WiFi (CSI and RSSI) Data of three Coarse-grained Dining Activities (filling an electric kettle with water and turning it on, stir-frying cubed potato, and taking several cans from the fridge and putting them on a cabinet) in an Authentic Kitchen

Device-free human activity recognition (HAR) methods are attracting considerable interest due to their privacy preservation and ease of use nature of them. The granularity of the activities that a device-free HAR method aims to recognize is an important characteristic of it. This study aims to investigate the effect of activity granularity on the performance of device-free HAR methods. For this purpose, first, we utilized an authentic kitchen with an ESP32 microcontroller as a WiFi transceiver and an iPhone 12 min as a WiFi receiver. Then, we asked one user to perform three coarse-grained dining activities (i.e., filling an electric kettle with water and turning it on, stir-frying cubed potatoes, and taking several cans from the fridge and putting them on a cabinet) in the kitchen and gathering the Channel State Information (CSI) and Received Signal Strength Indicator (RSSI) data.The dataset contains 31 files for different activities (filling an electric kettle with water and turning it on, stir-frying cubed potato, and taking several cans from the fridge and putting them on a cabinet)Each file contains a list of data entries.Each data entry contains the following parts:type (CSI_DATA) - role (AP)- mac (96:DC:5A:81:E5:46) - rssi (-59) - rate (11) - sig_mode (1) - mcs (4) - bandwidth (0) - smoothing (1) - not_sounding (1) - aggregation (0) - stbc (0) - fec_coding (0) - sgi (0) - noise_floor (-95) - ampdu_cnt (0) - channel (8) - secondary_channel (0) - local_timestamp (1718710) - ant (0) - sig_len (126) - rx_state (0) - real_time_set (0) - real_timestamp (2.45605) - len (256) - CSI_DATA (a list of numbers)CSI_DATA in each data entry contains 128 numbers (64 complex numbers), The middle 11th complex numbers (22 numbers) which are 0 and we called the null subcarrier. In addition, the first complex number (2 numbers) is not valid because they are "LO Leakage". So, we will have 128 – 24 = 104 numbers which are 52 complex numbers. These are our 52 subcarriers of CSI data.

无设备人类活动识别（Device-free Human Activity Recognition, HAR）方法凭借其隐私保护特性与易用性，正受到广泛关注。活动粒度是无设备HAR方法的一项重要特征。本研究旨在探究活动粒度对无设备HAR方法性能的影响。为此，我们首先选取一间真实厨房作为实验场景，以ESP32微控制器作为WiFi收发端，iPhone 12 mini作为WiFi接收端。随后，邀请一名受试者在厨房内完成三项粗粒度用餐类活动：分别为给电水壶加水并启动、翻炒切块土豆、从冰箱取出若干罐头并放置于橱柜上，同时采集信道状态信息（Channel State Information, CSI）与接收信号强度指示（Received Signal Strength Indicator, RSSI）数据。本数据集共包含31个文件，对应上述三类活动。每个文件包含若干数据条目，每条数据条目包含以下字段：类型（type）为CSI_DATA、角色（role）为AP、MAC地址（mac）为96:DC:5A:81:E5:46、接收信号强度（rssi）为-59、传输速率（rate）为11、信号模式（sig_mode）为1、调制编码方案（mcs）为4、带宽（bandwidth）为0、平滑处理（smoothing）为1、非探测帧（not_sounding）为1、聚合（aggregation）为0、空时块编码（stbc）为0、前向纠错编码（fec_coding）为0、短保护间隔（sgi）为0、噪声基底（noise_floor）为-95、A-MPDU计数（ampdu_cnt）为0、信道编号（channel）为8、辅助信道（secondary_channel）为0、本地时间戳（local_timestamp）为1718710、天线（ant）为0、信号长度（sig_len）为126、接收状态（rx_state）为0、实时设置（real_time_set）为0、真实时间戳（real_timestamp）为2.45605、数据长度（len）为256、CSI数据（CSI_DATA）。每条数据条目中的CSI_DATA包含128个数值，对应64个复数值。其中，中间的第11组复数值（共22个数值）均为0，我们将其称为空子载波；此外，首个复数值（共2个数值）因属于“本振泄露（LO Leakage）”而无效。因此，有效CSI数据的数值数量为128 – 24 = 104，对应52个复数值，即本数据集所采用的52个CSI子载波。