• Smart Structures and Systems
• /
• v.32 no.4
• /
• pp.219-233
• /
• 2023

Crack width is an important indicator to evaluate the health condition of the concrete structure. The crack width is measured by manual using crack width gauge commonly, which is time-consuming and laborious. In this paper, we have proposed a fast and simplified crack width quantification method via deep Q learning and geometric calculation. Firstly, the crack edge is extracted by using U-Net network and edge detection operator. Then, the intelligent decision of is made by the deep Q learning model. Further, the geometric calculation method based on endpoint and curvature extreme point detection is proposed. Finally, a case study is carried out to demonstrate the effectiveness of the proposed method, achieving high precision in the real crack width quantification.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.4D
• /
• pp.351-360
• /
• 2010

In 2010, the number of registered vehicles reached almost at 17.48 millions in Korea. This dramatic increase of vehicles influenced to increase the number of traffic accidents which is one of the serious social problems and also to soar the personal and economic losses in Korea. Through this research, an enhanced intersection hazard prediction model by combining Genetic Algorithm and Artificial Neural Network will be developed in order to obtain the important data for developing the countermeasures of traffic accidents and eventually to reduce the traffic accidents in Korea. Firstly, this research has investigated the influencing factors of road geometric features on the traffic volume of each approaching for the intersections where traffic accidents and congestions frequently take place and, a linear regression model of traffic accidents and traffic conflicts were developed by examining the relationship between traffic accidents and traffic conflicts through the statistical significance tests. Secondly, this research also developed an intersection hazard prediction model by combining Genetic Algorithm and Artificial Neural Network through applying the intersection traffic volume, the road geometric features and the specific variables of traffic conflicts. Lastly, this research found out that the developed model is better than the existed forecasting models in terms of the reliability and accuracy by comparing the actual number of traffic accidents and the predicted number of accidents from the developed model. In conclusion, it is expect that the cost/effectiveness of any traffic safety improvement projects can be maximized if this developed intersection hazard prediction model by combining Genetic Algorithm and Artificial Neural Network use practically at field in the future.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.4
• /
• pp.1166-1186
• /
• 2022

Artistic font design has become an integral part of visual media. However, without prior knowledge of the font domain, it is difficult to create distinct font styles. When the number of characters is limited, this task becomes easier (e.g., only Latin characters). However, designing CJK (Chinese, Japanese, and Korean) characters presents a challenge due to the large number of character sets and complexity of the glyph components in these languages. Numerous studies have been conducted on automating the font design process using generative adversarial networks (GANs). Existing methods rely heavily on reference fonts and perform font style conversions between different fonts. Additionally, rather than capturing style information for a target font via multiple style images, most methods do so via a single font image. In this paper, we propose a network architecture for generating multilingual font sets that makes use of geometric structures as content. Additionally, to acquire sufficient style information, we employ multiple style images belonging to a single font style simultaneously to extract global font style-specific information. By utilizing the geometric structural information of content and a few stylized images, our model can generate an entire font set while maintaining the style. Extensive experiments were conducted to demonstrate the proposed model's superiority over several baseline methods. Additionally, we conducted ablation studies to validate our proposed network architecture.

• Journal of Information Processing Systems
• /
• v.19 no.6
• /
• pp.791-802
• /
• 2023

The manual inspection of photovoltaic (PV) panels to meet the requirements of inspection work for large-scale PV power plants is challenging. We present a hot spot detection and positioning method to detect hot spots in batches and locate their latitudes and longitudes. First, a network based on the YOLOv3 architecture was utilized to identify hot spots. The innovation is to modify the RU_1 unit in the YOLOv3 model for hot spot detection in the far field of view and add a neural network residual unit for fusion. In addition, because of the misidentification problem in the infrared images of the solar PV panels, the DeepLab v3+ model was adopted to segment the PV panels to filter out the misidentification caused by bright spots on the ground. Finally, the latitude and longitude of the hot spot are calculated according to the geometric positioning method utilizing known information such as the drone's yaw angle, shooting height, and lens field-of-view. The experimental results indicate that the hot spot recognition rate accuracy is above 98%. When keeping the drone 25 m off the ground, the hot spot positioning error is at the decimeter level.

• Wind and Structures
• /
• v.36 no.6
• /
• pp.423-434
• /
• 2023

Aerodynamic force coefficients are generally obtained from traditional wind tunnel tests or computational fluid dynamics (CFD). Unfortunately, the techniques mentioned above can sometimes be cumbersome because of the cost involved, such as the computational cost and the use of heavy equipment, to name only two examples. This study proposed to build a deep neural network model to predict the aerodynamic force coefficients based on data collected from CFD simulations to overcome these drawbacks. Therefore, a series of CFD simulations were conducted using different geometric parameters to obtain the aerodynamic force coefficients, validated with wind tunnel tests. The results obtained from CFD simulations were used to create a dataset to train a multilayer perceptron artificial neural network (ANN) model. The models were obtained using three optimization algorithms: scaled conjugate gradient (SCG), Bayesian regularization (BR), and Levenberg-Marquardt algorithms (LM). Furthermore, the performance of each neural network was verified using two performance metrics, including the mean square error and the R-squared coefficient of determination. Finally, the ANN model proved to be highly accurate in predicting the force coefficients of similar bridge sections, thus circumventing the computational burden associated with CFD simulation and the cost of traditional wind tunnel tests.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.11
• /
• pp.3493-3506
• /
• 2022

In the field of scene segmentation, the precise segmentation of object boundaries in sports movement scene images is a great challenge. The geometric information and spatial information of the image are very important, but in many models, they are usually easy to be lost, which has a big influence on the performance of the model. To alleviate this problem, a parallel dense dilated convolution merging Network (termed PDDCM-Net) was proposed. The proposed PDDCMNet consists of a feature extractor, parallel dilated convolutions, and dense dilated convolutions merged with different dilation rates. We utilize different combinations of dilated convolutions that expand the receptive field of the model with fewer parameters than other advanced methods. Importantly, PDDCM-Net fuses both low-level and high-level information, in effect alleviating the problem of accurately segmenting the edge of the object and positioning the object position accurately. Experimental results validate that the proposed PDDCM-Net achieves a great improvement compared to several representative models on the COCO-Stuff data set.

• Journal of electromagnetic engineering and science
• /
• v.10 no.4
• /
• pp.290-295
• /
• 2010

In this paper, an interference analysis method with a site-specific path loss model for a wireless personal area network (WPAN) is proposed. The site-specific path loss model is based on geometrical optics and geometric probability to consider both site-specific radio propagation characteristics and a closed-form expression to obtain the mean interference from which the uniformly distributed multiple interferers are derived. Therefore, the proposed interference analysis method can achieve more computational simplicity than the Monte-Carlo (MC) simulation, which uses the ray-tracing (RT) technique. In addition, better accuracy than the conventional interference analysis model that uses stochastic method can also be achieved. To evaluate the proposed method, a signal to the interference-noise ratio with a mean interference concept for uniformly distributed interferers is calculated and compared in two simulation scenarios. As a result, the proposed method produces not only better matched results with the MC simulation using the RT technique than the conventional interference analysis model, but also simpler and faster calculation, which is due to the site-specific path loss model and closed-form expression for interference calculation.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2001.04a
• /
• pp.376-381
• /
• 2001

This paper presents a methodology of machining error compensation by using Artificial Neural Network(ANN) model based on the inspection database of On-Machine-Measurement(OMM) system. First, the geometric errors of the machining center and the probing errors are significantly reduced through compensation processes. Then, we acquire machining error distributions from a specimen workpiece. In order to efficiently analyze the machining errors, we define two characteristic machining error parameters. These can be modeled by using an ANN model, which allows us to determine the machining errors in the domain of considered cutting conditions. Based on this ANN model, we try to correct the tool path in order to effectively reduce the errors by using an iterative algorithm. The iterative algorithm allows us to integrate changes of the cutting conditions according to the corrected tool path. Experimentation is carried out in order to validate the approaches proposed in this paper.

• Journal of Biosystems Engineering
• /
• v.17 no.1
• /
• pp.65-78
• /
• 1992

When using a computer vision system for a measurement, the geometrically distorted input image usually restricts the site and size of the measuring window. A geometrically distorted image caused by the image sensing and processing hardware degrades the accuracy of the visual measurement and prohibits the arbitrary selection of the measuring scope. Therefore, an image calibration is inevitable to improve the measuring accuracy. A calibration process is usually done via four steps such as measurement, modeling, parameter estimation, and compensation. In this paper, the efficient error calibration technique of a geometrically distorted input image was developed using a neural network. After calibrating a unit pixel, the distorted image was compensated by training CMLAN(Cerebellar Model Linear Associator Network) without modeling the behavior of any system element. The input/output training pairs for the network was obtained by processing the image of the devised sampled pattern. The generalization property of the network successfully compensates the distortion errors of the untrained arbitrary pixel points on the image space. The error convergence of the trained network with respect to the network control parameters were also presented. The compensated image through the network was then post processed using a simple DDA(Digital Differential Analyzer) to avoid the pixel disconnectivity. The compensation effect was verified using known sized geometric primitives. A way to extract directly a real scaled geometric quantity of the object from the 8-directional chain coding was also devised and coded. Since the developed calibration algorithm does not require any knowledge of modeling system elements and estimating parameters, it can be applied simply to any image processing system. Furthermore, it efficiently enhances the measurement accuracy and allows the arbitrary sizing and locating of the measuring window. The applied and developed algorithms were coded as a menu driven way using MS-C language Ver. 6.0, PC VISION PLUS library functions, and VGA graphic functions.

• Proceedings of the CALSEC Conference
• /
• 2001.08a
• /
• pp.615-624
• /
• 2001

Internet technology opens up another domain for building future CAD/CAM environment. The environment will be global, network-centric, and spatially distributed. In this paper, we present a new approach to network-centric virtual prototyping (NetVP) in a distributed design environment. The presented approach combines the current virtual assembly modeling and analysis technique with distributed computing and communication technology fur supporting virtual prototyping activities over the network. This paper focuses on interoperability, shape representation, and geometric processing for distributed virtual prototyping. STEP standard and CORBA-based interfaces allow the bi-directional communication between the CAD model and virtual prototyping model, which makes it possible to solve the problems of interoperability, heterogeneity of platforms, and data sharing. STEP AP203 and AP214 are utilized as a means of transferring and sharing product models. In addition, Attributed Abstracted B-rep (AAB) is introduced as 3D shape abstraction for transparent and efficient transmission of 3D models and for the maintenance of naming consistency between CAD models and virtual prototyping models over the network.