Privacy-preserving Occupancy Detection in Smart Buildings: Three Weeks of Data from Infrared Array Sensor

The dataset contains temperature measurements taken with an 8x8 infrared array (Panasonic Grid-EYE) over a period of three weeks during 2018 in Bucharest, Romania, in an educational facility.The experimental system, composed of a Panasonic Grid-Eye development kit and an associated Raspberry Pi wireless gateway, has been deployed for three weeks in an IT Hub where young students are taking classes of programming and robotics. We found this scenario very appealing since we have previously deployed our equipment in the university laboratory where adults are using the spaces, but this one is from another perspective since the young students have different behavior: they are faster when they enter in the room, they are walking in groups of two often, and they have a much smaller height than adults; this means a larger distance to the sensing grid places on the top of the doorcase. Data is recorded with a frequency of 1 Hertz, in frames of 64 values of temperature in degrees Celsius, correspond- ing to the 64 cells of the sensing grid. We hope the dataset is useful to researchers in building energy efficiency and user comfort in order to develop algorithms that infer and predict the occupancy levels in smart buildings for optimal HVAC control schemes.A two-stage method to first detect and subsequently predict occupancy using random forest algorithms using data is presented and can be referenced below:Grigore Stamatescu, Claudia Chitu, "Privacy-Preserving Sensing and Two-Stage Building Occupancy Prediction Using Random Forest Learning", Journal of Sensors, vol. 2021, Article ID 8000595, 12 pages, 2021. https://doi.org/10.1155/2021/8000595

本数据集收录了2018年在罗马尼亚布加勒斯特一所教育设施内，使用8x8红外阵列（松下Grid-EYE）在三周时间内所采集的温度测量数据。实验系统由松下Grid-EYE开发套件及配套的Raspberry Pi无线网关构成，该系统已在信息枢纽中部署三周，年轻学生在此处接受编程与机器人课程。鉴于我们之前已在大学实验室部署过相关设备，而成人用户在此使用空间，此场景颇具吸引力，因年轻学生的行为模式有所不同：他们进入房间更为迅速，经常以两人一组行走，且身高远低于成人；这意味着他们与门框顶部放置的传感网格之间的距离更大。数据以每秒1赫兹的频率记录，以摄氏度为单位，每帧包含64个温度值，对应传感网格的64个单元格。我们期望该数据集能为研究人员在建筑能源效率及用户舒适度方面提供助力，以开发出能够推断和预测智能建筑中占用率的算法，从而实现最优化的暖通空调控制方案。本文提出了一种两阶段方法，首先使用随机森林算法进行检测，随后进行预测，具体内容可参考以下文献：Grigore Stamatescu, Claudia Chitu, 《基于随机森林学习的隐私保护感知与两阶段建筑占用率预测》，传感器杂志，2021年第2021卷，文章编号8000595，12页，2021年。https://doi.org/10.1155/2021/8000595