• Proceedings of the Korean Institute of Resources Recycling Conference
• /
• 2005.05a
• /
• pp.57-61
• /
• 2005

In this study, the machine vision system for inspection using color recognition method have been designed and developed to automatically sort out a specified material such as Cu scraps or other non-ferrous metal scraps mixed in Fe scraps. The system consists of a CCD camera, light sources, a frame grabber, conveying devices and an air nozzled ejector, and is program-controlled by a image processing algorithm. The ejector is designed to be operated by an I/O interface communication with a hardware controller. The sorting examination results show that the efficiency of separating Cu scraps from the Fe scraps mixed with Cu scraps is around 90 % at the conveying speed of 15 m/min. and the system is proven to be excellent in terms of its efficiency. Therefore, it is expected that the system can be commercialized in shredder firms, if the high-speed automated sorting system will be realized.

• Journal of Information Technology Services
• /
• v.18 no.2
• /
• pp.143-159
• /
• 2019

Machine learning (ML) is a method of fitting given data to a mathematical model to derive insights or to predict. In the age of big data, where the amount of available data increases exponentially due to the development of information technology and smart devices, ML shows high prediction performance due to pattern detection without bias. The feature engineering that generates the features that can explain the problem to be solved in the ML process has a great influence on the performance and its importance is continuously emphasized. Despite this importance, however, it is still considered a difficult task as it requires a thorough understanding of the domain characteristics as well as an understanding of source data and the iterative procedure. Therefore, we propose methods to apply deep learning for solving the complexity and difficulty of feature extraction and improving the performance of ML model. Unlike other techniques, the most common reason for the superior performance of deep learning techniques in complex unstructured data processing is that it is possible to extract features from the source data itself. In order to apply these advantages to the business problems, we propose deep learning based methods that can automatically extract features from transaction data or directly predict and classify target variables. In particular, we applied techniques that show high performance in existing text processing based on the structural similarity between transaction data and text data. And we also verified the suitability of each method according to the characteristics of transaction data. Through our study, it is possible not only to search for the possibility of automated feature extraction but also to obtain a benchmark model that shows a certain level of performance before performing the feature extraction task by a human. In addition, it is expected that it will be able to provide guidelines for choosing a suitable deep learning model based on the business problem and the data characteristics.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.559-563
• /
• 2024

Currently, in Korea, large-scale, deep excavations are being carried out adjacent to structures due to overcrowding in urban areas. for adjacent excavations in urban areas, it is very important to ensure the safety of earth retaining structures and underground structures. accordingly, an automated measurement system is being introduced to manage the safety of subway tunnel structures. however, the utilization of automated measurement system results is very low. existing evaluation techniques rely only on the maximum value of measured data, which can overestimate abnormal behavior. accordingly, in this study, a vast amount of automated measurement data was analyzed using the Gaussian probability density function, a technique that can quantitatively evaluate. highly reliable results were derived by applying probabilistic statistical analysis methods to a vast amount of data. therefore, in this study, the safety evaluation of subway tunnel structures due to adjacent excavation work was performed using a technique that can process a large amount of data.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.579-584
• /
• 2024

Currently, large-scale, deep construction is being carried out adjacent to subway tracks in korea. when excavating adjacent to each other, it is very important to ensure the safety of earth retaining structures and underground structures. therefore, we are managing the safety of the subway by introducing an automated measurement system. deformation of the subway track during adjacent excavation may affect train running stability. this is a factor that can be linked to train derailments. however, current subway track safety evaluation using automated measurement systems relies only on the maximum value of measured data. therefore, a method to improve the usability of automated measurement system results is needed. in this study, we utilized a technique that can quantitatively evaluate the measurement results of a large amount of subway track deformation. a safety evaluation was conducted on subway track deformation due to adjacent excavation using a vast amount of data using probabilistic statistical analysis techniques.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.3
• /
• pp.723-730
• /
• 2024

In order to trace the changes in the concept and understanding of automatically generated images, this study analogously explores the creative methods of photography and cinema, which represent the existing image fields, in terms of AI-based image creation methods and 'automaticity', and discusses the understanding and possibilities of new automatic image creation. At the time of the invention of photography and cinema, the field of 'automatic creation' was established for them in comparison to traditional art genres such as painting. Recently, as AI has been applied to video production, the concept of 'automatic creation' has been expanded, and experimental creations that freely cross the boundaries of literature, art, photography, and film are active. By utilizing technologies such as machine learning and deep learning, AI automated creation allows AI to perform the creative process independently. Automated creation using AI can greatly improve efficiency, but it also risks compromising the personal and subjective nature of art. The problem stems from the fact that AI cannot completely replace human creativity.

• Proceedings of the KSR Conference
• /
• 2011.10a
• /
• pp.1335-1341
• /
• 2011

Conserving clean air and removing contaminants and particular matters accumulated in the ventilation system of the subway stations are key issue for green railway environment. There is no national guideline or industrial regulations to sustain clean duct and ventilation system, which requires rapid reformation of cleaning procedure and system. In fact, accumulated various particular matters and dusts can occur secondary air contamination and become a primary health harm factor for subway passengers. This study investigates various duct cleaning technologies and trends. In additon, effective cleaning method with an automated robot device is proposed. In particular, current dust cleaning technologies and duct cleaning robots are analyzed based on their functions and feasibilities. The proposed design of automated device is expected to save the operating cost of subway HVAC system and sustain clean air environment.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.5
• /
• pp.65-71
• /
• 2016

Bluetooth technology(BT) is a standard for short distance wireless communication and widely used to connect and control various electronic and telecommunication devices without wires, where CSR8670 chip is generally adopted. These BT devices are required to comply with BT specification and the equipments for conformance test are also important. However, the existing BT testing methods have inconvenience in that they are mostly time-consuming procedure due to not only repetitive execution for each evaluation element but also error-prone nature of manual experiments. This paper proposes an automated BT communication test method using CSR8670 chip, which solves the problems related to manual testing methods. The proposed method can reduce the development period of BT products and guarantee the quality improvement owing to the exact system error detection capability.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1853-1856
• /
• 2003

This paper considers the problem of longitudinal control of a platoon of automotive vehicles on a straight lane of a highway and proposes control laws in the event of loss of communication between the lead vehicle and the other vehicles in the platoon. Since safety plays a key role in the development of an Automated Highway System, fault-tolerant control is vital. In this paper, we develop a control algorithm in vehicle platooning and prove that this control algorithm is stable for certain class of faults such as parameter uncertainties. The performance of the controller is demonstrated through a series of simulations incorporating various vehicles and AHS faults. Results of simulation shows that the vehicles have good performance in spite of simple automotive and AHS failure, such as actuator failure,that is to say, engine input failure, communication failure between lead vehicle and the another vehicles.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2008.04a
• /
• pp.269-274
• /
• 2008

It is attempted that the standardization of the construction, globalization of the engineering construction and an information oriented construction spread by setting a goal of the advanced construction industry and productivity increase of human resources within the country. Hence, it has been brought in the information oriented construction of BIM based technology for the field of construction and equipment of Korea. The current study that examines the possibility of application of 3D ; that is BIM based programs of building equipment, and make better the problems of 3D building equipment system through the Pilot Test, indicates the way of growth development about the construction of building equipment process system.

• The Journal of Information Technology and Database
• /
• v.6 no.2
• /
• pp.19-28
• /
• 1999

Digital image and video libraries require new algorithms for the automated extraction and indexing of salient image features. Eigen values of an image provide one important cue for the discrimination of image content. In this paper we propose a new approach for automated content extraction that allows efficient database searching using eigen values. The algorithm automatically extracts eigen values from the image matrix represented by the covariance matrix for the image. We demonstrate that the eigen values representing shape information and the skewness of its distribution representing complexity provide good performance in image query response time while providing effective discriminability. We present the eigen value extraction and indexing techniques. We test the proposed algorithm of searching by eigen value and its skewness on a database of 100 images.