• Journal of Institute of Control, Robotics and Systems
• /
• v.5 no.7
• /
• pp.841-847
• /
• 1999

For successful assembly of flexible parts, informations about their deformation as well as possible misalignments between the holes and their mating parts are essential. Such informations can be acquired from visual sensors. For robotic assembly, the corrective assembly motion to compensate for such misalignments has to be determined from the measured informations. However, this may not be simply derived from the measured misalignment alone because the part deformation progressively occurs during misalignment compensation. Based on the analysis of flexible parts assembly process, this paper presents a neural net-based inference system that can infer the complex relationship between the corrective motion and the measured information of parts deformation and misalignments. And it verifies the performance of the implemented inference system. The results show that the proposed neural net-based misalignment compensation algorithm Is effective in compensating for the lateral misalignment, and that it can be extended to the assembly tasks under more general conditions.

• Geomechanics and Engineering
• /
• v.20 no.5
• /
• pp.385-397
• /
• 2020

This paper presents an application of artificial neural networks (ANNs) in settlement prediction of a foundation on sandy soil. In order to train the ANN model, a wide experimental database about settlement of foundations acquired from available literatures was collected. The data used in the ANNs model were arranged using the following five-input parameters that covered both geometrical foundation and sandy soil properties: breadth of foundation B, length to width L/B, embedment ratio D_f/B, foundation net applied pressure q_net, and average SPT blow count N. The backpropagation algorithm was implemented to develop an explicit predicting formulation. The settlement results are compared with the results of previous studies. The accuracy of the proposed formula proves that the ANNs method has a huge potential for predicting the settlement of foundations on sandy soils.

• KIEE International Transaction on Systems and Control
• /
• v.2D no.2
• /
• pp.108-114
• /
• 2002

This paper describes the design of a robust adaptive controller for a nonlinear dynamical system with unknown nonlinearities. These unknown nonlinearities are approximated by multilayered neural networks (MNNs) whose parameters are adjusted on-line, according to some adaptive laws far controlling the output of the nonlinear system, to track a given trajectory. The main contribution of this paper is a method for considering input constraint with a rigorous stability proof. The Lyapunov synthesis approach is used to develop a state-feedback adaptive control algorithm based on the adaptive MNN model. An overall control system guarantees that the tracking error converges at about zero and that all signals involved are uniformly bounded even in the presence of input saturation. Theoretical results are illustrated through a simulation example.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.636-638
• /
• 2022

This paper is a study to apply CNN(Convolution Neural Network) to fundus images for identifying glaucoma. Fundus images are evaluated in the field of medical diagnosis detection, which are diagnosing of blood vessels and nerve tissues, retina damage, various cardiovascular diseases and dementia. For the experiment, using normal image set and glaucoma image set, two types of image set are classifed by using AlexNet. The result performs that glaucoma with abnormalities are activated and characterized in feature map.

• Communications for Statistical Applications and Methods
• /
• v.29 no.2
• /
• pp.161-176
• /
• 2022

There has been active research in image classification using deep learning convolutional neural network (CNN) models. ImageNet large-scale visual recognition challenge (ILSVRC) (2010-2017) was one of the most important competitions that boosted the development of efficient deep learning algorithms. This paper introduces and compares six monumental models that achieved high prediction accuracy in ILSVRC. First, we provide a review of the models to illustrate their unique structure and characteristics of the models. We then compare those models under a unified framework. For this reason, additional devices that are not crucial to the structure are excluded. Four popular data sets with different characteristics are then considered to measure the prediction accuracy. By investigating the characteristics of the data sets and the models being compared, we provide some insight into the architectural features of the models.

• ETRI Journal
• /
• v.46 no.2
• /
• pp.307-322
• /
• 2024

Most object detection methods use a horizontal bounding box that causes problems between adjacent objects with arbitrary directions, resulting in misaligned detection. Hence, the horizontal anchor should be replaced by a rotating anchor to determine oriented bounding boxes. A two-stage process of delineating a horizontal bounding box and then converting it into an oriented bounding box is inefficient. To improve detection, a box-boundary-aware vector can be estimated based on a convolutional neural network. Specifically, we propose a ResNeXt101 encoder to overcome the weaknesses of the conventional ResNet, which is less effective as the network depth and complexity increase. Owing to the cardinality of using a homogeneous design and multi-branch architecture with few hyperparameters, ResNeXt captures better information than ResNet. Experimental results demonstrate more accurate and faster oriented object detection of our proposal compared with a baseline, achieving a mean average precision of 89.41% and inference rate of 23.67 fps.

• Korean Journal of Radiology
• /
• v.22 no.3
• /
• pp.476-488
• /
• 2021

Objective: We aimed to develop a deep neural network for segmenting lung parenchyma with extensive pathological conditions on non-contrast chest computed tomography (CT) images. Materials and Methods: Thin-section non-contrast chest CT images from 203 patients (115 males, 88 females; age range, 31-89 years) between January 2017 and May 2017 were included in the study, of which 150 cases had extensive lung parenchymal disease involving more than 40% of the parenchymal area. Parenchymal diseases included interstitial lung disease (ILD), emphysema, nontuberculous mycobacterial lung disease, tuberculous destroyed lung, pneumonia, lung cancer, and other diseases. Five experienced radiologists manually drew the margin of the lungs, slice by slice, on CT images. The dataset used to develop the network consisted of 157 cases for training, 20 cases for development, and 26 cases for internal validation. Two-dimensional (2D) U-Net and three-dimensional (3D) U-Net models were used for the task. The network was trained to segment the lung parenchyma as a whole and segment the right and left lung separately. The University Hospitals of Geneva ILD dataset, which contained high-resolution CT images of ILD, was used for external validation. Results: The Dice similarity coefficients for internal validation were 99.6 ± 0.3% (2D U-Net whole lung model), 99.5 ± 0.3% (2D U-Net separate lung model), 99.4 ± 0.5% (3D U-Net whole lung model), and 99.4 ± 0.5% (3D U-Net separate lung model). The Dice similarity coefficients for the external validation dataset were 98.4 ± 1.0% (2D U-Net whole lung model) and 98.4 ± 1.0% (2D U-Net separate lung model). In 31 cases, where the extent of ILD was larger than 75% of the lung parenchymal area, the Dice similarity coefficients were 97.9 ± 1.3% (2D U-Net whole lung model) and 98.0 ± 1.2% (2D U-Net separate lung model). Conclusion: The deep neural network achieved excellent performance in automatically delineating the boundaries of lung parenchyma with extensive pathological conditions on non-contrast chest CT images.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.12a
• /
• pp.10-13
• /
• 2001

Nonlinear Function Approximation of Moduled Neural Network Using Genetic Algorithm Neural Network consists of neuron and synapse. Synapse memorize last pattern and study new pattern. When Neural Network learn new pattern, it tend to forget previously learned pattern. This phenomenon is called to catastrophic inference or catastrophic forgetting. To overcome this phenomenon, Neural Network must be modularized. In this paper, we propose Moduled Neural Network. Modular Neural Network consists of two Neural Network. Each Network individually study different pattern and their outputs is finally summed by net function. Sometimes Neural Network don't find global minimum, but find local minimum. To find global minimum we use Genetic Algorithm.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.5
• /
• pp.205-212
• /
• 2019

Scene graph is a kind of knowledge graph that represents both objects and their relationships found in a image. This paper proposes a 3D scene graph generation model for three-dimensional indoor environments. An 3D scene graph includes not only object types, their positions and attributes, but also three-dimensional spatial relationships between them, An 3D scene graph can be viewed as a prior knowledge base describing the given environment within that the agent will be deployed later. Therefore, 3D scene graphs can be used in many useful applications, such as visual question answering (VQA) and service robots. This proposed 3D scene graph generation model consists of four sub-networks: object detection network (ObjNet), attribute prediction network (AttNet), transfer network (TransNet), relationship prediction network (RelNet). Conducting several experiments with 3D simulated indoor environments provided by AI2-THOR, we confirmed that the proposed model shows high performance.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.3
• /
• pp.529-536
• /
• 2022

In the past two years, Severe Acute Respiratory Syndrome Coronavirus-2(SARS-CoV-2) has been hitting more and more to people. This paper proposes a novel U-Net Convolutional Neural Network to classify and segment COVID-19 lung CT images, which contains Sub Coding Block (SCB), Atrous Spatial Pyramid Pooling(ASPP) and Attention Gate(AG). Three different models such as FCN, U-Net and U-Net-SCB are designed to compare the proposed model and the best optimizer and atrous rate are chosen for the proposed model. The simulation results show that the proposed U-Net-MMFE has the best Dice segmentation coefficient of 94.79% for the COVID-19 CT scan digital image dataset compared with other segmentation models when atrous rate is 12 and the optimizer is Adam.