• Journal of the Architectural Institute of Korea Structure & Construction
• /
• v.34 no.4
• /
• pp.65-74
• /
• 2018

The primary objective of this study is to develop a conceptual design of automated pothole patching machine that improves the conventional work in safety, quality, and productivity. For this, the following research works are conducted sequentially; 1)literature review, 2)selection of element technology for conceptual design, 3)deduction of work process and conceptual design, 4)life cycle cost analysis of the conceptual design. As a result, X-Y table telescopic manipulator, pothole patching end effector, realtime pothole recognizer, 3D pothole volume profiler, automated pothole patching machine controller are selected as core technologies. Furthermore, a conceptual design and working process of an automated pothole patching machine are developed based on the core technologies. According to the life cycle cost analysis result, the cost of the automated method was 38.3% less than that of the conventional method, and the economic efficiency was also superior(ROR 77.1%, Break-even Point 23.8month). It is expected that the application range and impact on the construction industry will be enormous due to the increasing trend of road maintenance market.

• ETRI Journal
• /
• v.44 no.4
• /
• pp.613-623
• /
• 2022

Autism spectrum disorder (ASD) is a developmental disorder associated with cognitive and neurobehavioral disorders. It affects the person's behavior and performance. Autism affects verbal and non-verbal communication in social interactions. Early screening and diagnosis of ASD are essential and helpful for early educational planning and treatment, the provision of family support, and for providing appropriate medical support for the child on time. Thus, developing automated methods for diagnosing ASD is becoming an essential need. Herein, we investigate using various machine learning methods to build predictive models for diagnosing ASD in children using facial images. To achieve this, we used an autistic children dataset containing 2936 facial images of children with autism and typical children. In application, we used classical machine learning methods, such as support vector machine and random forest. In addition to using deep-learning methods, we used a state-of-the-art method, that is, automated machine learning (AutoML). We compared the results obtained from the existing techniques. Consequently, we obtained that AutoML achieved the highest performance of approximately 96% accuracy via the Hyperpot and tree-based pipeline optimization tool optimization. Furthermore, AutoML methods enabled us to easily find the best parameter settings without any human efforts for feature engineering.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 1999.05a
• /
• pp.145-153
• /
• 1999

We consider a Direct Input Output Manufacturing System(DIOMS) which has a munber of machine centers placed along a built-in Automated Storage/Retrieval System(AS/RS). The Storage/Retrieval (S/R) machine handles parts placed on pallets for the machine centers located at either one or both sides of the As/Rs. This report studies the operational aspect of DIOMS and determines the optimal operating policy by combining computer simulation and genetic algorithm. The operational problem includes: input sequencing control, dispatching rule of the S/R machine, machine center-based part type selection rule, and storage assignment policy. For each operating policy, several different policies are considered based on the known research results. In this report, using the computer simulation and genetic algorithm we suggest a method which gives the optimal configuration of operating policies within reasonable computation time.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.22 no.1
• /
• pp.125-130
• /
• 2013

In this paper, in order to overcome shortcomings of manual inspection for the automotive PWM Shaft, we developed an automated inline inspection system. The automated inline inspection system consists of the work feeder unit, conveying unit, outer diameter check unit, run-out and roundness check unit, machine vision, defective separation unit and status alarm unit. We used the machine vision system for automatic inspection process and designed the inline systems for automatic feeding and selecting process. Also the repeated operation test was performed in order to verify the precision and reliability of the proposed automated inline inspection system.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2000.11a
• /
• pp.195-198
• /
• 2000

It can be acquired the high effective productivity through of high speed, precision of machine tools, and then, machine tools will be got a competitive power. Industrially advanced countries already developed that the high speed feed is 60m/min using the high speed ball screw. Also, a lot of problems have happened the feed drive system. It is necessary to study about the characteristics of thermal deformation played a more critical role than static stiffness and dynamic rigidity in controlling the level of machining accuracy. In spite of the improving the thermal deformation characteristics of machine tools at the design stage, there are always some residual errors that have to be compensated for during machining. In this study, thermal deformation error automated compensation device with multiple linear regression is proposed that thermal deformation error can be eliminated at the machining stage. The developed device has been practically applied to the feed drive unit.

• Electronics and Telecommunications Trends
• /
• v.34 no.4
• /
• pp.32-42
• /
• 2019

The performance of machine learning algorithms significantly depends on how a configuration of hyperparameters is identified and how a neural network architecture is designed. However, this requires expert knowledge of relevant task domains and a prohibitive computation time. To optimize these two processes using minimal effort, many studies have investigated automated machine learning in recent years. This paper reviews the conventional random, grid, and Bayesian methods for hyperparameter optimization (HPO) and addresses its recent approaches, which speeds up the identification of the best set of hyperparameters. We further investigate existing neural architecture search (NAS) techniques based on evolutionary algorithms, reinforcement learning, and gradient derivatives and analyze their theoretical characteristics and performance results. Moreover, future research directions and challenges in HPO and NAS are described.

• Journal of the Korean Society for Precision Engineering
• /
• v.18 no.3
• /
• pp.61-67
• /
• 2001

The finishing process for die is an important process because it has influence on final quality of products. Recently s study on development of 5-axis die automated finishing machine has been progressed. But die must be moved from the cutting machine to the die automated finishing machine. So manufacturing cost and time increase and machining error occurs by transfer. So, in this study, a 3-axis machining center was applied to die finishing. Because cutting tool can be changed to finishing tool by ATC, both of cutting and finishing process are possible on the machine. However, this application results in the decrease of finishing for the improvement of form accuracy. So this study focused on the generation of finishing tool path suitable to 3-axis die finishing for the improvement of form accuracy. The form accuracy evaluation is performed by the measurement of removal depth using a stylus profilometer. From the result, it is confirmed that form accuracy was improved less than 2$\mu$m of removal depth error.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.795-798
• /
• 1997

• Nuclear Engineering and Technology
• /
• v.37 no.2
• /
• pp.151-158
• /
• 2005

Advanced nuclear power plants are generally large complex systems automated by computers. Whenever a rare plant emergency occurs the plant operators must cope with the emergency under severe mental stress without committing any fatal errors. Furthermore, The operators must train to improve and maintain their ability to cope with every conceivable situation, though it is almost impossible to be fully prepared for an infinite variety of situations. In view of the limited capability of operators in emergency situations, there has been a new approach to preventing the human error caused by improper human-machine interaction. The new approach has been triggered by the introduction of advanced information systems that help operators recognize and counteract plant emergencies. In this paper, the adverse effect of automation in human-machine systems is explained. The discussion then focuses on how to configure a joint human-machine system for ideal human-machine interaction. Finally, there is a new proposal on how to organize technologies that recognize the different states of such a joint human-machine system.

• International Journal of Advanced Culture Technology
• /
• v.10 no.4
• /
• pp.420-426
• /
• 2022

Developing a machine learning model and putting it into production goes through a number of steps. Automated Machine Learning(AutoML) appeared to increase productivity and efficiency by automating inefficient tasks that occur while repeating this process whenever machine learning is applied. The high degree of automation of AutoML models allows non-experts to use machine learning models and techniques without the need to become machine learning experts. Automating the process of applying machine learning end-to-end with AutoML models has the added benefit of creating simpler solutions, generating these solutions faster, and often generating models that outperform hand-designed models. In this paper, the AutoML data is collected and AutoML's Color Petri net model is created and analyzed based on it.