MEMS sensors add machine learning in the edge and electrostatic sensing 

A third generation of MEMS sensors are intended for consumer mobiles and smart industries, healthcare, and retail.

MEMS technology drives the intuitive context-aware features of today’s smartphones and wearables. STMicroelectronics claims that its latest generation of MEMS sensors take performance beyond established technical limitations on output accuracy and power consumption. The new sensors can deliver the highest accuracy for product features such as activity detection, indoor navigation, and precision industrial sensing. At the same time, they keep battery demand low for longer runtimes.

Selected variants include extra features such as ST’s machine learning core (MLC) and electrostatic sensing. The MLC brings adaptive, machine learning capabilities to edge applications that operate at extremely low power. The charge variation (QVAR) sensing channel monitors changes in electrostatic charge, either through contact with the body in a smartwatch or fitness band or by non-contact sensing (radar). The MEMS sensors with QVAR can enhance user interface controls for seamless interactions or to simplify detection of moisture and condensation. Radar mode applications include human presence detection, activity monitoring and people counting.

The LPS22DF and waterproof LPS28DFW barometric pressure sensors operate from 1.7 microA and have absolute pressure accuracy of 0.5hPa. The LPS28DFW has dual full scale capability, enabling accurate vertical position both underwater and out of water. The full scale range is selectable up to 1260 or 4060hPa, equivalent to water pressure at a depth of about 98 feet (30m). The sensors enhance altimeter and barometer performance in portable devices and wearables including sport watches. Typical industrial applications include equipment for weather monitoring and accurate water-depth sensing.

The LIS2DU12 three-axis accelerometer has been designed to build a low power architecture with active anti-aliasing. The anti-aliasing filter operates with a current consumption among the lowest in the market, claims STMicroelectronics. The LIS2DU12 consumes only 3.5 microA at 100Hz output data rate (ODR) and is also the first accelerometer with I3C interface, according to the company. 

The accelerometer is a small footprint of 2.0 x 2.0 x 0.74mm. The accelerometer is designed for wearable devices, hearing aids, true wireless stereo (TWS) and wireless sensor nodes.

The LSM6DSV16X six-axis iNEMO inertial module contains QVAR electrostatic sensing as well as the MLC and a finite state machine (FSM). The operating current can be as little as 12 microA. The FSM enables adaptive self-configuration (ASC). With ASC, the device understands the context and reconfigures itself without waking up the system, gaining a significant extra power saving. 

The MEMS sensor will enter production and has been demonstrated in an electrostatic radar application for early user detection to accelerate waking-up a laptop PC.

The LPS22DF pressure sensor is supplied in a 2.0 x 2.0 x 0.73mm 10-lead LGA package and the LPS28DFW is supplied in a 2.8 x 2.8 x 1.95mm seven-lead LGA are in production now. Free samples are available. The LIS2DU12 and LSM6DSV16X are scheduled for production later in 2022.

http://www.st.com

> Read More

STMicroelectronics integrates AI to MEMS sensors

Signal processing and AI algorithms have been combined in MEMS (micro electromechanical systems) sensors by STMicroelectronics. The Intelligent Sensor Processing Unit (ISPU) injects local decision-making while substantially saving space and power, says the company.

The ISPU combines a digital signal processor (DSP) able to run AI algorithms and a MEMS sensor on the same silicon. In addition to a reduction in size, compared to system-in-package devices, the ISPU is also claimed to cut power by up to 80 per cent. Merging sensor and AI puts electronic decision-making at the edge, said ST, where products enabled by smart sensors are able to sense, process, and take actions, in what has been called the Onlife Era, fusing technology and the physical world.

The Onlife Era acknowledges living with continuous assistance from connected technologies, enjoying natural, transparent interactions, and seamless transitions, with no discernible distinction between online and offline, ST explained. The ISPU allows the migration of intelligent processing into sensors that support the fabric of life, or as ST puts it: no longer at the edge but in the edge. 

The proprietary low power DSP can be programmed in C, a language familiar to many engineers. It also allows quantised AI sensors to support full- to single-bit-precision neural networks. This ensures superior accuracy and efficiency in tasks such as activity recognition and anomaly detection by analysing inertial data, said ST.

“While technically challenging, integrating ST’s sensors on the same piece of silicon with our ISPU does improve sensor-based systems from an online experience to an Onlife one,” said Andrea Onetti, executive vice president, MEMS Sub-Group, at STMicroelectronics.

“It advances the sensor’s features to speed decision-making by reducing data transfers, enhancing privacy by keeping data local, while reducing size and power consumption, which cuts costs,” he added.

“Moreover, the ISPU is easily programmable with commercial AI models and can ultimately operate with all of the leading AI tools.” 

ST’s proprietary, C-language-programmable DSP is an enhanced 32-bit RISC (reduced instruction set computing) machine. It is extensible (in the chip-design phase) for dedicated instructions and hardware components. The processor offers a full precision floating point unit, uses a fast four-stage pipeline, operates from 16-bit variable-length instructions, and includes a single-cycle 16-bit multiplier. Interrupt response is four cycles. 

ST’s sensors with ISPUs will be packaged in standard 3.0 x 2.5 x 0.83mm packages and will be pin compatible with earlier models available from the company, for ease of upgrades.

ST also claims that combining the sensor and ISPU save five to six time power saving compared with system-in-package approaches in sensor-fusion applications. They also show a two to three times saving in Run mode. 

http://www.st.com

> Read More

Sensor development kit delivers AI/ML for smart industrial applications

AI tool developer, SensiML has teamed up with onsemi to deliver ML for autonomous sensor data processing and predictive modelling. SensiML develops AI tools for building intelligent IoT endpoints. Its analytics toolkit development software has been combined with the RSL10 sensor development kit from onsemi for edge sensing applications such as industrial process control and monitoring. SensiML can support AI functions in a small memory footprint, and the RSL10 provides advanced sensing and Bluetooth Low Energy connectivity for smart sensing without the need for cloud analytics of highly dynamic raw sensor data.

Claimed to have the industry’s lowest power Bluetooth Low Energy connectivity,  the RSL10 sensor development kit combines the RSL10 radio with a range of environmental and inertial motion sensors onto a tiny form factor board that interfaces with the SensiML Toolkit. Developers using the RSL10-based platform and the SensiML software together can add low latency local AI predictive algorithms to industrial wearables, robotics, process control, or predictive maintenance applications regardless of expertise in data science and AI. 

The auto-generated code enables smart sensing embedded endpoints that transform raw sensor data into critical insight events where they occur and can take appropriate action in real time. The smart endpoints reduce network traffic by communicating data only when it offers valuable insight.

“Cloud-based analytics add unwanted, non-deterministic latency, and are too slow, too remote and too unreliable for critical industrial processes,” said Dave Priscak, vice president of Applications Engineering at onsemi. 

“Other AutoML solutions for the edge rely only on neural network classification models with only rudimentary AutoML provisions, yielding suboptimal code for a given application,” adds Chris Rogers, SensiML’s CEO. The company’s AutoML model search includes neural networks with an array of classic ML algorithms, as well as segmenters, feature selection, and digital signal conditioning transforms, he explains.

The SensiML analytics toolkit is available now from SensiML and the RSL10 sensor development kit is available now from onsemi.

 http://www.sensiml.com

> Read More

Intelligent sensors automatically sense human presence

Three sensors, the PerSe Connect, PerSe Connect Pro and PerSe Control, have been released by Semtech.  They can be used in smartphones, laptops and wearables.

The PerSe sensors intelligently sense human presence near the mobile device and other consumer electronics, and enable advanced RF control when the user is in close proximity. The smart human sensing feature, low power and tiny footprint enable the sensors to be used in a range of wearable applications, such as gesture control and automation. 

Consumer electronics manufacturers can integrate the sensors for connectivity in 5G/Wi-Fi 6 with increased RF performance in smartphones and laptops, while also helping ensure compliance with the worldwide Specific Absorption Rate (SAR) regulations, explains Semtech. PerSe is claimed to provide best-in-class sensing and robust noise immunity allowing OEMs and ODMs to design devices with longer detection distance within a smaller sensor area.

The PerSe Connect sensor enhances connectivity for smartphones and laptops (5G Sub-6, 4G and Wi-Fi). They help optimise the RF power for best connectivity and help to maintain SAR compliance while delivering a fast wireless experience, says Semtech. 

The PerSe Connect Pro is designed for high band 5G mmWave devices in smartphones, laptops and tablets. It enables higher sensing distance to safely manage the increased RF exposure, confirms Semtech. 

The third model is PerSe Control which enables smarter control in wearables. It enables human detection, automatic on/off and start/stop response. It also delivers gesture control and response including smart assistant, noise cancellation activation and media player control.

“Smart sensors, such as the PerSe portfolio from Semtech, can differentiate between humans and inanimate objects, including handheld positions. This advanced sensing capability is essential for mobiles, wearables and 5G mmWave devices to deliver a superior user experience,” said Joe Hoffman, director, intelligent edge and sensor technologies research at SAR Insight. “Mobile, portable and wearable devices complicate the design window of performance, battery life and human RF absorption,” he added. 

http://www.semtech.com

> Read More

About Smart Cities

This news story is brought to you by smartcitieselectronics.com, the specialist site dedicated to delivering information about what’s new in the Smart City Electronics industry, with daily news updates, new products and industry news. To stay up-to-date, register to receive our weekly newsletters and keep yourself informed on the latest technology news and new products from around the globe. Simply click this link to register here: Smart Cities Registration