Discussion 4/14

[Vopaaz]

Work left to do

Modify the docstring and squash commit. - Vopaaz

More features

1. The final recorded coordinate. - Vopaaz
2. Convert the path to the image and then apply the neural network. - Suspend
3. Vopaaz and Xiaochr each come up with a feature considering device.

DDL

4/17 24:00, 4/18 Further discussion.

---

--- DELETE, UNNECESSARY ---

Malkov - Xiaochr

1. Frequency -> Probability
2. Consider time, estimate the position by assuming constant velocity and straight line.
3. Also, write a time-unconsidered version

Classify for Path - Vopaaz

Consider the classification against a path. The (only) feature is the entry point, the prediction is whether the exit is in the center.
Apply generally used classifier.
Actually Malkov is the same idea.

--- DELETE ---

[Vopaaz]

Feature:

1. distance to the border of the last record minus distance to the border of the first record, representing the overall trend whether this person is moving towards the center or leaving the center.
2. similar to 1, but use the points on the last path instead, representing the trend of moving in the final time span.

[Xiaochr]

Feature:

3. The average, min, max length of each path.
4. Similar to feature 3, but to calculate the 'speed', which means the length the device travels per minute.

[Vopaaz]

The unfinished work are mentioned in #8