• Journal of Communications and Networks
• /
• v.11 no.2
• /
• pp.134-147
• /
• 2009

Tracking and exploiting instantaneous spectrum opportunities are fundamental challenges in opportunistic spectrum access (OSA) in presence of the bursty traffic of primary users and the limited spectrum sensing capability of secondary users. In order to take advantage of the history of spectrum sensing and access decisions, a sequential decision framework is widely used to design optimal policies. However, many existing schemes, based on a partially observed Markov decision process (POMDP) framework, reveal that optimal policies are non-stationary in nature which renders them difficult to calculate and implement. Therefore, this work pursues stationary OSA policies, which are thereby efficient yet low-complexity, while still incorporating many practical factors, such as spectrum sensing errors and a priori unknown statistical spectrum knowledge. First, with an approximation on channel evolution, OSA is formulated in a multi-armed bandit (MAB) framework. As a result, the optimal policy is specified by the wellknown Gittins index rule, where the channel with the largest Gittins index is always selected. Then, closed-form formulas are derived for the Gittins indices with tunable approximation, and the design of a reinforcement learning algorithm is presented for calculating the Gittins indices, depending on whether the Markovian channel parameters are available a priori or not. Finally, the superiority of the scheme is presented via extensive experiments compared to other existing schemes in terms of the quality of policies and optimality.

• Journal of Families and Better Life
• /
• v.30 no.4
• /
• pp.13-24
• /
• 2012

This study attempts to examine the effect of family friendly work policies on the work-family balance of employed married women with young children. While previous research has investigated the effects of family friendly work policies, the effects has often been confounded with the effects of other covariates such as worker's and workplace's characteristics. In this study, we try to distinguish the effects of the family friendly work policies from those of other covariates. We draw a sample of 131 employed married women with children under age 12 from the $2^{nd}$ National Korean Family Survey. We compare the level of work-famiy balance of the women by the type of workplace: public sector, large enterprise, medium enterprise, and small enterprise. The results of this study show that some of the differences in the work-family balance of the women working in the different type of workplace can be attributed to socio-demographic background of the women and the work characteristics of workplace. There is, however, an effect of family friendly policies on the work-family balance between those who work in public sector and in medium enterprise after controlling the effects of the covariates.

• Informatization Policy
• /
• v.24 no.4
• /
• pp.79-92
• /
• 2017

As city functions develop more complex and advanced, interests in smart cities are also increasing. Smart cities refer to the cities effectively solving urban problems such as traffic, safety, welfare, and living issues by utilizing ICT. Recently, many countries are attempting to introduce big data, Internet of Things, and artificial intelligence into smart cities, but they have not yet developed into comprehensive urban services. In this paper, we review the current status of domestic and overseas smart cities and suggest ways to solve issues of data sharing and service compatibility. To this end, we propose a "Deep Learning City Framework" that incorporates the deep learning technology into smart city services, and propose a new smart city strategy that safely shares spatial and temporal data in cities and converges learning data of various cities.

• Electronics and Telecommunications Trends
• /
• v.36 no.1
• /
• pp.109-119
• /
• 2021

The Korean government recently announced a plan of the Carbon Neutral policy in addition to the Green New Deal of the Korean New Deal and the Renewable Energy 3020. The energy sector is entering the era of major transformation involving the expansion of decarbonization, decentralization, and digitalization. DNA-oriented ICT technology will be incorporated into the sector. Further, new energy industries and services are being realized via efficient and smart operation and by appropriately managing the energy-environment changes. Recently, ETRI presented a technology development map for 2035 comprising 12 new concepts in four major fields(personal, social, industrial and public) of national intelligence. This map includes the concept of "Energy Maestro" associated with the field of public intelligence for human sustainability. This paper briefly introduces this concept and ETRI's Energy-R&D status. Based on the domain knowledge and the experience acquired through the R&D, ETRI will lead to a new paradigm with respect to the creation of new energy services and industries via the incorporation of the new ICT technologies including AI and big-data into the energy sector.

• KEPCO Journal on Electric Power and Energy
• /
• v.7 no.1
• /
• pp.115-123
• /
• 2021

Through machine learning-based load prediction, it is possible to prevent excessive power generation or unnecessary economic investment by estimating the appropriate amount of facility investment in consideration of the load that will increase in the future or providing basic data for policy establishment to distribute the maximum load. However, in order to secure the reliability of the developed load prediction model in the field, the performance comparison verification between the distribution line load prediction models must be preceded, but a comparative performance verification system between the distribution line load prediction models has not yet been established. As a result, it is not possible to accurately determine the performance excellence of the load prediction model because it is not possible to easily determine the likelihood between the load prediction models. In this paper, we developed a reliability verification system for load prediction models including a method of comparing and verifying the performance reliability between machine learning-based load prediction models that were not previously considered, verification process, and verification result visualization methods. Through the developed load prediction model reliability verification system, the objectivity of the load prediction model performance verification can be improved, and the field application utilization of an excellent load prediction model can be increased.

• Korean Journal of Artificial Intelligence
• /
• v.8 no.2
• /
• pp.11-16
• /
• 2020

Among the innovative companies leading the era of the 4th industrial revolution, the world's largest Internet company is Google. Google has grown by providing convenient services such as Internet search, Android smartphone operating system, and video. Now, Google is leading the global IT industry by continuing to develop in various new business fields based on open service platforms, artificial intelligence, and big data. In this study, an exploratory discussion was conducted on Google's success factors and future directions. The purpose of the research is to understand the development process of the IT field from the successfactors of Google and to analyze the development direction of the future IT industry. Google's success factors were its open platform policy and successful acquisitions of external companies. In fact, most of the services Google offers come from companies that have acquired and acquired them. In addition, there was a corporate culture that values and supportsthe spirit of challenge and autonomy of members who are not afraid of failure. Based on this study's review of Google's direction analysis, the follow-up study will infer the direction of the IT industry in depth and look at the future technologies that IT majors need to prepare.

• East Asian mathematical journal
• /
• v.38 no.2
• /
• pp.187-214
• /
• 2022

This study compares the functions of the Learning Management Systems (LMS) in three widely used Edu-Tech platforms, that support students' individualized learning by using the learning characteristics of the students. The rapid advances in artificial intelligence (AI) are broadening their impacts in the education industry, and play a broad role in supporting student learning. In many countries, online classes have become a norm due to the COVID-19 crisis, and the demand for Edu-Tech in classes has increased rapidly. As a result, many countries, including South Korea, are now preparing and implementing various policy measures to adopt Edu-Tech in the class setting. Therefore, in this study, we analyze and compare the structures and characteristics of the three widely used Edu-Tech platforms that support individualized mathematics learning. In particular, we compare the LMSs of the three platforms by considering the elements such as learning design, learning management, learner analysis, learning result analysis, and student management functions. The results of this study give implications in the future directions to take on how to build Edu-Tech platform models that promote students' individualized mathematics learning in public education.

• The Journal of Korea Robotics Society
• /
• v.17 no.3
• /
• pp.264-272
• /
• 2022

Human-robot cooperative tasks are increasingly required in our daily life with the development of robotics and artificial intelligence technology. Interactive reinforcement learning strategies suggest that robots learn task by receiving feedback from an experienced human trainer during a training process. However, most of the previous studies on Interactive reinforcement learning have required an extra feedback input device such as a mouse or keyboard in addition to robot itself, and the scenario where a robot can interactively learn a task with human have been also limited to virtual environment. To solve these limitations, this paper studies training strategies of robot that learn table balancing tasks interactively using deep reinforcement learning with human's facial expression feedback. In the proposed system, the robot learns a cooperative table balancing task using Deep Q-Network (DQN), which is a deep reinforcement learning technique, with human facial emotion expression feedback. As a result of the experiment, the proposed system achieved a high optimal policy convergence rate of up to 83.3% in training and successful assumption rate of up to 91.6% in testing, showing improved performance compared to the model without human facial expression feedback.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.4_2
• /
• pp.627-636
• /
• 2022

Market convergence plays an increasingly important role in sustaining competitiveness and providing impetus for the new product development. However, existing research focused mostly on the analysis of convergence at technology level. This study examines the phenomenon of market convergence based on the start-up data. Similar to the analysis of technology convergence, this study adopts the concept of co-classification analysis for constructing the co-occurrence matrix and the corresponding network. In this context, network centrality measures were calculated to assess the influence of individual market segments. Based on three metrics "growth", "persistence" and "novelty", the market convergence dynamics were explored and promising interactions between two distinct market segments were highlighted. The findings suggest that both segments "AI" and "blockchain" are acting as a driver that fosters market convergence in the startup landscape. The analysis results can provide valuable information for the R&D managers and policy makers in the design of targeted policies and programs, which can promote market convergence and interdisciplinary knowledge transfer.

• International Journal of Advanced Culture Technology
• /
• v.11 no.2
• /
• pp.191-195
• /
• 2023

An X-event is an event that is difficult to predict and unlikely to occur, but if it occurs, it has a very large ripple effect, such as loss of life, property, territory, and emotional turmoil. Extreme events are unlikely to occur, but they can happen someday, and if they do, they have a great impact on society as a whole, so they must be prepared to minimize the impact and impact. For this purpose, we collected opinions from low-level experts at the Korea Army Research Center for Future & Innovation and the Army College on extreme events that can trigger the near future (10 years) in the field of high-tech science and technology, which is currently developing rapidly after the 4th Industrial Revolution. The researchers intend to synthesize and analyze this data to derive implications and provide a response direction to alleviate the ultra-uncertainty of extreme events and provide a cornerstone for crisis management strategies for the occurrence of serial and simultaneous extreme events.