• Journal of Navigation and Port Research
• /
• v.46 no.1
• /
• pp.33-41
• /
• 2022

An important operational goal of a container terminal is to maximize the efficiency of the operation of quay cranes (QCs) that load and/or unload containers onto and from vessels. While the maximization of the efficiency of the QC operation requires minimizing the delay of yard tractors (YT) that transport containers between the storage yard and QCs, the delay is often inevitable because of traffic congestion. In this paper, we propose a method for learning a model that predicts traffic speed in a terminal using only YT operation data, even though the YT traffic is mixed with that of external trucks. Without any information on external truck traffic, we could still make a reasonable traffic forecast because the YT operation data contains information on the YT routes in the near future. The results of simulation experiments showed that the model learned by the proposed method could predict traffic speed with significant accuracy.

• Industrial Engineering and Management Systems
• /
• v.9 no.2
• /
• pp.178-194
• /
• 2010

To improve the ship operation in automated container terminals, it is important to schedule different types of handling equipment to operate synchronously. For example, a vehicle with container receiving and lifting capabilities is used to transport containers from a storage yard to a vessel and vice versa, while a triple quay crane (QC) can handle up to three 40-ft containers simultaneously. This paper discusses the manner in which vehicles should be assigned to containers to support such multi-lifts of QCs by using information about the locations and times of deliveries. A mixed-integer programming model is introduced to optimally assign delivery tasks to vehicles. This model considers the constraint imposed by the limited buffer space under each QC. A procedure for converting buffer-space constraints into time window constraints and a heuristic algorithmfor overcoming the excessive computational time required for solving the mathematical model are suggested. A numerical experiment is conducted to compare the objective values and computational times of the heuristic algorithm with those of the optimizing method to evaluate the performance of the heuristic algorithm.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.32 no.6B
• /
• pp.399-406
• /
• 2012

The objective of this research is to develop greenhouse gas generation models and estimation method of their parameters for solid waste landfills. Two models obtained by differentiating the Modified Gompertz and Logistic models were employed to evaluate two parameters of a first-order decay model, methane generation potential ($L_0$) and methane generation rate constant (k). The parameters were determined by the statistical comparison of predicted gas generation rate data using the two models and actual landfill gas collection data. The values of r-square obtained from regression analysis between two data showed that one model by differentiating the Modified Gompetz was 0.92 and the other model by differentiating the Logistic was 0.94. From this result, the estimation methods showed that $L_0$ and k values can be determined by regression analysis if landfill gas collection data are available. Also, new models based on two models obtained by differentiating the Modified Gompertz and Logistic models were developed to predict greenhouse gas generation from solid waste landfills that actual landfill generation data could not be available. They showed better prediction than LandGEM model. Frequency distribution of the ratio of Qcs (LFG collection system) to Q (prediction value) was used to evaluate the accuracy of the models. The new models showed higher accuracy than LandGEM model. Thus, it is concluded that the models developed in this research are suitable for the prediction of greenhouse gas generation from solid waste landfills.

• Journal of Broadcast Engineering
• /
• v.25 no.2
• /
• pp.200-207
• /
• 2020

Recently, deep neural networks such as CNN are showing excellent performance in various fields such as image classification, object recognition, visual quality enhancement, etc. However, as the model size and computational complexity of deep learning models for most applications increases, it is hard to apply neural networks to IoT and mobile environments. Therefore, neural network compression algorithms for reducing the model size while keeping the performance have been being studied. In this paper, we apply few compression methods to CNN models and evaluate their performances in the embedded environment. For evaluate the performance, the classification performance and inference time of the original CNN models and the compressed CNN models on the image inputted by the camera are evaluated in the embedded board equipped with QCS605, which is a customized AI chip. In this paper, a few CNN models of MobileNetV2, ResNet50, and VGG-16 are compressed by applying the methods of pruning and matrix decomposition. The experimental results show that the compressed models give not only the model size reduction of 1.3~11.2 times at a classification performance loss of less than 2% compared to the original model, but also the inference time reduction of 1.2~2.21 times, and the memory reduction of 1.2~3.8 times in the embedded board.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2010.10a
• /
• pp.110-111
• /
• 2010

Recently, container terminal managers make an experiment on the double cycle and dual cycle operation, which ship loading and unloading were carried out simultaneously, for increasing the productivity of quay side. However, if we make an experiment on dual cycle operation in a real job site, the efficiency is poor up to terminal operation method as YTs(Yard Tractors)' allocation method, QCs(Quay Cranes)' working speed, and position of export containers. So, this paper examine more efficient terminal operation method, when terminal uses dual cycle operation.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.11a
• /
• pp.44-45
• /
• 2019

최근 CNN 등 인공신경망은 최근 이미지 분류, 객체 인식, 자연어 처리 등 다양한 분야에서 뛰어난 성능을 보이고 있다. 그러나, 대부분의 분야에서 보다 더 높은 성능을 얻기 위해 사용한 인공신경망 모델들은 파라미터 수 및 연산량 등이 방대하여, 모바일 및 IoT 디바이스 같은 연산량이나 메모리가 제한된 환경에서 추론하기에는 제한적이다. 따라서 연산량 및 모델 파라미터 수를 압축하기 위한 딥러닝 경량화 알고리즘이 연구되고 있다. 본 논문에서는 임베디트 보드에서의 압축된 CNN 모델의 성능을 검증한다. 인공지능 지원 맞춤형 칩인 QCS605 를 내장한 임베디드 보드에서 카메라로 입력한 영상에 대해서 원 CNN 모델과 압축된 CNN 모델의 분류 성능과 동작속도 비교 분석한다. 본 논문의 실험에서는 CNN 모델로 MobileNetV2, VGG16 을 사용했으며, 주어진 모델에서 가지치기(pruning) 기법, 양자화, 행렬 분해 등의 인공신경망 압축 기술을 적용하였을 때 원래의 모델 대비 추론 시간 및 분류의 정확도 성능을 분석하고 인공신경망 압축 기술의 유용성을 확인하였다.

• Journal of Navigation and Port Research
• /
• v.35 no.1
• /
• pp.71-76
• /
• 2011

Recently, container terminal managers make an experiment on the double cycle and dual cycle operation, which ship loading and unloading were carried out simultaneously, for increasing the productivity of quay side. If, however, we make an experiment on dual cycle operation in a real job site, the efficiency is poor up to terminal operation method as YTs(Yard Tractors)' allocation method, QCs(Quay Cranes)' working speed, and position of export containers. Especially, using the existing yard operation method, it is difficult to support to dual and double cycle operation. Therefore, this paper examine more efficient terminal operation method, when terminal uses dual cycle operation. We developed a simulation model using simulation analysis software, Arena.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2011.11a
• /
• pp.170-171
• /
• 2011

Recently, container terminal managers make an experiment on the double cycle and dual cycle operation, which ship loading and unloading were carried out simultaneously, for increasing the productivity of quay side. If, however, we make an experiment on dual cycle operation in a real job site, the efficiency is poor up to terminal operation method as YTs(Yard Tractors)' allocation method, QCs(Quay Cranes)' working speed, and position of export containers. Especially, using the existing yard operation method, it is difficult to support to dual and double cycle operation. Therefore, this paper examine more efficient terminal operation method, when terminal uses dual cycle operation. We developed a simulation model using simulation analysis software, Arena.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.3 s.309
• /
• pp.1-8
• /
• 2006

In this paper, we propose a new post-processing method, based on the theory of the projection onto convex sets (POCS) to reduce the blocking artifacts in decoded images. We propose a few smoothness constraint set (SCS) and its projection operator in the wavelet transform (WT) domain to remove unnecessary high-frequency components caused by blocking artifacts. We also propose a new method to find and preserve the original high frequency components of the image edge. Experimental results show that the proposed method can not only achieve a significantly enhanced subjective quality, but also have the PSNR improvement in the output image.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.43 no.3 s.309
• /
• pp.54-60
• /
• 2006

This paper presents an effective algorithm for transcoding between the Enhanced Variable Rate Codec(EVRC) and G.729A. The simplest way to communicate between heterogeneous speech networks is the cascade connection of two different codecs, called tandem coding. However, tandem coding not only produces high computational loads, but also makes long delay, These problems can be solved by using the transcoding algorithm. The proposed algorithm consists of LSP (Line Spectral Pair) conversion, pitch delay conversion and algorithm for reduction of delay. Experimental results show the proposed algorithm produces lower computational complexity, shorter algorithm delay, and similar speech quality when compared with the tandem algorithm.