Method and system for sensor data recognition using data enrichment for the learning process
AssigneesSamsung ElectrôNica Da AmazôNia Ltda., Universidade Federal De Minas Gerais - Ufmg
InventorsOtávio A. B. Penatti, Milton F. S. Santos, Artur Jordão Lima Correia, William Robson Schwartz, Leonardo Antônio Borges Torres, Priscila Louise Ribeiro Aguirre
Life of this patent
Estimating the term…
Abstract
A method and system for the recognition of sensor data, like an accelerometer and a gyroscope. The method includes data/feature enrichment before a learning process. Thus, the learning process can benefit from better data, which includes both raw sensor data and enriched data/features. As a consequence, classification models may become less complex without harming accuracy and, therefore, can be more easily deployed to mobile devices, consuming less processing power and battery.
Claims19
A method for recognition of sensor data using enriched data for a learning process based on mobile inertial sensors, the method comprising:
- receiving data from the mobile inertial sensors as input;
- obtaining data/features from input raw sensor data that is received as the input from the mobile inertial sensors;
- enriching the data/features obtained from the input raw sensor data of the mobile inertial sensors by performing pre-processing in association with the data/features obtained from the input raw sensor data and generating enriched data for use in the learning process;
- learning features/classifier based on the input raw sensor data together with the generated enriched data as input for the learning process;
- and
- outputting a classification information generated according to the learned features/classifier.
A system for recognition of sensor data to obtain enriched data for a learning process based on mobile inertial sensors, the system comprising:
- a memory;
- a processor coupled to the memory and the processor configured to:
- receive data from the mobile inertial sensors stimulated by a user;
- obtain data/features from input raw sensor data that is received as the data from the mobile inertial sensors;
- enrich the data/features obtained from the input raw data from the mobile inertial sensors by performing pre-processing in association with the data/features obtained from the input raw sensor data and generate enriched data for use in the learning process;
- learn features and classifier based on the input raw sensor data together with the generated enriched data as input for the learning process;
- and
- analyze a classification information generated according to the features and classifier.
Dependencies are inferred from the claim text.