• International Journal of Computer Science & Network Security
• /
• v.21 no.6
• /
• pp.77-88
• /
• 2021

Heart Failure represents a critical pathological case that is challenging to predict and discover at an early age, with a notable increase in morbidity and mortality. Machine Learning and Neural Network techniques play a crucial role in predicting heart attacks, diseases and more. These techniques give valuable perspectives for clinicians who may then adjust their diagnosis for each individual patient. This paper evaluated neural network models for heart attacks predictions. Several online learning methods were investigated to automatically and accurately predict heart attacks. The UCI dataset was used in this work to train and evaluate First Order and Second Order Online Learning methods; namely Backpropagation, Delta bar Delta, Levenberg Marquardt and QuickProp learning methods. An optimizer technique was also used to minimize the random noise in the database. A regularization concept was employed to further improve the generalization of the model. Results show that a three layers' NN model with a Backpropagation algorithm and Nadam optimizer achieved a promising accuracy for the heart attach prediction tasks.

• Annual Conference of KIPS
• /
• 2022.11a
• /
• pp.402-404
• /
• 2022

Recent research has shown that deep learning models are vulnerable to adversarial attacks not only in the digital but also in the physical domain. This becomes very critical for applications that have a very high safety concern, such as self-driving cars. In this study, we propose a physical adversarial attack technique for one of the common tasks in self-driving cars, namely segmentation of the urban scene. Our method can create a texture on a wall so that it can be misclassified as a road. The demonstration of the technique on a state-of-the-art cityscape pretrained model shows a fairly high success rate, which should raise awareness of more potential attacks in self-driving cars.

• Journal of the military operations research society of Korea
• /
• v.28 no.2
• /
• pp.125-136
• /
• 2002

This paper is aimed to develop Tank Simulation Model. The model simulates Tank-to-Tank engagement and Tank-to-Helicopter engagement by considering Korean battlefield environment. The simulated entities are command tanks, fight tanks, scout helicopters, attack helicopters, anti-tank guided missiles, and decoys. In this paper, we explain the model operational concept, model development and finally we will show some illustrative examples.

• Journal of the Korea Computer Industry Society
• /
• v.4 no.4
• /
• pp.491-500
• /
• 2003

The need for network security is being increasing due to the development of information communication and internet technology, In this paper, firewall models, operating system models and other network component models are constructed. Each model Is defined by basic or compound model using MODSIM III. In this simulation environment with representative attacks, the following attacks are generated, SYN flooding and Smurf attack as an attack type of denial of service. The simulation is performed with the models that exploited various security policies against these attacks. In addition, the results of the simulation show that the analysis of security performance according to various security policies, and the analysis of correlation between availability and confidentiality according to security empowerment.

• Journal of Aerospace System Engineering
• /
• v.7 no.3
• /
• pp.1-6
• /
• 2013

Numerical optimization of two dimensional high lift configuration was performed with flow solver and optimization method based on RSM(Response Surface Model). Navier-Stokes solver with Spalart-Allmaras turbulence model was selected for the simulation of highly complex and separated flows on the flap. For the simultaneous optimization of both flap shape and setting (gap/overlap), 10 design variables (eight variables for flap shape variation and two variables for flap setting) were chosen. In order to generate the response surface model, 128 experimental points were selected for 10 design variables. The objective function considering maximum lift coefficient, lift to drag ratio and lift coefficient at specific angle of attack was selected to reduce flow separation on the flap surface. The present method was applied to two dimensional fowler flap in landing configuration. After applying the present method, it was shown that the optimized high lift configuration had less flow separation on the flap surface and lift to drag ratio was suppressed over entire angle of attack range.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.3
• /
• pp.1785-1801
• /
• 2017

In recent years, image encryption algorithms have been developed rapidly in order to ensure the security of image transmission. With the assistance of our previous work, this paper proposes a novel chaotic image encryption algorithm based on self-adaptive model and feedback mechanism to enhance the security and improve the efficiency. Different from other existing methods where the permutation is performed by the self-adaptive model, the initial values of iteration are generated in a novel way to make the distribution of initial values more uniform. Unlike the other schemes which is on the strength of the feedback mechanism in the stage of diffusion, the piecewise linear chaotic map is first introduced to produce the intermediate values for the sake of resisting the differential attack. The security and efficiency analysis has been performed. We measure our scheme through comprehensive simulations, considering key sensitivity, key space, encryption speed, and resistance to common attacks, especially differential attack.

• Convergence Security Journal
• /
• v.5 no.2
• /
• pp.9-17
• /
• 2005

Recently It's difficult to deal with about variety of attack. And Simple Security management have a problem. It is that they don't develop system measuring their system envoirment and have efficient attack detector, countermeasure organization about large network. Therefore, need model about enterprise management of various security system and intrusion detection of each systems and response. In this paper, improve PBNM structure that manage wide network resources and presented suitable model in intrusion detection and response of security system. Also, designed policy-based enterprise security management system for effective intrusion detection and response by applying presented model to enterprise security management system.

• Journal of Digital Convergence
• /
• v.13 no.5
• /
• pp.251-257
• /
• 2015

Intrusion protection system is a security system that stop abnormal traffics through automatic activity by finding out attack signatures in network. Unlike firewall or intrusion detection system that defends passively, it is a solution that stop the intrusion before intrusion warning. The security performance of intrusion protection system is influenced by security auditability, user data protection, security athentication, etc., and performance is influenced by detection time, throughput, attack prevention performance, etc. In this paper, we constructed a convergence performance evaluation model about software product evaluation to construct the model for security performance evaluation of intrusion protection system based on CC(Common Criteria : ISO/IEC 15408) and ISO international standard about software product evaluation.

• Journal of the Korean Society of Visualization
• /
• v.19 no.3
• /
• pp.106-114
• /
• 2021

In the present study, we investigate the flow characteristics of a paraglider canopy with leading-edge tubercles by performing force measurement and surface flow visualizations. The experiment is conducted at Re = 3.3×10⁵ in a wind tunnel, where Re is the Reynolds number based on the mean chord length and the free-stream velocity. The canopy model with leading-edge tubercles has flow characteristics of a two-step stall, showing an earlier onset of the first stall than the canopy model without leading-edge tubercles. However, the main stall angle of the tubercled model is much larger than that of the canopy model without tubercles, resulting in a higher aerodynamic performance at high angles of attack. The delay in the main stall is ascribed to the suppression of separation bubble collapse around the wingtip at high angles of attack.

• Wind and Structures
• /
• v.38 no.2
• /
• pp.147-160
• /
• 2024

The aerodynamic force is a significant component that influences the stability and safety of structures. It has unstable properties and depends on computer precision, making its long-term prediction challenging. Accurately estimating the aerodynamic traits of structures is critical for structural design and vibration control. This paper establishes an unsteady aerodynamic time series prediction model using Long Short-Term Memory (LSTM) network. The unsteady aerodynamic force under varied Reynolds number and angles of attack is predicted by the LSTM model. The input of the model is the aerodynamic coefficients of the 1 to n sample points and output is the aerodynamic coefficients of the n+1 sample point. The model is predicted by interpolation and extrapolation utilizing Unsteady Reynolds-average Navier-Stokes (URANS) simulation data of flow around a circular cylinder, square cylinder and airfoil. The results illustrate that the trajectories of the LSTM prediction results and URANS outcomes are largely consistent with time. The mean relative error between the forecast results and the original results is less than 6%. Therefore, our technique has a prospective application in unsteady aerodynamic force prediction of structures and can give technical assistance for engineering applications.