• Journal of the Semiconductor & Display Technology
• /
• v.22 no.3
• /
• pp.149-154
• /
• 2023

This paper presents a novel approach to multi-focus image fusion using light field cameras. The proposed neural network, LFFCNN (Light Field Focus Convolutional Neural Network), is composed of three main modules: feature extraction, feature fusion, and feature reconstruction. Specifically, the feature extraction module incorporates SPP (Spatial Pyramid Pooling) to effectively handle images of various scales. Experimental results demonstrate that the proposed model not only effectively fuses a single All-in-Focus image from images with multi focus images but also offers more efficient and robust focus fusion compared to existing methods.

• 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.

• International Commerce and Information Review
• /
• v.15 no.2
• /
• pp.71-82
• /
• 2013

The automotive supply chain is increasingly complex as automakers seek more profitable solutions with global out-sourcing and manufacturing strategies. In the automotive industry, using returnable plastic containers (RPCs) is very common for domestic operations, but for internationally, it has not been considered by many companies because of issues such as overall distance and difficulty of control. The results of this simulation can help to analyze the interactive and coherent behavior of packaging and supply chain systems. The data obtained from the model can be applied to make substantial decisions for choosing the most profitable packaging types, at the same time as it can lead to designing an optimum supply chain for RPCs used in international supply chains.

• Journal of Korea Game Society
• /
• v.9 no.6
• /
• pp.163-170
• /
• 2009

There is a request from the client, we almost apply dynamic memory allocating method using Accept() of looping method; thus, there could be process of connecting synchronously lots of client in most of On-line gaming server engine. However, this kind of method causes on-line gaming server which need to support and process the clients, longer loading and bottle necking. Therefore we propose the object pooling scheme to minimize the memory fragmentation and the load of the initialization to the client using an AcceptEx() and static allocating method for an efficient gaming server of the On-line in this paper. We design and implement the gaming server applying to our proposed scheme. Also, we show efficiency of our proposed scheme by performance analysis in this paper.

• Journal of Labour Economics
• /
• v.38 no.4
• /
• pp.83-107
• /
• 2015

Free Agent(FA) system allows a professional player to make a salary contract with the other clubs as well as the incumbent one after the player has played in one club for a fixed periods. Sometimes compared with the salary FA players performs very poorly, which leads to a debate about FA busts. We extend the model of Yang and Wang(2013) to the one with incomplete information about the productivity of the player to explain the possibility of FA busts. FA busts do not arise in the separating equilibrium where the private information is fully revealed. The FA busts do occur in the pooling equilibrium We show that the separating equilibrium does not exist. We also show that under some conditions, in particular with strong compensation rule, the unique pooling equilibrium exists.

• Applied Microscopy
• /
• v.48 no.3
• /
• pp.55-61
• /
• 2018

The synaptic vesicle is a specialized structure in presynaptic terminals that stores various neurotransmitters. The actin filament has been proposed for playing an important role in mobilizing synaptic vesicles. To understand the role of actin filament on synaptic vesicle pooling, we characterized synaptic vesicles and actin filament after treatment of brain-derived neurotrophic factor (BDNF) or Latrunculin A on primary cultured neuron from rat embryo hippocampus. Western blots revealed that BDNF treatment increased the expression of synapsin I protein, but Latrunculin A treatment decreased the synapsin I protein expression. The increased expression of synapsin I after BDNF disappeared by the treatment of Latrunculin A. Three-dimensional (3D) tomography of synapse showed that more synaptic vesicles localized near the active zone and total number of synaptic vesicles increased after treatment of BDNF. But the number of synaptic vesicle was 2.5-fold reduced in presynaptic terminals and the loss of filamentous network was observed after Latrunculin A application. The treatment of Latruculin A after preincubation of BDNF group showed that synaptic vesicle number was similar to that of control group, but filamentous structures were not restored. These data suggest that the actin filament plays a significant role in synaptic vesicles pooling in presynaptic terminals.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.6
• /
• pp.1271-1278
• /
• 2020

Deep learning-based profiling side-channel analysis is a powerful analysis method that utilizes the neural network to profile the relationship between the side-channel information and the intermediate value. Since the neural network interprets each point of the signal in a different dimension, jitter makes it much hard that the neural network with dimension-wise weights learns the relationship. This paper shows that replacing the fully-connected layer of the traditional CNN (Convolutional Neural Network) with global average pooling (GAP) allows us to design the inherently robust neural network inherently for jitter. We experimented with the ChipWhisperer-Lite board to demonstrate the proposed method: as a result, the validation accuracy of the CNN with a fully-connected layer was only up to 1.4%; contrastively, the validation accuracy of the CNN with GAP was very high at up to 41.7%.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.10
• /
• pp.935-943
• /
• 2017

CNN (Convolution neural network), which is used for image classification and speech recognition among neural networks learning based on positive data, has been continuously developed to have a high performance structure to date. There are many difficulties to utilize in an embedded system with limited resources. Therefore, we use GPU (General-Purpose Computing on Graphics Processing Units), which is used for general-purpose operation of GPU to solve the problem because we use pre-learned weights but there are still limitations. Since CNN performs simple and iterative operations, the computation speed varies greatly depending on the thread allocation and utilization method in the Single Instruction Multiple Thread (SIMT) based GPGPU. To solve this problem, there is a thread that needs to be relaxed when performing Convolution and Pooling operations with threads. The remaining threads have increased the operation speed by using the method used in the following feature maps and kernel calculations.

• Smart Structures and Systems
• /
• v.32 no.3
• /
• pp.135-151
• /
• 2023

Using 3D asphalt pavement surface data, a deep and multiscale network named CrackNet-M is proposed in this paper for pixel-level crack detection for improvements in both accuracy and robustness. The CrackNet-M consists of four function-specific architectural modules: a central branch net (CBN), a crack map enhancement (CME) module, three pooling feature pyramids (PFP), and an output layer. The CBN maintains crack boundaries using no pooling reductions throughout all convolutional layers. The CME applies a pooling layer to enhance potential thin cracks for better continuity, consuming no data loss and attenuation when working jointly with CBN. The PFP modules implement direct down-sampling and pyramidal up-sampling with multiscale contexts specifically for the detection of thick cracks and exclusion of non-crack patterns. Finally, the output layer is optimized with a skip layer supervision technique proposed to further improve the network performance. Compared with traditional supervisions, the skip layer supervision brings about not only significant performance gains with respect to both accuracy and robustness but a faster convergence rate. CrackNet-M was trained on a total of 2,500 pixel-wise annotated 3D pavement images and finely scaled with another 200 images with full considerations on accuracy and efficiency. CrackNet-M can potentially achieve crack detection in real-time with a processing speed of 40 ms/image. The experimental results on 500 testing images demonstrate that CrackNet-M can effectively detect both thick and thin cracks from various pavement surfaces with a high level of Precision (94.28%), Recall (93.89%), and F-measure (94.04%). In addition, the proposed CrackNet-M compares favorably to other well-developed networks with respect to the detection of thin cracks as well as the removal of shoulder drop-offs.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• v.29 no.1
• /
• pp.377-382
• /
• 2005

This paper deals with productivity improvement of stevedoring system by pooling opertaions of transport vehicle at automated container terminal. Usually, in traditional container terminals, grouping operations of transport vehicle are applied for container crane because vehicle routing path is simple and vehicle assignment is easy. But this static assignment(SA) operation that arrsign vehicles to container crane ar apron reduces flexibility of vehicles. Therefore, This paper presented 4 dynamic assignment(DA) method to improve efficiency of vehicles. These 4 dynamic assignment method consider present situations of container crane such as sequence(Se), queue time(Qt), productivity(Pr), numeric of vehicle assignment(Nv), numeric of buffer(Nb) at vehicles assignment. At the results, dynamic assignment operation to consider Qt, Nv, Nb is most efficient and by next time, dynamic assignment operation to consider Se is superior more than static assignment operation. but, dynamic assignment operation to consider Pr or Qt of container crane only is inefficient than static assignment operation.