| KEYWORD |
Microelectronics
Edge AI for Inertial Measurement Unit (IMU) event classification
Thesis in external company
keywords MACHINE LEARNING, PATTERN RECOGNITION
Reference persons LUCIANO LAVAGNO
External reference persons Marcello Babbi, Reply Torino
Research Groups Microelectronics
Thesis type APPLIED RESEARCH
Description Reply has established in its experimental laboratory in Area 42 a ML methodology for IMU pattern
recognition. The student will be involved in the development of embedded AI algorithm to detect
acceleration pattern for human activity and object motions. The thesis project aims to develop
ML/DL algorithms able to classify different IMU signals pattern enabling safety procedure in micromobility
use cases.
Required skills Python programming, some knowledge of Machine Learning
Notes The student will be involved in:
❑ SW requirements definition for edge deployment;
❑ ML Classification problem definition;
❑ Data pre-processing and feature engineering;
❑ AI algorithms (e.g. tCNN) devolopment and fine tuning for classification task;
❑ On-edge performance optimization and compression methods development (e.g. pruning, quantization);
❑ Support and development of communication protocols for gateway connectivity;
❑ Hardware in the Loop validation and on-field testing.
Deadline 11/10/2024
PROPONI LA TUA CANDIDATURA