ASM330LHBG1 datasheet(6/130 Pages) STMICROELECTRONICS

6 / 130 page

2.2

Machine learning core

The ASM330LHBG1 embeds a dedicated core for machine learning processing that provides system flexibility,

allowing some algorithms run in the application processor to be moved to the MEMS sensor with the advantage of

consistent reduction in power consumption.

Machine learning core logic allows identifying if a data pattern (for example motion, pressure, temperature,

magnetic data, and so forth) matches a user-defined set of classes. Typical examples of applications could be

activity detection like running, walking, driving, and so forth.

The ASM330LHBG1 machine learning core works on data patterns coming from the accelerometer and gyro

sensors. The input data can be filtered using a dedicated configurable computation block containing filters and

features computed in a fixed time window defined by the user.

Machine learning processing is based on logical processing composed of a series of configurable nodes

characterized by "if-then-else" conditions where the "feature" values are evaluated against defined thresholds.

Figure 3. Machine learning core in the ASM330LHBG1

Machine

learning core

logical processing

Sensor

data

Computation

block

Decision

tree

Accelerometer

Results

Gyroscope

Features

Filters

Meta-classifier

The ASM330LHBG1 can be configured to run up to 8 flows simultaneously and independently and every flow can

generate up to 256 results. The total number of nodes can be up to 512.

The results of the machine learning processing are available in dedicated output registers readable from the

application processor at any time.

The ASM330LHBG1 machine learning core can be configured to generate an interrupt when a change in the

result occurs.

ASM330LHBG1

Embedded low-power features

DS14080 - Rev 1

page 6/130

ASM330LHBG1 Datasheet(PDF) 6 Page - STMicroelectronics