• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.41 no.1
• /
• pp.128-139
• /
• 2018

As The Fourth Industrial Revolution and Intelligent Information Age came into full-scale, the policy of open government data has become a hot topic for each country. The United States, the United Kingdom, and other countries are shifting policy direction to "creating value" of open government data. Also, in the age of the digital economy where the data market is soaring, open government data is gradually being recognized as a new raw material for new business and start-ups. In addition, Korea ranked first in the OECD open government data evaluation twice in a row, and was highly evaluated in the international evaluation. However, domestic firms are still lacking in qualitative openness of government data, data is dispersed among institutions, lack of public-private data linkage, and development of app-oriented development. This study attempts to analyze major national policies for the creation of a data ecosystem that considers data lifecycle, from production to storage, distribution and utilization of data. First, the target countries were the leading public data countries among the OGP member countries, the USA, the UK, Australia and Canada. The results of this study are as follows. As a result of analyzing the results and comparing Korea's policies, it was concluded that most of Korea is superior in open government data policy. However, improvement of data quality, development of open data portal as an open platform, support for finding various users including apps and web development companies, and cultivation of open government data utilizing personnel are analyzed as policy issues. In addition, the direction of policy for the balanced ecosystem of Korea is presented together.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2006.05a
• /
• pp.211-217
• /
• 2006

The learning control develops controllers that learn to improve their performance at executing a given task, based on experience performing this specific task. In a previous work, the authors presented an iterative precision of linear decentralized learning control based on p-integrated learning method for the vertical dynamic multiple systems. This paper develops an indirect decentralized learning control based on adaptive control method. The original motivation of the teaming control field was teaming in robots doing repetitive tasks such as on an assembly line. This paper starts with decentralized discrete time systems, and progresses to the robot application, modeling the robot as a time varying linear system in the neighborhood of the nominal trajectory, and using the usual robot controllers that are decentralized, treating each link as if it is independent of any coupling with other links. Error wave propagation method will show up in the numerical simulation for five-bar linkage as a vertical dynamic robot. The methods of learning system are shown up for the iterative precision of each link at each time step in repetition domain. Those can be helped to apply to the vertical multiple dynamic systems for precision quality assurance in the industrial robots and medical equipments.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.1
• /
• pp.615-621
• /
• 2016

The selection of a flagship industry is based on whether the industry's developmental impact is great and whether the industry can be the center of the national economy. Here, a ripple effect may be derived by analyzing the forward and backward linkage effects, but in the case of industries that are the centerpieces of the national economy, each researcher reported different results. Consequently, they could not agree on their flagship industry despite belonging to the same time. This study presents a prestige centrality of network analysis as a way of analyzing an industry, which was the center of the national economy, and performed empirical analysis utilizing the 2013 I-O Table. The analysis showed that the industries classified as those with high centrality include the energy industry, which is essential for economic development, can create a synergy effect with other industries, such as the transportation industry, industries with a high level of export and employment, such as electronics and chemicals, and industries for domestic demand, such as wholesale and retail, food services and accommodation.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.8
• /
• pp.344-349
• /
• 2017

Wall-climbing robots have been developed for various purposes, such as cleaning skyscraper windows, maintaining large structures, and welding vessels. Conventional wall-climbing robots use movement systems based on wheels or legs. However, wheeled robots suffer from slipping effects, while legged systems require many actuators and control systems for the complex linkage structure, which also increases the weight of the robot. To overcome these disadvantages, we propose a new wall-climbing robot that walks based on gorilla locomotion. The proposed robot consists of a DC drive motor, a vacuum pump for adsorption, and a micro controller for controlling the system. The performance of the robot was experimentally verified on vertical and horizontal flat surfaces. The robot could be used for various functions in industrial sites or disaster areas.

• Journal of Korea Society of Industrial Information Systems
• /
• v.11 no.2
• /
• pp.40-47
• /
• 2006

The learning control develops controllers that learn to improve their performance at executing a given task, based on experience performing this specific task. In a previous work the authors presented an iterative precision of linear decentralized learning control based on p-integrated teaming method for the vertical dynamic multiple systems. This paper develops an indirect decentralized learning control based on adaptive control method. The original motivation of the loaming control field was learning in robots doing repetitive tasks such as on a]1 assembly line. This paper starts with decentralized discrete time systems, and progresses to the robot application, modeling the robot as a time varying linear system in the neighborhood of the nominal trajectory, and using the usual robot controllers that are decentralized, treating each link as if it is independent of any coupling with other links. Error wave propagation method will show up in the numerical simulation for five-bar linkage as a vertical dynamic robot. The methods of learning system are shown up for the iterative precision of each link at each time step in repetition domain. Those can be helped to apply to the vertical multiple dynamic systems for precision quality assurance in the industrial robots and medical equipments.

• Journal of Advanced Technology Convergence
• /
• v.1 no.2
• /
• pp.01-09
• /
• 2022

Recently, safety issues in companies and public institutions are no longer a task that can be postponed, and when a major safety accident occurs, not only direct financial loss, but also indirect loss of social trust in the company and public institution is greatly increased. In particular, in the case of a fatal accident, the damage is even more serious. Accordingly, as companies and public institutions expand their investments in industrial safety education and prevention, open AI learning model creation technology that enables safety management services without being affected by user behavior in industrial sites where high-risk situations exist, edge terminals System development using inter-AI collaboration technology, cloud-edge terminal linkage technology, multi-modal risk situation determination technology, and AI model learning support technology is underway. In particular, with the development and spread of artificial intelligence technology, research to apply the technology to safety issues is becoming active. Therefore, in this paper, an open cloud platform design method that can support AI model learning for high-risk site safety management is presented.

• The Journal of Society for e-Business Studies
• /
• v.23 no.4
• /
• pp.109-126
• /
• 2018

With massive and dense production, the livestock industry is rapidly moving into a large-scale, capital-intensive industry especially in swine, poultry, and ducks. However, livestock epidemics can pose a serious threat to the livestock industry and the lives of the people. The government has established and operates the National Animal Protection and Prevention System (KAHIS) since 2013 in order to control the threat, in accordance with the five stages. The digitalized data and information are excellent in ease of management, but it is also pointed out that it is difficult to take countermeasures through linkage with the data in an emergency situation. Recently, the technology of the fourth industrial revolution such as Internet of Things (IoT), Big Data, Artificial intelligence (AI) has been rapidly implemented to the livestock industry, which makes smart livestock disease control system possible. Therefore, this study investigated the domestic and overseas cases which apply 4th Industrial Revolution technology in the industry, and derived 13 possible candidate tasks in the near future. In order to ascertain the priority of policy formulation, we surveyed the expert groups and examined the priority of each of the five stages of the prevention and the priority of each stage. The results of this study are expected to contribute to the establishment of policies for the advancement of smart livestock disease control research and livestock protection.

• Journal of Intelligence and Information Systems
• /
• v.28 no.1
• /
• pp.89-106
• /
• 2022

Recently, the amount of video data collected from smartphones, CCTVs, black boxes, and high-definition cameras has increased rapidly. According to the increasing video data, the requirements for analysis and utilization are increasing. Due to the lack of skilled manpower to analyze videos in many industries, machine learning and artificial intelligence are actively used to assist manpower. In this situation, the demand for various computer vision technologies such as object detection and tracking, action detection, emotion detection, and Re-ID also increased rapidly. However, the object detection and tracking technology has many difficulties that degrade performance, such as re-appearance after the object's departure from the video recording location, and occlusion. Accordingly, action and emotion detection models based on object detection and tracking models also have difficulties in extracting data for each object. In addition, deep learning architectures consist of various models suffer from performance degradation due to bottlenects and lack of optimization. In this study, we propose an video analysis system consists of YOLOv5 based DeepSORT object tracking model, SlowFast based action recognition model, Torchreid based Re-ID model, and AWS Rekognition which is emotion recognition service. Proposed model uses single-linkage hierarchical clustering based Re-ID and some processing method which maximize hardware throughput. It has higher accuracy than the performance of the re-identification model using simple metrics, near real-time processing performance, and prevents tracking failure due to object departure and re-emergence, occlusion, etc. By continuously linking the action and facial emotion detection results of each object to the same object, it is possible to efficiently analyze videos. The re-identification model extracts a feature vector from the bounding box of object image detected by the object tracking model for each frame, and applies the single-linkage hierarchical clustering from the past frame using the extracted feature vectors to identify the same object that failed to track. Through the above process, it is possible to re-track the same object that has failed to tracking in the case of re-appearance or occlusion after leaving the video location. As a result, action and facial emotion detection results of the newly recognized object due to the tracking fails can be linked to those of the object that appeared in the past. On the other hand, as a way to improve processing performance, we introduce Bounding Box Queue by Object and Feature Queue method that can reduce RAM memory requirements while maximizing GPU memory throughput. Also we introduce the IoF(Intersection over Face) algorithm that allows facial emotion recognized through AWS Rekognition to be linked with object tracking information. The academic significance of this study is that the two-stage re-identification model can have real-time performance even in a high-cost environment that performs action and facial emotion detection according to processing techniques without reducing the accuracy by using simple metrics to achieve real-time performance. The practical implication of this study is that in various industrial fields that require action and facial emotion detection but have many difficulties due to the fails in object tracking can analyze videos effectively through proposed model. Proposed model which has high accuracy of retrace and processing performance can be used in various fields such as intelligent monitoring, observation services and behavioral or psychological analysis services where the integration of tracking information and extracted metadata creates greate industrial and business value. In the future, in order to measure the object tracking performance more precisely, there is a need to conduct an experiment using the MOT Challenge dataset, which is data used by many international conferences. We will investigate the problem that the IoF algorithm cannot solve to develop an additional complementary algorithm. In addition, we plan to conduct additional research to apply this model to various fields' dataset related to intelligent video analysis.

• Asian Journal of Atmospheric Environment
• /
• v.10 no.4
• /
• pp.197-207
• /
• 2016

Large quantities of air pollutants are released into the atmosphere and hence, must be monitored and routinely assessed for their health implications. This paper proposes a stochastic technique to predict unobserved hazardous air pollutants (HAPs), especially Benzo[a]pyrene (BaP), which can have negative effects on human health. The proposed approach constructs a nearest-neighbor structure by incorporating the linkage between BaP and meteorology and meteorological effects. This approach is adopted in order to predict unobserved BaP concentrations based on observed (or forecasted) meteorological conditions, including temperature, precipitation, wind speed, and air quality. The effects of BaP on human health are examined by characterizing the cancer risk. The efficient prediction provides useful information relating to the optimal monitoring period and projections of future BaP concentrations for both industrial and residential areas within Korea.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.13 no.1
• /
• pp.185-196
• /
• 2017

Today, companies and social actors at the beginning of the Fourth Industrial Revolution are focusing on active innovation and efforts to adapt to rapidly changing environmental changes. Design thinking refers to creative strategies designers utilize during the process of designing. Design thinking is also an approach that can be used to consider issues and resolve problems more broadly than within professional design practice, and has been applied in business and to social issues. However, there are some limitations in the design thinking methodology during the project in the field. This paper presents a novel design - thinking process that incorporates a lean start - up based business model into the design thinking process. We conducted a case study to verify the effectiveness of our new design thinking process in social innovation projects. In this paper, it is meaningful to suggest and verify a new process that combines business model Zen to complement the limit of design thinking. It will also provide guidelines for design thinking projects as tools for social innovation.