Knowledge base

Selecting the right part BMA456 is 16bit, digital, triaxial acceleration sensor with intelligent on-chip motion triggered interrupt features optimized for wearable and hearable applications. BMA456 support different advanced features via different configure file. Table 1 shows an overview of the features. Parameter BMA456 Digital resolution 16bit Range and sensitivity +/-2g: 16384LSB/g +/-4g: 8192LSB/g +/-8g: 4096LSB/g +/-4g: 2048LSB/g Zero-g offset(typ.) +/-20mg Noise density(typ.) 120µg/√Hz Bandwidths 5Hz …684Hz Interfaces SPI & I2C, 2 x digital interrupt pins Supply voltage VDD: 1.62 to 3.6V VDDIO: 1.2 to 3.6V LGA package(mm3) 2.0 x 2.0 x 0.65 Feature/Interrupts Step Counter/Step detector (optimized for wearables) Activity recognition: running, walking, still Tilt on wrist Tab/Double Tab Any-motion/No-motion High-g/ low-g Table 1: Overview BMA456 features Common characteristics The main characteristics of this product family are: Key features: 2.0 x 2.0 mm² size Pin to pin compatibility with all other 2.0 x 2.0 accelerometers from Bosch Sensortec SPI or I²C interface Configurable range from ±2G to ±16g Configurable output data rate up to 1.6kHz Integrated 1kB FIFO Auxiliary I²C interface for connecting external magnetometer, including data synchronization Built-in smart interrupt controller, with features such as step-counter which offers high performance for all wearing positions, including wrist-worn. BMA456 parameters BMA456 offers higher performance and stability in a smaller package. See the complete description in Table 2. Parameter BMA456 Units Height 0,65 mm Digital resolution 16 bits Zero-g offset (typ.) ±20 mg Noise density (typ.) 120 µg/√Hz TCO (X&Y axis) 0.2 mg/K TCO (Z axis) 0.35 mg/K TCS 0.005 %/K Cross Axis Sensitivity 0.5 % Table 2: BMA456 parameter value Available evaluation tools and software To best to evaluate the products from the BMA456 family, we recommend the following combination of evaluation tools: COINES Desktop software Application board 3.0 Sensor Shuttle board BMA456 Shuttle board. Layout recommendations Because the BMA4xy sensor family contains tiny mechanical structure inside the package, care must be taken during the layout phase to ensure the best performance. The complete handling and soldering guide can be found on the Bosch Sensortec's website. First power-on After powering the sensor for the first time, the initial specs would be to test for communication with the device. This can be done simply by reading the chip identification code in the register 0x00. See below for the expected values: Device Chip ID BMA456 0x16 Table 3: Chip IDs of the BMA4xy product family Here is some sample code on how to perform this test, based on BMA456, using the COINES software as the host. /*!  * @brief This internal API is used to initializes the bma456 and verify the  *communication by reading the chip id.  *  * @param[in] void  * @return void  *  */ static void init_comm_test_bma456(void) {     int8_t rslt;                    struct bma4_dev bma456dev = { 0 };       rslt = bma4_interface_init(&bma456dev, BMA4_I2C_INTF, BMA45X_VARIANT);     rslt = bma456_init(&bma456devbma425dev);     if (rslt == BMA4_OK)     {         printf("BMA456 Initialization Success!\n");         printf("Test #1: Communication. PASSED. Chip ID 0x%x\n", bma456dev.chip_id);     }       else     {         char err_string[255];         printf("BMA456 Initialization Failure!\n");                                        if (BMA4_E_INVALID_SENSOR == rslt)         {              sprintf(err_string, "Test #1: Communication. FAILED. Expected Chip ID: 0x%x. Received 0x%x\n",\                             BMA456_CHIP_ID, bma456dev.chip_id);         }         else         {              sprintf(err_string, "Test #1: Communication. FAILED. No response from the sensor.");         }                                        coines_exit_error(err_string);     }     coines_delay_msec(100); } How to test the sensor's functionality The BMA4xy series of accelerometers feature a fully integrated and motionless self-test procedure on the ASIC itself. When the self-test is triggered, the accelerometer uses electric fields to physically move the electrodes in all directions, senses the deflection and compares it with the expected output. Therefore, the built-in self-test features is the recommended way to test the sensor's functionality. Here is some sample code on how to perform this self-test, based on BMA456, using the COINES software as the host. /*!  * @brief This internal API is used to test if the sensor is working by triggering the self-test.  *  * @param[in] void  * @return void  *  */ static void function_test_bma456(void) {     uint16_t rslt;     uint8_t testrslt;       rslt = bma4_perform_accel_selftest(&testrslt, &bma456dev);                    if ( 0 != rslt ) coines_exit_error("Test #2: Functionnality. FAILED. Unknown communication error\n");                if ( BMA4_SELFTEST_PASS == testrslt ) {         printf("Test #2: Functionnality. PASSED. Sensor self-test successful\n");     } else {         printf("Test #2: Functionnality. FAILED. Sensor self-test failed\n");     }                } How to test the sensor's performance There are 2 performance parameters that can easily be tested with the device motionless: offset and noise. See below for the typical values of the sensors. Note: Typical values are defined as ±1σ, which means that we expect 68.3% of sensors to fall within these values. Min/Max values are defined as ±3σ, which means 99.7% of sensors shall be within these values. Parameter BMA456 units Offset ±20 mg Noise 120 µg/√Hz Table 4: Typical performance of BMA456 For the offset, the test procedure is quite simple. With the device in a known position, such as a flat surface, calculate the average value for each axis, and substract the expected output (e.g. 0G, 0G, +1G) from the data. The result is the offset of the sensor. Here is some sample code on how to perform this test, based on BMA456, using the COINES software as the host. /*! Average value calculation */ double x_avg_mg=0; double y_avg_mg=0; double z_avg_mg=0; for (int i=0; i<1000; ++i) {     double xval, yval, zval;     /* ( 'datapoint' * '4G' * '2' * '1000mg') / ('scaling factor for 16 bits') */     xval = (((double)sens_data[i].x) * 4. * 2. * 1000) / pow(2,16);     yval = (((double)sens_data[i].y) * 4. * 2. * 1000) / pow(2,16);     zval = (((double)sens_data[i].z) * 4. * 2. * 1000) / pow(2,16);                                    x_avg_mg += xval / 1000.;     y_avg_mg += yval / 1000.;     z_avg_mg += zval / 1000.; }                /*! Offset Calculation */ double x_off_mg=x_avg_mg - X_REST_POSITION_MG; double y_off_mg=y_avg_mg - Y_REST_POSITION_MG; double z_off_mg=z_avg_mg - Z_REST_POSITION_MG;                if( OFFSET_THRESHOLD_MG > x_off_mg && OFFSET_THRESHOLD_MG > y_off_mg && \                                OFFSET_THRESHOLD_MG > z_off_mg ) {     printf("Test #3: Performance. Offset. PASSED: X=%4.1lfmg Y=%4.1lfmg Z=%4.1lfmg Threshold <\        %4.1lf\n",       x_off_mg, y_off_mg, z_off_mg, OFFSET_THRESHOLD_MG); } else {     printf("Test #3: Performance. Offset. FAILED: X=%4.1lfmg Y=%4.1lfmg Z=%4.1lfmg Threshold <\ %4.1lf\n", x_off_mg, y_off_mg, z_off_mg, OFFSET_THRESHOLD_MG); } The noise calculation is a bit more complicated. First, subtract the offset from each datapoint. The RMS value can be calculated as the square root of the arithmetic mean of the squares of the noise values.  x_rms = sqrt[1/n( x_1^2 + x_2^2 + .... + x_n^2)] Since the noise value is affected by the bandwidth of the digital filter, we need to convert it back to noise density with the following formula. Note: this applied only to a second order filter noise_density = noise_RMS/[sqrt(1.22 x bandwidth)] Here is some sample code on how to perform this test, based on BMA456, using the COINES software as the host. /*! RMS Noise Calculation */ double x_rms_noise_mg=0; double y_rms_noise_mg=0; double z_rms_noise_mg=0; for (int i=0; i<1000; ++i) {     double xval, yval, zval;     /* ( 'datapoint' * '4G' * '2' * '1000mg') / ('scaling factor for 12 bits') */     xval = (((double)sens_data[i].x) * 4. * 2. * 1000.) / pow(2,16);     yval = (((double)sens_data[i].y) * 4. * 2. * 1000.) / pow(2,16);     zval = (((double)sens_data[i].z) * 4. * 2. * 1000.) / pow(2,16);                                    x_rms_noise_mg += pow(xval - x_avg_mg,2) / 1000.;     y_rms_noise_mg += pow(yval - y_avg_mg,2) / 1000.;     z_rms_noise_mg += pow(zval - z_avg_mg,2) / 1000.; }                /* rms noise is the square root of the arithmetic mean of the squares of the noise values */ x_rms_noise_mg = sqrt(x_rms_noise_mg); y_rms_noise_mg = sqrt(y_rms_noise_mg); z_rms_noise_mg = sqrt(z_rms_noise_mg);                /*! RMS Noise to RMS noise density convertion */ /* noise density = RMS noise  / sqrt ( 1.22 * bandwidth) */ /* BMA456 has 40.5Hz bandwidth at 100Hz normal mode */   double x_noise_dens_ug = 1000 * x_rms_noise_mg / sqrt(1.22 * 40.5); double y_noise_dens_ug = 1000 * y_rms_noise_mg / sqrt(1.22 * 40.5); double z_noise_dens_ug = 1000 * z_rms_noise_mg / sqrt(1.22 * 40.5);   if( NOISE_THRESHOLD_MG > x_noise_dens_ug &&                                NOISE_THRESHOLD_MG > y_noise_dens_ug &&                                NOISE_THRESHOLD_MG > z_noise_dens_ug ) {     printf("Test #3: Performance. Noise. PASSED: X=%4.1lfug/sqrt(Hz) Y=%4.1lfug/sqrt(Hz) \ Z=%4.1lfug/sqrt(Hz) Threshold < %4.1lf\n", x_noise_dens_ug, y_noise_dens_ug, z_noise_dens_ug,\ NOISE_THRESHOLD_MG); } else {     printf("Test #3: Performance. Noise. FAILED: X=%4.1lfug/sqrt(Hz) Y=%4.1lfug/sqrt(Hz) \   Z=%4.1lfug/sqrt(Hz) Threshold < %4.1lf\n", x_noise_dens_ug, y_noise_dens_ug,\ z_noise_dens_ug,NOISE_THRESHOLD_MG);   } Calibrating the sensor The first question to ask concerning calibration is whether it is required for the intended application. Accelerometer calibration mainly consists of calibrating the accelerometer's offset. The main impact for this is in tilt-sensing application, where the offset will induce an error in the measurement of the horizon. The accelerometer comes from the factory pre-trimmed, but the soldering process and PCB bending due to assembly can vary the offset, therefore it is preferable to calibrate the accelerometer after assembling the device into the device housing. Pre- and post-calibration accuracy     Sample code The calibration procedure is outlined in the inline calibration application note. Here is some sample code on how to perform this calibration, based on BMA456, using the COINES software as the host. Note : Although the concept is the same, the BMA4xy family of accelerometers does not include a built-in offset calculation on the ASIC. Since the offset are calculated inside of the Sensor API itself, it allows for a much more flexible target position.  rslt = bma456_init(&bma456dev); if (rslt == BMA4_OK) {     printf("BMA456 Initialization Success!\n"); } else {                  coines_exit_error("BMA456 Initialization Failure!\n"); } coines_delay_msec(100); rslt = bma456_write_config_file(&bma456dev); /* Enable the accelerometer */ rslt = bma4_set_accel_enable(BMA4_ENABLE, &bma456dev); /* Set the accel configurations */ struct bma4_accel_config accel_conf = { 0 }; accel_conf.odr = BMA4_OUTPUT_DATA_RATE_50HZ; accel_conf.bandwidth = BMA4_ACCEL_NORMAL_AVG4; accel_conf.perf_mode = BMA4_CIC_AVG_MODE; accel_conf.range = BMA4_ACCEL_RANGE_8G; rslt = bma4_set_accel_config(&accel_conf, &bma456dev); dev.delay_us(20000, dev.intf_ptr);                         if (rslt == BMA4_OK) {     /* Set accel foc axis and it's sign (x, y, z, sign)*/ struct bma4_accel_foc_g_value g_value_foc = { 0, 0, 0, 0 };       rslt = bma4_perform_accel_foc( &g_value_foc, &bma456dev);                          if (rslt == BMA4_OK) {         printf("BMA456 perform FOC successful!\n");         /* Delay after performing Accel FOC */         dev->delay_us(30000, bma456dev ->intf_ptr);         /*! calculates the offset after compensation */         rslt = bma4_read_regs(BMA4_OFFSET_0_ADDR, data_array, 3, & bma456dev);         printf("Post-calibration offset : X=%4.1lfmg Y=%4.1lfmg Z=%4.1lfmg", data_array[0],\                data_array[1], data_array[3]);     } else {                  coines_exit_error("Unknown communication error. Exiting...\n");     } } Once the offsets are determined, they can be written into the NVM so that the sensor automatically compensates for the soldering offset even after physically removing the power. Here is some sample code on how to save calibration data to NVM, based on BMA456, using the COINES software as the host. /*!  * @brief This internal API is used to update the nvm content  *  * @param[in] void  * @return void  *  */ static void bma456_update_nvm(void) {     uint16_t rslt;     uint8_t data;       /* unlocks the NVM for writing */     data = 0x02;     bma4_write_regs(0x6A, &data, 1, &bma456dev);                    /* makes sure the BMA456 is not executing another command */ do {         rslt = bma4_read_regs(BMA4_STATUS_ADDR, &data, 1, &bma456dev);         if ( 0 != rslt ) coines_exit_error("Unknown communication error. Exiting...\n");     } while ( 0 == (data&0x10) );                    /* performs the writing of the NVM */     rslt = bma4_set_command_register( 0xA0,  &bma456dev);     if ( 0 != rslt ) coines_exit_error("Unknown communication error. Exiting...\n");                        /* wait for the command to be completed */ do {         rslt = bma4_read_regs(BMA4_STATUS_ADDR, &data, 1, &bma456dev);         if ( 0 != rslt ) coines_exit_error("Unknown communication error. Exiting...\n");     } while ( 0 == (data&0x10) );                    /* locks the NVM writing */     data = 0x00;     bma4_write_regs(0x6A, &data, 1, &bma456dev); }   Further reads Datasheets: BMA456 Datasheet Application notes: Inline calibration of accelerometers Handling, soldering and mounting instructions, Accelerometers HSMI  

Introduction Accelerometer (Acc), Gyroscope (Gyro) and Magnetometer (Mag) sensors (components) have their own coordinates. By default BHA and BHI are configured to ENU axis convention (East-North-Up), as commonly used in consumer electronic devices. It is usually obtained by the integration of Accelerometer (Acc), Gyroscope (Gyro) and Magnetometer (Mag) sensors readings. The ENU coordinate system is defined as a direct orthonormal basis where:     x points east and is tangential to the ground.     y points north and is tangential to the ground.     z points towards the sky and is perpendicular to the ground.  Users can download the BHI/BHA firmware from Bosch Sensortec Website. All firmware’s coordinates are the same. Figure 2(left) shows the coordinate of the BHI/BHA shuttle board. Cares must be taken that the direction of BHI/BHA and Magnetometer sensor must follow the BHI/BHA shuttle board when customer do the PCB placement. Figure 2(right) shows the direction of BHI/BHA and Magnetometer on the shuttle board. It is the easiest and best way that customer can reuse the same coordinate of BHI/BHA shuttle board on their product. It is possible to change the coordinate based on customer definition. This document is to tell the customer the way how to do the axis-remapping on their products. Axes definition Define the coordination of your board (X BOARD, Y BOARD, Z BOARD ). Normally this is the default coordination system of your final application (i.e. your system coordination). In standard Android system the ENU (east north up) orientation is required. For other applications, the Z BOARD is normally pointing to the sky or ground when the board is placed on a horizontal surface. Find the coordinates of the sensors mounted on the board in their datasheets. Draw all the coordinates on the paper. Figure 3 shows an example. In Figure 3, it is highly recommended to follow the placement on the BHI160 shuttle board, if the user do not want to pay more effort on it.  If you are using a standard Bosch sensor, their coordinates follow the right-handed coordinate principle (Figure 4). You can apply it to find the sensor axes when it placed on the board.   Orientation matrix When the sensors axes orientation are different to the board, we need to convert it to the board coordinate by following formula: [X Y Z] is the board coordinate [Xs Ys Zs] is the sensor coordinate (C 0 … C 8 ) is the orientation matrix. The coefficient has three possible value: 1, 0 and -1. 1 --- Two axes are paralleled and have same direction -1 --- Two axes are paralleled and have opposite direction 0 --- Two axes are perpendicular Example If we have a board shown in Figure 3. On this board, there are a BHI160 and a BMM150. The dots on the sensor indicate their coordinates. You can try to find the coordinates and write the orientation matrix. Table 1shows the result. Orientation matrix: C s = (0 -1 0 1 0 0 0 0 1), Updating via product API (Host side) Basic configuration When customer follow the requirement (components placement), so only one matrix is needed for the sensor(A,M,G). Users can configure the axes before enable the BHI160/BHA250 by editting the remapping matrix in its .c file. The following code is content of the accelerometer_remapping_example.c in the API. Use this as a reference to update your matrix accordingly. The matrix can also be edited within the product API which is available on GitHub: https://github.com/BoschSensortec/BHy1_driver_and_MCU_solution int main(void) { u8 array[ARRAYSIZE], *fifoptr, bytes_left_in_fifo=0; u16 bytes_remaining, bytes_read; bhy_data_generic_t fifo_packet; bhy_data_type_t packet_type; BHY_RETURN_FUNCTION_TYPE result; s8 mapping[9] = {0}; s8 mapping_all[9] = {0 -1 0 1 0 0 0 0 1}; // new mapping matrix, example on Figure3 … … /* config mapping matrix, it is not necessary to change mapping matrix if its orientation is aligned with the board */ bhy_get_mapping_matrix(PHYSICAL_SENSOR_INDEX_ACC,mapping); // get current ACC mapping matrix bhy_set_mapping_matrix (PHYSICAL_SENSOR_INDEX_ACC,mapping_all); // set new mapping matrix in the fw bhy_get_mapping_matrix(PHYSICAL_SENSOR_INDEX_ACC,mapping); // check if the matrix is set successfully … … bhy_get_mapping_matrix(PHYSICAL_SENSOR_INDEX_GYRO,mapping); // get current GYRO mapping matrix bhy_set_mapping_matrix (PHYSICAL_SENSOR_INDEX_GYRO,mapping_all); // set new mapping matrix in the fw bhy_get_mapping_matrix(PHYSICAL_SENSOR_INDEX_GYRO,mapping); // check if the matrix is set successfully … … bhy_get_mapping_matrix(PHYSICAL_SENSOR_INDEX_MAG,mapping); // get current MAG mapping matrix bhy_set_mapping_matrix (PHYSICAL_SENSOR_INDEX_MAG,mapping_all); // set new mapping matrix in the fw bhy_get_mapping_matrix(PHYSICAL_SENSOR_INDEX_MAG,mapping); // check if the matrix is set successfully ​ Advanced configuration If the sensor placement is not followed the Shuttle Board, the user can configure matrix for each sensor. In this configuration, customer can place the sensor on the board as they need(no need to follow the chip placement on shuttle board). int main(void) { u8 array[ARRAYSIZE], *fifoptr, bytes_left_in_fifo=0; u16 bytes_remaining, bytes_read; bhy_data_generic_t fifo_packet; bhy_data_type_t packet_type; BHY_RETURN_FUNCTION_TYPE result; s8 mapping[9] = {0}; s8 mapping_ACC[9] = {0 -1 0 1 0 0 0 0 1}; // new mapping matrix, example on Figure3 s8 mapping_GYRO[9] = {0 -1 0 1 0 0 0 0 1}; // s8 mapping_MAG[9] = {0 -1 0 1 0 0 0 0 1}; // can be different … … /* config mapping matrix, it is not necessary to change mapping matrix if its orientation is aligned with the board */ bhy_get_mapping_matrix(PHYSICAL_SENSOR_INDEX_ACC,mapping); // get current ACC mapping matrix bhy_set_mapping_matrix (PHYSICAL_SENSOR_INDEX_ACC,mapping_ACC); // set new mapping matrix in the fw bhy_get_mapping_matrix(PHYSICAL_SENSOR_INDEX_ACC,mapping); // check if the matrix is set successfully … … bhy_get_mapping_matrix(PHYSICAL_SENSOR_INDEX_GYRO,mapping); // get current GYRO mapping matrix bhy_set_mapping_matrix (PHYSICAL_SENSOR_INDEX_GYRO,mapping_GYRO); // set new mapping matrix in the fw bhy_get_mapping_matrix(PHYSICAL_SENSOR_INDEX_GYRO,mapping); // check if the matrix is set successfully … … bhy_get_mapping_matrix(PHYSICAL_SENSOR_INDEX_MAG,mapping); // get current MAG mapping matrix bhy_set_mapping_matrix (PHYSICAL_SENSOR_INDEX_MAG,mapping_MAG); // set new mapping matrix in the fw bhy_get_mapping_matrix(PHYSICAL_SENSOR_INDEX_MAG,mapping); // check if the matrix is set successfully   For more details and technical support with respect to the product API the *.h file and the MCU porting please refer to the Bosch Sensortec documents “MCU Driver Porting Guide” and “Interfacing Reference Code from Generic Driver” for BHA and/or BHI placed within the section “Application notes”, available onhttps://www.bosch-sensortec.com/bst/support_tools/downloads/overview_downloads Check the orientation After the orientation matrix has been updated, you need to check whether the remapping is successful. You can read the uncalibrated data of the sensors to check if the remapping is successful. Please define the coordination of the board (X BOARD, Y BOARD, Z BOARD ) first. Check the Acc axes (XA, YA, ZA) Enable Acc uncalibrated data; Place the board on a horizontal surface and make sure Z BOARD is pointing to the sky. Z-axis should output 1g. Turn the board at perpendicular position and make sure X BOARD is pointing to the sky. X-axis should output 1g. Turn the board at perpendicular position and make sure Y BOARD is pointing to the sky. Y-axis should output 1g. Check the Gyro axes (XG, YG, ZG) If you use BHI160, the axes of Acc and Gyro are same. In Bosch product, a Gyro axis direction can be found by your right hand. Move your four fingers follow the rotation direction to make a fist and the thumb will be pointing to the positive axis like Figure 5 (This is similar to right-hand crew rule). Enable Gyro uncalibrated data; Place the board on a horizontal surface and make sure Z BOARD is pointing to the sky. Quickly rotate left 180 degree. The output has significant change is the rotation axis. It should be z-axis and output positive data. Rotate the board according to X BOARD and Y BOARD . Check the output with right-hand crew rule respectively. Check the Mag axes (XM, YM, ZM) Method 1 Enable Mag uncalibrated data and only log the first three data, which is the original data; Place the board on the table and make sure the X BOARD is pointing to the planet's North Pole by using a reference compass. Record the (X M, Y M, Z M ) stable output below. Then Point X BOARD to planet's South Pole and record the stable output. The axis output has the maximum difference is parallel to X BOARD Here |X 1 - X 2 | should be the largest, and X 1 > X 2 . Then the remapping is correct.   Apply same method to Y BOARD, Z BOARD to find if the orientation of other two axes are correct.  Method 2 1.Enable Mag uncalibrated data and only log the first three data; 2.Rotate the board in following steps and record the output data: If X1>X2 & X4>X3, min(X1,X2,X3,X4)=X2, and max(X1,X2,X3,X4)=X4; Y1>Y2 & Y4>Y3, min(Y1,Y2,Y3,Y4)=Y3, and max(Y1,Y2,Y3,Y4)=Y1; Z2>Z1. Then the remapping is correct.  

The Arduino Nicla Sense ME board featuring a rich set of Bosch Sensortec sensors is a robust and versatile development board that enables users to develop smart sensing applications. This series of tutorial videos aim to help users to get started and familiar with the board and quickly explore some of the functionalities and resources around it.  

Please find attached the two white papers for our BHI260AP self-learning AI sensor: White paper: Me, myself and AI How the new self-learning AI sensor pesonalizes your home workout Fitness tracking is presently experiencing a huge upswing in popularity. The market for fitness trackers and step counters has surged by 65% year-on-year [1], with just the Fitbit platform alone claiming nearly 30 million active users [2]. Current activity tracking devices have demonstrated the huge market potential of this segment and have laid the groundwork for next-generation AI-enabled devices to take centre stage as individual fitness tracking goes mainstream. White paper: Swim like a fish with Artificial Intelligence Combining AI and sensors to create a new generation of intelligent wearables Artificial intelligence (AI) is rapidly becoming a natural and integral part of our everyday lives – working silently and unnoticed in the background. AI makes sense of the multitude of data streaming in from various sensors to deliver detailed and precise insights, which have the potential to increase the utility of virtually all electronic devices on the market today. This defining technology can accurately determine whether the user of a device is walking, running, sitting, sleeping – or even swimming in real-time. This article explores how sensors synergize with AI in wearables to deliver valuable information to users – even in demanding environments like swimming pools.

The last few years have seen a remarkable increase in the number of use cases involving barometric pressure sensors in consumer electronics devices such as smartphones, tablets, wearable devices, and various home appliances. Barometric pressure sensors have been used for ambient air pressure measurement for several decades, however, recent developments and improvements in both these sensors and the devices in which they are installed have paved the way to superior performance and lower costs. The barometric pressure sensor has found its place across a wide range of products, no longer limited to traditional "weather stations". Today’s barometric pressure sensors are so incredibly accurate that they can determine altitude to within just a few centimeters. This, coupled with low-cost manufacture, has made these sensors the mainstays for motion tracking, enabling what had previously been solely the realm of science fiction. This paper will describe the two primary types of technologies used for pressure sensors, capacitive and piezoresistive, and subsequently, focus on several applications and key requirements.