UM2580
User manual
How to use the wireless multi-sensor development kit with customizable app for
IoT and wearable sensor applications
Introduction
The STEVAL-MKSBOX1V1 (SensorTile.box) is a ready-to-use box kit with wireless IoT sensor platform designed to help you
build apps that use motion and environmental sensors, regardless of your level of expertise.
The hardware node is a board that fits into a small plastic case (IP54) with a rechargeable battery. You can connect with your
smartphone to the board via Bluetooth by using the ST BLE Sensor app (available both on Google Play and Apple Store) and
immediately build your own apps through a special interface that offers beginner and expert level functionality. This multi-sensor
kit therefore allows you to design wireless IoT and wearable sensor applications quickly and easily, without performing any
programming.
SensorTile.box includes a firmware programming and debugging interface that allows professional developers to engage in
more complex firmware customization using the STM32 Open Development Environment (STM32 ODE), which includes a
sensing AI function pack with neural network libraries.
The kit board includes an embedded SPBTLE-1S Bluetooth SMART application processor that is compliant with BT
specification v4.2. This transmitter module is FCC (ID:S9NSPBTLE1S) certified and IC (IC:8976-SPBTLE1S) certified.
Note: SPBTLE-1S has been replaced by the BlueNRG-M2 module, compliant with BT specification v5.2 in latest
production batches.
Figure 1. STEVAL-MKSBOX1V1 (SensorTile.box) multi-sensor development kit
UM2580 - Rev 6 - April 2021
For further information contact your local STMicroelectronics sales office.
www.st.com
UM2580
How to set up the hardware
1 How to set up the hardware
Important:
Before you begin, please check the insert card that comes with the SensorTile.box blister pack. If it doesn't show a procedure
for battery connection similar to the steps below, then your device is supplied with the battery already connected to the board.
In this case, you only need to connect the device via USB to wake it up the first time.
If the insert card has a similar procedure to the steps below, your device is supplied with the battery disconnected and you
should follow this procedure to connect the battery and wake the device up.
Step 1. Remove the SensorTile.box contents from its package.
Step 2. Unscrew the shroud cover.
You should have the following items:
– An evaluation board in a plastic shroud
– A LiPo battery
Step 3. Slide the male battery connector vertically into the female connector on the board.
You will hear a light click when the connector is attached correctly.
Figure 2. STEVAL-MKSBOX1V1 battery connection
Step 4. Re-position the circuit with the battery below it and the close the shroud with one of the following types
of lid:
– with flanges
– without flanges
Step 5. If necessary, charge the battery via a USB cable.
The blinking of the red LED indicates the battery charging status.
UM2580 - Rev 6
page 2/40
How to use ST BLE Sensor app with SensorTile.box
2 How to use ST BLE Sensor app with SensorTile.box
Before you begin, you need to download and install our ST BLE Sensor app on your smartphone. The app is
available from the Google and Apple online stores.
Step 1. Launch the app on your smartphone.
Figure 3. ST BLE Sensor app main screen
UM2580
UM2580 - Rev 6
page 3/40
UM2580
How to use ST BLE Sensor app with SensorTile.box
Step 2. Select [CREA
The Example Apps screen that follows lists the preloaded apps that you can use immediately.
TE A NEW APP].
Figure 4. Example Apps screen
UM2580 - Rev 6
page 4/40
Step 3. Select one of the apps with the icon from the list.
After you select the app, ST BLE Sensor will scan for available SensorTile.box devices in range.
Figure 5. Board selection
UM2580
How to use ST BLE Sensor app with SensorTile.box
Step 4. Select the appropriate SensorTile.box device from the Board screen.
A blue LED on the SensorTile.box device will flash slowly to confirm Bluetooth pairing.
A pop up message in ST BLE Sensor will prompt you to confirm loading the new app in replacement of
any previously opened apps.
Step 5. Select the appropriate SensorTile.box device from the Device List.
The app will commence monitoring or logging activity and return real time feedback data to the
corresponding app screen in ST BLE Sensor.
UM2580 - Rev 6
page 5/40
3 Application descriptions
3.1 Mode 1 example apps
The ST BLE Sensor bundles the following ready-to-use app scenarios:
• Baby Crying Detector
• Barometer
• Compass and Level
• Data Recorder
• Human Activity recognition
• In-Vehicle Baby Alarm
• Pedometer
• Sensor Fusion - Quaternion
• Vibration Monitor - Training
• Vibration Monitor - Compare
UM2580
Application descriptions
Figure 6. Apps screen
UM2580 - Rev 6
App scenarios with the icon produce immediate outputs on your smartphone in real time.
App scenarios with the
App scenarios with the
icon store sample data on the internal micro SD card.
icon are reserved for Expert mode.
page 6/40
RELATED LINKS
2 How to use ST BLE Sensor app with SensorTile.box on page 3
3.1.1 Baby crying detector
The baby crying detector (BCD) app implements the Fast Fourier Transform (FFT) and artificial intelligence
processing to detect baby crying events using the Sensortile.box
The analysis of the acquired audio is based on the FFT that converts a signal from its original time domain to a
representation in the frequency domain.
UM2580
Mode 1 example apps
on-board microphone.
Figure 7. FFT analysis - from time to frequency domain
The FFT of the audio signal is the result of all the contributions of each frequency and the related magnitude
factor generated by the audio signal.
Figure 8. FFT analysis - principles
UM2580 - Rev 6
page 7/40
UM2580
Mode 1 example apps
The FFT feature extraction of the acquired signal is processed by the STM32 MCU which calculates the MEL FFT
and the MFCC (MEL frequency cepstral coef
baby crying event is detected, the green user LED on the Sensortile.box board lights up and a warning is sent to
the smartphone via Bluetooth.
Figure 9. STBLESensor - baby crying detection process
ficient) parameters sent to the implemented MCU neural network: if a
The neural network is classified as a deep feed forward neural network and its structure is composed of 2 hidden
nodes of 100 neurons each.
The tool used to develop the neural network is Keras with an open source high level library written in Python.
Optimization and loading of the neural network on the Sensortile.box
has been performed using
STM32CubeMX.AI.
Figure 10. STBLESensor - baby crying app neural network
UM2580 - Rev 6
page 8/40
The baby crying app works with the following ST high sensitivity audio sensor and operating parameter settings:
• APP DA
TA INPUT: microphone audio acquisition
• SENSOR USED: MP23ABS1 MEMS microphone
• SENSOR SETTINGS: 16 KHz sample acquisition
• APP DATA OUTPUT: baby crying/not crying icon
RELATED LINKS
Appendix A ARMA filter coefficient calculation on page 35
3.1.2 Barometer app
The Barometer app uses the Sensortile.box on-board environmental sensors (STTS751, LPS22HH and HTS221).
UM2580
Mode 1 example apps
Figure 1
1. Barometer app screen
UM2580 - Rev 6
The Barometer app monitors the environmental information in real-time and shows the data on your smartphone
as icons or graph plot.
The LPS22HH pressure sensor embeds another built-in sensor for temperature compensation (0.5 hPa with a
range of 260-1260 hPa of absolute pressure).
The STTS751 digital temperature sensor has an operating temperature range of -40/+125 °C, with maximum
resolution 0.0625 °C/LSB and precision of ± 0.5 °C (typ.).
The HTS221
digital relative humidity and temperature sensor has a relative humidity range of 0/100%, a
sensitivity of 0.004% RH/LSB, a humidity accuracy of ± 3.5% RH, 20-80% RH and an accuracy in temperature of
± 0.5 °C (typ,) in the range of 15/+40 °C.
page 9/40
UM2580
Mode 1 example apps
When you run the Barometer app and connect the Sensortile.box
monitoring screen for the environmental sensors.
Figure 12. Environmental screen
device, the ST BLE Sensor app shows a
UM2580 - Rev 6
You can access other output options from the menu icon in the top left of the screen.
page 10/40
Figure 13. Plot Data screen - humidity
UM2580
Mode 1 example apps
UM2580 - Rev 6
page 11/40
Figure 14. Plot Data screen - temperature
UM2580
Mode 1 example apps
Thanks to the low power sensors, low output data rate and low power MCU, this app is highly suitable for
battery-based projects with very low power consumption.
UM2580 - Rev 6
page 12/40
Mode 1 example apps
The Barometer app sets the following operating parameter settings for the following ST high accuracy
environmental sensors:
• APP DATA INPUT: pressure, temperature and humidity values
• SENSORS USED:
– LPS22HH (absolute pressure MEMS digital sensor)
– STTS751 (temperature digital sensor)
– HTS221 (relative humidity and temperature digital sensor)
• SENSOR SETTINGS:
– LPS22HH settings:
◦ Power mode: Low Noise
◦ Output Data Rate: 1 Hz
◦ Filter: ODR/2
– STTS751 settings:
◦ Low power mode
◦ Output data rate: 1 Hz
– HTS221 settings:
◦ Low power mode
◦ Output data rate: 1 Hz
• APP DATA OUTPUT:
– Relative humidity (%)
– Temperature (°C)
– Absolute Pressure (mBar)
– Plot collected data
UM2580
3.1.3 Compass and Level app
The Compass and Level app shows the orientation estimation of the Sensortile.box in relation to the Earth
magnetic North or level indication.
The app is based on the sensor fusion firmware algorithm (MotionFX library) embedded in the Sensortile.box
MCU.
The sensor fusion algorithm is an extended Kalman filter (EKF) that minimizes sensor inaccuracies and includes
gyroscope calibration and magnetometer calibration (to compensate the magnetometer offset).
The algorithm uses the LSM6DSOX iNemo 6-axis accelerometer and gyroscope data and the LIS2MDL 3-axis
compensated magnetometer data as inputs, combining the two sensors in a virtual 9-axis sensor.
Figure 15. MotionFX algorithm flow
UM2580 - Rev 6
page 13/40
UM2580
Mode 1 example apps
The magnetometer indicates yaw angle and heading, but only if hard-iron offset is compensated and when there
is no additional magnetic field around the Sensortile.box disturbing the measurement.
Figure 16. MotionFX algorithm flow - magnetometer function
Data regarding yaw and angle heading are also given when tilt is compensated by the accelerometer.
Figure 17. MotionFX algorithm flow - accelerometer tilt compensation
The gyroscope indicates the new orientation based on the previous one, when its bias is compensated by the
accelerometer. The gyroscope can detect the static condition of the Sensortile.box,
Figure 18. MotionFX algorithm flow - gyroscope function
UM2580 - Rev 6
page 14/40
Mode 1 example apps
To enable the magnetometer calibration, you need to touch the symbol highlighted in the picture below.
Figure 19. STBLESensor Compass and Level app - calibration icon
UM2580
UM2580 - Rev 6
page 15/40
UM2580
Mode 1 example apps
Then, move the Sensortile.box in a 8-pattern figure as shown below; the calibration is completed when the icon
becomes green.
Figure 20. STBLESensor Compass and Level app - starting the calibration
The MotionFX library provides orientation estimation, magnetometer hard-iron offset compensation,
accelerometer vibration rejection and gyroscope bias compensation.
The sensor fusion algorithm calculates the quaternion coefficient and the Euler angles to detect the right
orientation of the Sensortile.box represented by a compass rotation or level indicator.
UM2580 - Rev 6
page 16/40
Figure 21. STBLESensor Compass and Level app - orientation screen
UM2580
Mode 1 example apps
UM2580 - Rev 6
page 17/40
Figure 22. STBLESensor Compass and Level app - offset example 1
UM2580
Mode 1 example apps
UM2580 - Rev 6
page 18/40
Figure 23. STBLESensor Compass and Level app - offset example 2
UM2580
Mode 1 example apps
UM2580 - Rev 6
page 19/40
UM2580
Mode 1 example apps
The Compass and Level app works with the following ST high accuracy motion sensors and operating parameter
settings:
• APP DA
• SENSORS USED:
– LSM6DSOX (acceleration and gyroscope sensor)
– LIS2MDL (compensated magnetometer)
• SENSOR SETTINGS:
– LSM6DSOX:
– LIS2MDL settings:
• APP DATA OUTPUT:
– Compass orientation model
– Level indication model
TA INPUT: Accelerometer, gyroscope and magnetometer values
◦ Low power mode
◦ Output data rate: 52 Hz
◦ Low pass filter: 700 Hz
◦ Full scale: 2 g for accelerometer, 2000 dps for gyroscope
◦ Low power mode
◦ Output data rate: 50 Hz
◦ Full scale: 50 gauss
◦ Quaternion values
◦ Heading
◦ Euler angles
◦ Plot collected data
3.1.4 Data Recorder app
Data recorder can be used to monitor and record movements and/or environmental conditions that parcels or
objects are subjected to during movement or shipping.
The data can be used to verify whether a parcel has suf
damage the goods, or if a vehicle has been driven according to appropriate speed and safety parameters.
Certain sensors are enabled according to what is being monitored, and data is stored in the internal memory
card for later retrieval and analysis. Motion sensors are set to Low Power Mode with a data rate of around 50 to
100 Hz, while a data rate of 1 Hz is appropriate for environmental sensors.
3.1.5 Human Activity Recognition app
The Human Activity Recognition app uses the Sensortile.box LSM6DSOX MEMS accelerometer and the
embedded Machine Learning Core (MLC).
The following activities can be recognized by icons on the screen, independently from the Sensortile.box
orientation:
•
Stationary
• Walking
• Fast walking
• Jogging
• Biking
• Driving
fered shocks or undesirable temperatures that could
UM2580 - Rev 6
page 20/40
Figure 24. Human Activity Recognition app
UM2580
Mode 1 example apps
Four features are used (mean, variance, peak-to-peak, zero-crossing) for MLC code generation.
The algorithm runs at 26 Hz, with a window of 75 samples.
The Human Activity Recognition app works with the following ST high accuracy MEMS acceleration sensor and
operating parameter settings:
• APP DATA INPUT: Accelerometer values
• SENSOR USED: LSM6DSOX (high bandwidth acceleration sensor)
• SENSOR SETTINGS:
– Low power mode
– Output data rate: 52 Hz
– Low pass filter: 700 Hz
– Full scale: 2 g
• APP DATA OUTPUT :
– Activity recognized icon
3.1.6 In-Vehicle Baby Alarm app
The In-Vehicle Baby Alarm app combines the state of baby crying (see Section 3.1.1 ) and the vehicle
movement detector.
The sensors used are the MP23ABS1 analog MEMS microphone and the LSM6DSOX MEMS accelerometer,
gyroscope, as well as the embedded Machine Learning Core.
For the MLC code generation, the following features calculated from accelerometer and gyroscope values have
been used: MEAN-acc, VAR-acc, PeakToPeak-acc, MAX-acc, MEAN-gyro, VAR-gyro, PeakToPeak-gyro, MAXgyro, MIN-gyro, ENERGY-gyro.
The app shows:
• whether the adult is in-vehicle or not
• whether the baby is crying or not
• the alarm icon if there is no adult in vehicle and the baby is crying
UM2580 - Rev 6
page 21/40
UM2580
Mode 1 example apps
Figure 25. In-V
ehicle Baby Alarm app - baby not crying state
UM2580 - Rev 6
page 22/40
UM2580
Mode 1 example apps
Figure 26. In-V
ehicle Baby Alarm app - baby crying state
The In-Vehicle Baby Alarm app works with the following ST high accuracy MEMS acceleration and gyroscope
sensor
, analog MEMS microphone and the following operating parameter settings:
• APP DATA INPUT: accelerometer and gyroscope values, and microphone audio
• SENSORS USED:
– LSM6DSOX (acceleration/gyroscope sensor)
– MP23ABS1 (analog MEMS microphone)
• SENSOR SETTINGS:
LSM6DSOX
– Low power mode
– Output data rate: 52 Hz
– Low pass filter: 700 Hz
– Full scale: 2 g for accelerometer, 2000 dps for gyroscope
MP23ABS1 settings:
– 1600 Hz acquisition sample frequency
• APP DATA OUTPUT:
– Baby crying/ not crying status
– Adult is in-vehicle or not status
– Alarm in case of baby-crying and adult is not in vehicle status
UM2580 - Rev 6
page 23/40
3.1.7 Pedometer app
The Pedometer app uses the pedometer software algorithm (MotionPM library) based on the Sensortile.box
embedded LSM6DSOX 3-axis MEMS accelerometer data to count the steps and the steps per minute of your
walking/running activity and show acquired data.
The 3-axis accelerometer measures the acceleration of your body during the walking.
The walking steps have a specific pattern of acceleration values and peak frequency
acceleration values pattern of other types of movements.
UM2580
Mode 1 example apps
, different from the body
Figure 27. Raw accelerometer data - user walking with the device
The algorithm is optimized for the Sensortile.box belt positioning as shown below.
Figure 28. Sensortile.box belt positioning
UM2580 - Rev 6
To avoid counting false positive steps, the step counting starts after 10 seconds of constant walking (debounce
time); after this time, the algorithm shows the steps and continues counting from the number of steps already
accumulated during the debounce time.
page 24/40
Figure 29. Pedometer app - step count
UM2580
Mode 1 example apps
The accuracy of the Pedometer is Mean Absolute Percentage Error (MAPE)=97.5% with sigma=5 thanks to the
high precision of the LSM6DSOX
These parameters are appropriate to capture human movement, filter unwanted noise and save battery energy to
extend the potential working time.
The app works with the following ST high accuracy acceleration sensor and operating parameter settings:
• APP DATA INPUT: 3-axis acceleration values
• SENSOR USED: LSM6DSOX (accelerometer)
• SENSOR SETTINGS:
– Low power mode accelerometer
– Power down gyroscope
– Output data rate: 52 Hz
– Full scale: 4 g
• APP DATA OUTPUT:
– Number of steps
– Cadence (number of steps per minute)
3.1.8 Sensor Fusion app
The Sensor Fusion app is based on the sensor fusion firmware algorithm (MotionFX library) embedded in the
MCU.
The app shows the orientation estimation of Sensortile.box in the 3D space.
3-axis MEMS accelerometer
UM2580 - Rev 6
page 25/40
UM2580
Mode 1 example apps
The algorithm uses the LSM6DSOX iNemo 6-axis accelerometer and gyroscope data and the LIS2MDL 3-axis
compensated magnetometer data as inputs (9-axis), and calculates the quaternion coefficient and the Euler
angles to detect the right orientation of the Sensortile.box represented by a cube on the smartphone app or by
value plots for all sensors and results calculated.
Figure 30. Sensor fusion app - Sensortile.box orientation (cube representation)
UM2580 - Rev 6
page 26/40
Figure 31. Sensor fusion app - Sensortile.box orientation (plot)
UM2580
Mode 1 example apps
Figure 32. Sensor fusion app - Sensortile.box orientation (results)
UM2580 - Rev 6
To enable magnetometer calibration, you need to touch the symbol shown in the picture below.
page 27/40
Figure 33. Sensor fusion app - enabling magnetometer calibration
UM2580
Mode 1 example apps
Move the board in an 8-pattern shape as shown in the figure below to calibrate the magnetometer: the calibration
is completed when the icon turns green.
Figure 34. Sensor fusion app - enabling magnetometer calibration
UM2580 - Rev 6
page 28/40
Mode 1 example apps
The Sensor Fusion Motion FX library provides orientation estimation, magnetometer hard-iron offset
compensation, accelerometer vibration rejection and gyroscope bias compensation.
The app works with the following ST high accuracy acceleration sensor and magnetometer
, and operating
parameter settings:
• APP DATA INPUT: accelerometer, gyroscope and magnetometer values
• SENSORS USED:
– LSM6DSOX (high bandwidth acceleration sensor and gyroscope)
– LIS2MDL (compensated magnetometer)
• SENSOR SETTINGS:
LSM6DSOX
– Low power mode
– Output data rate: 52 Hz
– Low pass filter: 700 Hz
– Full scale: 2 g for accelerometer, 2000 dps for gyroscope
LIS2MDL
– Low power mode
– Output data rate: 50 Hz
– Full scale: 50 gauss
• APP DATA OUTPUT:
– 3D-Cube orientation model
◦ Quaternion values
◦ Heading
◦ Euler angles
◦ Plot collected data
UM2580
3.1.9 Vibration Monitoring
The Vibration Monitoring app demonstrates how engines, electric motors and the like are monitored to detect
potential problems by their mechanical vibrations.
The sensor used is the LSM6DSOX
of 6666 Hz, to reach the highest level of bandwidth and best performance.
The app can compare two mechanical vibration data patterns, the vibration under test (Compare-app) with the
vibration of a standard scenario previously acquired (Training-app).
• Vibration Monitor - Training: is designed to acquire the vibration pattern of new or correctly functioning
equipment. The vibration pattern is converted using the Fast Fourier Transform (FFT) function and is stored
in the memory card on the SensorTile.box device.
• Vibration Monitor - Compare: is designed to monitor the same equipment and compare the vibration
patterns with the original sample captured by Vibration Monitor - Training.
If the difference between the vibration analysis in Vibration Monitor - Training and Vibration Monitor - Compare
exceeds a set delta parameter (which can be modified according to equipment age and load conditions), the
green user LED on the Sensortile.box device and the LED icon on the smartphone screen turn on.
accelerometer configured in high performance mode, with an output data rate
UM2580 - Rev 6
page 29/40
UM2580
Mode 1 example apps
Figure 35. V
ibration Monitoring app - event detection
The Vibration Monitoring apps work with the following ST high accuracy motion sensor and operating parameter
settings:
• APP DATA INPUT: accelerometer values for training and compare phases
• SENSORS USED: LSM6DSOX high bandwidth acceleration sensor
• SENSOR SETTINGS:
– High Performance power mode
– Output data rate: 6666 Hz
– Filter: none
– Full scale: 2 g
• APP DATA OUTPUT:
– Green LED on the SensorTile.box
– LED icon on the smartphone screen
UM2580 - Rev 6
page 30/40
3.2 How to use Expert Mode functionality
The STE BLE Sensor app can help you develop your own app or customize an existing one, which you can then
upload and run on the SensorT
Step 1. Return to the main screen of the ST BLE Sensor app.
Step 2. Select [CREATE A NEW APP].
ile.box device.
Figure 36. Example Apps screen
UM2580
How to use Expert Mode functionality
Step 3. Select [EXPERT VIEW].
A new screen appears with saved apps.
UM2580 - Rev 6
page 31/40
Step 4. Select [+ NEW APP].
UM2580
How to use Expert Mode functionality
Figure 37. Input sources screen
Step 5. Select one or more of the desired sensor data inputs.
Unselected sensors are put in sleep mode.
Step 6. Select [SET INPUT] to confirm
Figure 38. Sensor data configuration screen
UM2580 - Rev 6
page 32/40
Step 7. Select the gear icon next to each sensor and set the parameters according to your application
requirements
ou can set parameters such as full scale, data rate (ODR), Power Mode, Filter, etc., according to
Y
device specifications provided in corresponding sensor datasheets.
Following sensor selection, the function screen lists the available functions for the enabled sensors.
For the temperature sensor, for example, the available functions are shown below.
Figure 39. Custom app function screen
UM2580
Pro Mode
Step 8. Choose between one of the following output types:
–
– To the memory card (micro SD)
– Via USB to a host master (i.e., a PC).
– To the user LED for logic data types (like the output of a threshold function or comparison).
The LED option is achieved by selecting [Save as EXP] in the output selection screen and enabling the
associated output property.
There are two special output types:
– [Save as INPUT]: is a way to concatenate different functions and generate different branches
– [Save as EXP]: produces an app branch whose output is a digital “true” or “false”. This value can
An app saved as EXP or as INPUT appears in the input selection screen so it can be used more
complex app generation.
Step 9. Save your app with an appropriate name and optional comment.
RELATED LINKS
Appendix A ARMA filter coefficient calculation on page 35
3.3 Pro Mode
SensorTile.box is fully compatible with the STM32 Open Development Environment (STM32 ODE) for developers
to customize the SensorT
FP-SNS-ALLMEMS2 and FP-AI-SENSING1
Via Bluetooth to your smartphone (to view certain data)
which will be processed one after the other.
be used in other comparisons or logic functions.
ile.box firmware. In fact, you can use the STM32Cube function packs FP-SNS-STBOX1,
UM2580 - Rev 6
page 33/40
UM2580
Pro Mode
The board is compatible with STLINK-V3 and STLINK-V3MINI (with UAR
T pins for debugging), and the most
recent release of the Sensortile.box includes an adapter board and cable for the ST-LINK/V2 programming and
debugging device.
Important:
You must use STLINK-V3 (or STLINK-V3MINI) and the corresponding level shifter if you require Cube.AI library compatibility
with the debugging option.
RELATED LINKS
Visit the ST website for all the resources you need regarding the STM32 Open Development Environment
UM2580 - Rev 6
page 34/40
ARMA filter coefficient calculation
Appendix A ARMA filter coefficient calculation
UM2580
The built-in ARMA filter implemented by SensorT
described by the equation:
ma 0 u t + ma 1 u t − 1 + ma2 u t − 2 + ma 3 u t − 3 + ma4 u t − 4 + ma 5 u t − 5
t =
y
1 + ar1 y t − 1 + ar 2 y t − 2 + ar 3 y t − 3 + ar 4 y t − 4 + ar 5 y t − 5
Where:
y(t) = output of the filter
u(t) = input signal
With this function, low-pass, high-pass, band-pass and band-reject filters can be implemented, and higher filter
orders can be obtained by cascading two or more filters, one after the other
The simplest way to calculate the ma(i) and ar(i) coefficients for the required filter shape is to use a math program
like Octave. Octave has a “signal” extension package that can be loaded by typing the command pkg load
signal at the Octave prompt. Once done, there are few filter calculation options, depending on the type of filter
that is requested by the application: Butterworth, Bessel, Chebyshev and elliptic (Cauer) filters can be computed.
RELATED LINKS
3.1.1 Baby crying detector on page 7
3.2 How to use Expert Mode functionality
Visit this web page for further insight regarding ARMA filters
GNU Octave home page
A.1 Filter calculation example
The following example illustrates how a second-order Butterworth band-pass filter can be implemented. W
assume that we want to filter our microphone signal with a band-pass filter in the 1 kHz – 3 kHz range.
Step 1. We set a microphone sampling rate of 16 kHz.
The maximum signal frequency (or Nyquist frequency) is therefore 16/2 = 8 kHz, according to Nyquist/
Shannon theorem.
ile.box firmware is a general IIR fifth-order polynomial filter
.
on page 31
e will
Step 2. Open the Octave command line prompt.
Step 3. Type the following command:>>[MA, AR]=butter(2, [1/8, 3/8])
This calls the butter function in Octave, where:
– 2 is the filter order
– 1/8 and 3/8 are the band limits relative to the Nyquist frequency
The program output is:
MA =
0.09763 0.00000 -0.19526 0.00000 0.09763
AR =
1.00000 -2.25233 2.27614 -1.23184 0.33333
Step 4. Set the above values for ma(0) to ma(4), and set ma(5) to zero in the ARMA property screen for the
SensorT
ile.box app.
Step 5. Set the above values for ar(0) to ar(4), and set ar(5) to zero in the ARMA property screen for the
SensorTile.box app.
Note that ar(0) is always equal to 1, so the ARMA property screen does not require it to be inserted.
RELATED LINKS
Similar functions can be used for the other type of filters; check Octave documentation for all the options
UM2580 - Rev 6
page 35/40
UM2580
Formal notices required by the U.S. Federal Communications Commission ("FCC")
Appendix B Formal notices required by the U.S. Federal Communications
Commission ("FCC")
FCC NOTICE: This device complies with part 15 of the FCC Rules. Operation is subject to the following two
conditions: (1) This device may cause harmful interference, and (2) this device must accept any interference
received, including interference that may cause undesired operation.
Changes or modifications not expressly approved by the manufacturer could void the user
the equipment.
Additional warnings for FCC
This equipment has been tested and found to comply with the limits for a Class B digital device, pursuant to part
15 of the FCC Rules. These limits are designed to provide reasonable protection against harmful interference
in a residential installation. This equipment generates, uses and can radiate radio frequency energy and, if not
installed and used in accordance with the instructions, may cause harmful interference to radio communications.
However, there is no guarantee that interference will not occur in a particular installation. If this equipment does
cause harmful interference to radio or television reception, which can be determined by turning the equipment off
and on, the user is encouraged to try to correct the interference's by one or more of the following measures:
• Reorient or relocate the receiving antenna.
• Increase the separation between the equipment and the receiver.
• Connect the equipment into an outlet on a circuit different from that to which the receiver is connected.
• Consult the dealer or an experienced radio/TV technician for help.
’s authority to operate
B.1 SPBTLE-1S Bluetooth communication module specifications
Operating frequency: 2402 MHz to 2480 MHz
Output power: around 4 dBm (approx.) at ambient temperature
T
able 1. SPBTLE-1S Bluetooth module power specifications
Channel
Test conditions
Temperature Voltage
+25 °C 3.3 V 3.31 4.48 4.30
-40 °C 3.3 V 3.96 5.16 4.99
+85 °C 3.3 V 2.71 3.78 3.58
Low
2.402 GHz
Middle
2.440 GHz
Measured equivalent isotropic power (dBm)
High
2.480 GHz
UM2580 - Rev 6
page 36/40
Revision history
Date Version Changes
13-May-2019 1 Initial release.
14-Nov-2019 2
02-Dec-2019 3
15-Apr-2020 4
13-May-2020 5
06-Apr-2021 6
UM2580
T
able 2. Document revision history
Minor text edits
Added information regarding ST
kit.
Updated Introduction.
Updated Section 1 How to set up the hardware.
Updated Section 3.1.4 Baby crying app.
Added Section Appendix B Formal notices required by the U.S. Federal Communications
Commission ("FCC").
Minor text edits.
Added Section B.1 SPBTLE-1S Bluetooth communication module specifications.
Updated Figure 4. Example Apps screen, Section 3.1 Entry level example apps, Section 3.1.1 Baby
crying detector
Data Recorder app, Section 3.1.7 Pedometer app, Section 3.1.9 Vibration Monitoring and Section 3.3
Pro Mode.
Added Section 3.1.5 Human Activity Recognition app, Section 3.1.6 In-Vehicle Baby Alarm app and
Section 3.1.8 Sensor Fusion app.
Updated Section 3.1.1 Baby crying detector, Section 3.1.2 Barometer app, Section 3.1.3 Compass
and Level app, Section 3.1.5 Human Activity Recognition app, Section 3.1.6 In-V
app, Section 3.1.7 Pedometer app, Section 3.1.8 Sensor Fusion app and Section 3.1.9 Vibration
Monitoring.
Updated Introduction.
Minor text changes.
, Section 3.1.2 Barometer app, Section 3.1.3 Compass and Level app, Section 3.1.4
-LINK/V2 adapter board and cable included in latest version of the
ehicle Baby Alarm
UM2580 - Rev 6
page 37/40
UM2580
Contents
Contents
1 How to set up the hardware ........................................................2
2 How to use ST BLE Sensor app with SensorT
ile.box ...............................3
3 Application descriptions ...........................................................6
3.1 Mode 1 example apps ..........................................................6
3.1.1 Baby crying detector ......................................................7
3.1.2 Barometer app ..........................................................9
3.1.3 Compass and Level app ..................................................13
3.1.4 Data Recorder app ......................................................20
3.1.5 Human Activity Recognition app ............................................20
3.1.6 In-Vehicle Baby Alarm app ................................................21
3.1.7 Pedometer app .........................................................24
3.1.8 Sensor Fusion app ......................................................25
3.1.9 Vibration Monitoring .....................................................29
3.2 How to use Expert Mode functionality ............................................31
3.3 Pro Mode ....................................................................33
Appendix A ARMA filter coefficient calculation .......................................35
A.1 Filter calculation example.......................................................35
Appendix B Formal notices required by the U.S. Federal Communications Commission
("FCC")...........................................................................36
B.1 SPBTLE-1S Bluetooth communication module specifications.........................36
Revision history .......................................................................37
UM2580 - Rev 6
page 38/40
List of figures
UM2580
List of figures
Figure 1. STEV
Figure 2. STEVAL-MKSBOX1V1 battery connection .................................................2
Figure 3. ST BLE Sensor app main screen ....................................................... 3
Figure 4. Example Apps screen ............................................................... 4
Figure 5. Board selection....................................................................5
Figure 6. Apps screen......................................................................6
Figure 7. FFT analysis - from time to frequency domain...............................................7
Figure 8. FFT analysis - principles .............................................................7
Figure 9. STBLESensor - baby crying detection process .............................................. 8
Figure 10. STBLESensor - baby crying app neural network .............................................8
Figure 11. Barometer app screen ...............................................................9
Figure 12. Environmental screen .............................................................. 10
Figure 13. Plot Data screen - humidity .......................................................... 11
Figure 14. Plot Data screen - temperature ........................................................ 12
Figure 15. MotionFX algorithm flow ............................................................ 13
Figure 16. MotionFX algorithm flow - magnetometer function ...........................................14
Figure 17. MotionFX algorithm flow - accelerometer tilt compensation.....................................14
Figure 18. MotionFX algorithm flow - gyroscope function .............................................. 14
Figure 19. STBLESensor Compass and Level app - calibration icon ......................................15
Figure 20. STBLESensor Compass and Level app - starting the calibration ................................. 16
Figure 21. STBLESensor Compass and Level app - orientation screen ....................................17
Figure 22. STBLESensor Compass and Level app - offset example 1 .....................................18
Figure 23. STBLESensor Compass and Level app - offset example 2 .....................................19
Figure 24. Human Activity Recognition app ....................................................... 21
Figure 25. In-Vehicle Baby Alarm app - baby not crying state...........................................22
Figure 26. In-Vehicle Baby Alarm app - baby crying state ............................................. 23
Figure 27. Raw accelerometer data - user walking with the device ....................................... 24
Figure 28. Sensortile.box belt positioning ........................................................24
Figure 29. Pedometer app - step count .......................................................... 25
Figure 30. Sensor fusion app - Sensortile.box orientation (cube representation) ..............................26
Figure 31. Sensor fusion app - Sensortile.box orientation (plot) ......................................... 27
Figure 32. Sensor fusion app - Sensortile.box orientation (results) .......................................27
Figure 33. Sensor fusion app - enabling magnetometer calibration ....................................... 28
Figure 34. Sensor fusion app - enabling magnetometer calibration ....................................... 28
Figure 35. Vibration Monitoring app - event detection ................................................ 30
Figure 36. Example Apps screen .............................................................. 31
Figure 37. Input sources screen ............................................................... 32
Figure 38. Sensor data configuration screen ...................................................... 32
Figure 39. Custom app function screen .......................................................... 33
AL-MKSBOX1V1 (SensorTile.box) multi-sensor development kit..............................1
UM2580 - Rev 6
page 39/40
UM2580
IMPORTANT NOTICE – PLEASE READ CAREFULLY
STMicroelectronics NV and its subsidiaries (“ST”) reserve the right to make changes, corrections, enhancements, modifications, and improvements to ST
products and/or to this document at any time without notice. Purchasers should obtain the latest relevant information on ST products before placing orders. ST
products are sold pursuant to ST’
Purchasers are solely responsible for the choice, selection, and use of ST products and ST assumes no liability for application assistance or the design of
Purchasers’ products.
No license, express or implied, to any intellectual property right is granted by ST herein.
Resale of ST products with provisions different from the information set forth herein shall void any warranty granted by ST for such product.
ST and the ST logo are trademarks of ST. For additional information about ST trademarks, please refer to www
names are the property of their respective owners.
Information in this document supersedes and replaces information previously supplied in any prior versions of this document.
s terms and conditions of sale in place at the time of order acknowledgement.
.st.com/trademarks. All other product or service
© 2021 STMicroelectronics – All rights reserved
UM2580 - Rev 6
page 40/40
Loading...