• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.944-946
• /
• 2014

Localization of a sensor network node using machine learning has been recently studied. It is easy for Support vector machines algorithm to implement in high level language enabling parallelism. In this paper, we realized Support vector machine using python language and built a sensor network cluster with 5 Pi's. We also established a Hadoop software framework to employ MapReduce mechanism. We modified the existing Support vector machine algorithm to fit into the distributed hadoop architecture system for localization of a sensor node. In our experiment, we implemented the test sensor network with a variety of parameters and examined based on proficiency, resource evaluation, and processing time.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.70-72
• /
• 2019

최근 ICT의 발전으로 인해 웹사이트 수가 폭발적으로 증가하고 있으며 인터넷상에는 여러 가지 다양하고 방대한 데이터들이 존재한다. 이러한 데이터를 효과적으로 검색하고 이용하기 위하여 웹 검색 기능은 주요한 역할을 담당한다. 본 논문에서는 웹 데이터를 자동으로 스크랩하여 파일로 저장하는 웹 크롤러를 구현하고 처리 속도 향상을 위하여 쓰레드 기능을 추가하였다. 웹 크롤러 구현을 위한 프로그래밍 언어는 파이썬을 사용하였으며 다양한 크기의 레퍼런스 사이트의 크롤링 속도 비교는 쓰레드 수를 변경함으로 측정하여 성능향상을 확인하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.103-104
• /
• 2021

본 논문에서는 텍스트 마이닝 기반의 토픽 모델링 웹 애플리케이션 모델을 제안한다. 웹크롤링 기법을 활용하여 키워드를 입력하면 요약된 논문 정보를 파일로 저장할 수 있고 또한 키워드 빈도 분석과 토픽 모델링 등을 통해 연구 동향을 손쉽게 확인해볼 수 있는 웹 애플리케이션을 설계하고 구현하는 것을 목표로 한다. 제안 모델인 웹 애플리케이션을 통해 프로그래밍 언어와 데이터 분석 기법에 대한 지식이 부족하더라도 논문 수집과 저장, 텍스트 분석을 경험해볼 수 있다. 또한, 이러한 웹 시스템 개발은 기존의 html, css, java script와 같은 언어에 의존하지 않고 파이썬 라이브러리를 활용하였기 때문에 파이썬을 기반으로 데이터 분석과 머신러닝 교육을 수행할 경우 프로젝트 기반 수업 교육 과정으로 채택이 가능할 것으로 기대된다.

• The Journal of Korean Association of Computer Education
• /
• v.20 no.4
• /
• pp.15-25
• /
• 2017

The purpose of this study is to verify the effectiveness of the flipped class by comparing Python programming classes divided into flipped class and general class. The participants who participated in each class had 36 students, so that they could participate in the class without knowing the difference of the class method. The students's academic achievement was applied the two groups with similar test items, and then the overall achievement were compared. The analysis showed that the achievements in flipped class in the basic grammar and intermediate grammar were higher than those in the general class. As a result of gender achievement analysis, there was no effect on the type of instruction. However, male student were generally higher in academic achievement. In conclusion, flipped class in the programming is a good way to improve students' understanding.

• Journal of The Korean Association of Information Education
• /
• v.25 no.6
• /
• pp.1015-1024
• /
• 2021

There are various educational programming environments in which students can train artificial intelligence (AI) using block-based programming languages, such as Entry, Machine Learning for Kids, and Teachable Machine. However, these programming environments are designed so that students can train AI through a separate menu, and then use the trained model in the code editor. These approaches have the advantage that students can check the training process more intuitively, but there is also the disadvantage that both the training menu and the code editor must be used. In this paper, we present a novel artificial intelligence block that can perform both AI training and programming in the code editor. While this AI block is presented as a Scratch block, the training process is performed through a Python server. We describe the blocks in detail through the process of training a model to classify a blue pen and a red pen, and a model to classify a dental mask and a KF94 mask. Also, we experimentally show that our approach is not significantly different from Teachable Machine in terms of performance.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.12
• /
• pp.2885-2890
• /
• 2014

Localization of a sensor network node using machine learning has been recently studied. It is easy for Support vector machines algorithm to implement in high level language enabling parallelism. Raspberrypi is a linux system which can be used as a sensor node. Pi can be used to construct IP based Hadoop clusters. In this paper, we realized Support vector machine using python language and built a sensor network cluster with 5 Pi's. We also established a Hadoop software framework to employ MapReduce mechanism. In our experiment, we implemented the test sensor network with a variety of parameters and examined based on proficiency, resource evaluation, and processing time. The experimentation showed that with more execution power and memory volume, Pi could be appropriate for a member node of the cluster, accomplishing precise classification for sensor localization using machine learning.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.10
• /
• pp.291-298
• /
• 2023

In this paper, we study whether the programming questions of the Informatics·Computer recruitment tests were suitable for selecting teachers with required programming skills. The average points of the programming questions constituted 38%(20.8 points) of the total scores for the entire curriculum based on the results from analyzing the previous questions in the past 5 years. Moreover, the distribution of points for each evaluation criteria within programming and data structure, two exam subjects which have a high proportion of programming questions, demonstrated a large deviation ranging from 0% to 47% and 0% to 53% respectively. In this study, a questionnaire survey was conducted on 31 teachers to examine if the previous programming questions were suitable for measuring teachers' competency in programming abilities required in the actual teaching experience. Computational thinking ability was ranked the highest at 58% in response to the area that needs to be evaluated in the recruitment test. In response to the relevance of previous questions, problem solving ability was ranked the highest at 2.84 on a 5-point scale, but the overall appropriateness was deemed low. C language and Python were regarded as the computer languages suitable to be tested for programming questions with each ranked 55% and 45%. The finding confirms that teachers preferred Python and the incumbent C language to others. Based on the results of the questionnaire, we recommend changes in the programming questions to improve the selection criteria.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.537-538
• /
• 2021

코딩 교육에 대한 중요성이 높아짐에 따라 국가 주도적 교육이 강화되고 있다. 컴퓨터 프로그래밍이 낯선 교육생을 위해 교육 커리큘럼에 블록 코딩을 도입하고 있으나 낮은 흥미도로 인해 여전히 교육 성취도가 낮게 나타난다. 본 논문에서는 컴퓨터 프로그래밍에 대한 관심을 유발하고 학습을 보조하는 드론 기반의 체감형 교육 프로그램모델을 제시한다. 제시하는 교육 모델은 사용자가 코딩한 블록 코드를 파이썬 코드로 변환하여 보여주고, 블록 코드로 첨부된 드론의 동작을 제어하도록 코딩할 수 있다. 사용자의 심화학습을 위해 추가적으로 제공하는 웨어러블 장갑 컨트롤러를 통해 드론과 연관하여 동작 제어가 가능하게 하여 흥미 유발과 더불어 학습 효과 향상을 기대할 수 있다.

• Journal of Practical Engineering Education
• /
• v.16 no.2
• /
• pp.151-157
• /
• 2024

Most of the existing game-based education programmes for lower grades are simple block-coding studies, and there is a lack of examples of programming-intensive classes. In this study, we implemented a Minecraft-based Python coding fundamentals class for 3 classes at a local elementary school during a 2-week school holiday. The learning programme was reorganised from the standard learning programme on the official website, such as building quests through LAN-PARTY and self-scripting in-game, to improve class interest and motivation. In addition, we analysed the satisfaction and preferences of the class topics through a survey, and obtained meaningful results for future educational program development. This study is significant as a basic research for the design and development of game-based educational programmes for all age groups.

• Annual Conference on Human and Language Technology
• /
• 2015.10a
• /
• pp.163-164
• /
• 2015

본 연구는 특수목적영어분인 해사영어코퍼스의 구축을 목적으로 한다. 구축과정에서 코퍼스 구축에 필요한 대표성과 균형성을 고려하여 네 가지 장르인 학술, 뉴스, 법, 책으로 나누고 각 하위코퍼스를 백만 단어씩 구축하였다. 코퍼스 구축과정에서 웹사이트와 PDF형태의 자료에서 텍스트만을 수집하고 정제하기 위하여 파이썬(Python) 프로그래밍 코딩을 하였고 무료 공개 프로그램도 병행하였다. 앞으로 해사영어코퍼스는 해사영어어휘교육에 필요한 단어목록제공이나 예문 검색 등을 통한 자료중심학습법에 활용될 수 있을 것이다. 또한 본 연구의 코퍼스구축 과정은 다른 분야의 ESP코퍼스 구축에도 응용 될 수 있을 것이다.