Analyzing My Google Location History

Re:Analyzing My Google Location History by ehsankia on Thursday November 22, 2018 @07:48PM (#18513597)

> I assumed confidence to be the probability of each task. However, often they do not add up to 100. If they do not represent probabilities what do they represent?

The probability of each being true independently?

> How can Google possibly predict activity type between IN_TWO_WHEELER_VEHICLE vs IN_FOUR_WHEELER_VEHICLE ?!

Two wheel vehicles can often make it through traffic, in between cars.

[ Parent | on HN ]

Re:Analyzing My Google Location History by egypturnash on Thursday November 22, 2018 @08:12PM (#18513685)

Measuring how much the phone rolled back and forth could be a factor, too. You don’t have to keep a car balanced, you do have to keep a bike/scooter/motorcycle balanced.

[ Parent | on HN ]

Re:Analyzing My Google Location History by GChevalier on Friday November 23, 2018 @01:23AM (#18514735)

> How can Google possibly predict activity type between IN_TWO_WHEELER_VEHICLE vs IN_FOUR_WHEELER_VEHICLE ?!

Could they be using this from accelerometer data instead of GPS? https://github.com/guillaume-chevalier/LSTM-Human-Activity-R...

[ Parent | on HN ]

Re:Analyzing My Google Location History by GChevalier on Friday November 23, 2018 @01:44AM (#18514806)

https://news.ycombinator.com/item?id=13049143

[ Parent | on HN ]

Re:Analyzing My Google Location History by toadi on Thursday November 22, 2018 @08:53PM (#18513829)

I drive a motorcycle in Thailand all the time google is more wrong than right when predicting this.

[ Parent | on HN ]

Re:Analyzing My Google Location History by aasasd on Friday November 23, 2018 @01:30AM (#18514755)

I'm gonna bet that Thai bike-driving habits are different from those of people in the US, at least in cities.

[ Parent | on HN ]

Re:Analyzing My Google Location History by nl on Friday November 23, 2018 @01:48AM (#18514818)

I going to bet there are more bike driving people with Android phones in places like Thailand, Indonesia, India and the Philippines where on-road behavior is more similar to each other than to the US.

I think it's a pretty hard problem, and we shouldn't be surprised if the accuracy there is low.

[ Parent | on HN ]

Re:Analyzing My Google Location History by stuppalupp on Thursday November 22, 2018 @09:23PM (#18513933)

https://developers.google.com/android/reference/com/google/a...

[ Parent | on HN ]

Re:Analyzing My Google Location History by cameldrv on Thursday November 22, 2018 @11:32PM (#18514373)

It's probably a combination of features, but the suspensions are different, and two wheelers lean when they turn, which should be easy to distinguish from the accelerometer and gyros.

[ Parent | on HN ]

Re:Analyzing My Google Location History by jayd16 on Thursday November 22, 2018 @09:02PM (#18513862)

Seems feasible to detect a user at above foot speed,that appears to be stopping at intersections but seems to be more immune to congestion than others and label it as a two wheeled vehicle.

[ Parent | on HN ]

Re:Analyzing My Google Location History by kingosticks on Friday November 23, 2018 @04:28AM (#18515376)

There are also certain roads/paths that are bike only, through convention (bike lanes) or physical width restrictions.

[ Parent | on HN ]

Re:Analyzing My Google Location History by mathur68 on Friday November 23, 2018 @05:56AM (#18515710)

LOL. There are no such paths in India - Article Author

[ Parent | on HN ]

Re:Analyzing My Google Location History by kingosticks on Friday November 23, 2018 @06:30AM (#18515832)

I've never been to India but presumably you have some parks... However, I do see that google maps has the bicycle overlay greyed out for New Delhi!

[ Parent | on HN ]