• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1995년도 추계학술대회 논문집
• /
• pp.151-156
• /
• 1995

This paper presents a methodology for real-time detecting and identifying the runout geometry of an end mill. Cutter runout is a common but undesirable phenomenon in multi-tooth machining such as end-milling process because it introduces variable chip loading to insert which results in a accelerated tool wear,amplification of force variation and hence enlargement vibration amplitude. Form understanding of chip load change kinematics, the analytical sutting force model was formulated as the angular domain convolution of three dynamic cutting force component functions. By virtue of the convolution integration property, the frequency domain expression of the total cutting forces can be given as the algebraic multiplication of the Fourier transforms of the local cutting forces and the chip width density of the cutter. Experimental study are presented to validata the analytical model. This study provides the in-process monitoring and compensation of dynamic cutter runout to improve machining tolerance tolerance and surface quality for industriql application.

• 한국추진공학회:학술대회논문집
• /
• 한국추진공학회 2017년도 제48회 춘계학술대회논문집
• /
• pp.310-319
• /
• 2017

충격파 시험장치를 이용하여 추력을 측정하는 방법을 소개하였다. 충격파 시험장치를 이용하여 엔진의 추력을 측정하기 위해서는 일반적인 엔진시험 시설에서 추력을 측정하기 위해 사용하는 밸런스가 힘의 평형상태에 도달하지 못하기 때문에 응력파 힘 밸런스(Stress Wave Force Balance) 방법을 이용하여 측정한다. 본 논문에서는 모델 힘 밸런스(force balance)에 대해 충격하중을 주고 유한요소법(FEM)으로 변형률을 계산하였다. 충격하중과 변형률의 관계를 역합성곱(de-convolution)하여 천이함수를 도출하였다.

• 정보보호학회논문지
• /
• 제29권1호
• /
• pp.117-125
• /
• 2019

최근 다양한 분야에서 활용중인 딥러닝은 적대적 공격 가능성의 발견으로 위험성이 제기되고 있다. 본 논문에서는 딥러닝의 이미지 분류 모델에서 악의적 공격자가 생성한 적대적 샘플에 의해 분류 정확도가 낮아짐을 실험적으로 검증하였다. 대표적인 이미지 샘플인 MNIST데이터 셋을 사용하였으며, 텐서플로우와 파이토치라이브러리를 사용하여 만든 오토인코더 분류 모델과 CNN(Convolution neural network)분류 모델에 적대적 샘플을 주입하여 탐지 정확도를 측정한다. 적대적 샘플은 MNIST테스트 데이터 셋을 JSMA(Jacobian-based Saliency Map Attack)방법으로 생성한 방법과 FGSM(Fast Gradient Sign Method)방식으로 변형하여 생성하였으며, 분류 모델에 주입하여 측정하였을 때 최소 21.82%에서 최대 39.08%만큼 탐지 정확도가 낮아짐을 검증하였다.

• 한국인공지능학회지
• /
• 제11권3호
• /
• pp.17-22
• /
• 2023

In this paper, we propose a black ice detection system using Convolutional Neural Networks (CNNs). Black ice poses a serious threat to road safety, particularly during winter conditions. To overcome this problem, we introduce a CNN-based architecture for real-time black ice detection with an encoder-decoder network, specifically designed for real-time black ice detection using thermal images. To train the network, we establish a specialized experimental platform to capture thermal images of various black ice formations on diverse road surfaces, including cement and asphalt. This enables us to curate a comprehensive dataset of thermal road black ice images for a training and evaluation purpose. Additionally, in order to enhance the accuracy of black ice detection, we propose a multi-scale dilation convolution feature fusion (MsDC-FF) technique. This proposed technique dynamically adjusts the dilation ratios based on the input image's resolution, improving the network's ability to capture fine-grained details. Experimental results demonstrate the superior performance of our proposed network model compared to conventional image segmentation models. Our model achieved an mIoU of 95.93%, while LinkNet achieved an mIoU of 95.39%. Therefore, it is concluded that the proposed model in this paper could offer a promising solution for real-time black ice detection, thereby enhancing road safety during winter conditions.

• International Journal of Computer Science & Network Security
• /
• 제22권11호
• /
• pp.265-271
• /
• 2022

Social media is a form of communication based on the internet to share information through content and images. Their choice of profile images and type of image they post can be closely connected to their personality. The user posted images are designated as personality traits. The objective of this study is to predict five factor model personality dimensions from profile images by using deep learning and neural networks. Developed a deep learning framework-based neural network for personality prediction. The personality types of the Big Five Factor model can be quantified from user profile images. To measure the effectiveness, proposed two models using convolution Neural Networks to classify each personality of the user. Done performance analysis among two different models for efficiently predict personality traits from profile image. It was found that VGG-69 CNN models are best performing models for producing the classification accuracy of 91% to predict user personality traits.

• Journal of applied mathematics & informatics
• /
• 제34권1_2호
• /
• pp.145-156
• /
• 2016

It is known that certain convolution sums can be expressed as a combination of divisor functions and Bernoulli formula. In this article, we consider relationship between fifth-order combinatoric convolution sums of divisor functions and Bernoulli polynomials. As applications of these identities, we give a concrete interpretation in terms of the procedural modeling method.

• Steel and Composite Structures
• /
• 제11권5호
• /
• pp.403-421
• /
• 2011

In the present manuscript, geometrically nonlinear free vibration analysis of thin laminated plates resting on non-linear elastic foundations is investigated. Winkler-Pasternak type foundation model is used. Governing equations of motions are obtained using the von Karman type nonlinear theory. The method of discrete singular convolution is used to obtain the discretised equations of motion of plates. The effects of plate geometry, boundary conditions, material properties and foundation parameters on nonlinear vibration behavior of plates are presented.

• Geomechanics and Engineering
• /
• 제2권1호
• /
• pp.45-56
• /
• 2010

The current study presents a mathematical model and numerical method for free vibration of tapered piles embedded in two-parameter elastic foundations. The method of Discrete Singular Convolution (DSC) is used for numerical simulation. Bernoulli-Euler beam theory is considered. Various numerical applications demonstrate the validity and applicability of the proposed method for free vibration analysis. The results prove that the proposed method is quite easy to implement, accurate and highly efficient for free vibration analysis of tapered beam-columns embedded in Winkler- Pasternak elastic foundations.

• Journal of Information Processing Systems
• /
• 제17권5호
• /
• pp.892-904
• /
• 2021

An image semantic segmentation model is proposed based on improved ENet network in order to achieve the low accuracy of image semantic segmentation in complex environment. Firstly, this paper performs pruning and convolution optimization operations on the ENet network. That is, the network structure is reasonably adjusted for better results in image segmentation by reducing the convolution operation in the decoder and proposing the bottleneck convolution structure. Squeeze-and-excitation (SE) module is then integrated into the optimized ENet network. Small-scale targets see improvement in segmentation accuracy via automatic learning of the importance of each feature channel. Finally, the experiment was verified on the public dataset. This method outperforms the existing comparison methods in mean pixel accuracy (MPA) and mean intersection over union (MIOU) values. And in a short running time, the accuracy of the segmentation and the efficiency of the operation are guaranteed.

• 방송공학회논문지
• /
• 제27권7호
• /
• pp.1011-1020
• /
• 2022

Recent high-performance panoptic segmentation models are based on transformer architectures. However, transformer-based panoptic segmentation methods are basically slower than convolution-based methods, since the attention mechanism in the transformer requires quadratic complexity w.r.t. image resolution. Also, sine and cosine computation for positional embedding in the transformer also yields a bottleneck for computation time. To address these problems, we adopt three modules to speed up the inference runtime of the transformer-based panoptic segmentation. First, we perform channel-level reduction using depth-wise separable convolution for inputs of the transformer decoder. Second, we replace sine and cosine-based positional encoding with convolution operations, called conv-embedding. We also apply a separable self-attention to the transformer encoder to lower quadratic complexity to linear one for numbers of image pixels. As result, the proposed model achieves 44% faster frame per second than baseline on ADE20K panoptic validation dataset, when we use all three modules.