• Steel and Composite Structures
• /
• 제46권4호
• /
• pp.565-575
• /
• 2023

This study represents a numerical research in vibration and buckling of functionally graded material (FGM) beam comprising edge crack by using finite element method (FEM) and multilayer perceptron (MLP). It is assumed that the material properties change only according to the exponential distributions along the beam thickness. FEM and MLP solutions of the natural frequencies and critical buckling load are obtained of the cracked FGM beam for clamped-free (C-F), hinged-hinged (H-H), and clamped-clamped (C-C) boundary conditions. Numerical results are obtained to show the effects of crack location (c/L), material properties (E₂/E₁), slenderness ratio (L/h) and end supports on the bending vibration and buckling properties of cracked FGM beam. The FEM analysis used in this paper was verified with the literature, and the fundamental frequency ratio ($\overline{P_{cr}}$) and critical buckling load ratio ($\overline{{\omega}}$) results obtained were compared with FEM and MLP. The results obtained are quite compatible with each other.

• 드라이브 ㆍ 컨트롤
• /
• 제20권3호
• /
• pp.25-34
• /
• 2023

In this study, we conducted a research on optimizing the spraying performance of agricultural drones and predicted the spraying performance in various flight conditions using the multi-layer perceptron (MLP). Data was collected using a test device for pesticide spraying performance according to the water sensitive paper (WSP) evaluation. MLP training involved supervised learning to achieve a coefficient of variation (CV), which indicates the degree of uniform spraying. The performance evaluation was conducted using R-squared (R²), the test samples showed an R² of 0.80. The results of this study showed that drone spraying performance can be predicted under various flight environments. In addition, the correlation analysis between flight conditions and predicted spraying performance will be useful for further research on optimizing the spraying performance of agricultural drones.

• 융합보안논문지
• /
• 제23권5호
• /
• pp.73-79
• /
• 2023

사이버 위협은 기술의 발전에 따라 진화되고 정교해지고 있으며, DDoS 공격으로 인한 서비스 장애를 발생 이슈들이 증가하고 있다. 최근 DDoS 공격은 특정 서비스나 서버의 도메인 주소에 대량의 트래픽을 유입시켜 서비스 장애를 발생시키는 유형이 많아지고 있다. 본 논문에서는 대역폭 소진 공격의 대표적인 공격 유형인 Syn Flooding 공격의 데이터를 생성 후, 효과적인 공격 탐지를 위해 Random Forest, Decision Tree, Multi-Layer Perceptron, KNN 알고리즘을 사용하여 비교 분석하였고 최적의 알고리즘을 도출하였다. 이 결과를 토대로 Syn Flooding 공격 탐지 정책을 위한 기법으로 효과적인 활용이 가능할 것이다.

• 한국통신학회:학술대회논문집
• /
• 한국통신학회 1990년도 하계종합학술발표회 논문집
• /
• pp.692-694
• /
• 1990

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 1991년도 춘계공동학술대회 발표논문 및 초록집; 전북대학교, 전주; 26-27 Apr. 1991
• /
• pp.5-5
• /
• 1991

• Journal of information and communication convergence engineering
• /
• 제1권3호
• /
• pp.104-108
• /
• 2003

A biologically inspired fuzzy multilayer perceptron is proposed in this paper. The proposed algorithm is established under consideration of biological neuronal structure as well as fuzzy logic operation. We applied this suggested learning algorithm to benchmark problem in neural network such as exclusive OR and 3-bit parity, and to digit image recognition problems. For the comparison between the existing and proposed neural networks, the convergence speed is measured. The result of our simulation indicates that the convergence speed of the proposed learning algorithm is much faster than that of conventional backpropagation algorithm. Furthermore, in the image recognition task, the recognition rate of our learning algorithm is higher than of conventional backpropagation algorithm.

• 한국멀티미디어학회논문지
• /
• 제23권9호
• /
• pp.1155-1163
• /
• 2020

Deep learning approach is emerging as a new way to improve the accuracy of tree species identification using bark image. However, the approach has not been studied enough because it is confronted with the problem of acquiring a large volume of bark image dataset. This study solved this problem by utilizing a pretrained off-the-shelf DCNN model. It compares the discrimination power of bark features extracted by each DCNN model. Then it extracts the features by using a selected DCNN model and feeds them to a multi-layer perceptron (MLP). We found out that the ResNet50 model is effective in extracting bark features and the MLP could be trained well with the features reduced by the principal component analysis. The proposed approach gives accuracy of 99.1% and 98.4% for BarkTex and Trunk12 datasets respectively.

• 한국측량학회지
• /
• 제35권4호
• /
• pp.313-318
• /
• 2017

Land surface temperature is essential for monitoring abnormal climate phenomena such as UHI (Urban Heat Islands), and for modeling weather patterns. However, the quality of surface temperature obtained from the optical space imagery is affected by many factors such as, revisit period of the satellite, instance of capture, spatial resolution, and cloud coverage. Landsat 8 imagery, often used to obtain surface temperatures, has a high resolution of 30 meters (100 meters rearranged to 30 meters) and a revisit frequency of 16 days. On the contrary, MODIS imagery can be acquired daily with a spatial resolution of about 1 kilometer. Many past attempts have been made using both Landsat and MODIS imagery to complement each other to produce an imagery of improved temporal and spatial resolution. This paper applied machine learning methods and performed downscaling which can obtain daily based land surface temperature imagery of 30 meters.

• 전기학회논문지
• /
• 제59권6호
• /
• pp.1136-1142
• /
• 2010

In this study, an efficient removal algorithm for specular reflections in a tooth color image is proposed to minimize the artefact interrupting color image segmentation. The pixel values of RGB color channels are initially reversed to emphasize the features in reflective regions, and then those regions are automatically detected by utilizing perceptron artificial neural network model and those prominent intensities are corrected by applying a smoothing spatial filter. After correcting specular reflection regions, multiple seeds in the tooth candidates are selected to find the regional minima and MCWA(Marker-Controlled Watershed Algorithm) is applied to delineate the individual tooth region in a CCD tooth color image. Therefore, the accuracy in segmentation for separating tooth regions can be drastically improved with removing specular reflections due to the illumination effect.

• 한국정보전자통신기술학회논문지
• /
• 제6권4호
• /
• pp.249-254
• /
• 2013

In the area of computer vision, face recognition is being intensively researched. It is generally known that before a face is recognized it must be localized. Skin-color information is an important feature to segment skin-color regions. To extract skin-color regions the skin-color model based on multi-layer perceptron has been proposed. Extracted regions are analyzed to emphasize ellipsoidal regions. The results from this study show good accuracy for our vehicle driver face detection system.