Introduction
What is the problem we are trying to solve?
We are trying to recognize the activities carried out by a person while
engaged in everyday activities in the home setting. Recognizing activities
is important for a variety of health related applications such as judging
the level of independency in elderly people, tracking changes in behavior
over time as well as in human computer interaction.
What is our approach to the problem?
Our approach is to decompose human activities in the home setting
as a sequence of binary sensor activations by installing sensors that
sense movement or opening/closing events when everyday objects are manipulated.
What is the objective of this analysis?
The objective of this analysis is to explore different supervised machine
learning algorithms to the problem of recognizing human activities in
real-time from sensor data. Thus, we will walk you thru all the different
decisions we made to try to achieve such a goal for real-time applications.
Dataset Description
How was the dataset collected?
The dataset was collected by installing 77 and 84 sensor in two single-person
apartments for two weeks. The sensors were installed in everyday objects
such as drawers, refrigerators, containers, etc. to record opening-closing
events (activation deactivation events) as the subject carried out everyday
activities.
How were the sensors installed?
by installing the sensor and attaching the datacollection board to
the surface of different objects.
![](graphs/examples.jpg)
Sensor installation examples
|
Where were the sensors installed?
The sensors were installed in different locations in the home setting.
Please refer to the following figure.
CLICK
HERE FOR AN EXAMPLE OF THE SENSOR ACTIVATIONS FOR A DAY
What information does the dataset provides?
From the dataset, we know the following information:
1 .Activities: activity label, start and end times.
- Activity Label
- Start time
- End time
2.Sensors
- Sensor ID (e.g 22)
- Sensor location (e.g. kitchen)
- Object in which the sensor was installed (e.g. drawer)
- Activation time
- Deactivation time
|