guadacasuso / dronedataanalytics Goto Github PK

Some Drone Data Processing and Visualization Samples

Hypotesis: In any autonomous flight mission, the number of UAVs needed to accomplish a mission is very important in order to keep SLA of the Service. As an example, think about Fire Rescue: several considerations need to be taken to define the right number of units that can perform de Job. Environmental conditions such as Weather, Season, Territory coverage extension, Altitude, Closeness to the water Drone Data: Batery Capacity, Sensors Information, etc

First question to answer will be: How many drones do I need in a fleet to accomplish a mission? A mission can be a fire rescue, a monitoring service, an agriculture scenario, etc

My Datasources will be: The Flight Data that is [here] (https://raw.githubusercontent.com/guadacasuso/DroneDataAnalytics/master/Data/flight_data.csv) and also I will need to add some other measurements such as Battery and Sensors operation.

For weather I will use the Accuweather Public Datasource https://www.wunderground.com/weather/api/

Models Clustering DBScan

Challenges and successes

Business Impact The mail goal of this project is to be able to achieve efficiency in the use of drones In terms of potentiality I see the possibility of:

• Analizing sensors performance and improve batteries development/usage (For Manufacturers)
• Track Drones components life and improve (For Manufacturers)
• ReStock of drones

Conclusions and Key Learnings

Topics to cover: Problem statement and hypothesis Description of your data set and how it was obtained Description of any pre-processing steps you took What you learned from exploring the data, including visualizations How you chose which features to use in your analysis Details of your modeling process, including how you selected your models and validated them Your challenges and successes Possible extensions or business applications of your project Conclusions and key learnings