Sussex-Huawei Locomotion and Transportation Dataset

This dataset is a highly versatile and precisely annotated large-scale dataset of smartphone sensor data for multimodal locomotion and transportation analytics of mobile users.The dataset comprises 7 months of measurements, collected from all sensors of 4 smartphones carried at typical body locations, including the images of a body-worn camera, while 3 participants used 8 different modes of transportation in the southeast of the United Kingdom, including in London.In total 28 context labels were annotated, including transportation mode, participant’s posture, inside/outside location, road conditions, traffic conditions, presence in tunnels, social interactions, and having meals.The total amount of collected data exceed 950 GB of sensor data, which corresponds to 2812 hours of labelled data and 17562 km of traveled distance. The potential applications arising from this dataset include:Machine-learning systems to automatically recognize modes of transportations from mobile phone dataRoad condition analysis and recognitionTraffic conditions analysis and recognition.Assessment of Google’s activity and transportation recognition API in comparison to custom algorithmsProbabilistic mobility modellingActivity recognition (e.g. automatic detection of eating and drinking)Novel localization techniques using dynamic fusion of sensorsRadio signal propagation analsisImage-based activity and transportation mode recognition The current recommended publication regarding the dataset is [1]. The current recommended publication regarding the application which was used to collect the dataset is [2].[1] H. Gjoreski, M. Ciliberto, L. Wang, F. J. Ordoñez Morales, S.Mekki, S.Valentin, D. Roggen, “The University of Sussex-Huawei Locomotion and Transportation Dataset for Multimodal Analytics with Mobile Devices”, In IEEE Access, 2018[2] M. Ciliberto, F. J. Ordoñez Morales, H. Gjoreski, D. Roggen, S.Mekki, S.Valentin. “High reliability Android application for multidevice multimodal mobile data acquisition and annotation.” In ACM Conference on Embedded Networked Sensor Systems. ACM, 2017.We recommend to refer to the dataset as follows in your publications:Use at least once the complete name: “The University of Sussex-Huawei Locomotion and Transportation Dataset” or “The Sussex-Huawei Locomotion and Transportation Dataset“. You may introduce the acronym of the dataset as well: “The University of Sussex-Huawei Locomotion and Transportation (SHL) Dataset“.Subsequently, you may refer to the dataset with its acronym: “The SHL Dataset“.

本数据集为一款通用性极强、标注精准的大规模智能手机传感器数据集，面向移动用户的多模态移动与交通分析任务。
本数据集包含7个月的采集数据，采集自4台智能手机的全传感器，设备佩戴于典型人体部位，还包含佩戴式相机采集的图像。实验共有3名参与者，在英国东南部（含伦敦地区）使用了8种不同的交通出行方式。
总计标注了28类上下文标签，涵盖交通方式、参与者姿态、室内/室外位置、道路状况、交通状况、隧道通行状态、社交互动状态以及用餐状态等。
本次采集的传感器数据总容量超过950 GB，对应2812小时的标注数据与17562公里的出行里程。
本数据集可支撑的潜在应用场景包括：
1. 基于移动设备数据自动识别交通方式的机器学习系统；
2. 道路状况分析与识别；
3. 交通状况分析与识别；
4. 谷歌（Google）活动与交通识别API与自研算法的性能对比评估；
5. 概率性移动建模；
6. 行为识别（例如自动检测用餐与饮水行为）；
7. 基于传感器动态融合的新型定位技术；
8. 无线电信号传播分析；
9. 基于图像的行为与交通方式识别。
当前推荐引用的数据集相关文献为[1]；用于采集该数据集的相关应用的推荐引用文献为[2]。
[1] H. Gjoreski、M. Ciliberto、L. Wang、F. J. Ordoñez Morales、S. Mekki、S. Valentin、D. Roggen：《面向移动设备多模态分析的萨塞克斯大学-华为移动与交通数据集》，发表于《IEEE Access》，2018年
[2] M. Ciliberto、F. J. Ordoñez Morales、H. Gjoreski、D. Roggen、S. Mekki、S. Valentin：《用于多设备多模态移动数据采集与标注的高可靠性安卓（Android）应用》，发表于ACM嵌入式网络传感器系统会议（ACM Conference on Embedded Networked Sensor Systems），ACM出版社，2017年
我们建议在学术出版物中按以下规范引用本数据集：首先需至少使用一次完整名称："The University of Sussex-Huawei Locomotion and Transportation Dataset"（萨塞克斯大学-华为移动与交通数据集）或"The Sussex-Huawei Locomotion and Transportation Dataset"（萨塞克斯-华为移动与交通数据集）；您也可先标注带缩写的完整名称："The University of Sussex-Huawei Locomotion and Transportation (SHL) Dataset"（萨塞克斯大学-华为移动与交通（SHL）数据集），后续即可直接使用缩写名称"SHL数据集"指代本数据集。

搜集汇总

背景与挑战

背景概述

Sussex-Huawei Locomotion and Transportation Dataset是一个大规模、多模态的智能手机传感器数据集，包含7个月的测量数据和28种上下文标签注释，用于移动用户的运动和交通模式分析。数据集由3名参与者使用8种不同交通方式在英国东南部收集，总数据量超过950GB，对应2812小时的标注数据和17562公里的行程。