如[1]所述，该数据集代表了环境辅助生活应用领域的现实基准。

二元分类任务包括根据无线传感器网络（WSN）生成的时间序列预测现实办公环境中的用户移动模式。

输入数据包含无线传感器网络节点之间测量的无线电信号强度（RSS）的时间流，包括5个传感器：部署在环境中的4个锚和用户佩戴的1个遥控器。在用户移动期间以8 Hz的频率（每秒8个样本）收集数据。在提供的数据集中，RSS信号已被重新缩放到间隔[-1,1]，仅在从每个锚点收集的一组记录道上（如[1]）。

目标数据包含在一个类标签中，该类标签指示用户的轨迹是否会导致空间上下文的变化（即房间变化）。特别地，目标类+1与位置改变运动相关联，而目标类-1与位置保持运动相关联。

测量活动涉及3个不同的环境设置，每个环境设置包括两个房间（包含典型的办公家具），由走廊分隔。附图中提供了所考虑的常见设置的草图。在每个环境设置中，锚部署在靠近房间角落的固定位置（离地面1.5 m的高度），而移动设备则佩戴在用户的胸前。该图还显示了所考虑的用户轨迹类型的简化说明，直线路径导致空间上下文变化，曲线路径导致空间上下文保留。每条路径产生一条从轨迹开始到标记点（图中表示为M）的RSS测量轨迹。标记M对于所有运动都是相同的，因此不能仅根据在M处收集的RSS值来区分不同的路径。

提供的数据集中的每个输入文件都包含与输入RSS数据的一个时间序列有关的数据（每个文件1个用户轨迹）。数据集包含314个序列，总共13197个步骤。

Further information can be found at the webpage: [Web link].
该数据集的完整描述见[1]，其中还提供了回声状态网络在相应分类任务中实现的性能的详细信息。

Attribute Information:

Data is provided in comma separated value (csv) format.

- Input data
Input RSS streams are provided in files named MovementAAL_RSS_SEQID.csv, where IDSEQ is the progressive numeric sequence ID.
In each file, each row corresponds to a time step measurement (in temporal order) and contains the following information:
RSS_anchor1, RSS_anchor2, RSS_anchor3, RSS_anchor4

- Target data
Target data is provided in the file MovementAAL_target.csv
Each row in this file contains:
sequence_ID, class_label


- Dataset grouping
Data is grouped in 3 sets, as described in [1].
File MovementAAL_DatasetGroup.csv, provides information about such data grouping.
Each row in this file contains:
sequence_ID, dataset_ID

- Path grouping
Users' movements are divided in 6 prototypical paths, as described in [1].
File MovementAAL_Paths.csv provides information about data grouping based on path type.
Each row in this file contains:
sequence_ID, path_ID

Relevant Papers:

[1] D. Bacciu, P. Barsocchi, S. Chessa, C. Gallicchio, and A. Micheli, 'An experimental characterization of reservoir computing in ambient assisted living applications', Neural Computing and Applications, Springer-Verlag, vol. 24 (6), pp. 1451-1464, [Web link], ISSN 0941-0643, 2014.

[2] D. Bacciu, S. Chessa, C. Gallicchio, A. Micheli, P. Barsocchi, 'An Experimental evaluation of Reservoir Computation for Ambient Assisted Living', 22nd Italian Workshop on Neural Networks, Vietri sul Mare, Salerno, Italy, 17-19 May 2012, Neural Networks and Surroundings, Springer Smart Innovation, Systems and Technologies series, Volume 19, pag. 41-50, ISBN: 978-3-642-35466-3, 2013.

[3] C. Gallicchio, A. Micheli, P. Barsocchi, S. Chessa, 'User Movements Forecasting by Reservoir Computing Using Signal Streams Produced by Mote-Class Sensors', Mobile Lightweight Wireless Systems (MOBILIGHT), Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, Volume 81, Part 3, pag. 151-168, ISBN 978-3-642-29478-5, 2012.

[4] D. Bacciu, C. Gallicchio, A. Micheli, S. Chessa, P. Barsocchi, 'Predicting user movements in heterogeneous indoor environments by reservoir computing', M. Bhatt, H. W. Guesgen, and J. C. Augusto, editors, Proceedings of the IJCAI Workshop on Space, Time and Ambient Intelligence (STAMI), pag. 1-6, 2011.

Citation Request:

D. Bacciu, P. Barsocchi, S. Chessa, C. Gallicchio, and A. Micheli, 'An experimental characterization of reservoir computing in ambient assisted living applications', Neural Computing and Applications, Springer-Verlag, vol. 24 (6), pp. 1451-1464, [Web link], ISSN 0941-0643, 2014.

Davide Bacciu (a), Paolo Barsocchi (b), Stefano Chessa (a), Claudio Gallicchio (a), Alessio Micheli (a)

(a) Department of Computer Science, University of Pisa.
Largo Bruno Pontecorvo 3, 56127 Pisa, Italy
(b) Institute of Information Science and Technologies,  Italian National Research Council.
Via G. Moruzzi 1, 56124 Pisa, Italy

For info about this dataset contact
Paolo Barsocchi: paolo.barsocchi '@' isti.cnr.it
Claudio Gallicchio: gallicch '@' di.unipi.it