• Journal of the Korea Society for Simulation
• /
• v.25 no.1
• /
• pp.45-52
• /
• 2016

In this study, we consider a capacity planning problem of reentrant hybrid flowshops. High-tech electronic products such as semiconductor or TFT-LCD, are produced from manufacturing systems which can be considered as reentrant hybrid flowshops. In the considered capacity planning problem, we determine the number of machines at each stage in the manufacturing system. We introduce criteria indicating which stage needs additional machines or which stage needs reduction of machines considering the characteristics of the product types and the manufacturing system. The objective function of the problem is maximizing throughput rate of the system, of which values are obtained from the simulation model depicting the hybrid flowshops. The performance of the proposed methods were evaluated through a series of computational experiments. The simulation model was also used for conducting the comparison experiments among the proposed method and benchmarks.

• Journal of the Korea Society for Simulation
• /
• v.20 no.3
• /
• pp.1-10
• /
• 2011

In this study, we consider a capacity planning problem where the number of machines at each workstation is determined in manufacturing systems of top-edge electronic products such as semiconductor or display. The considered manufacturing system is the typical hybrid flowshop which has identical parallel machines at each workstation and the setup operation occurs when the types of consecutively processed products are different. The objective of the problem is finding good combinations of the numbers of machines at all workstations, under the given capital amount for purchasing machines. Various heuristic methods for determining the numbers of machines at workstations are proposed and the performances were tested through a series of computational experiments. In the study, a simulation model has been developed in order to simulate the considered manufacturing system with dynamic orders and complex process. The simulation model is also used for conducting the computational comparison test among various proposed methods.

• Journal of the Korean Society for Precision Engineering
• /
• v.22 no.5 s.170
• /
• pp.103-112
• /
• 2005

This paper presents one-axis high precision scanning system and illustrates the design of modified $X-Y-{\theta}$ stage as a tracker using VCM and commercialized air bearings for it. The scanning system for 100nm resolution is composed of the 3-axis stage and one axis long stroke linear motor stage as a follower. In this study a previous proposed and presented structure of VCM for the fine stage is modified. The tracker has 3 DOF($X-Y-{\theta}$ motions by four VCM actuators which are located on the same plane. So 4 actuating forces are suggested and designed to create least pitch and roll motions. This article will show about the design especially about optimal design. The design focus of this fine stage is to have high acceleration to accomplish high throughput. The optimal design of maximizing acceleration is performed in restrained size. The most sensitive constraint of this optimal design is heat dissipation of coil. There are 5 design variables. Because the relationship between design variables and system parameters are quite complicated, it is very difficult to set design variables manually. Due to it, computer based optimal design procedure using MATLAB is used. Then, this paper also describes the procedures of selecting design variables for the optimal design and a mathematical formulation of the optimization problem. Based on the solution of the optimization problem, the final design of the stage is also presented. The results can be verified by MAXWELL. The designed stage has the acceleration of about 5 $m/s^{2}$ with 40kg total mass including wafer chuck and interferometer mirror. And the temperature of coil is increased $50^{\circ}C$. In addition, the tracker is controlled by high precision controller system with HP interferometer for it and linear scaler for the follower. At that time, the scanning system has high precision resolution about 5nm and scanning resolution about 40nm in 25mm/s constant speed

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.5
• /
• pp.2233-2252
• /
• 2018

For the problem of cross-layer joint resource allocation (JRA) in the Long-Term Evolution (LTE)-Advanced standard using carrier aggregation (CA) technology, it is difficult to obtain the optimal resource allocation scheme. This paper proposes a joint resource allocation algorithm based on the weights of user's average quality of experience (JRA-WQOE). In contrast to prevalent algorithms, the proposed method can satisfy the carrier aggregation abilities of different users and consider user fairness. An optimization model is established by considering the user quality of experience (QoE) with the aim of maximizing the total user rate. In this model, user QoE is quantified by the mean opinion score (MOS) model, where the average MOS value of users is defined as the weight factor of the optimization model. The JRA-WQOE algorithm consists of the iteration of two algorithms, a component carrier (CC) and resource block (RB) allocation algorithm called DABC-CCRBA and a subgradient power allocation algorithm called SPA. The former is used to dynamically allocate CC and RB for users with different carrier aggregation capacities, and the latter, which is based on the Lagrangian dual method, is used to optimize the power allocation process. Simulation results showed that the proposed JRA-WQOE algorithm has low computational complexity and fast convergence. Compared with existing algorithms, it affords obvious advantages such as improving the average throughput and fairness to users. With varying numbers of users and signal-to-noise ratios (SNRs), the proposed algorithm achieved higher average QoE values than prevalent algorithms.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.5
• /
• pp.49-54
• /
• 2022

With the recent widespread adoption of general-purpose GPUs (GPGPUs) in cloud systems, maximizing the resource utilization through multitasking in GPGPU has become an important issue. In this article, we show that resource allocation based on the workload classification of computing-bound and memory-bound is not sufficient with respect to resource utilization, and present a new thread block scheduling policy for GPGPU that makes use of fine-grained resource utilizations of each workload. Unlike previous approaches, the proposed policy reduces scheduling overhead by separating profiling and scheduling, and maximizes resource utilizations by co-locating workloads with different bottleneck resources. Through simulations under various virtual machine scenarios, we show that the proposed policy improves the GPGPU throughput by 130.6% on average and up to 161.4%.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.89-106
• /
• 2022

Recently, the amount of video data collected from smartphones, CCTVs, black boxes, and high-definition cameras has increased rapidly. According to the increasing video data, the requirements for analysis and utilization are increasing. Due to the lack of skilled manpower to analyze videos in many industries, machine learning and artificial intelligence are actively used to assist manpower. In this situation, the demand for various computer vision technologies such as object detection and tracking, action detection, emotion detection, and Re-ID also increased rapidly. However, the object detection and tracking technology has many difficulties that degrade performance, such as re-appearance after the object's departure from the video recording location, and occlusion. Accordingly, action and emotion detection models based on object detection and tracking models also have difficulties in extracting data for each object. In addition, deep learning architectures consist of various models suffer from performance degradation due to bottlenects and lack of optimization. In this study, we propose an video analysis system consists of YOLOv5 based DeepSORT object tracking model, SlowFast based action recognition model, Torchreid based Re-ID model, and AWS Rekognition which is emotion recognition service. Proposed model uses single-linkage hierarchical clustering based Re-ID and some processing method which maximize hardware throughput. It has higher accuracy than the performance of the re-identification model using simple metrics, near real-time processing performance, and prevents tracking failure due to object departure and re-emergence, occlusion, etc. By continuously linking the action and facial emotion detection results of each object to the same object, it is possible to efficiently analyze videos. The re-identification model extracts a feature vector from the bounding box of object image detected by the object tracking model for each frame, and applies the single-linkage hierarchical clustering from the past frame using the extracted feature vectors to identify the same object that failed to track. Through the above process, it is possible to re-track the same object that has failed to tracking in the case of re-appearance or occlusion after leaving the video location. As a result, action and facial emotion detection results of the newly recognized object due to the tracking fails can be linked to those of the object that appeared in the past. On the other hand, as a way to improve processing performance, we introduce Bounding Box Queue by Object and Feature Queue method that can reduce RAM memory requirements while maximizing GPU memory throughput. Also we introduce the IoF(Intersection over Face) algorithm that allows facial emotion recognized through AWS Rekognition to be linked with object tracking information. The academic significance of this study is that the two-stage re-identification model can have real-time performance even in a high-cost environment that performs action and facial emotion detection according to processing techniques without reducing the accuracy by using simple metrics to achieve real-time performance. The practical implication of this study is that in various industrial fields that require action and facial emotion detection but have many difficulties due to the fails in object tracking can analyze videos effectively through proposed model. Proposed model which has high accuracy of retrace and processing performance can be used in various fields such as intelligent monitoring, observation services and behavioral or psychological analysis services where the integration of tracking information and extracted metadata creates greate industrial and business value. In the future, in order to measure the object tracking performance more precisely, there is a need to conduct an experiment using the MOT Challenge dataset, which is data used by many international conferences. We will investigate the problem that the IoF algorithm cannot solve to develop an additional complementary algorithm. In addition, we plan to conduct additional research to apply this model to various fields' dataset related to intelligent video analysis.

• Journal of Navigation and Port Research
• /
• v.40 no.6
• /
• pp.485-494
• /
• 2016

The primary purpose of this study is to analyze the impact and determinants of bilateral Free Trade Agreements on international total bulk shipment trade volume at the port of Korea using the Panel Gravity Model. The model estimates the aggregated panel data of exports and imports (excluding transshipment) as a dependent variable during the period from 1996 to 2015. GDP, GDP per capita, distances between bilateral countries, and FTA dummies are included as independent variables. And the economic integration of FTAs including ASEAN+3 and NAFTA3 countries were used as dummy variables. Study results show that GDP and GDP per capita have positive impacts on bulk shipment trade volume at the port of Korea. In addition, Korea's bilateral FTAs with Singapore, India and the United States have positive effects on total bulk trade volume in Korea. This is the so called trade creation effect. On the other hand, ASEAN+3 and NAFTA have negative effects on the total bulk trade. This is the so called trade diversion effect. Also, the distance between Korea and its trade partners has a negative impact. These findings provide insights for: further academic research, site operators who work in related trade and maritime sectors, and policy makers engaged in port and maritime operations. The results can be used to develop strategies for maximizing bulk port throughput.

• Journal of Korean Port Research
• /
• v.13 no.2
• /
• pp.333-350
• /
• 1999

Today freeway is thought to be a very important transportation facility carrying tremendous traffic flow as the main corridor within the area of between the areas. However freeway is experiencing severe congestion and accidents by increased entrance ramp flow especially at peak time period. Ramp meters on the freeway entrance ramps that supply traffic to the freeway in a measured or appropriately regulated amount are needed for alleviating freeway congestion. Because ramp meters can be operated to discharge traffic at a measured or regulated rate thus maintaining more uniform speed on the mainline section maximizing the throughput to the freeway within the capacity of a downstream bottleneck and reducing the congestion related accidents. Thus the objectives in this study were to analyze the traffic characteristics on the freeway I-94 with ramp metering system before/after ITS technology in Detroit (Michigan) area compare shifts of the traffic characteristics on the freeway I-94 before/after ITS technology and finally suggest a better ramp metering strategy for the freeway system The following results were obtained: i)Flow occupancies and speeds on the mainline merge section of freeway were shown to be a big difference depending on the peak periods areas and directions based on the distribution of traffic flow characteristics on the freeway. ii)Reduced speed was shown to be more than 5 mph and ramp flow was also shown to be more than 240 vph at peak periods if there was the ramp metering system constructed on the freeway. iii)Ramp metering system was shown to be optimally operated on the freeway if ramp flow could be maximized within the range of over 900 vph and reduced occupancy could be also maximized by no more than 2 percent at peak periods. iv)The average flows on the freeway after the ITS technology were shown to be a decrease of over 20% depending on the peak periods areas and directions when compared with those flow on the freeway before the ITS technology. over 20% depending on the peak periods areas and directions when compared with those speeds on the freeway before the ITS technology. vi)The average metering rates on the freeway after the ITS technology were shown to be an increase of over 10% depending on the peak periods areas and directions when compared with those metering rates on the freeway before the ITS technology.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.8
• /
• pp.215-222
• /
• 2021

In order to alleviate the limited resource problem and interference problem in cellular networks, the dual connectivity technology has been introduced with the cooperation of small cell base stations. In this paper, we design a new efficient and fair resource allocation scheme for the dual connectivity technology. Based on two different bargaining solutions - Generalizing Tempered Aspiration bargaining solution and Gupta and Livne bargaining solution, we develop a two-stage radio resource allocation method. At the first stage, radio resource is divided into two groups, such as real-time and non-real-time data services, by using the Generalizing Tempered Aspiration bargaining solution. At the second stage, the minimum request processing speeds for users in both groups are guaranteed by using the Gupta and Livne bargaining solution. These two-step approach can allocate the 5G radio resource sequentially while maximizing the network system performance. Finally, the performance evaluation confirms that the proposed scheme can get a better performance than other existing protocols in terms of overall system throughput, fairness, and communication failure rate according to an increase in service requests.