STMicroelectronics, a global semiconductor leader serving a wide range of customers in electronics applications, announced new bio-sensing chips for next-generation healthcare wearables such as smart watches, sports bands, connected rings, and smart glasses. The ST1VAFE3BX chip combines high-precision biopotential inputs with ST’s proven inertial sensing and AI cores that perform on-chip activity detection to ensure faster performance with lower power consumption. .
“Wearable electronics are an important technology that enables individuals to improve their health awareness and fitness. Now, everyone has heart rate monitoring, activity tracking, and geolocation on their wrist.” said Simone Ferri, APMS Group Vice President and MEMS Subgroup General Manager at STMicroelectronics. “Our latest biosensor chips improve the performance of wearable devices, enabling motion and body signal sensing in an ultra-compact form factor with low power consumption.”
Yole Development analysts see opportunities for wearable monitors beyond the general wellness market, including consumer healthcare devices that are approved by medical institutions and available over-the-counter1. By creating complete high-precision sensor inputs in silicon, ST’s chip design experts are driving innovation in all fields with advanced features such as heart rate variability, cognitive function, and mental state. Masu.
ST1VAFE3BX offers the opportunity to extend wearable applications beyond the wrist to other locations on the body, such as intelligent patches for lifestyle and medical monitoring purposes. ST customers BM Innovations GmbH (BMI) and Pison are working at the forefront of this field and have quickly adopted new sensors to drive new product development.
BMI is an electronic design contractor with extensive experience in wireless sensing, with an extensive project portfolio that includes several cutting-edge heart rate and performance monitoring systems. “ST’s new biosensor enables us to develop next-generation accurate athlete performance monitoring systems, including ECG analysis on chest bands and small patches,” said Richard Mayerhofer, Managing Director of BM Innovation GmbH. states. “Combining analog signals from the vAFE and motion data from the accelerometer in a single, compact package facilitates accurate and context-aware data analysis. It also provides additional support for AI algorithms directly on the sensor. This is exactly what we were looking for.”
David Cipoletta, CTO of Pison, a developer focused on advanced technologies that improve health and human potential, added: “ST’s new biosensor stands out as an excellent solution for gesture recognition, cognitive performance, and neurological health in smartwatches. We are leveraging this advancement to significantly enhance the functionality and user experience of wearable devices. It has been strengthened.”
The ST1VAFE3BX is in production now in a 2mm x 2mm 12-lead LGA package and is available from eSTore (free samples available) and distributors starting at $1.50 in orders of 1000 pieces.
Visitors to the leading industry trade fair Electronica 2024 in Munich from 12 to 15 November will be able to see the ST1VAFE3BX in a sensing technology demonstration at the ST booth in Hall C3 101. For more information, please visit us online at www.st.com/biosensors.
Further technical information
Analog front-end circuits for biopotential sensors are difficult to design and are susceptible to unpredictable influences such as skin preparation and position of electrodes attached to the body. ST1VAFE3BX provides a complete vertical analog front end (vAFE) that simplifies the detection of various types of vital signs that may indicate physical or emotional conditions.
Manufacturers of wellness and healthcare equipment can therefore expand their product range to include functions such as electrocardiography (ECG), electroencephalography (EEG), seismic cardiography (SCG), and neuroelectrical testing (ENG). can. This could facilitate the emergence of new devices that are affordable, easy to use, and reliably indicative of physiological responses to health conditions and events such as stress and excitement. The future is likely to feature a wider variety of wearable devices that can contribute to improved health care, fitness, and self-awareness.
With this precision front end on-chip, the ST1VAFE3BX builds on ST’s established capabilities in MEMS (microelectromechanical systems) devices by integrating an accelerometer for inertial sensing. Accelerometers provide information about the wearer’s movements and are synchronized with biopotential sensing to allow applications to infer associations between measured signals and physical activity.
ST1VAFE3BX also integrates ST’s Machine Learning Core (MLC) and Finite State Machine (FSM), allowing product designers to implement simple decision trees for neural processing on-chip. These AI skills allow the sensor to autonomously handle functions such as activity detection, offloading the main host CPU to accelerate system response and minimize power consumption. In this way, ST’s sensors enable smart devices to offer more advanced functionality, longer operating times between battery charges, and improved ease of use. ST also offers software tools such as MEMS Studio in the ST Edge AI Suite to help designers extract maximum performance from the ST1VAFE3BX. This also includes tools for configuring decision trees in MLC.
The liveness detection signal channel of the ST1VAFE3BX consists of a vAFE with programmable gain and 12-bit ADC resolution. The maximum output data rate of 3200Hz is suitable for a variety of biopotential measurements to quantify heart, brain, and muscle activity.
The device operates from supply voltages ranging from 1.62V to 3.6V and has a typical operating current of only 50μA, which can be reduced to only 2.2μA in power-save mode.
The integrated low-noise accelerometer has a programmable full-scale range from ±2g to ±16g.
ST1VAFE3BX implements advanced pedometer, step detector, and step counting functionality, in addition to a machine learning core and programmable finite state machine that can provide features such as activity detection.
