4 July, 2019 – STMicroelectronics, has integrated machine-learning technology into its advanced inertial sensors to improve activity-tracking performance and battery life in mobiles and wearable’s.
During their annual media briefing, Vishal Goyal, Senior Manager -Technical Marketing, RF, Sensor and Custom Analog – South Asia AMG- Asia Pacific Region, ST share a mutual interaction perception.
Found Out about STMicroelectronics’s focus into Machine Learning and Finite State machine enabled sensors, Vibration and sound fusion, Sensor based algorithm generation tool, Ready-to-use box kit with wireless IoT and sensor.
The LSM6DSOX iNEMO sensor contains a machine-learning core to classify motion data based on known patterns. Relieving this first stage of activity tracking from the main processor saves energy and accelerates motion-based apps such as fitness logging, wellness monitoring, personal navigation, and fall detection.
Devices equipped with ST’s LSM6DSOX can deliver a convenient and responsive “always-on” user experience without trading battery runtime. The sensor also has more internal memory than conventional sensors, and a state-of-the-art high-speed I3C digital interface, allowing longer periods between interactions with the main controller and shorter connection times for extra energy savings.
The sensor is easy to integrate with popular mobile platforms such as Android and iOS, simplifying use in smart devices for consumer, medical, and industrial markets.
The LSM6DSOX is in full production and available now, priced from $2.50 for orders of 1000 pieces.
Further technical information:
The LSM6DSOX contains a 3D MEMS accelerometer and 3D MEMS gyroscope, and tracks complex movements using the machine-learning core at low typical current consumption of just 0.55mA to minimize load on the battery.
The machine-learning core works in conjunction with the sensor’s integrated finite-state machine logic to handle motion pattern recognition or vibration detection. Customers creating activity-tracking products with the LSM6DSOX can train the core for decision-tree based classification using Weka, an open-source PC-based application, to generate settings and limits from sample data such as acceleration, speed, and magnetic angle that characterize the types of movements to be detected.
Support for free-fall, wakeup, 6D/4D orientation, click and double-click interrupts allows a wide variety of applications such as user-interface management and laptop protection in addition to activity tracking. Auxiliary outputs and configuration options also simplify use in optical image stabilization (OIS).
SensorTile.box is a ready-to-use box kit with wireless Internet of things and a wearable sensor platform that helps you use and develop apps based on remote motion and environmental sensor data, regardless of your level of expertise.
The SensorTile.box board fits in a small plastic box with a long plastic rechargeable battery, and the STMicroelectronics BLE Sensor app on your smartphone connects to the board via Bluetooth and lets you quickly access the wide range of default Internet of things Allows to use. And wearable sensor applications.
You can build the Customs application from your selection of SensorTile.box sensors available in expert mode, operating parameters, data and output types and special functions and algorithms. This multi sensor kit therefore allows you too quickly and easily design wireless IoT and wearable sensor applications without any programming.
SensorTile.box includes a firmware programming and debugging interface that allows professional developers to engage in more complex firmware code development using the STM32 ODE, which includes an artificial intelligence function pack with neural network libraries.
AlgoBuilder is available with a new feature that allows you to send data to the cloud, run your application and perform machine learning calculations, everything in the cloud. This is one of the most important features for Industry 4.0 and is called AWS connectivity.
AlgoBuilder is an application for graphical design of algorithms. It extends prototypes of applications for STM32 microcontrollers and MEMS sensors, including pre-existing algorithms, user-defined data processing blocks, and additional functionality.
The application makes the process of implementing a proof of concept easier by using a graphical interface without writing code.
AlgoBuilder reuses previously defined blocks, adds multiple functionalities to a single project and visualizes data using Unicleo-GUI in real time using plots and displays.
Ready-to-use MEMS motherboard STEVAL-MKI109V3, this multi-platform GUI lets you easily set sensors, configure registers, and detect advanced features.
Unico GUI is supported by the STEVAL-MKI109V3 motherboard with all MEMS display boards and allows a quick and easy setup of the sensor, as well as complete configuration of all registers and advanced features embedded in the digital output device. The software visualizes the sensor’s output in both graphical and numeric format and allows the user to save or generally manage data coming from the device.
Interesting Attractions include LSM6DSOX iNEMO sensors:
The LSM6DSOX INEMO sensor includes a machine-learning core to classify motion data based on known patterns. Relieving this first step of tracking activity from the main processor saves energy and accelerates motion-based apps such as fitness-logging, wellness monitoring, personal navigation and fall detection.
Devices equipped with ST’s LSM6DSOX can provide a convenient and responsive “always on” user experience without battery runtime. The sensor has more internal memory than traditional sensors, and a state-of-the-art high-speed I3C digital interface, which allows for longer connection with the main controller and shorter connection times for additional energy savings.
Machine-learning core for classifying motion data based on known patterns. Relieving this first phase of tracking activity from the main processor saves energy and accelerates motion-based apps such as fitness logging, wellness monitoring, personal navigation and fall detection.
“Machine learning is already used for fast and efficient pattern recognition in social media, financial modeling or autonomous driving,” said Andrea Onetti, vice president of Analog, MEMS and Sensors Group, STMiroelectronics. “LSM6DSOX Motion Sensor integrates machine-learning capabilities to increase activity tracking in smartphones and wearable’s” he added.
This year’s all-round STMicroelectronics annual media briefing demonstrated the company’s leadership in growing MEMS and sensor technology.
Further information can be found at www.st.com.