• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1999.11a
• /
• pp.494-497
• /
• 1999

Neural networks are shown to be effective in being able to distinguish incomplete penetration-like weld defects by directly analyzing the plasma which is generated on each impingement of the laser on the materials. The performance is similar to that of existing methods based on extracted feature parameters. In each case around 93% of the defects in a database derived from 100 artificially produced defects of known types can be placed into one of two classes: incomplete penetration and bubbling. Especially we present simulator for weld defects classification and data analysis. The present method based on classification using plasma is faster, and the speed is sufficient to allow on-line classification during data collection.

• International Journal of Advanced Culture Technology
• /
• v.9 no.3
• /
• pp.305-314
• /
• 2021

Currently, due to COVID-19, household waste has a lot of impact on the environment due to packaging of food delivery. In this paper, we design and implement Faster-RCNN, SSD, and YOLOv4 models for municipal waste detection and classification. The data set explores two types of plastics, which account for a large proportion of household waste, and the types of aluminum cans. To classify the plastic type and the aluminum can type, 1,083 aluminum can types and 1,003 plastic types were studied. In addition, in order to increase the accuracy, we compare and evaluate the loss value and the accuracy value for the detection of municipal waste classification using Faster-RCNN, SDD, and YoloV4 three models. As a final result of this paper, the average precision value of the SSD model is 99.99%, the average precision value of plastics is 97.65%, and the mAP value is 99.78%, which is the best result.

• Design Convergence Study
• /
• v.16 no.3
• /
• pp.51-68
• /
• 2017

User-centered design and Experience Design are emerging in the design area. Therefore, the Role-Playing Method has been actively utilized in the process of design development. But the terms of Role-Playing Method which follow these trends. has not been integrated. Further, it is hard to utilize the process of design development because the process method is not settled yet. Therefore, this study is into two parts of the research: Defining the concept of Role-Playing and the experiment of Role-Playing. Firstly, defining concept part is to research the design method corresponds to a wide range of Role-Playing that has a similar definition. After then, analyzed the examples of Role-Playing Methods which was derived matrix from Role-Playing classification. With this process, two axes of the matrix have been produced such as role·scenario and puppet. Through the analysis of the utility and vulnerability of the Role-Playing classification matrix, this study was able to propose the using step of the Role-Playing in the double diamond model. Secondly, two experiments were conducted in the experiment part. Through the pilot experiment explored the possibility of a study of the Role-Playing Method. In the second experiment, the process was conducted with Role-Playing classification matrix. As a result, each Role-Playing has different insights. In terms of design, different aspects of composing elements were found. Plus, in the position of the user, Role-Playing are can observe different parts of user's cognition between acting and puppet. Thus, the role-playing was proven to be useful to find out the point of improvement and insight in service from different perspectives and it resulted in the role playing which can be utilized selectively according to the type of service.

• International Journal of Highway Engineering
• /
• v.16 no.6
• /
• pp.181-189
• /
• 2014

PURPOSES : Ambiguous decision on whether rural or urban area for road design can increase the construction cost and restrict the land use of surrounding area. However, administrative classification on rural and urban area is not directly related to road design because of this classification is not based on the engineering viewpoint, so method which can explain the road design context is required. METHODS : Method which enables to identify the area for road design is suggested based on the deceleration expected to be experienced by drivers who use the road section concerned. Deceleration rate corresponding to the area such as rural or urban suggested in Road Design Guideline is used as the criteria to identify the area by comparing this value with the estimated deceleration rate at the road section concerned. Speed profile method is utilized to derive the deceleration rate, and speed estimation way for reflecting both road geometry and intersection is suggested using stopping sight distance concept. RESULTS : The procedure of the method application is suggested, and the design example utilizing the method is provided. CONCLUSIONS : The method is expected to be used to identify the area for road design with engineering viewpoint, and design consistency among the roads with similar driving environment can be made.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.13 no.1
• /
• pp.31-38
• /
• 1988

This paper presents a methodology for the development of a part classification and coding system suited to each individual company. When coding a group of parts for a specific company by a general purpose part classification & coding system like OPITZ system, it is frequently observed that we use only a small subset of total available code numbers. Such sparsity in the actual occurrences of code numbers implies that we can design a better system which uses digits of the system more parsimoniously. A 2-dimensional fuzzy ISODATA algorithm is developed to extract the important characteristics for the classification from the set of given parts. Based on the extracted characteristics nd the distances between fuzzy clustering cenetroids, a company-unique classification and coding system can be developed. An example case study for a medium sized machine shop is presented.

• Journal of information and communication convergence engineering
• /
• v.16 no.3
• /
• pp.173-178
• /
• 2018

Accurate classification of cloud images is a challenging task. Almost all the existing methods rely on hand-crafted feature extraction. Their limitation is low discriminative power. In the recent years, deep learning with convolution neural networks (CNNs), which can auto extract features, has achieved promising results in many computer vision and image understanding fields. However, deep learning approaches usually need large datasets. This paper proposes a deep learning approach for classification of cloud image patches on small datasets. First, we design a suitable deep learning model for small datasets using a CNN, and then we apply data augmentation and dropout regularization techniques to increase the generalization of the model. The experiments for the proposed approach were performed on SWIMCAT small dataset with k-fold cross-validation. The experimental results demonstrated perfect classification accuracy for most classes on every fold, and confirmed both the high accuracy and the robustness of the proposed model.

• Asia pacific journal of information systems
• /
• v.5 no.2
• /
• pp.143-176
• /
• 1995

We present an overview of the Extensional Object Model (ExOM) and describe in detail the learning and classification components which integrate concepts from machine learning and object-oriented databases. The ExOM emphasizes flexibility in information acquisition, learning, and classification which are useful to support tasks such as diagnosis, planning, design, and database mining. As a vehicle to integrate machine learning and databases, the ExOM supports a broad range of learning and classification methods and integrates the learning and classification components with traditional database functions. To ensure the integrity of ExOM databases, a subsumption testing rule is developed that encompasses categories defined by type expressions as well as concept definitions generated by machine learning algorithms. A prototype of the learning and classification components of the ExOM is implemented in Smalltalk/V Windows.

• Nuclear Engineering and Technology
• /
• v.48 no.4
• /
• pp.1015-1021
• /
• 2016

Structures, systems, and components (SSCs) important to safety of nuclear facilities shall be designed, fabricated, erected, and tested to quality standards commensurate with the importance of the safety functions. Although SSC classification guidelines for nuclear power plants have been well established and applied, those for research reactors have been only recently established by the International Atomic Energy Agency (IAEA). Korea has operated a pool-type research reactor (the High Flux Advanced Neutron Application Reactor) and has recently exported another pool-type reactor (Jordan Research and Training Reactor), which is being built in Jordan. Korea also has a plan to build one more pool-type reactor, the Kijang Research Reactor, in Kijang, Busan. The safety classification of SSCs for pool-type research reactors is proposed in this paper based on the IAEA methodology. The proposal recommends that the SSCs of pool-type research reactors be categorized and classified on basis of their safety functions and safety significance. Because the SSCs in pool-type research reactors are not the pressure-retaining components, codes and standards for design of the SSCs following the safety classification can be selected in a graded approach.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.43 no.6
• /
• pp.1027-1035
• /
• 1994

This paper aims to make an artificial arm control strategy. For this, we propose a new feature extraction method and design artificial neural network for the functional classification of myoelectric signal(MES). We first transform the two channel myoelectric signals (MES) for biceps and triceps into frequency domain using fast Fourier transform (FFT). And features were obtained by comparing the magnitudes of ensemble spectrum data and used as inputs to the three-layer neural network for the learning. By changing the number of units in hidden layer of neural network we observed the improvement of classification performance. To observe the effeciency of the proposed scheme we performed experiments for classification of six arm functions to the three subjects. And we obtained on average 94[%] the ratio of classification.

• Journal of the Semiconductor & Display Technology
• /
• v.15 no.3
• /
• pp.6-11
• /
• 2016

Silicon wafer is one of main materials in solar cell. Micro-cracks in silicon wafer are one of reasons to decrease efficiency of energy transformation. They couldn't be observed by human eye. Also, their shape is not only various but also complicated. Accordingly, their shape classification is absolutely needed for manufacturing process quality and its feedback. The performance of typical classification techniques which is principal component analysis(PCA), neural network, fusion model to integrate PCA with neural network, and support vector machine(SVM), are evaluated using pattern features of micro-cracks. As a result, it has been confirmed that the SVM gives good results in micro-crack classification.