buffer of size larger than 100kB has 0.8x as low a DRAM access count as the global buffer of size smaller than 100kB.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.466-467
• /
• 2018

Recently, artificial intelligence has been applied to various fields such as image recognition, image recognition speech recognition, and natural language processing, and interest in Deep Learning technology is increasing. Many researches on Convolutional Neural Network(CNN), which is one of the most representative algorithms among Deep Learning, have strong advantages in image recognition and classification and are widely used in various fields. In this paper, we propose a new network structure that transforms the general CNN structure. A typical CNN structure consists of a convolution layer, ReLU layer, and a pooling layer. Therefore in this paper, We intend to construct a new network by adding fully connected layer inside a general CNN structure. This modification is intended to increase the learning and accuracy of the convoluted image by including the generalization which is an advantage of the neural network.

• Journal of IKEEE
• /
• v.20 no.3
• /
• pp.303-306
• /
• 2016

In this paper, we propose a method to accelerate convolutional neural network by utilizing a GPGPU. Convolutional neural network is a sort of the neural network learning features of images. Convolutional neural network is suitable for the image processing required to learn a lot of data such as images. The convolutional layer of the conventional CNN required a large number of multiplications and it is difficult to operate in the real-time on the embedded environment. In this paper, we reduce the number of multiplications through Winograd convolution operation and perform parallel processing of the convolution by utilizing SIMT-based GPGPU. The experiment was conducted using ModelSim and TestDrive, and the experimental results showed that the processing time was improved by about 17%, compared to the conventional convolution.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.4
• /
• pp.201-205
• /
• 2020

The structural texture is defined as a form which a texel is regularly repeated in the texture. Structural texture analysis/recognition has various industrial applications, such as automatic inspection of textiles, automatic testing of metal surfaces, and automatic analysis of micro images. In this paper, we propose a Convolution Neural Network (CNN) based system for structural texture analysis. The proposed method learns texles, which are components of textures to be classified. Then, this trained CNN recognizes a structural texture using a partial image obtained from input texture. The experiment shows the superiority of the proposed system.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.1
• /
• pp.133-138
• /
• 2020

This paper introduces a method for improving accuracy using the first convolution layer, which is not used in most modified CNN(: Convolution Neural Networks). In CNN, such as GoogLeNet and DenseNet, the first convolution layer uses only the traditional methods(3×3 convolutional computation, batch normalization, and activation functions), replacing this with RGB-csb. In addition to the results of preceding studies that can improve accuracy by applying RGB values to feature maps, the accuracy is compared with existing CNN using a limited number of images. The method proposed in this paper shows that the smaller the number of images, the greater the learning accuracy deviation, the more unstable, but the higher the accuracy on average compared to the existing CNN. As the number of images increases, the difference in accuracy between the existing CNN and the proposed method decreases, and the proposed method does not seem to have a significant effect.

• 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%.

• The Bulletin of The Korean Astronomical Society
• /
• v.45 no.1
• /
• pp.49.4-50
• /
• 2020

We introduce a novel method for reconstructing the projected matter distributions of galaxy clusters with weak-lensing (WL) data based on convolutional neural network (CNN). We control the noise level of the galaxy shear catalog such that it mimics the typical properties of the existing Subaru/Suprime-Cam WL observations of galaxy clusters. We find that our mass reconstruction based on multi-layered CNN with architectures of alternating convolution and trans-convolution filters significantly outperforms the traditional mass reconstruction methods.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.27 no.1
• /
• pp.48-55
• /
• 2022

This paper proposes a battery remaining useful life (RUL) prediction method using a deep learning-based EMD-CNN-LSTM hybrid method. The proposed method pre-processes capacity data by applying empirical mode decomposition (EMD) and predicts the remaining useful life using CNN-LSTM. CNN-LSTM is a hybrid method that combines convolution neural network (CNN), which analyzes spatial features, and long short term memory (LSTM), which is a deep learning technique that processes time series data analysis. The performance of the proposed remaining useful life prediction method is verified using the battery aging experiment data provided by the NASA Ames Prognostics Center of Excellence and shows higher accuracy than does the conventional method.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.4
• /
• pp.288-294
• /
• 2017

Recently, deep learning using convolutional neural network (CNN) has been extensively studied in image recognition. Convolution consists of addition and multiplication. Multiplication is computationally expensive in hardware implementation, relative to addition. It is also important factor limiting a chip design in an embedded deep learning system. In this paper, I propose a parallel-addition processing algorithm that converts grayscale images to the superposition of binary images and performs convolution only with addition. It is confirmed that the convolution can be performed by a parallel-addition method capable of reducing the processing time in experiment for verifying the availability of proposed algorithm.

• Journal of Broadcast Engineering
• /
• v.23 no.5
• /
• pp.669-681
• /
• 2018

CNN (Convolution Neural Network) is one of the most important techniques to identify the kind of objects in the captured pictures. Whereas the conventional models have been used for low resolution images, the technique to recognize the high resolution images becomes crucial in the field of artificial intelligence. In this paper, we proposed an efficient CNN model based on dilated convolution and thresholding techniques to increase the recognition ratio and to decrease the computational complexity. The simulation results show that the proposed algorithm outperforms the conventional method and the thresholding technique enhances the performance of the proposed model.