Intelligent Disaster Early-Warning System (1-2S/M)

Status: Available

• Type: Semester Thesis
• Professor: Prof. Dr. L. Benini
• Supervisors:
  • Philip Wiese (IIS): wiesep@iis.ee.ethz.ch
  • Victor Kartsch Morinigo (IIS): victor.kartsch@iis.ee.ethz.ch

Introduction

Multi-modal sensing enables on-device feature extraction, reducing communication overhead, perform predictions, increases privacy and enable on-device learning.

Smart sensors, which are sensors equipped with advanced computation capabilities, present a unique opportunity for innovation in multiple critical domains such as environmental sensing to reduce global greenhouse gas emissions or infrastructure monitoring.

A near-sensor processing of the gathered data that directly extracts meaning from the signal can lead to huge improvements in terms of energy efficiency and increased privacy. The reduced energy consumption comes from the fact that more specialized hardware such as the PULP platform including the GAP9 [1] can be used, and, additionally, that the information density of the transmitted data is higher, and thus less data must be transmitted via the often very power-intensive wireless link.

Our long-term goal is to develop a low-power sensing node with very low power consumption. These nodes should incorporate multiple sensors to enable multi-modal sensing. In other words, combine the data of the different sensors to extract additional data. The idea is to use the very efficient GAP9 multicore processor and deploy multi-modal neural networks to perform feature extraction, prediction, anomaly detection, and even on-device learning to adaptively fine-tune the model based on the measured data.

In this project, you will develop a multi-modal sensor system for an Intelligent Disaster Early-Warning System, aimed at early detection and warning of natural disasters such as floods, earthquakes, and wildfires. You will integrate environmental sensors to monitor changes in air quality, pressure, and temperature, which may indicate conditions leading to wildfires or severe weather events. Additionally, your task includes collecting datasets that incorporate IMU and microphone data to detect ground vibrations and sounds that could signify seismic activities. You will implement machine learning algorithms on the energy-efficient GAP9 platform to analyze data patterns that precede these disasters, aiming to enhance prediction accuracy. The culmination of your project will be the development of a sophisticated notification system designed to automatically alert both local authorities and the public about potential dangers, thereby enhancing community preparedness and safety.

Project

• Base Framework: Integrate environmental sensors to detect changes in air quality, pressure, and temperature indicative of wildfires or severe weather conditions.
• Data Acquisition: Dataset collection including IMU and microphone data aiming to capture ground vibrations and sounds that could indicate seismic activity.
• Application Specific Algorithm Development: Implement machine learning algorithms on GAP9 to analyze data patterns that precede disasters, improving prediction accuracy.
• Automated Warning System: Develop a notification system that automatically alerts local authorities and the public of potential dangers.

Prerequisites

• Good understanding of deep learning concepts.
• PCB Design and embedded C programming.
• Familiarity with Python programming.
• Familiarity with the PyTorch deep learning framework.

References

[1] GAP9 IoT Application Processor