How can you get the training data？

yscacaca / DeepSense

Deepsense: a unified deep learning framework for time-series mobile sensing data processing.

196 stars 71 forks source link

Closed oiwio closed 7 years ago

oiwio commented 7 years ago

I noticed that the data you shared is different from the original data, can you share your code that for data processing? Thanks for your sharing!!!

yscacaca commented 7 years ago

Hi,

I've opened a new repository for the data-processing code https://github.com/yscacaca/HHAR-Data-Process

oiwio commented 7 years ago

您的代码里实践的是HHAR的例子，想请教下，如果是做UserID的问题，确定当前手机用户是不是本人，作为一个二分类问题，如何找到足够多的“不是本人”数据来确保模型的准确度呢？

yscacaca commented 7 years ago

如果没有privacy issue的话，可以用别人手机的数据作为negative samples。

oiwio commented 7 years ago

这儿的mataDict是作为什么用的呢？下面的TRAIN_SIZE并没有用到，但是EVAL_ITER_NUM用到了，这儿'a':[119080, 1193]是哪儿来的呢？

yscacaca commented 7 years ago

mataDict 包含的是training和testing data的数量

FelixHuiweiLin commented 5 years ago

您好，请问您是否还保存了原始数据？数据原文提供的链接貌似已经失效