• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권5호
• /
• pp.2253-2272
• /
• 2018

We propose a deep learning method for multi-focus image fusion. Unlike most existing pixel-level fusion methods, either in spatial domain or in transform domain, our method directly learns an end-to-end fully convolutional two-stream network. The framework maps a pair of different focus images to a clean version, with a chain of convolutional layers, fusion layer and deconvolutional layers. Our deep fusion model has advantages of efficiency and robustness, yet demonstrates state-of-art fusion quality. We explore different parameter settings to achieve trade-offs between performance and speed. Moreover, the experiment results on our training dataset show that our network can achieve good performance with subjective visual perception and objective assessment metrics.

• International Journal of Computer Science & Network Security
• /
• 제22권2호
• /
• pp.232-240
• /
• 2022

To fulfill user expectations, the rapid evolution of software techniques and approaches has necessitated reliable and flawless software operations. Aging prediction in the software under operation is becoming a basic and unavoidable requirement for ensuring the systems' availability, reliability, and operations. In this paper, an improved evolutionary computing-driven extreme learning scheme (ECD-ELM) has been suggested for object-oriented software aging prediction. To perform aging prediction, we employed a variety of metrics, including program size, McCube complexity metrics, Halstead metrics, runtime failure event metrics, and some unique aging-related metrics (ARM). In our suggested paradigm, extracting OOP software metrics is done after pre-processing, which includes outlier detection and normalization. This technique improved our proposed system's ability to deal with instances with unbalanced biases and metrics. Further, different dimensional reduction and feature selection algorithms such as principal component analysis (PCA), linear discriminant analysis (LDA), and T-Test analysis have been applied. We have suggested a single hidden layer multi-feed forward neural network (SL-MFNN) based ELM, where an adaptive genetic algorithm (AGA) has been applied to estimate the weight and bias parameters for ELM learning. Unlike the traditional neural networks model, the implementation of GA-based ELM with LDA feature selection has outperformed other aging prediction approaches in terms of prediction accuracy, precision, recall, and F-measure. The results affirm that the implementation of outlier detection, normalization of imbalanced metrics, LDA-based feature selection, and GA-based ELM can be the reliable solution for object-oriented software aging prediction.

• Journal of the Korea Society for Simulation
• /
• 제8권4호
• /
• pp.9-24
• /
• 1999

We describe a heterogeneous simulation framework, so called DEVS-HLA, in which conventional simulation models and the DEVS (Discrete Event System Specification) models are interoperable. DEVS-HLA conceptually consists of three layers: model layer, DEVS BUS layer, and HLA (High Level Architecture) layer. The model layer has a collection of heterogeneous simulation models, such as DEVS, CSIM, SLAM, and so on, to represent various aspects of a complex system. The DEVS BUS layer provides a virtual software bus, DEVS BUS, so that such simulation models can communicate with each other. Finally, the HLA layer is employed as a communication infrastructure, which supports several good features for distributed simulation. The DEVS BUS has been implemented on the HLA/RTI (Run-Time Infrastructure) and a simple example of a flexible manufacturing system has been developed to validate the DEVS-HLA.

• Journal of the Korea Society of Computer and Information
• /
• 제24권3호
• /
• pp.19-27
• /
• 2019

This paper proposes a new method using multi-layer overlapped windows to improve the performance of YOLO network which is vulnerable to detect small dense objects. In particular, the proposed method uses the YOLO Network based on the multi-layer overlapped windows to track small dense vehicles that approach from long distances. The method improves the detection performance for location and size of small vehicles. It allows crossing area of two multi-layer overlapped windows to track moving vehicles from a long distance to a short distance. And the YOLO network is optimized so that GPU computation time due to multi-layer overlapped windows should be reduced. The superiority of the proposed algorithm has been proved through various experiments using captured images from road surveillance cameras.

• Journal of Computational Design and Engineering
• /
• 제1권4호
• /
• pp.243-255
• /
• 2014

The present study describes the development of control hardware and software for a mobile welding robot. This robot is able to move and perform welding tasks in a double hull structure. The control hardware consists of a main controller and a welding machine controller. Control software consists of four layers. Each layer consists of modules. Suitable combinations of modules enable the control software to perform the required tasks. Control software is developed using C programming under QNX operating system. For the modularizing architecture of control software, we designed control software with four layers: Task Manager, Task Planner, Actions for Task, and Task Executer. The embedded controller and control software was applied to the mobile welding robot for successful execution of the required tasks. For evaluate this imbedded controller and control software, the field tests are conducted, it is confirmed that the developed imbedded controller of mobile welding robot for shipyard is well designed and implemented.

• Journal of the Korean Society for Precision Engineering
• /
• 제18권8호
• /
• pp.64-70
• /
• 2001

In all the Rapid Prototyping (RP) techniques, the computer-aided design (CAD) model of a three-dimensional part is sliced into horizontal layers of uniform, but not necessarily constant, thickness in the building direction. Each cross- sectional layer is successively deposited and, at the same time, bonded onto the previous layer. The stacked layers form a physical part of the model. The objective of this study is to develop a software for automatic generation of unit shape part(USP) for a new RP process, Variable Lamination Manufacturing using the linear hotwire cutting technique and expandable polystyrene foam sheet as part material(VLM-S). In order to examine the applicability of the developed software to VLM-S, USPs of general three-dimensional shapes, such as an auto-shift lever knob and a pyramid shape were generated.

• Journal of Institute of Control, Robotics and Systems
• /
• 제4권1호
• /
• pp.113-122
• /
• 1998

This paper presents an implementation method of Profibus interface software using FMS(Fieldbus Message Specification). The Profibus interface software is implemented on PC which is widely used as an industrial computer as well as a commercial embedded controller called IUC(Intelligent Universal Controller). In order to enable the Profibus interface software to handle many application tasks and communication services, two kinds of real-time/multi-tasking operating system, OS-9 and CTask, are utilized. We also develop an experimental model of Profibus-based automation system, and evaluate the performance of the Profibus network. Through experiments, the user layer level message latency is measured with respect to the change of message length, message generation interval and TRT(Target Rotation Time). The results of experiment are compared with those of a simulation model which comprises only the physical and data link layers of Profibus. The results of this study shows that the message latency in the user layer level occupies fairly a large part of the total message latency.

• ETRI Journal
• /
• 제42권2호
• /
• pp.186-195
• /
• 2020

Software-defined networking (SDN) acts as a centralized management unit, especially in a network with devices that operate under the transport layer of the OSI model. However, when a network with layer 7 middleboxes (MBs) is considered, current SDNs exhibit limitations. As such, to achieve a real-centralized management unit, a new architecture is required that decouples the data and control planes of all network devices. In this report, we propose such a complementary architecture to the current SDN in which SDN-enabled MBs are included along with contemporary SDN-enabled switches. The management unit of this architecture improves network performance and reduces routing cost by considering the status of the MBs during flow forwarding. This unit consists of the following two parts: an SDN controller (SDNC) and a middlebox controller (MBC). The latter selects the best MBs for each flow and the former determines the best path according to its routing algorithm and provides information via the MBC. The results show that the proposed architecture improved performance because the utilization of all network devices including MBs is manageable.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 한국정보통신학회 2021년도 추계학술대회
• /
• pp.186-188
• /
• 2021

본 논문에서는 초음파 영상에서 DBSCAN(Density-based spatial clustering of applications with noise)과 FCM 클러스터링 기반 양자화 기법을 적용하여 결절종을 추출하는 방법을 제안한다. 본 논문에서는 초음파 영상 촬영 시 좌우 상단의 지방층 영역과 하단 영역의 명암도가 어두운 영역을 잡음 영역으로 설정한다. 그리고 초음파 영상에 퍼지스트레칭 기법을 적용하여 잡음 영역을 최대한 제거 한 후에 ROI 영역을 추출한다. 추출된 ROI 영역에서 밀도 분포를 분석하기 위하여 히스토그램을 분석한 후에 DBSCAN을 적용하여 초음파 영상에서 결절종 후보에 해당되는 명암도를 추출한다. 추출한 후보 명암도를 대상으로 FCM 클러스터링 기법을 적용한다. FCM을 적용하는 단계에서 결절종의 저에코 혹은 무에코의 특징을 이용하여 클러스터 중심 값이 가장 낮은 클러스터를 양자화 한 후에 라벨링 기법을 적용시켜 결절종의 후보 객체를 추출한다. 제안된 결절종 추출 방법의 성능을 분석하기 위해 전문의가 결절종 영역을 표기한 초음파 영상과 표기되지 않은 초음파 영상 120쌍을 대상으로 DBSCAN, FCM, 그리고 제안된 방법 간의 성능을 비교 분석하였다. 제안된 방법에서는 120개의 초음파 영상에서 106개 결절종 영역이 추출되었고 FCM 기법에서는 80개가 추출되었고 DBSCAN에서는 36개가 추출되었다. 따라서 제안된 방법이 결절종 추출에 효율적인 것을 확인하였다.

• 한국정보디스플레이학회:학술대회논문집
• /
• 한국정보디스플레이학회 2008년도 International Meeting on Information Display
• /
• pp.540-542
• /
• 2008

By ETFOS software simulation to swiftly find out the shortcomings of the device structure and conserve the wastage of time cost in experiments, including the instruments deviations or human errors. Thereby we can calibrate the correct organic layer thickness by comparing the EL spectra with different NPB thicknesses.