基于多传感器数据融合（AReM）数据集，无线电子系统的IRIS节点收集RSS数据

Data Set Information: This dataset represents a real-life benchmark in the area of Activity Recognition applications, as described in [1]. The classification tasks consist in predicting the activity performed by the user from time-series generated by a Wireless Sensor Network (WSN), according to the EvAAL competition technical annex ([Web link]). In our activity recognition system we use information coming the implicit alteration of the wireless channel due to the movements of the user. The devices measure the RSS of the beacon packets they exchange among themselves in the WSN [2]. We collect RSS data using IRIS nodes embedding a Chipcon AT86RF230 radio subsystem that implements the IEEE 802.15.4 standard and programmed with a TinyOS firmware. They are placed on the usera€?s chest and ankles. For the purpose of communications, the beacon packets are exchanged by using a simple virtual token protocol that completes its execution in a time slot of 50 milliseconds. A modified version of the Spin ([Web link]) token-passing protocol is used to schedule node transmission, in order to prevent packet collisions and maintain high data collection rate. When an anchor is transmitting, all other anchors receive the packet and perform the RSS measurements. The payload of the transmitting packet is the set of RSS values between the transmitting node and the other sensors sampled during the previous cycle. From the raw data we extract time-domain features to compress the time series and slightly remove noise and correlations. We choose an epoch time of 250 milliseconds according to the EVAAL technical annex. In such a time slot we elaborate 5 samples of RSS (sampled at 20 Hz) for each of the three couples of WSN nodes (i.e. Chest-Right Ankle, Chest-Left Ankle, Right Ankle-Left Ankle). The features include the mean value and standard deviation for each reciprocal RSS reading from worn WSN sensors. For each activity 15 temporal sequences of input RSS data are present. The dataset contains 480 sequences, for a total number of 42240 instances. We also consider two kind of bending activity, illustrated in the figure provided (bendingTupe.pdf). The positions of sensor nodes with the related identifiers are shown in figure sensorsPlacement.pdf. Attribute Information: For each sequence, data is provided in comma separated value (csv) format. - Input data: Input RSS streams are provided in files named datasetID.csv, where ID is the progressive numeric sequence ID for each repetition of the activity performed. In each file, each row corresponds to a time step measurement (in temporal order) and contains the following information: avg_rss12, var_rss12, avg_rss13, var_rss13, avg_rss23, var_rss23 where avg and var are the mean and variance values over 250 ms of data, respectively. - Target data: Target data is provided as the containing folder name. For each activity, we have the following parameters: # Frequency (Hz): 20 # Clock (millisecond): 250 # Total duration (seconds): 120 Relevant Papers: [1] F. Palumbo, C. Gallicchio, R. Pucci and A. Micheli, Human activity recognition using multisensor data fusion based on Reservoir Computing, Journal of Ambient Intelligence and Smart Environments, 2016, 8 (2), pp. 87-107. [2] F. Palumbo, P. Barsocchi, C. Gallicchio, S. Chessa and A. Micheli, Multisensor data fusion for activity recognition based on reservoir computing, in: evaluating AAL Systems Through Competitive Benchmarking, Communications in Computer and Information Science, Vol. 386, Springer, Berlin, Heidelberg, 2013, pp. 24a€“35. Citation Request: F. Palumbo, C. Gallicchio, R. Pucci and A. Micheli, Human activity recognition using multisensor data fusion based on Reservoir Computing, Journal of Ambient Intelligence and Smart Environments, 2016, 8 (2), pp. 87-107.

数据集信息：本数据集为活动识别应用领域的真实基准数据集，详情参见文献[1]。分类任务旨在根据EvAAL竞赛技术附件（[网页链接]）中给出的规则，由无线传感器网络（Wireless Sensor Network, WSN）生成的时间序列中预测用户当前执行的活动。本活动识别系统利用用户移动引发的无线信道隐性变化所携带的信息。实验设备会测量无线传感器网络中各节点间交换的信标数据包的接收信号强度（Received Signal Strength, RSS）[2]。本数据集采用搭载Chipcon AT86RF230射频子系统的IRIS节点采集RSS数据，该子系统符合IEEE 802.15.4标准，并运行TinyOS固件。这些节点被部署在用户的胸部与脚踝处。为实现通信，节点采用简单的虚拟令牌协议交换信标数据包，该协议的单次执行时隙为50毫秒。本研究对Spin协议（[网页链接]）的令牌传递机制进行改进，以此调度节点的传输行为，从而避免数据包冲突并维持较高的数据采集速率。当某锚节点进行传输时，其余所有锚节点都会接收该数据包并执行RSS测量。传输数据包的有效载荷为：传输节点与上一采样周期内其余传感器之间的RSS值集合。研究人员从原始数据中提取时域特征，以实现时间序列的压缩，并适度去除噪声与相关性。根据EvAAL竞赛技术附件的要求，我们将采样窗时长设为250毫秒。在该采样窗内，我们针对三对无线传感器网络节点（即胸部-右脚踝、胸部-左脚踝、右脚踝-左脚踝）分别采集5个RSS样本（采样频率为20 Hz）。提取的特征包括各穿戴式无线传感器节点间双向RSS读数的均值与标准差。每类活动对应15条输入RSS数据时序序列，本数据集共包含480条序列，总计42240个数据实例。本数据集还包含两类弯腰活动，相关说明见附件图bendingTupe.pdf。传感器节点的部署位置及其对应标识符详见图sensorsPlacement.pdf。
属性信息：每条序列的数据以逗号分隔值（Comma-Separated Values, CSV）格式存储。
- 输入数据：输入RSS流存储于名为datasetID.csv的文件中，其中ID为对应活动每次重复的连续数字序列编号。每个文件的每一行对应一个时间步的测量值（按时间顺序排列），包含以下字段：avg_rss12、var_rss12、avg_rss13、var_rss13、avg_rss23、var_rss23，其中avg与var分别代表250毫秒时长内数据的均值与方差。
- 目标数据：目标数据以所属文件夹的名称标识。每类活动的相关参数如下：# 采样频率（Hz）：20 # 采样窗时长（毫秒）：250 # 总时长（秒）：120
相关文献：
[1] F. Palumbo、C. Gallicchio、R. Pucci与A. Micheli，《基于储层计算的多传感器数据融合人体活动识别》，《环境智能与智能环境期刊》，2016年，第8卷第2期，第87-107页。
[2] F. Palumbo、P. Barsocchi、C. Gallicchio、S. Chessa与A. Micheli，《基于储层计算的活动识别多传感器数据融合》，收录于《通过竞争性基准测试评估AAL系统》，《计算机与信息科学通讯》，第386卷，Springer，柏林、海德堡，2013年，第24-35页。
引用要求：F. Palumbo、C. Gallicchio、R. Pucci与A. Micheli，《基于储层计算的多传感器数据融合人体活动识别》，《环境智能与智能环境期刊》，2016年，第8卷第2期，第87-107页。

搜集汇总

背景与挑战

背景概述

该数据集是一个多传感器数据融合的活动识别基准数据集，通过无线传感器网络收集RSS数据，包含480个序列和42240个实例，用于预测用户活动。数据通过IRIS节点收集，遵循IEEE 802.15.4标准，并包含RSS的平均值和方差等特征。