• Title/Summary/Keyword: lab-based science learning

Search Result 62, Processing Time 0.022 seconds

Properties of Human Cognitive Learning in a Movie Scene-Dialogue Memory Game Using EEG-Based Brain Function Analysis (EEG 기반 뇌기능 분석을 이용한 영화 장면-대사 기억 게임에서의 인지 학습 특성)

  • Lee, Chung-Yeon;Kim, Eun-Sol;Lee, Sang-Woo;Ko, Bong-Kyung;Kim, Joon-Shik;Zhang, Byoung-Tak
    • Proceedings of the Korean Information Science Society Conference
    • /
    • 2011.06c
    • /
    • pp.210-213
    • /
    • 2011
  • 기억 인출 단서는 학습을 통해 장기기억 공간에 저장된 정보를 인출하는 과정에서 중요하며, 서로 다른 종류의 기억 인출 단서에 따른 기억 인출 결과 및 이에 대한 인지 학습적 특성 규명은 교육, 범죄 수사, 그리고 인간의 뇌 기능을 모방한 기계학습 연구 등에서 중요하게 다루어져야 할 문제이다. 본 논문에서는 비디오 데이터를 이용하여 학습한 내용을 인출하는 과정에서 텍스트와 이미지가 각각 인출 단서로서 기억인출 결과에 미치는 영향을 분석하고, 기억 정보 및 시각 정보 처리와 관련된 뇌 영역에서의 뇌전도 분석을 이용하여 이를 해석하였다. 실험 결과를 통해 기억 인출을 위해 이미지-텍스트를 제시할 경우 전전두엽의 기억인출 관련 부위와 시각 피질이 위치한 후두엽의 인터랙션이 높게 이루어지면서 암묵적인 시각적기억 표상의 인출이 발생하는 것을 알 수 있었다.

Deep Learning-Based Companion Animal Abnormal Behavior Detection Service Using Image and Sensor Data

  • Lee, JI-Hoon;Shin, Min-Chan;Park, Jun-Hee;Moon, Nam-Mee
    • Journal of the Korea Society of Computer and Information
    • /
    • v.27 no.10
    • /
    • pp.1-9
    • /
    • 2022
  • In this paper, we propose the Deep Learning-Based Companion Animal Abnormal Behavior Detection Service, which using video and sensor data. Due to the recent increase in households with companion animals, the pet tech industry with artificial intelligence is growing in the existing food and medical-oriented companion animal market. In this study, companion animal behavior was classified and abnormal behavior was detected based on a deep learning model using various data for health management of companion animals through artificial intelligence. Video data and sensor data of companion animals are collected using CCTV and the manufactured pet wearable device, and used as input data for the model. Image data was processed by combining the YOLO(You Only Look Once) model and DeepLabCut for extracting joint coordinates to detect companion animal objects for behavior classification. Also, in order to process sensor data, GAT(Graph Attention Network), which can identify the correlation and characteristics of each sensor, was used.

Detection of Marine Oil Spills from PlanetScope Images Using DeepLabV3+ Model (DeepLabV3+ 모델을 이용한 PlanetScope 영상의 해상 유출유 탐지)

  • Kang, Jonggu;Youn, Youjeong;Kim, Geunah;Park, Ganghyun;Choi, Soyeon;Yang, Chan-Su;Yi, Jonghyuk;Lee, Yangwon
    • Korean Journal of Remote Sensing
    • /
    • v.38 no.6_2
    • /
    • pp.1623-1631
    • /
    • 2022
  • Since oil spills can be a significant threat to the marine ecosystem, it is necessary to obtain information on the current contamination status quickly to minimize the damage. Satellite-based detection of marine oil spills has the advantage of spatiotemporal coverage because it can monitor a wide area compared to aircraft. Due to the recent development of computer vision and deep learning, marine oil spill detection can also be facilitated by deep learning. Unlike the existing studies based on Synthetic Aperture Radar (SAR) images, we conducted a deep learning modeling using PlanetScope optical satellite images. The blind test of the DeepLabV3+ model for oil spill detection showed the performance statistics with an accuracy of 0.885, a precision of 0.888, a recall of 0.886, an F1-score of 0.883, and a Mean Intersection over Union (mIOU) of 0.793.

Fine-tuning BERT Models for Keyphrase Extraction in Scientific Articles

  • Lim, Yeonsoo;Seo, Deokjin;Jung, Yuchul
    • Journal of Advanced Information Technology and Convergence
    • /
    • v.10 no.1
    • /
    • pp.45-56
    • /
    • 2020
  • Despite extensive research, performance enhancement of keyphrase (KP) extraction remains a challenging problem in modern informatics. Recently, deep learning-based supervised approaches have exhibited state-of-the-art accuracies with respect to this problem, and several of the previously proposed methods utilize Bidirectional Encoder Representations from Transformers (BERT)-based language models. However, few studies have investigated the effective application of BERT-based fine-tuning techniques to the problem of KP extraction. In this paper, we consider the aforementioned problem in the context of scientific articles by investigating the fine-tuning characteristics of two distinct BERT models - BERT (i.e., base BERT model by Google) and SciBERT (i.e., a BERT model trained on scientific text). Three different datasets (WWW, KDD, and Inspec) comprising data obtained from the computer science domain are used to compare the results obtained by fine-tuning BERT and SciBERT in terms of KP extraction.

A Comparison Analysis of Usability Evaluation for Simulation Learning based on Web 3D and Virtual Reality (웹 3D와 가상현실 시뮬레이션 학습의 사용성 평가 비교분석)

  • So, Yo-Hwan
    • The Journal of the Korea Contents Association
    • /
    • v.16 no.10
    • /
    • pp.719-729
    • /
    • 2016
  • This study is analyzed by comparing the evaluation of usability and study achievement for simulation learning based on Web 3D and VR and it is aimed to verify the characteristics of the virtual reality through a difference in studying effect between each learning method. Therefore, this study is analyzed by comparing the evaluation of usability and study achievement for the CSI Forensics Lab simulation content that has been developed in two learning methods for scientific experiments of DNA analysis with the 75 university students of Life Science as a population(Web 3D=37, VR=38). The results of the study, in usability of user task action, exploratory and navigation, Web 3D simulation learning was positive in a significant difference, but in usability of satisfaction, VR simulation learning was positive in a significant difference. In study achievement, Web 3D simulation learning was slightly higher but did not confirm the significant differences between both of learning.

Deep learning-based post-disaster building inspection with channel-wise attention and semi-supervised learning

  • Wen Tang;Tarutal Ghosh Mondal;Rih-Teng Wu;Abhishek Subedi;Mohammad R. Jahanshahi
    • Smart Structures and Systems
    • /
    • v.31 no.4
    • /
    • pp.365-381
    • /
    • 2023
  • The existing vision-based techniques for inspection and condition assessment of civil infrastructure are mostly manual and consequently time-consuming, expensive, subjective, and risky. As a viable alternative, researchers in the past resorted to deep learning-based autonomous damage detection algorithms for expedited post-disaster reconnaissance of structures. Although a number of automatic damage detection algorithms have been proposed, the scarcity of labeled training data remains a major concern. To address this issue, this study proposed a semi-supervised learning (SSL) framework based on consistency regularization and cross-supervision. Image data from post-earthquake reconnaissance, that contains cracks, spalling, and exposed rebars are used to evaluate the proposed solution. Experiments are carried out under different data partition protocols, and it is shown that the proposed SSL method can make use of unlabeled images to enhance the segmentation performance when limited amount of ground truth labels are provided. This study also proposes DeepLab-AASPP and modified versions of U-Net++ based on channel-wise attention mechanism to better segment the components and damage areas from images of reinforced concrete buildings. The channel-wise attention mechanism can effectively improve the performance of the network by dynamically scaling the feature maps so that the networks can focus on more informative feature maps in the concatenation layer. The proposed DeepLab-AASPP achieves the best performance on component segmentation and damage state segmentation tasks with mIoU scores of 0.9850 and 0.7032, respectively. For crack, spalling, and rebar segmentation tasks, modified U-Net++ obtains the best performance with Igou scores (excluding the background pixels) of 0.5449, 0.9375, and 0.5018, respectively. The proposed architectures win the second place in IC-SHM2021 competition in all five tasks of Project 2.

Development of Humanoid Robot HUMIC and Reinforcement Learning-based Robot Behavior Intelligence using Gazebo Simulator (휴머노이드 로봇 HUMIC 개발 및 Gazebo 시뮬레이터를 이용한 강화학습 기반 로봇 행동 지능 연구)

  • Kim, Young-Gi;Han, Ji-Hyeong
    • The Journal of Korea Robotics Society
    • /
    • v.16 no.3
    • /
    • pp.260-269
    • /
    • 2021
  • To verify performance or conduct experiments using actual robots, a lot of costs are needed such as robot hardware, experimental space, and time. Therefore, a simulation environment is an essential tool in robotics research. In this paper, we develop the HUMIC simulator using ROS and Gazebo. HUMIC is a humanoid robot, which is developed by HCIR Lab., for human-robot interaction and an upper body of HUMIC is similar to humans with a head, body, waist, arms, and hands. The Gazebo is an open-source three-dimensional robot simulator that provides the ability to simulate robots accurately and efficiently along with simulated indoor and outdoor environments. We develop a GUI for users to easily simulate and manipulate the HUMIC simulator. Moreover, we open the developed HUMIC simulator and GUI for other robotics researchers to use. We test the developed HUMIC simulator for object detection and reinforcement learning-based navigation tasks successfully. As a further study, we plan to develop robot behavior intelligence based on reinforcement learning algorithms using the developed simulator, and then apply it to the real robot.

Inquiry Learning in the high School Biology: Status Survey and Problem Analysis (고등학교 생물과 탐구 학습의 실태 조사와 문제점 분석)

  • Chung, Kun-Sang;Hur, Myung
    • Journal of The Korean Association For Science Education
    • /
    • v.13 no.2
    • /
    • pp.146-151
    • /
    • 1993
  • This study analyzed the problem associated with inquiry centered science education and formulated some improvement Strategies for inquiry learning in the standard Korean high school course. In order to attain the goals of questionaire survey methods were used. To examine the current status of biology education, seperate questionaires were developed through an educational research and development procedure used for tearchers and student. The questionaires were developed to ask about instruction and evaluation methods, the level of inquiry learing and abstacles to it. Here are some of our results: 1) Biology instruction and learning is more knowledge-orinted than inquiry-orinted, 2) Inquiry approach in science teaching is hard to be applied because of crowed classroom conditions. 3) The material is too broad in range and too difficult in content. There is virtually nothing that can be related to everyday life. The material focusing on inquiry activities is unsatisfactorily selected and organized. 4) Effective methods of inquiry-based instruction and evaluation are not available. 5) Biology teachers are burdened with too many class hour a week and too many varieties of additional works. 6) 91.1% of biology teachers and 90.3% of students recognize that lab and field works are needed to enhance inquiry learning. However, in reality, such inquiry activities are lacking. 7) 73.3% of schools have no lab assistants. 8) The university entrance examination is the greatest factor against inquiry learning. 9) There are very few chances of in-service education for biology teachers to learn more about biology curriculum and science education theory.

  • PDF

Deep Learning-based Vehicle Anomaly Detection using Road CCTV Data (도로 CCTV 데이터를 활용한 딥러닝 기반 차량 이상 감지)

  • Shin, Dong-Hoon;Baek, Ji-Won;Park, Roy C.;Chung, Kyungyong
    • Journal of the Korea Convergence Society
    • /
    • v.12 no.2
    • /
    • pp.1-6
    • /
    • 2021
  • In the modern society, traffic problems are occurring as vehicle ownership increases. In particular, the incidence of highway traffic accidents is low, but the fatality rate is high. Therefore, a technology for detecting an abnormality in a vehicle is being studied. Among them, there is a vehicle anomaly detection technology using deep learning. This detects vehicle abnormalities such as a stopped vehicle due to an accident or engine failure. However, if an abnormality occurs on the road, it is possible to quickly respond to the driver's location. In this study, we propose a deep learning-based vehicle anomaly detection using road CCTV data. The proposed method preprocesses the road CCTV data. The pre-processing uses the background extraction algorithm MOG2 to separate the background and the foreground. The foreground refers to a vehicle with displacement, and a vehicle with an abnormality on the road is judged as a background because there is no displacement. The image that the background is extracted detects an object using YOLOv4. It is determined that the vehicle is abnormal.

The Analysis of the Teachers' and Students' Views about the Difficulties within Teaching & Learning Activity on Geology Units in Elementary School Science (초등학교 과학과 지질 단원 교수-학습 활동에서 교사와 학생이 겪는 어려움)

  • Wee, Soo-Meen;Kwak, Jeong-Sil;Cho, Hyun-Jun;Kim, Hyeon-Jeong
    • Journal of Korean Elementary Science Education
    • /
    • v.27 no.4
    • /
    • pp.420-436
    • /
    • 2008
  • The purpose of this study was to investigate and analysis the elementary teachers' and students' views about the difficulties in teaching and learning in geology units of elementary school science. For the purpose of this study, semi-structured interviews were conducted individually with seventeen elementary teachers who have serviced more than three years, and with sixteen elementary students located in Cheongju City. The interview questions were developed through Seidman's step to acquire a reliability in the interview data with triangulation, then in-depth interview questions were modified and completed through pre-interview after constructing the trustworthiness of interviewees. In-depth interviews were performed in applying the analytic induction method and the interviews were recorded. From the interviews, we found that elementary teachers' views about the difficulties in teaching geology units; teachers' inner difficulties, the difficulty of lab activities, the problems of rock samples, the problems of curriculum in geology units, the difficulty of the geological feature, the problems of the cramming education, the lack of the opportunity for the speciality, and so on. And the students have the views about the difficulties in learning geology units; the difficulty of the unit contents understanding, the problems of learning by heart, the lack of the interest, the lack of materials, the problems of rock samples, the difficulty of the field learning, and so on. Based on the results, the study suggested that an interesting lab activities should be included in the geology units and taught in the geological field trip to help elementary school students more fully comprehend contents of the geology units.

  • PDF