• Journal of Korean Elementary Science Education
• /
• v.39 no.3
• /
• pp.433-448
• /
• 2020

In this study, the tasks of thermal equilibrium and heat insulation concept were divided into scientific and everyday contexts to analyzed the level of familiarity, feeling of knowing, state curiosity, and state anxiety that students feel in task contexts and their relationship. The subjects of this study were One hundred nine students in sixth grade of elementary schools located in metropolitan cities. The results of this study were as follows. First, there was no difference in the level of feeling of knowing, state curiosity, and state anxiety in the task of scientific and everyday contexts. In the case of familiarity, there was no consistent tendency in the concept of thermal equilibrium and heat insulation. And the group who recognized the task context familiarly had higher feeling of knowing and lower state anxiety than the group who recognized the task context unfamiliarly. Second, familiarity and feeling of knowing showed high positive correlation, state anxiety and familiarity showed negative correlation, and state anxiety and feeling of knowing had also negative correlation. In addition, familiarity had a negative effect on state anxiety, and FOK had a positive effect on state curiosity and a negative effect on state anxiety. There was no significant moderating effect of the task context. Third, in case of state curiosity, the group perceived the knowledge gap was very small had the highest state curiosity, and the group perceived the knowledge gap was very large had the lowest state curiosity. In case of state anxiety, the less the knowledge gap was perceived, the lower the anxiety was triggered. This study broadens our understanding of the learning process and provides implications for effective instruction strategies for students' cognitive and emotional states.

• The Journal of Korea Robotics Society
• /
• v.19 no.2
• /
• pp.196-202
• /
• 2024

The ability to understand given environments and plan a sequence of actions leading to goal state is crucial for personal service robots. With recent advancements in deep learning, numerous studies have proposed methods for state representation in planning. However, previous works lack explicit information about relationships between objects when the state observation is converted to a single visual embedding containing all state information. In this paper, we introduce graph-based state representation that incorporates both object and relationship features. To leverage these advantages in addressing the task planning problem, we propose a Graph Neural Network (GNN)-based subgoal prediction model. This model can extract rich information about object and their interconnected relationships from given state graph. Moreover, a search-based algorithm is integrated with pre-trained subgoal prediction model and state transition module to explore diverse states and find proper sequence of subgoals. The proposed method is trained with synthetic task dataset collected in simulation environment, demonstrating a higher success rate with fewer additional searches compared to baseline methods.

• Journal of Korean Elementary Science Education
• /
• v.42 no.4
• /
• pp.513-522
• /
• 2023

There is a lack of empirical research on the level of students' state anxiety according to their perceived task difficulty when confronting science questions. This study seeks to investigate whether perceived task difficulty moderates the process of arousing students' state anxiety in science learning. In pursuit of this objective, we engaged 410 fifth- and sixth-grade elementary school students (186 fifth graders; 194 females) in solving two science questions. We then verified the moderating effect of perceived task difficulty on the relationship between science anxiety and state anxiety arousal when confronting science questions using the PROCESS Macro Model 1. Results confirmed that science anxiety and perceived task difficulty significantly and positively predicted state anxiety. Notably, perceived task difficulty had a significant moderating effect on the process of arousing state anxiety, where lower perceived task difficulty led to a greater increase in state anxiety after confronting the science questions. We discuss the implications of the findings for science education and propose potential directions for future research.

• The Journal of Korea Robotics Society
• /
• v.1 no.2
• /
• pp.107-116
• /
• 2006

We propose a planning algorithm to automatically generate a robust behavior plan (RBP) with which mobile robots can achieve their task goal from any initial states under dynamically changing environments. For this, task description space (TDS) is formulated, where a redundant task configuration space and simulation model of physical space are employed. Successful task episodes are collected, where $A^*$ algorithm is employed. Interesting TDS state vectors are extracted, where occurrence frequency is used. Clusters of TDS state vectors are found by using state transition tuples and features of state transition tuples. From these operations, characteristics of successfully performed tasks by a simulator are abstracted and generalized. Then, a robust behavior plan is constructed as an ordered tree structure, where nodes of the tree are represented by attentive TDS state vector of each cluster. The validity of our method is tested by real robot's experimentation for a box-pushing-into-a-goal task.

• The Journal of Korea Robotics Society
• /
• v.3 no.1
• /
• pp.23-32
• /
• 2008

This paper presents a task planning system for a steward robot, which has been developed as an interactive intermediate agent between an end-user and a complex smart home environment called the ISH (Intelligent Sweet Home) at KAIST (Korea Advanced Institute of Science and Technology). The ISH is a large-scale robotic environment with various assistive robots and home appliances for independent living of the elderly and the people with disabilities. In particular, as an approach for achieving human-friendly human-robot interaction, we aim at 'simplification of task commands' by the user. In this sense, a task planning system has been proposed to generate a sequence of actions effectively for coordinating subtasks of the target subsystems from the given high-level task command. Basically, the task planning is performed under the framework of STRIPS (Stanford Research Institute Problem Solver) representation and the split planning method. In addition, we applied a state-partitioning technique to the backward split planning method to reduce computational time. By analyzing the obtained graph, the planning system decomposes an original planning problem into several independent sub-problems, and then, the planning system generates a proper sequence of actions. To show the effectiveness of the proposed system, we deal with a scenario of a planning problem in the ISH.

• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.383-392
• /
• 2023

Post-earthquake building condition assessment is crucial for subsequent rescue and remediation and can be automated by emerging computer vision and deep learning technologies. This study is based on an endeavour for the 2nd International Competition of Structural Health Monitoring (IC-SHM 2021). The task package includes five image segmentation objectives - defects (crack/spall/rebar exposure), structural component, and damage state. The structural component and damage state tasks are identified as the priority that can form actionable decisions. A multi-task Convolutional Neural Network (CNN) is proposed to conduct the two major tasks simultaneously. The rest 3 sub-tasks (spall/crack/rebar exposure) were incorporated as auxiliary tasks. By synchronously learning defect information (spall/crack/rebar exposure), the multi-task CNN model outperforms the counterpart single-task models in recognizing structural components and estimating damage states. Particularly, the pixel-level damage state estimation witnesses a mIoU (mean intersection over union) improvement from 0.5855 to 0.6374. For the defect detection tasks, rebar exposure is omitted due to the extremely biased sample distribution. The segmentations of crack and spall are automated by single-task U-Net but with extra efforts to resample the provided data. The segmentation of small objects (spall and crack) benefits from the resampling method, with a substantial IoU increment of nearly 10%.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.308-310
• /
• 2022

With the rise of the Al wave, task-oriented dialogue systems have become one of the popular research directions in academia and industry. Currently, task-oriented dialogue systems mainly adopt pipelined form, which mainly includes natural language understanding, dialogue state decision making, dialogue state tracking and natural language generation. However, pipelining is prone to error propagation, so many task-oriented dialogue systems in the market are only for single-round dialogues. Usually single- domain dialogues have relatively accurate semantic understanding, while they tend to perform poorly on multi-domain, multi-round dialogue datasets. To solve these issues, we developed a paddle-based multi-domain task-oriented Chinese dialogue system. It is based on NEZHA-base pre-training model and CrossWOZ dataset, and uses intention recognition module, dichotomous slot recognition module and NER recognition module to do DST and generate replies based on rules. Experiments show that the dialogue system not only makes good use of the context, but also effectively addresses long-term dependencies. In our approach, the DST of dialogue tracking state is improved, and our DST can identify multiple slotted key-value pairs involved in the discourse, which eliminates the need for manual tagging and thus greatly saves manpower.

• Journal of Korean Elementary Science Education
• /
• v.40 no.2
• /
• pp.175-190
• /
• 2021

The purpose of this study was to find out how interest in thermal concepts and the perceived difficulty affect the stimulation of science state curiosity. To achieve this purpose, 410 elementary school students in 5th to 6th grade were asked to measure interest in the content of the thermal concept tasks, the perceived difficulty and science state curiosity while solving the thermal concept tasks. 2 (low interest vs. high interest)×2 (easy vs. difficult) ANCOVA was conducted with the covariate of the student's level of science curiosity, which is expected to affect the stimulation of science state curiosity. As a result of the analysis, students with high interest in the contents of the task were showed high science state curiosity. Meanwhile, there was no difference in the level of science state curiosity according to the perceived difficulty. In addition, science state curiosity level of the students with low interest in the content of the task were high when they perceived the task as easy, but science state curiosity level of the students with high interest in the content of the task were high when they perceived the task as difficult. This study was meaningful in that it empirically verified that interest in the content of the tasks has an effect on the stimulation of science state curiosity, and that the effect of interest on the stimulation of science state curiosity varies according to the level of the perceived difficulty.

• Safety and Health at Work
• /
• v.10 no.3
• /
• pp.321-326
• /
• 2019

Background: Performing cognitive tasks and muscular fatigue have been shown to increase muscle activity of the lower extremity during quiet standing. A common intervention to reduce muscular fatigue is to provide a softer shoe-surface interface. However, little is known regarding how muscle activity is affected by softer shoe-surface interfaces during static standing. The purpose of this study was to assess lower extremity muscular activity during erect standing on three different standing surfaces, before and after an acute workload and during cognitive tasks. Methods: Surface electromyography was collected on ankle dorsiflexors and plantarflexors, and knee flexors and extensors of fifteen male participants. Dependent electromyography variables of mean, peak, root mean square, and cocontraction index were calculated and analyzed with a $2{\times}2{\times}3$ within-subject repeated measures analysis of variance. Results: Pre-workload muscle activity did not differ between surfaces and cognitive task conditions. However, greater muscle activity during post-workload balance assessment was found, specifically during the cognitive task. Cognitive task errors did not differ between surface and workload. Conclusions: The cognitive task after workload increased lower extremity muscular activity compared to quite standing, irrespective of the surface condition, suggesting an increased demand was placed on the postural control system as the result of both fatigue and cognitive task.

• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.335-349
• /
• 2023

Bridges constantly undergo deterioration and damage, the most common ones being concrete damage and exposed rebar. Periodic inspection of bridges to identify damages can aid in their quick remediation. Likewise, identifying components can provide context for damage assessment and help gauge a bridge's state of interaction with its surroundings. Current inspection techniques rely on manual site visits, which can be time-consuming and costly. More recently, robotic inspection assisted by autonomous data analytics based on Computer Vision (CV) and Artificial Intelligence (AI) has been viewed as a suitable alternative to manual inspection because of its efficiency and accuracy. To aid research in this avenue, this study performs a comparative assessment of different architectures, loss functions, and ensembling strategies for the autonomous segmentation of bridge components and damages. The experiments lead to several interesting discoveries. Nested Reg-UNet architecture is found to outperform five other state-of-the-art architectures in both damage and component segmentation tasks. The architecture is built by combining a Nested UNet style dense configuration with a pretrained RegNet encoder. In terms of the mean Intersection over Union (mIoU) metric, the Nested Reg-UNet architecture provides an improvement of 2.86% on the damage segmentation task and 1.66% on the component segmentation task compared to the state-of-the-art UNet architecture. Furthermore, it is demonstrated that incorporating the Lovasz-Softmax loss function to counter class imbalance can boost performance by 3.44% in the component segmentation task over the most employed alternative, weighted Cross Entropy (wCE). Finally, weighted softmax ensembling is found to be quite effective when used synchronously with the Nested Reg-UNet architecture by providing mIoU improvement of 0.74% in the component segmentation task and 1.14% in the damage segmentation task over a single-architecture baseline. Overall, the best mIoU of 92.50% for the component segmentation task and 84.19% for the damage segmentation task validate the feasibility of these techniques for autonomous bridge component and damage segmentation using RGB images.