• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.429-431
• /
• 2003

The induced learning retardation method involves the temporary inhibition of the artificial neural network’s active units from participating in the error reduction process during training. This stimulates the less active units to contribute significantly to reduce the network error. However, some less active units are not sensitive to stimulation making them almost useless. The network can then be pruned by removing the less active units to make it smaller and more efficient. This study focuses on making the network more efficient and accurate by developing the induced learning retardation and pruning sequence training method. The developed procedure results to faster learning and more accurate artificial neural network for satellite image classification.

• Annual Conference of KIPS
• /
• 2019.05a
• /
• pp.485-486
• /
• 2019

Simulated driving behavior is an important aspect of realistic simulation systems. To simulate natural driving behavior, this paper proposes an imitation learning method based on active learning that combines demonstration and experience. Driving demonstrations are collected from human drivers in a driving simulator. A driving behavior policy is learned from these demonstrations. The driving demonstration dataset is augmented with new demonstrations that the original demonstrations did not contain, in the form of behaviors from another driving behavior policy learned from experience. The final driving behavior policy is learned from an augmented demonstration dataset.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• pp.4776-4794
• /
• 2020

We propose a rapid adaptive learning framework for streaming object detection, called EER-ASSL. The method combines the expected error reduction (EER) dependent rollback learning and the active semi-supervised learning (ASSL) for a rapid adaptive CNN detector. Most CNN object detectors are built on the assumption of static data distribution. However, images are often noisy and biased, and the data distribution is imbalanced in a real world environment. The proposed method consists of collaborative sampling and EER-ASSL. The EER-ASSL utilizes the active learning (AL) and rollback based semi-supervised learning (SSL). The AL allows us to select more informative and representative samples measuring uncertainty and diversity. The SSL divides the selected streaming image samples into the bins and each bin repeatedly transfers the discriminative knowledge of the EER and CNN models to the next bin until convergence and incorporation with the EER rollback learning algorithm is achieved. The EER models provide a rapid short-term myopic adaptation and the CNN models an incremental long-term performance improvement. EER-ASSL can overcome noisy and biased labels in varying data distribution. Extensive experiments shows that EER-ASSL obtained 70.9 mAP compared to state-of-the-art technology such as Faster RCNN, SSD300, and YOLOv2.

• The Journal of Korean Academic Society of Nursing Education
• /
• v.20 no.4
• /
• pp.577-586
• /
• 2014

Purpose: This study investigates patterns of small group interaction and examines the influence among graduate nursing students of online collaborative learning strategies on small group interaction patterns, task performance and learning attitude in web-based team learning environments. Method: To analyze patterns of small group interaction, group discussion dialogues were reviewed by two instructors. Groups were divided into two categories depending on the type of feedback given (passive or active). For task performance, evaluation of learning processes and numbers of postings were examined. Learning attitude toward group study and coursework were measured via scales. Results: Explorative interactions were still low among graduate nursing students. Among the students given active feedback, considerable individual variability in interaction frequency was revealed and some students did not show any specific type of interaction pattern. Whether given active or passive feedback, groups exhibited no significant differences in terms of task performance and learning attitude. Also, frequent group interaction was significantly related to greater task performance. Conclusion: Active feedback strategies should be modified to improve task performance and learning attitude among graduate nursing students.

• International Journal of Contents
• /
• v.12 no.4
• /
• pp.8-16
• /
• 2016

This research proposes the composition logic of an Active Learning Environment (ALE), to enable discovery by learning through experience, whilst increasing knowledge about modern architectural heritage. Linking information to the historical heritage using Information and Communication Technology (ICT) helps to overcome the limits of previous learning methods, by providing rich learning resources on site. Existing field trips of cultural heritages are created to impart limited experience content from web resources, or receive content at a specific place through humanities Geographic Information System (GIS). Therefore, on the basis of the blended space theory, an augmented space experience method for overcoming these shortages was composed. An ALE space framework is proposed to enable discovery through learning in an expanded space. The operation of ALE space is needed to create full coordination, such as a Content Management System (CMS). It involves a relation network to provide knowledge to the rule engine of the CMS. The application is represented with the Deoksugung Palace Seokjojeon hall example, by describing a user experience scenario.

• Nuclear Engineering and Technology
• /
• v.54 no.9
• /
• pp.3283-3292
• /
• 2022

Based on the Deep Q-Network(DQN) algorithm of reinforcement learning, an active fault-tolerance method with incremental action is proposed for the control system with sensor faults of the once-through steam generator(OTSG). In this paper, we first establish the OTSG model as the interaction environment for the agent of reinforcement learning. The reinforcement learning agent chooses an action according to the system state obtained by the pressure sensor, the incremental action can gradually approach the optimal strategy for the current fault, and then the agent updates the network by different rewards obtained in the interaction process. In this way, we can transform the active fault tolerant control process of the OTSG to the reinforcement learning agent's decision-making process. The comparison experiments compared with the traditional reinforcement learning algorithm(RL) with fixed strategies show that the active fault-tolerant controller designed in this paper can accurately and rapidly control under sensor faults so that the pressure of the OTSG can be stabilized near the set-point value, and the OTSG can run normally and stably.

• Journal of KIISE
• /
• v.43 no.2
• /
• pp.269-274
• /
• 2016

Named entity recognition is a process which extracts named entities in sentences and determines categories of the named entities. Previous studies on named entity recognition have primarily been used for supervised learning. For supervised learning, a large training corpus manually annotated with named entity categories is needed, and it is a time-consuming and labor-intensive job to manually construct a large training corpus. We propose a semi-supervised learning method to minimize the cost needed for training corpus construction and to rapidly enhance the performance of named entity recognition. The proposed method uses distance supervision for the construction of the initial training corpus. It can then effectively remove noise sentences in the initial training corpus through the use of an active bagging method, an ensemble method of bagging and active learning. In the experiments, the proposed method improved the F1-score of named entity recognition from 67.36% to 76.42% after active bagging for 15 times.

• Smart Media Journal
• /
• v.8 no.1
• /
• pp.67-73
• /
• 2019

This study investigates Active Learning and Facilitation Convergence Education Program which can improve core competency to cope with vocational education in the fourth industrial revolution era. I applied the integrated advantages of Active Learning which enhances 'problem solving skill' and those of Facilitation for creative thinking idea to application design process coursework and verified the effectiveness of such education method through student satisfaction survey. I also designed application contents for the students who are familiar with the mobile environments and UI contents for data visualization which can help those students to improve their skills in software. Every coursework was conducted as a team project. As a result, Active Learning and Facilitation Convergence Education Program is found to be helpful in improving the basic skills and competencies required in college education. I hope this work helps to reduce the educational gap between industry and professional colleges.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.163-166
• /
• 2007

최근에 국내외의 인공지능 분야에서는, 강화학습(reinforcement learning)에 관한 연구가 활발히 진행되고 있다. 본 논문에서는 능동형 현가장치(active-suspension)의 제어를 위하여 RLS 기반 NAC(natural actor-critic)을 활용한 강화학습 기법을 적용해보고, 그 성능을 시뮬레이션을 통해 확인해본다.

• Journal of Korea Multimedia Society
• /
• v.20 no.11
• /
• pp.1720-1728
• /
• 2017

Active shape model is widely used in the field of image processing especially on arbitrary meaningful shape extraction from single gray level image. Cootes et. al. showed efficient detection of variable shape from image by using covariance and mean shape from learning. There are two stages of learning and testing. Hahn applied enhanced shape alignment method rather than using Cootes's rotation and scale scheme. Hahn did not modified the profile itself. In this paper, the method using directional one dimensional profile is proposed to enhance Cootes's one dimensional profile and the shape alignment algorithm of Hahn is combined. The performance of the proposed method was superior to Cootes's and Hahn's. Average landmark estimation error for each image was 27.72 pixels and 39.46 for Cootes's and 33.73 for Hahn's each.