基于被动红外传感器的室内人行为机器学习模型
CSTR:
作者:
作者单位:

同济大学 机械与能源工程学院,上海 201804

作者简介:

周 翔(1980—),男,教授,博士生导师,工学博士,主要研究方向为人行为与建筑节能等。 E-mail: zhouxiang@tongji.edu.cn

通讯作者:

张静思(1990—),女,博士后,工学博士,主要研究方向为人行为与建筑节能等。 E-mail: zhang_js@tongji.edu.cn

中图分类号:

TU1;TN215

基金项目:

“十三五”国家重点研发计划(2017YFC0702200);国家自然科学基金(51778439)


Machine Learning Model of Indoor Occupant Behavior Based on Passive Infrared Sensor
Author:
Affiliation:

School of Mechanical Engineering , Tongji University,Shanghai 201804,China

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [16]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    室内人行为的准确识别,包括人员位置和活动类型的判定,是智能家居领域中各类电器设备实现多场景控制模式的重要输入参数。采用被动红外(PIR)传感器阵列监测人行为,分析人员不同位置及不同强度动作的数据特征。基于机器学习算法建立室内人员位置及动作识别模型,并对比不同累加时长和机器学习算法的模型预测准确度。最终以PIR传感器当前1 min的计数累加值(分钟计数值)及其前30 min计数累加值作为模型输入,选取随机森林算法构建了位置及动作识别模型。该模型在训练数据集十折交叉验证下准确率为99.9%,对新测试数据集的预测准确率为88.3%,能够识别实际人员的活动位置和动作强弱,具有一定的有效性和通用性。

    Abstract:

    Accurate recognition of indoor occupant behavior, including the recognition of position and activity type, is an important input for multi-scene control mode of various electrical equipment at intelligent homes. In the study described in this paper, the passive infrared (PIR) sensor array is used to monitor indoor occupant behavior. After analyzing the data characteristics of different positions and different activity intensities, based on the machine learning algorithm, the indoor occupant position and activity recognition model is established and the recognition accuracy of different cumulative time and machine learning algorithms are compared. The cumulative count value of this minute and of the previous 30 minutes of the PIR sensors are selected as the model input and the random forest algorithm is used to construct the final position and activity recognition model. The accuracy of the model is 99.9% under the 10-fold cross-validation of the training data set, while 88.3% under the new test data set, which shows that the position and activity recognition model has a certain validity and generality.

    参考文献
    [1] 彭洪明. 智能家居的体系结构及关键技术研究[D]. 北京:北京交通大学,2012.
    [2] BAHADORI S, CESTA A , IOCCHI L , et al. Towards ambient intelligence for the domestic care of the elderly[C]// Ambient Intelligence. New York: Springer, 2005:15-38.
    [3] 石高涛,王伯远,吴斌.基于WiFi与移动智能终端的室内定位方法综述[J].计算机工程,2015,41(9):39. DOI: 10.3969/j.issn.1000-3428.2015.09.007.
    [4] 胡秋扬. 可穿戴式个人室内位置和行为监测系统[D].杭州:浙江大学,2015.
    [5] 莫文.心理学实验中的各种效应及解决办法[J].实验科学与技术,2008,6(6):118. DOI: 10.3969/j.issn.1672-4550.2008.06.042.
    [6] 凡祖兵. 大型办公建筑房间日用能模式挖掘与用能评价方法研究[D].广州:华南理工大学,2018.
    [7] 董吉虹, 白明, 郎培,等. 热释电红外报警器的设计[J]. 天津理工大学学报, 2007,23(5):74. DOI: 10.3969/j.issn.1673-095X.2007.05.021.
    [8] BAI Y W, KU Y T. Automatic room light intensity detection and control using a microprocessor and light sensors[J]. IEEE Transactions on Consumer Electronics, 2008, 54(3): 1173. DOI: 10.1109/TCE.2008.4637603.
    [9] AI-NAIMI I, WONG C B, MOORE P, et al. Advanced approach for indoor identification and tracking using smart floor and pyroelectric infrared sensors[C]// International Conference on Information and Communication Systems. New York: IEEE, 2014:1-6. DOI: 10.1109/IACS.2014.6841966.
    [10] 杨丹, 徐彬. 基于人行为地图的室内PIR定位方法[J]. 东北大学学报(自然科学版), 2018, 39(6):776. DOI:10.12068/j.issn. 1005-3026.2018.06.004.
    [11] 陈龙. 基于无线热释电红外传感器人体目标识别的研究[D]. 武汉:武汉理工大学, 2013.
    [12] 万柏坤, 冯莉, 明东,等. 基于热释电红外信息的人体运动特征提取与识别[J]. 纳米技术与精密工程, 2012,10(3):249. DOI: 10.13494/j.npe.2012.044.
    [13] YANG Bo, LI Xiaoshan, LUO Jing. A novel multi-human location method for distributed binary pyroelectric infrared sensor tracking system: region partition using PNN and bearing-crossing location[J]. Infrared Physics and Technology, 2015,68:35. DOI: 10.1016/j.infrared.2014.10.006.
    [14] KIM H H, HA K N, LEE S, et al. Resident location-recognition algorithm using a bayesian classifier in the PIR sensor-based indoor location-aware system[J]. IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews), 2009, 39(2):240. DOI: 10.1109/TSMCC.2008.2008099.
    [15] 秦锋, 杨波, 程泽凯. 分类器性能评价标准研究[J]. 计算机技术与发展, 2006,16(10):91. DOI: 10.3969/j.issn.1673-629X.2006.10.029.
    [16] 周超,方秀琴,吴小君,等.基于三种机器学习算法的山洪灾害风险评价[J].地球信息科学学报,2019,21(11):1679. DOI:10.12082/dqxxkx.2019.190185.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

周翔,赵婷,张静思,王纪隆,张心悦.基于被动红外传感器的室内人行为机器学习模型[J].同济大学学报(自然科学版),2022,50(3):446~454

复制
分享
文章指标
  • 点击次数:271
  • 下载次数: 652
  • HTML阅读次数: 75
  • 引用次数: 0
历史
  • 收稿日期:2021-05-17
  • 在线发布日期: 2022-04-11
文章二维码