ANLY482 AY2017-18T2 Group19 Data
Revision as of 01:03, 12 January 2018 by Joanne.ong.2014 (talk | contribs)
DATA DESCRIPTION
The data required for us comes in 3 parts.
- The demand side where the patients live which is derived from the percentage distribution of elderly in the respective subzones. This data will be created at random to simulate the daily nodes for each patient.
- The supply side where the foundation/organisation dispatches nurses to their scheduled patients
- The details of services with details such as the mean and standard deviation to provide a more realistic constraint for the algorithm to take into account when routing the nurses to their patients.
The dataset for the demand side will need to be generated by ourselves which includes:
- Address: Address of patient
- Latitude: Latitude of patient’s address
- Longitude: Longitude of patient’s address
- Type:
- Appointment_Times: Prefered appointment time
The dataset for the supply side will need to be generated by ourselves which includes:
- Id: Identification for nurse
- Address: Address of origin
- Latitude: Latitude of address
- Longitude: Longitude of address
- Type:
The dataset for the details of services includes:
- Discipline:
- Type (i.e. revisits, etc):
- Request count:
- Average: average time required for the treatment type
- SD: standard deviation of time required for the treatment type
DATA COLLECTION
We need to conduct research to better understand the demand side and supply side to generate sufficient amount of data to work with.
DATA CLEANING AND TRANSFORMATION
The data will need to be transformed into the required formats in order for us to perform the necessary processing later.
EXPLORATION OF DATA
At this phase, the data will be explored in order for us to choose a suitable model to be built.