• Computers and Concrete
• /
• v.33 no.3
• /
• pp.285-299
• /
• 2024

Recently, many engineering computations have realized their digital transformation to Machine Learning (ML)-based systems. Predicting the behavior of a structure, which is mainly computed with structural analysis software, is an essential step before construction for efficient structural analysis. Especially in the seismic-based design procedure of the structures, predicting the lateral load capacity of reinforced concrete (RC) columns is a vital factor. In this study, a novel ML-based model is proposed to predict the maximum lateral load capacity of RC columns under varying axial loads or cyclic loadings. The proposed model is generated with a Deep Neural Network (DNN) and compared with traditional ML techniques as well as a popular commercial structural analysis software. In the design and test phases of the proposed model, 319 columns with rectangular and square cross-sections are incorporated. In this study, 33 parameters are used to predict the maximum lateral load capacity of each RC column. While some traditional ML techniques perform better prediction than the compared commercial software, the proposed DNN model provides the best prediction results within the analysis. The experimental results reveal the fact that the performance of the proposed DNN model can definitely be used for other engineering purposes as well.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.21 no.5
• /
• pp.649-657
• /
• 2018

It is essential that weapons which are mounted on aircraft need to prove its reliability and safety during its developments. A guided missile should have high reliability and safety throughout various tests which are including ground tests, captive flight tests, detailed technical tests and operational tests. In these various tests, it is vital that software of each component in the guided missile should be easily updated in order to correct algorithms or errors. In this paper, we propose a software update technique based on MDTP(mass data transfer protocol) which are defined in MIL-STD-1760. The proposed techniques have the following advantages: First, software of each unit in a weapon can be updated through a test equipment without disassemble a guided missile. Second, development periods for a software update can be reduced by reusing MDTP. Third, we can easily maintenance of the software because it is based on standard. We proved its efficiency and validity through experiments. Therefore, the proposed technique should be effectively utilized for software update of a weapon mounted on an aircraft during development processes.

• International Journal of Automotive Technology
• /
• v.6 no.4
• /
• pp.341-350
• /
• 2005

In this study, fault diagnosis and monitoring of serial wound pre-engaged starter motors have been carried out. Starter motors are DC motors that enable internal combustion engine (ICE) to run. In case of breakdown of a starter motor, internal combustion engine can not be worked. Starter motors have vital importance on internal combustion engines. Kohonen network based fault diagnosis system is proposed for fault diagnosis and monitoring of starter motors. A graphical user interface (GUI) software has been developed by using Visual Basic 6.0 for fault diagnosis. Six faults, seen in starter motors, have been diagnosed successfully by using the developed fault diagnosis system. GUI software makes it possible to diagnose the faults in starter motors before they occur by keeping fault records of past occurrences.

• Proceedings of the KSR Conference
• /
• 2007.05a
• /
• pp.1000-1007
• /
• 2007

Recently, many critical control systems are developed using formal methods. When software applied to such systems is developed, the employment of formal methods in the software requirements specification and verification will provide increased assurance for such applications. Earlier error of overlooked requirement specification can be detected using formal specification method. Also the testing and full verification to examine all reachable states using model checking to undertake formal verification are able to be completed. In the comparison of other formal specification methods, we choose the Z formal language for applying to the train control system. Using Z is able to realize higher correctness in the requirement specification, and we propose the Statemate of the best solution in formal verification tools for the system modeling and verification. The Statemate makes it possible to prove thoroughly the system execution from the simple graphical modeling of the complicated train control system. Then we can expect that the model-based formal method combining Z with Statemate will be utilized widely for the railway systems due to various strong points.

• International Journal of Computer Science & Network Security
• /
• v.22 no.4
• /
• pp.374-386
• /
• 2022

Nowadays, research in deep learning leveraged automated computing and networking paradigm evidenced rapid contributions in terms of Software Defined Networking (SDN) and its diverse security applications while handling cybercrimes. SDN plays a vital role in sniffing information related to network usage in large-scale data centers that simultaneously support an improved algorithm design for automated detection of network intrusions. Despite its security protocols, SDN is considered contradictory towards DDoS attacks (Distributed Denial of Service). Several research studies developed machine learning-based network intrusion detection systems addressing detection and mitigation of DDoS attacks in SDN-based networks due to dynamic changes in various features and behavioral patterns. Addressing this problem, this research study focuses on effectively designing a multistage hybrid and intelligent deep learning classifier based on modified deep forest classification to detect DDoS attacks in SDN networks. Experimental results depict that the performance accuracy of the proposed classifier is improved when evaluated with standard parameters.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2008.03a
• /
• pp.226-234
• /
• 2008

Grain design has always been a vital and integral part of Solid Rocket Motor(SRM) design. Basing on the design objectives set by the system designer, the SRM designer has many options available for selecting the Grain configuration. Many of the available configurations may fulfill the required parameters of volumetric loading fraction, web fraction & Length to diameter ratios and produce internal ballistic results that may be in accordance to the design objectives. However, for any given set of design objectives, it is deemed necessary that best possible configuration be selected, designed and optimized. Hence optimal results of all applicable configurations are vital to be attained in order to compare and finalize the design that will produce most efficient performance. Generally the engineers pay attention and have skills on a specific grain configuration. The designing methodologies and computer codes available usually focus on single grain configuration may it be Star, Wagon Wheel or slotted tube. Hardly one can find a software or a design methodology where all such configurations can be worked on jointly and not only adequate designs be found but optimal solutions reached by applying an optimization method to find final design best suited for any design objective. In the present work design requirements have been set, grain configurations have been selected and their designing has been conducted. The internal ballistic parameters have been calculated and after finding the preliminary design solutions, the optimal solutions have been found. In doing so, software has been developed comprising of computer programs for designing the 2D grains including Star, Wagon Wheel and Slotted Tube configurations. The optimization toolbox of Matlab Fmincon has been used for getting optimal solutions. The affects of all the independent geometric design variables on the optimized solutions have been analyzed. Based on results attained from Optimization Method, an in depth comparison of Grain Configurations and analysis of performance prediction outputs have been conducted to come to conclusion as to which grain configuration is ideal for the current design requirement under study.

• Journal of Digital Policy
• /
• v.2 no.4
• /
• pp.25-32
• /
• 2023

This paper is a study to develop a deep neural network (DNN) blood glucose prediction model based on heart rate (HR) and heart rate variability (HRV) data measured by PPG-based sensors. MLP deep learning consists of an input layer, a hidden layer, and an output layer with 11 independent variables. The learning results of the blood glucose prediction model are MAE=0.3781, MSE=0.8518, and RMSE=0.9229, and the coefficient of determination (R²) is 0.9994. The study was able to verify the feasibility of glycemic control using non-blood vital signs using PPG-based digital devices. In conclusion, a standardized method of acquiring and interpreting PPG-based vital signs, a large data set for deep learning, and a study to demonstrate the accuracy of the method may provide convenience and an alternative method for blood glucose management in dogs.

• Journal of Korea Game Society
• /
• v.7 no.4
• /
• pp.33-42
• /
• 2007

Advanced technologies and techniques make it possible to express digital animation with higher quality. Characters in the virtual animation space are playing an important role in emphasizing the human audiences or interacting directly with them. The movement of characters gives them vital power, and shows their intentions and emotions. To analyze the emotion of character movements, the study develops basic movement sources based on Laban's property elements of movement such as time, space, and flow, and tries to find the relationship between their movements and the emotions they arouse by positioning them on Plutchik's emotional circle. We find that each element of 9 movements represent its own emotion consistently, and has influence on the intensity of emotions clearly.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.377-379
• /
• 2022

POI refers to the point of Interest in Location-Based Social Networks (LBSNs). With the rapid development of mobile devices, GPS, and the Web (web2.0 and 3.0), LBSNs have attracted many users to share their information, physical location (real-time location), and interesting places. The tremendous demand of the user in LBSNs leads the recommendation systems (RSs) to become more widespread attention. Recommendation systems assist users in discovering interesting local attractions or facilities and help social network service (SNS) providers based on user locations. Therefore, it plays a vital role in LBSNs, namely POI recommendation system. In the machine learning model, most of the training data are stored in the centralized data storage, so information that belongs to the user will store in the centralized storage, and users may face privacy issues. Moreover, sharing the information may have safety concerns because of uploading or sharing their real-time location with others through social network media. According to the privacy concern issue, the paper proposes a recommendation model to prevent user privacy and eliminate traditional RS problems such as cold-start and data sparsity.

• Journal of Korean Academy of Fundamentals of Nursing
• /
• v.10 no.1
• /
• pp.96-107
• /
• 2003

Objective: The purpose of this study was to identify the effects of tracheal suction and the effects of different methods of bronchodilator inhalation (Ultrasonic nebulizer: MDI puff, MDI puff with spacer) in VSD surgery patients. Material & Method: From June 2001 to March 2002, sixty consecutive patients were randomly assigned to a control group (n= 15), ultrasonic nebulizer group (n=15), metered dose inhalation (MDI) puff group (n=15) and MDI with spacer group (n=15). Vital signs (HR, BP, CVP), ABGA and pulmonary functions were measured before suction (baseline for suction), after suction, 15 minutes after suction (base of bronchodilator inhalation), 30 minutes after bronchodilator inhalation, and 2 hours after bronchodilator inhalation. Stastistical analysis was performed using SPSS software. Repeated measure ANOVA was used to examine the effects of tracheal suction. One way ANOVA with Bonferroni's correction and multiple range test (the least significant difference test) were used to examine the effects of albuterol inhalation. Result: 1. Heart .ate increased significantly immediately after suction (p<.01) and recovered 15 minutes after suction. 2. $PaO_2$ and PH decreased significantly immediately after suction (p<.05) and $PaO_2$ recovered 15 minutes after suction. $PaCO_2$ increased immediately after suction and significantly 15 minutes after suction (p<.01). But changes in vital signs and ABGA were within the normal range. 3. Tidal volume decreased significantly 15 minutes after suction (p<.05). 4. Changes of HR and tidal volume were greater in the nebuizer group compared to the other groups (p<.05) 30 minutes after bronchodilator inhalation and recovered 2 hours after bronchodilator inhalation. 5. Changes of airway deadspace was greater in the nebulizer group compared to the control group and MDI puff group 30 minutes after albuterol inhalation (p<.05) and at 2 hours (p<.01). Conclusion: Tracheal suction did not have significant effect on vital signs and pulmonary functions after OHS. Although the methods of bronchodilator inhalation did not showed any significant difference on pulmonary function, the nebulizer method increased $PaO_2$ (20%) and tidal volume transiently. If the patient needs bronchodilator inhalation with bronchospasm after OHS, the nebulizer method is the best choice. More study on the effects of bronchodilator inhalation in bronchospasm group is needed.