• The Journal of Korea Robotics Society
• /
• v.14 no.2
• /
• pp.81-86
• /
• 2019

Robots are used in various industrial sites, but traditional methods of operating a robot are limited at some kind of tasks. In order for a robot to accomplish a task, it is needed to find and solve accurate formula between a robot and environment and that is complicated work. Accordingly, reinforcement learning of robots is actively studied to overcome this difficulties. This study describes the process and results of learning and solving which applied reinforcement learning. The mission that the robot is going to learn is bottle flipping. Bottle flipping is an activity that involves throwing a plastic bottle in an attempt to land it upright on its bottom. Complexity of movement of liquid in the bottle when it thrown in the air, makes this task difficult to solve in traditional ways. Reinforcement learning process makes it easier. After 3-DOF robotic arm being instructed how to throwing the bottle, the robot find the better motion that make successful with the task. Two reward functions are designed and compared the result of learning. Finite difference method is used to obtain policy gradient. This paper focuses on the process of designing an efficient reward function to improve bottle flipping motion.

• The Journal of Asian Finance, Economics and Business
• /
• v.5 no.2
• /
• pp.81-94
• /
• 2018

The purpose of this study is to substantiate the affecting factors of informal learning outcomes for professions in various dimensions of an individual and organization. In specific, the study analyzed the effects of learning motivation, job characteristics, and a supportive learning environment which have on task-related knowledge acquisition, adapting to organization and understanding contexts, relationship formation, and improving self-development-ability. The participants of the study were 261 professionals working at four major accounting firms in South Korea. Multiple regression models were applied step by step for analysis. In this study, the informal learning of professionals working at four major accounting firms is influenced by various factors of learning motivation, job characteristics, and a supportive learning environment. The detailed analysis results were as follows. Firstly, peer-support showed the most positive effect on task-related knowledge acquisition. Secondly, for adapting to organization and understanding contexts, task autonomy showed the greatest effect. Thirdly, peer-support was found to be the most important factor for relationship formation. Fourthly, for improving self-development ability, learning goal orientation showed to be the most important factor. The various factors facilitated the professional learning by empirical identification. The study presented practical implications for creating an effective informal learning support environment.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.29-30
• /
• 2022

Curriculum learning은 딥러닝의 성능을 향상시키기 위해 사람의 학습 과정과 유사하게 일종의 'curriculum'을 도입해 모델을 학습시키는 방법이다. 대부분의 연구는 학습 데이터 중 개별 샘플의 난이도를 기반으로 점진적으로 모델을 학습시키는 방안에 중점을 두고 있다. 그러나, coarse-to-fine 메카니즘은 데이터의 난이도보다 학습에 사용되는 class의 유사도가 더욱 중요하다고 주장하며, 여러 난이도의 auxiliary task를 차례로 학습하는 방법을 제안했다. 그러나, 이 방법은 혼동행렬 기반으로 class의 유사성을 판단해 auxiliary task를 생성함으로 다중 레이블 분류에는 적용하기 어렵다는 한계점이 있다. 따라서, 본 논문에서는 multi-label 환경에서 multi-class와 binary task를 생성하는 방법을 제안해 coarse-to-fine 메카니즘 적용을 위한 방안을 제시하고, 그 결과를 분석한다.

• Journal of The Korean Association For Science Education
• /
• v.33 no.3
• /
• pp.679-693
• /
• 2013

The purpose of this study is to develop an inventory to classify task commitment types of science learning and to classify highschool students' task commitment types. Firstly, inventory questions were designed following the literature analysis on the task commitment components which involve self confidence, high goal setting, and focused attention. Prototype inventory underwent the content validity test, pilot test, and reliability test. Through these steps, final inventory was input to 462 high school students and underwent the factor analysis and cluster analysis. Factor analysis confirmed three components of task commitment as the three factors of inventory questions. In order to find how many clusters exist, factors of developed inventory became new variables. Each factor's factor mean was calculated and served as the new variable of the cluster analysis. Cluster analysis extracted five clusters as task commitment types. The 5 clusters were suggested by the agglomarative schedule and dendrogram gained from a hierarchical cluster analysis with the setting of the Ward algorithm and Squared Euclidean distance. Based on the factor mean score, traits of each cluster could be drawn out. Inventory developed by this study is expected to be used to identify student commitment types and assess the effectiveness of task commitment enhancement programs.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.4
• /
• pp.1258-1275
• /
• 2023

Cloud computing is a new technology that has adapted to the traditional way of service providing. Service providers are responsible for managing the allocation of resources. Selecting suitable containers and bandwidth for job scheduling has been a challenging task for the service providers. There are several existing systems that have introduced many algorithms for resource allocation. To overcome these challenges, the proposed system introduces an Optimized Task Scheduling Algorithm with Deep Learning (OTS-DL). When a job is assigned to a Cloud Service Provider (CSP), the containers are allocated automatically. The article segregates the containers as' Long-Term Container (LTC)' and 'Short-Term Container (STC)' for resource allocation. The system leverages an 'Optimized Task Scheduling Algorithm' to maximize the resource utilisation that initially inquires for micro-task and macro-task dependencies. The bottleneck task is chosen and acted upon accordingly. Further, the system initializes a 'Deep Learning' (DL) for implementing all the progressive steps of job scheduling in the cloud. Further, to overcome container attacks and errors, the system formulates a Container Convergence (Fault Tolerance) theory with high-level security. The results demonstrate that the used optimization algorithm is more effective for implementing a complete resource allocation and solving the large-scale optimization problem of resource allocation and security issues.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.9
• /
• pp.3663-3679
• /
• 2020

Scheduling plays a dynamic role in cloud computing in generating as well as in efficient distribution of the resources of each task. The principle goal of scheduling is to limit resource starvation and to guarantee fairness among the parties using the resources. The demand for resources fluctuates dynamically hence the prearranging of resources is a challenging task. Many task-scheduling approaches have been used in the cloud-computing environment. Security in cloud computing environment is one of the core issue in distributed computing. We have designed a deep learning-based security model for scheduling tasks in cloud computing and it has been implemented using CloudSim 3.0 simulator written in Java and verification of the results from different perspectives, such as response time with and without security factors, makespan, cost, CPU utilization, I/O utilization, Memory utilization, and execution time is compared with Round Robin (RR) and Waited Round Robin (WRR) algorithms.

• Journal of Korea Society of Industrial Information Systems
• /
• v.1 no.1
• /
• pp.153-176
• /
• 1996

The new field of learning control devleops controllers that learn to improve their performance at executing a given task, based on experience performing this task. the simplest forms of learning control are based on the same concepts as integral control, but operating in the domain of the repetitions of the task. This paper studies the use of such controllers ina decentralized system, such as a robot with the controller for each link acting independently. The basic result of the paper is to show that stability of the learning controllers for all subsystems when the coupling between subsystems is turned off, assures stability of the decentralized learning in the coupled system, provided that the sample time in the digital learning controller is sufficiently short.

• Journal of The Korean Association For Science Education
• /
• v.16 no.4
• /
• pp.441-450
• /
• 1996

Various contexts are involved in the processes of science learning and instruction. In the perspective that the results of science learning and instruction usually depend on the nature of learning task content and context, content effects or context effects have been researched up to now. But, the discrimination between them was very ambiguous. For the clarity of them, it was supposed that science content would be composed of decontextualized knowledges and contexts, which were respectively dichotomized in common and special ones among disciplines of science. Science learning and instruction was discussed in view of interactions between cognitive, learning task, and social-cultural contexts. Especially, it was emphasized that task contexts, as a bridging role among contexts should be constructed considering cognitive and social cultural contexts.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.2
• /
• pp.681-687
• /
• 2013

This study examined whether the combination of the indoor temperature on the learning environment and the colors of the learning materials affect the learning performance. To do this, the condition of indoor temperature was divided into three conditions: the neutral condition which is the appropriate temperature condition of the learning activities ($22.5{\sim}24^{\circ}C$), the high-temperature condition (> $24^{\circ}C$), and the low-temperature condition (< $22.5^{\circ}C$). In addition, colors of red, blue, black, and green were used as the warm, cold, and neutral colors, and the verbal-working memory task was used as the learning task. As a result, it was not significant differences in the response time of the learning task, whereas, in the accuracy rate of the learning task, the performance was more accurate in red- and black-color conditions. These results could be interpreted as the saliency and color-temperature of the red color, and the familiarity and specificity of the black color.

• Journal of KIISE
• /
• v.44 no.8
• /
• pp.822-831
• /
• 2017

In this paper, we propose a Korean dependency parsing model using multi-task learning based pointer networks. Multi-task learning is a method that can be used to improve the performance by learning two or more problems at the same time. In this paper, we perform dependency parsing by using pointer networks based on this method and simultaneously obtaining the dependency relation and dependency label information of the words. We define five input criteria to perform pointer networks based on multi-task learning of morpheme in dependency parsing of a word. We apply a fine-tuning method to further improve the performance of the dependency parsing proposed in this paper. The results of our experiment show that the proposed model has better UAS 91.79% and LAS 89.48% than conventional Korean dependency parsing.