生理数据给机器学习带来了许多挑战,包括处理大量数据、序列数据、传感器融合问题,以及包含噪声、隐藏变量和受环境显著影响的丰富领域。
Physiological data offers many challenges to the machine learning community including dealing with large amounts of data, sequential data, issues of sensor fusion, and a rich domain complete with noise, hidden variables, and significant effects of context.
- 每一列对应哪些传感器?Which sensors correspond to each column?
特征1:年龄
characteristic1 age
特征2:用右手或左手的习惯
characteristic2 handedness
传感器1:gsr_low_average
sensor1 gsr_low_average
传感器2:heat_flux_high_average
sensor2 heat_flux_high_average
传感器3:near_body_temp_average
sensor3 near_body_temp_average
传感器4:计步器
sensor4 pedometer
传感器5:skin_temp_average
sensor5 skin_temp_average
传感器6:纵向加速度计SAD
sensor6 longitudinal_accelerometer_SAD
传感器7:纵向加速度计平均值
sensor7 longitudinal_accelerometer_average
传感器8:横向加速度计SAD
sensor8 transverse_accelerometer_SAD
传感器9:横向加速度计平均值
sensor9 transverse_accelerometer_average
- 每个注解背后的活动是什么?What are the activities behind each annotation?
比赛的注解如下:
The annotations for the contest were:
5102 = sleep
3104 = watching TV
项目思路:
*行为分类;根据传感器测量数据对人进行分类。
- behavior classification; to classify the person based on the sensor measurements.
更多精彩文章请关注微信号: