도움말
Institutional Access | Log in | Register | Customer Center | Error Report | Korean

Go to DBpia main page

  • search
  • Advanced Search
    Global IME
지식공유캠페인
Home > KOREA INFORMATION SCIENCE SOCIETY > Journal of KIISE > Vol.45 No.6
알림서비스 통합 신청 Storage facebook share twitter share E-mail share

Activity Prediction from Sensor Data using Convolutional Neural Networks and an Efficient Compression Method

Woojeong JinIdentified author, Dongjin ChoiIdentified author, Youngjin KimIdentified author, U KangIdentified author
Vol.45 No.6, 2018.6, 564-571 (8 pages)
DOI :10.5626/JOK.2018.45.6.564
Copy
Quick View Quick View
Purchase $5.29
Export
Usage : 46
Citations : 0
분야내 활용도 : 6%
More detail >

· Usage : Full-text article downdloads count since 2010.

· Citations : Cited in the DBpia's articles

· Impact Score : Calculates the article impact score on a basis of the usage in the last 24 months.

Abstract
건물 내 IoT 시스템을 이용한 재실자의 수 및 행동 유형 파악은 스마트 냉/난방 시스템 등에 사용되어 전력 효율을 개선시키고 비용 절감에 도움되는 중요한 문제이다. 실제 건물 관리 시스템에서는 카메라 등의 장비를 이용하여 방 안의 현황을 파악하고 재실자의 수와 행동 유형을 직접 파악하는 방법 등이 사용되고 있다. 이 방법으로 사람 수와 행동 유형을 파악하는 것은 비효율적일뿐만 아니라 데이터를 위한 방대한 저장 공간이 필요하다. 본 연구에서는 적외선 그리드 아이 센서와 소음 센서를 이용하여 실내 센서 데이터를 수집하였다. 또한 이 데이터를 토대로 재실자 수와 행동 유형을 파악하는 딥러닝 모델과 데이터의 시간적 특성을 고려하는 딥러닝 모델을 제안한다. 제안하는 모델은 약 95.3%의 정확도로 사람 수를 파악하고 90.9%의 정확도로 사람 행동 유형을 파악한다. 또한 Truncated SVD를 이용하여 정확도의 손실을 최소화하면서 저장 공간을 줄이는 방법을 제안한다.

The identification of the number of occupants and their activities using the IoT system in a building is an important task to improve the power efficiency and reduce the cost of using smart cooling/heating systems. In the actual building management system, it is possible to use equipment such as a camera to understand the current situation in the room, and to directly determine the number of occupants and their types of behavior. However, identifying the number of people and behavior types in this way is inefficient and requires a large amount of storage space for data. In this study, indoor sensor data were collected using an infrared Grid-Eye sensor and noise sensor. Based on this data, we also propose a deep learning model that captures the number of participants and behavior patterns and a deep learning model that considers the temporal characteristics of data. The proposed model identifies the number of people with an accuracy of about 95.3% and human activities with an accuracy of 90.9%. We also propose a method to reduce the storage space while minimizing the loss of accuracy using truncated SVD.

TOC
요약
Abstract
1. 서론
2. 관련연구
3. 제안된 방법
4. 실험
5. 결론
References
Keyword

The Keywords of the article are provided. Click the keyword and check a related articles!

References (34)

Please found references of this article.

  1. K. He, X. Zhang, S. Ren, and J. Sun, Deep Residual Learning for Image Recognition, Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770-778, 2016.
  2. K. He, X. Zhang, S. Ren, and J. Sun, Deep Residual Learning for Image Recognition, Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770-778, 2016.
  3. M. C. Mozer, The neural network house: An environment that adapts to its inhabitants, Proc. of AAAI Spring Symp. Intelligent Environments, Vol. 58, 1998.
  4. M. C. Mozer, The neural network house: An environment that adapts to its inhabitants, Proc. of AAAI Spring Symp. Intelligent Environments, Vol. 58, 1998.
  5. H.-W. Gellersen, A. Schmidt, and M. Beigl, Multi- Sensor Context-Awareness in Mobile Devices and Smart Artefacts, Journal of Mobile Networks and Applications, Vol. 7, No. 5, pp. 341-351, 2001.
  6. H.-W. Gellersen, A. Schmidt, and M. Beigl, Multi- Sensor Context-Awareness in Mobile Devices and Smart Artefacts, Journal of Mobile Networks and Applications, Vol. 7, No. 5, pp. 341-351, 2001.
  7. A. Schmidt and K. Van Laerhoven, How to build smart appliances?, Journal of IEEE Personal Communications, Vol. 8, No. 4, pp. 66-71, 2001.
  8. A. Schmidt and K. Van Laerhoven, How to build smart appliances?, Journal of IEEE Personal Communications, Vol. 8, No. 4, pp. 66-71, 2001.
  9. F. Foerster and J. Fahrenberg, Motion pattern and posture: correctly assessed by calibrated accelerometers, Journal of Behavior research methods, instruments, & computers, Vol. 32, No. 3, pp. 450- 457, 2000.
  10. F. Foerster and J. Fahrenberg, Motion pattern and posture: correctly assessed by calibrated accelerometers, Journal of Behavior research methods, instruments, & computers, Vol. 32, No. 3, pp. 450- 457, 2000.
  • 처음
    •  
  • 이전
    •  
  • 1
    •  
  • 2
    •  
  • 3
    •  
  • 4
    •  
  • 다음
    •  
  • 마지막
Cited articles (0)

Please apply for Alerts and check the information by e-mail!

Cited articles not found.

Other articles of first author (1)

Please check the detailed of Woojeong Jin Identified author!

  1. Recommender system based on graph ranking using random walk

    진우정, 정진홍, 강유, 한국정보과학회, 정보과학회지 34(6), 2016, 30-35

Within this Journal (13)

Please check the detailed of Vol.45 No.6!

  1. 정보과학회논문지 제45권 제6호 목차

    편집부, Journal of KIISE, 45(6), 2018, 618-619

  2. Boosting the Forwarding Performance of Virtual Switches through Kernel-level Memory Optimization

    Heungsik Choi, Kyoungwoon Lee, Chuck Yoo, Journal of KIISE, 45(6), 2018, 511-515

  3. Streaming Compression Scheme for Reducing Network Resource Usage in Hadoop System

    Seung Joon Noh, Young Ik Eom, Journal of KIISE, 45(6), 2018, 516-521

  4. A Simplified Test Maturity Model (sTMM) for Small and Midsize Test Organization

    Bo Kyung Park, Woo Sung Jang, Ki Du Kim, R. Young Chul Kim, Journal of KIISE, 45(6), 2018, 522-532

  5. A Recognition of Violence Using Mobile Sensor Fusion in Intelligent Video Surveillance Systems

    HyunIn Cha, KwangHo Song, Yoo-Sung Kim, Journal of KIISE, 45(6), 2018, 533-544

  6. Quality Estimation of English-Korean Machine Translation using Neural Network based Predictor-Estimator Model

    Hyun Kim, Jaehun Shin, Wonkee Lee, Seungwoo Cho, Jong-Hyeok Lee, Journal of KIISE, 45(6), 2018, 545-553

  7. An Automatic Segmentation Algorithm for Colonic Glandular Lesions

    Migyung Cho, Hyekyung Lee, Hwan Gue Cho, Journal of KIISE, 45(6), 2018, 554-563

  8. Activity Prediction from Sensor Data using Convolutional Neural Networks and an Efficient Compression Method

    Woojeong Jin, Dongjin Choi, Youngjin Kim, U Kang, Journal of KIISE, 45(6), 2018, 564-571

  9. Regularizing Korean Conversational Model by Applying Denoising Mechanism

    Tae-Hyeong Kim, Yunseok Noh, Seong-Bae Park, Se-Yeong Park, Journal of KIISE, 45(6), 2018, 572-581

  10. A Splitting Technique of Hardware Transactional Memory in Multicore In-Memory Databases

    Munhwan Kang, Hyeongjin Kim, Hyeonkuk Ma, Jaewoo Chang, Journal of KIISE, 45(6), 2018, 582-588

  • 처음
    •  
  • 이전
    •  
  • 1
    •  
  • 2
    •  
  • 다음
    •  
  • 마지막
Recommended Articles (10)

We provide services, 'DBpia Recommended Articles' and 'Customers who used this article also used', that used text mining, usage and citations data.

DBpia Recommended Articles

More recommended articles!

  1. Cluster Feature Selection using Entropy Weighting and SVD

    Young Seok Lee, Soowon Lee, KOREA INFORMATION SCIENCE SOCIETY, Journal of KISS : Software and Applications 29(3·4), 2002, 248-257

  2. SVD를 이용한 과도기 형태 신호의 파라미터 추정 ( Parameter Estimation of Transient Data Using SVD )

    최규성, 김영수, Korea Institute Of Communication Sciences, Proceedings of Symposium of the Korean Institute of communications and Information Sciences 16(1), 1997, 820-824

  3. SVD-Based Digital Image Forensics for Detecting Tampering

    Geun-Sil Song, Mi-Ae Kim, Won-Hyung Lee, The Institute of Electronics and Information Engineers, 대한전자공학회 학술대회 , 2006, 683-684

  4. Implementation of the Maximum Likelihood Method with SVD Filter

    Kwan-Sik Wie, The Korean Society for Aeronautical & Space Sciences, Journal of the Korean Society for Aeronautical & Space Sciences 23(2), 1995, 89-95

  5. Foundation-Applied Skin Color Prediction Via SVD-Based Neural Network

    Kazuyuki Kobayashi, Kajiro Watanabe, Naruhito Toyoda, Hironobu Yoshikawa, Institute of Control, Robotics and Systems, 제어로봇시스템학회 국제학술대회 논문집 , 2006, 5470-5473

Customers who used this article also used

  1. The performance of Data Fitting Algorithm based-on Non-uniform Linear Sensor Array

    Xueyang Zhang, Lee Joon Ho, Korea Institute Of Communication Sciences, Proceedings of Symposium of the Korean Institute of communications and Information Sciences , 2018, 1246-1247

  2. Compressed Sensing Based Low Power Data Transmission Systems in Mobile Sensor Networks

    Jiyeon Hong, Jungmin Kwon, Minhae Kwon, Hyunggon Park, Korea Institute Of Communication Sciences, The Journal of Korean Institute of Communications and Information Sciences 41(11), 2016, 1589-1597

  3. Leveling routing algorithm Base in Zigbee Develop for Road Valancing

    Hyeon Su Han, Giyenko Andrey, Young Im Cho, Korean Institute of Intelligent Systems, 한국지능시스템학회 학술발표 논문집 26(1), 2016, 169-170

  4. Optimal Data Compression Algorithm Selection for Efficient Data Store and Transfer

    Young-Hye Min, Jai-Hoon Kim, KOREA INFORMATION SCIENCE SOCIETY, Journal of KIISE : Computer Systems and Theory 38(2), 2011, 107-115

  5. Analysis of Data Transmission Rate and Power Consumption in Zigbee Based Electrocardiography

    Nam-Jin Kim, Joo-Hyun Hong, Tae-Soo Lee, The Korea Contents Society, JOURNAL OF THE KOREA CONTENTS ASSOCIATION 6(12), 2006, 96-104

Metrics

Usage Status

· Usage

0 46

· Top 3 institutions list on usage

More detail >
No Top institutions Usage
1 충남대학교 5
2 울산대학교 5
3 한국교원대학교 3

Impact Score

· Impact Score

6% 32%

· The article impact score on the subject

More detail >

: %

2016-09
2016-10
2016-11
2016-12
0
20
40
60
80
100
  • 0%
  • 20%
  • 40%
  • 60%
  • 80%
  • 100%

Citations

0
Search Results

Click here to see the search results!

Detailed Info
Copyright Policy

The copyright of all work are belongs to the original author. The contents of each work shall not be responsible or guarantee. Crawl the metadata of articles do not allowed without agreement.

top

go to Nurimeda Site

About Nurimedia About DBpia Terms Of Use Privacy Policy Business Contacts About Author Membership Q&A SiteMap

NuriMedia Co. Ltd CEO: Choi, Soon Il  Business Registration Number: 816-81-00840 

TEL: +82 2 707 0496  FAX: +82 2 717 4305  E-mail: dbpia@nurimedia.co.kr

(07281) 63, Seonyu-ro, Yeongdeungpo-gu, Seoul, Korea

Copyright(C)1997-2019 NURIMEDIA. ALL RIGHTS RESERVED.

Good Content Service Logo Copyright OK Logo
DBpia logo KRpia logo

Get personalized recommendations,
customized citation styles&filename settings,
and latest articles alerts, all at your fingertips.

Register | Forgot username/password | Institutional Access

's affiliation with was certified.

For the next 90 days, will be able to access all the articles subscribed by anywhere, just by logging into DBpia.

After 90 days, please login again while you have institutional access.

Don't show this today Close

Access

Close

에서 현재 구독하지 않은 자료로, 미리보기(QuckView)를 이용하실 수 있습니다.

소속기관에서 이 논문이 수록된 간행물을 구독하길 희망하시면 ‘자료 구독 신청’을 해주세요.

자료구독신청

논문을 구매하시면 지금 바로 이용하실 수 있습니다.

Purchase

Access

Close

DBpia와 구독계약을 맺은 대학교 또는 기관의 구성원이라면, 계약된 범위 내 논문을 무료로 이용하실 수 있습니다. 소속기관명을 입력하시고, 이용 권한을 확인해 보세요.

Search

* 소속기관명을 입력하시면 이용권한을 확인하실 수 있습니다.

논문을 직접 구매하시면 지금 바로 이용하실 수 있습니다. 논문을 구매하시겠습니까?

Purchase

Access

Close

에서 현재 구독하지 않은 자료로, 미리보기(QuckView)를 이용하실 수 있습니다.

도서관의 '원문복사 서비스'를 이용하시면, 도서관을 통해 원문을 이용하실 수 있습니다.

원문복사신청

논문을 구매하시면 지금 바로 이용하실 수 있습니다.

Purchase

Access

Close

에서 현재 구독하지 않은 자료로, 미리보기(QuckView)를 이용하실 수 있습니다.

논문을 구매하시면 지금 바로 이용하실 수 있습니다.

Purchase

DBpia

팝업 닫기
  • Start
  • Select author name
  • Select article
  • Request

Checking

You have requested to for the following authors

Author Institute Research field Date range Articles Citations
Please wait..
취소 시작하기
  • Start
  • Select author name
  • Select article
  • Request

Select the preferred profile name

Please select the preferred name for your unique author profile.

이전 다음
  • Start
  • Select author name
  • Select article
  • Request

: Select authored articles

Please uncheck the documents not authored by this author.

  • 서울시 조선족 밀집지 간 특성 분석과 정책적 함의

    이석준, 김경민, 서울연구원, 서울도시연구 15(4), 2014, 1-16

이전 다음
  • Start
  • Select author name
  • Select article
  • Request

Fill in contact details and submit

If you want to be modified the authors information such as a research field, article list, please put the request as specific as possible after entering the requesters name and e-mail.

Modification Request
Name*
E-mail*
Comment
이전 요청하기