• IE interfaces
• /
• v.25 no.4
• /
• pp.431-440
• /
• 2012

Since pooling is a popular scheme in many areas to attain operational excellence, many researchers investigated the performance of pooling systems. However, rare research could be found on pooling with game situation which has much applicability to real world phenomenon. We analyze the performance of noncooperative pooling system with two servers having different sharing capacity. We investigate the sensitivity of the advantage of capacity pooling on the variation of system parameters, including sharing capacity numbers, pooling probability, pooling strategy and traffic intensity. As a result, we suggest an efficient control policy which facilitate the performance of pooling in a game situation.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.4
• /
• pp.161-166
• /
• 2018

In this paper, we propose a method for the random selection of pooling operations for the regularization and reduction of cross validation in convolutional neural networks. The pooling operation in convolutional neural networks is used to reduce the size of the feature map and for its shift invariant properties. In the existing pooling method, one pooling operation is applied in each pooling layer. Because this method fixes the convolution network, the network suffers from overfitting, which means that it excessively fits the models to the training samples. In addition, to find the best combination of pooling operations to maximize the performance, cross validation must be performed. To solve these problems, we introduce the probability concept into the pooling layers. The proposed method does not select one pooling operation in each pooling layer. Instead, we randomly select one pooling operation among multiple pooling operations in each pooling region during training, and for testing purposes, we use probabilistic weighting to produce the expected output. The proposed method can be seen as a technique in which many networks are approximately averaged using a different pooling operation in each pooling region. Therefore, this method avoids the overfitting problem, as well as reducing the amount of cross validation. The experimental results show that the proposed method can achieve better generalization performance and reduce the need for cross validation.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.6
• /
• pp.1621-1629
• /
• 2016

This paper studies Bayesian pooling for analysis of categorical data from small areas. Many surveys consist of categorical data collected on a contingency table in each area. Statistical inference for small areas requires considerable care because the subpopulation sample sizes are usually very small. Typically we use the hierarchical Bayesian model for pooling subpopulation data. However, the customary hierarchical Bayesian models may specify more exchangeability than warranted. We, therefore, investigate the effects of pooling in hierarchical Bayesian modeling for the contingency table from small areas. In specific, this paper focuses on the methods of direct or indirect pooling of categorical data collected on a contingency table in each area through Dirichlet priors. We compare the pooling effects of hierarchical Bayesian models by fitting the simulated data. The analysis is carried out using Markov chain Monte Carlo methods.

• Journal of Information Processing Systems
• /
• v.15 no.5
• /
• pp.1179-1191
• /
• 2019

We design an ingenious view-pooling method named learning-based multiple pooling fusion (LMPF), and apply it to multi-view convolutional neural network (MVCNN) for 3D model classification or retrieval. By this means, multi-view feature maps projected from a 3D model can be compiled as a simple and effective feature descriptor. The LMPF method fuses the max pooling method and the mean pooling method by learning a set of optimal weights. Compared with the hand-crafted approaches such as max pooling and mean pooling, the LMPF method can decrease the information loss effectively because of its "learning" ability. Experiments on ModelNet40 dataset and McGill dataset are presented and the results verify that LMPF can outperform those previous methods to a great extent.

• Journal of Navigation and Port Research
• /
• v.38 no.4
• /
• pp.399-407
• /
• 2014

Due to the increase of container terminals, as the volume of terminals become distributed, the competition of preserving existing volume and inviting new volume are becoming fierce, and various ways for processing terminal volume and inviting volume are being sought. Container terminal efforts to maximize efficiency in order to improve the volume handling capability and productivity by both expansion of the latest equipment and development of the latest terminal system. There are a variety of factors that influence the improvement of productivity at container terminals. Among them, in the case of yard transfer equipment, if it were to convert from the method of a Yard Tractor(YT) being fixed allocated to a certain Gantry Cranes(GC) to a Pooling System that processes in a method that properly distributes and allocates a Yard Tractor(YT) to multiple Gantry Cranes(GC), the terminal productivity and the fusibility of YT may be increased. The KPI which is an indicator for the productivity at container terminals is GC productivity and since GC productivity cannot exceed the speed of physical GC operations, a Pooling System is applied to increase productivity which its meaning and effect is massive. Here in the Report, we produce the Pooling Algorithm system to improve the efficiency of the transported equipments in container terminal which is actually applying for this method and have compared Non pooling system with Pooling system in the fields. By introducing a transfer equipment pooling system and enhancing the productivity compared to other terminals, it may become an essential factor for increasing the continuous service quality and profitability in terms of terminal business.

• Korean Journal of Agricultural Science
• /
• v.29 no.2
• /
• pp.98-108
• /
• 2002

Pooling system of jointly shipping farm products aims to realize economies of scale for it's farm products and strengthen bargaining power for the farmers. As adapting to pooling system, price received by farmers and competitive power of our farm products can be enhanced. Pooling system especially in Cheon-an pear and horticultural primary cooperatives is found to be required, because the pooling system is not introduced yet although the area is main region for domestic pear production. This study aims at establishing the appropriate pooling system and it's strengthening strategies in this cooperatives through survey of local producers' group in this cooperatives and case studies of successful pear primary cooperatives.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.9
• /
• pp.1158-1165
• /
• 2021

This paper proposes a CNN accelerator which is optimized Pooling layer operation incorporated in Multiplication And Accumulation(MAC) to reduce the memory size. For optimizing memory and data path circuit, the quantized 8bit integer weights are used instead of 32bit floating-point weights for pre-training of MNIST data set. To reduce chip area, the proposed CNN model is reduced by a convolutional layer, a 4*4 Max Pooling, and two fully connected layers. And all the operations use specific MAC with approximation adders and multipliers. 94% of internal memory size reduction is achieved by simultaneously performing the convolution and the pooling operation in the proposed architecture. The proposed accelerator chip is designed by using TSMC65nmGP CMOS process. That has about half size of our previous paper, 0.8*0.9 = 0.72mm². The presented CNN accelerator chip achieves 94% accuracy and 77us inference time per an MNIST image.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.87-90
• /
• 2020

GPU의 발전과 함께 성장한 딥러닝(Deep Learning)은 영상 분류 문제에서 최고의 성능을 보이고 있다. 그러나 합성곱 신경망 기반의 모델을 깊게 쌓음에 따라 신경망의 표현력이 좋아짐과 동시에 때로는 학습이 잘되지 않고 성능이 저하되는 등의 부작용도 등장했다. 성능 향상을 방해하는 주요 요인 중 하나는, 차원감소 목적에 따라 필연적으로 정보 손실을 겪어야 하는 풀링 계층에 있다. 따라서 특성맵(Feature map)의 차원감소를 통해 얻게 되는 비용적 이득과 모델의 분류 성능 사이의 취사선택(Trade-off)이 존재한다. 그리고 이로부터 자유로워지기 위한 다양한 연구와 기법이 존재하는데 Spectral Pooling도 이 중 하나이다. 본 논문에서는 이산 푸리에 변환(Discrete Fourier Transform, DFT)을 이용한 Spectral Pooling에 대한 소개와, 해당 풀링의 성질을 통상적으로 사용되고 있는 Max Pooling과의 성능 비교를 통해 분석한다. 또한 영상 내 고주파수 부분에서 특히 더 강건하지 못하다는 맥스 풀링의 고질적인 문제점을, Spectral Pooling과의 하이브리드(Hybrid) 구조를 통해 어떻게 극복해나갈 것인지 그 가능성을 중심으로 실험을 수행했다.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_2
• /
• pp.793-810
• /
• 2022

Synthetic Aperture Radar (SAR) is considered to be suitable for near real-time inundation monitoring. The distinctly different intensity between water and land makes it adequate for waterbody detection, but the intrinsic speckle noise and variable intensity of SAR images decrease the accuracy of waterbody detection. In this study, we suggest two modules, named 'morphology module' and 'edge-enhanced module', which are the combinations of pooling layers and convolutional layers, improving the accuracy of waterbody detection. The morphology module is composed of min-pooling layers and max-pooling layers, which shows the effect of morphological transformation. The edge-enhanced module is composed of convolution layers, which has the fixed weights of the traditional edge detection algorithm. After comparing the accuracy of various versions of each module for U-Net, we found that the optimal combination is the case that the morphology module of min-pooling and successive layers of min-pooling and max-pooling, and the edge-enhanced module of Scharr filter were the inputs of conv9. This morphologic and edge-enhanced U-Net improved the F1-score by 9.81% than the original U-Net. Qualitative inspection showed that our model has capability of detecting small-sized waterbody and detailed edge of water, which are the distinct advancement of the model presented in this research, compared to the original U-Net.

• Journal of Navigation and Port Research
• /
• v.33 no.6
• /
• pp.401-407
• /
• 2009

The improvement in the terminal productivity plays a key role for container terminals to be more competitive. The productivity of yard tractors(YT) is one of the most important factor accelerating the terminal productivity. Thus, YT pooling system is newly introduced in container terminals for increasing the YT productivity. Recently, the terminals in Korea tend to adopt YT pooling system. This paper proposes the important decision factors for YT pooling work space and several types of formulations according to states of container terminals.