Editors Blog – The weartech industry shapes up for sporting success

Wearable technology for sports can do more than record than record performance stats, of how far, how fast but can correct gait and style and alert them before injury strikes, writes Caroline Hayes

Next year, Tokyo will host the Olympics and the world will be gripped by the sporting prowess of nations and individuals for two weeks next summer. Winning an Olympic medal brings glory and pride and vindication of years of training, dedication and sacrifice. Making sure an athlete reaches their potential is the goal of coaches and managers at school, county and international level.

The wearable technology (weartech) for athletes industry is worth $2.8 billion today, up from $2 billion in 2018. Its scope goes far beyond monitoring heart rate while exercising. It encompasses intelligent data analysis that can improve performance but also indicate early signs of injury or health issues.

Don’t sweat it

Some interesting developments have been from North America. For example, the wearable patch developed by Kenzen that analyses the wearer’s sweat to assess fitness levels. It can determine levels of glucose, hydration and electrolyte. This is beyond what a heart rate monitor can achieve, explains the company, as these parameters indicate the level of fitness and how the body is reacting to stress.

Figure 1 Kenzen wearable patch Springwise

Figure 1: The Eco Smart Patch analyses a drop sweat to provide predictive data for sports and training (Picture credit: Kenzen)

The adhesive biosensor, the Eco Smart Patch (Figure 1) can provide real-time analysis from a single drop of perspiration to diagnose electrolyte balance, lactate and glucose levels based start-up Kenzen is developing a new peel-and-stick wearable sensor that will evaluate the content of sweat to provide a predictive analysis of your fitness and health.

The Kenzen biosensor, named the Eco Smart Patch, is designed to be worn 24/7 and will provide real-time analysis from a single drop of sweat – monitoring hydration levels, checking electrolyte balance – to ensure the body’s systems are functioning correctly and lactate blood levels – an imbalance can be caused by circulatory problems. Worn on the torso, the sensor is connected via Bluetooth to a smartphone app which sends an alert when the levels monitored reach pre-determined critical levels.

When the data is analysed, environmental factors, such as temperature and humidity are taken into account so that the wearer knows, for example, not just to hydrate but what electrolytes need to be replaced.

Kenzen partnered with its home football team, the San Francisco 49ers, whose players used the device in training.

GPS and the 40-yard line

Partnership with professional sports teams has been a key part of developing weartech. The Florida State University football team, Florida State Seminoles, rose up the league, as the team improved its performance and reduced pulled muscle, muscle strains and other soft tissue injuries by 88 per cent, when it adapted GPS monitors supplied by Australian technology company, Catapult Sports. Straps across the players’ chests were reprogrammed from Australian rules football to measure American football metrics.

The players were able to record dash times and receive immediate feedback on their on-pitch performances, leading to a new running practice and changed the training programme to reduce mid-week sessions so that the team was on top form for Saturdays.

Making a splash

Mud and sweat are part and parcel of some sports but developing reliable monitoring technology that can still operate when immersed in water is another hurdle altogether – if you will forgive me mixing my sporting metaphors!

How to monitor the speed and style of a swimmer is another challenge altogether. Canadian company, TritonWear has developed the waterproof Triton 2 which can be worn under the swimmer’s swimming cap which goes one better than watches that track the number of lengths completed – this use artificial intelligence (AI).

It can track 13 metrics simultaneously and transmit that data in real-time to an app on the coach’s smartphone (Figure 2).

Figure 2 screen

Figure 2: The Triton 2’s inertial measurement unit tracks a swimmer’s style and technique. (Picture credit: TritronWear)

The inertial measurement unit (IMU) combines an accelerometer and gyroscope to track stroke type, average speed per length, stroke rate, distance per stroke, time underwater and number of breaths per length. This data is recorded and displayed on the app on a mobile device and can be processed by AI-based algorithms. TritonWear says that these algorithms were developed in collaboration with coaches to not only ensure relevant data is gathered but that it can be analysed to provide suggestions for improvement or to avoid injury. TritonWear reports that automated load monitoring can keep the risk of injury during training to below five per cent.

A video of the swimmer in action, taken on the same mobile device can be synchronised with the performance analytics allowing the swimmer to see where errors may lie. By tracking training, in terms of volume and intensity, the swimmer can monitor load changes over time, receive alerts for injury risks and amend their training programme to safe in proscribed ‘safe zones’.

Figure 3 swim cap

Picture credit: TritonWear

This second generation weartech device’s firmware, Triton v1.1.19 has been updated with algorithms to recognise a dive-start, improvements to accuracy and timing, increased rejection of false starts, detected from stepping onto starting block, more accurate capture of repetition ends to increase timing accuracy and auto-calibration of sensors when the device is still for four to 10 seconds.

> Read More

Aaeon uses Jetson TX2 for AI edge computing

Embedded computer specialisr, Aaeon, has introduced the Boxer-8170AI, for artificial intelligence (AI) at the edge networks.

The embedded computer is based on Nvidia’s Jetson TX2 and has four PoE LAN ports and four USB 3.0 ports.

At the heart of the computer is the Nvidia Jetson TX2 6-core processor, created by pairing the dual Denver 2 and quad Arm 57 processors into a single system on chip (SoC). The design has up to 256 CUDA cores which provide speed and performance to power AI at the edge, says Aaeon. The Boxer-8170AI comes with 8Gbyte LPDDR4 memory and 32Gbyte eMMC storage on-board. It supports AI frameworks such as TensorFlow and Caffe, as well as AI inference software from developers and customers.

The Boxer-8170AI’s four PoE LAN ports each have their own dedicated chip. This allows for higher bandwidth and stability for each port, allowing PoE cameras to operate individually on dedicated connections, explains Aaeon. The Boxer-8170AI supports a maximum output of 60W for up to four PoE cameras. It can be used for a range of AI solutions incorporating PoE cameras such as smart retail, virtual fences, and access control.

I/O features include four USB 3.0 ports, allowing for additional cameras or devices to be connected to the system. The Boxer-8170AI also features two COM ports for easy integration into industrial systems, two HDMI ports, and remote on/off. The Boxer-8170AI connects to networks with a Gigabit LAN port and two antenna ports to connect to wireless networks or act as an artificial intelligence of things (AIoT) gateway. The BOXER-8170AI also features an SD Card slot and USB on-the-go (OTG) for easy maintenance.

For operation in harsh environments, the Boxer-8170AI has a fanless design and all- aluminium chassis to protect the system from dust, vibration and other hazards. The Boxer-8170AI operates in temperatures from -20 to +50 degrees C and has an input voltage range of 12 to 24V DC.

The company module is only 48 mm thick, to fit into almost the constrained space needed to power AI edge applications.

Established in 1992, Aaeon designs and manufactures professional IoT solutions. It is committed to innovative engineering and provides reliable computing platforms, including industrial motherboards and systems, industrial displays, rugged tablets, embedded controllers, network appliances and related accessories, as well as integrated solutions.

The company is an Associate Member of the Intel Internet of Things Solutions Alliance.

http://www.aaeon.com

> Read More

Secure flash memory enhances secure data storage in self-driving cars

Macronix’s secure flash memory has been integrated in Nvidia’s next-generation autonomous driving platforms.

The automotive-grade ArmorFlash memory is being used on the Nvidia Drive AGX Xavier and Drive AGX Pegasus autonomous vehicle computing platforms.

The ArmorFlash memory is secure for data storage in the artificial intelligence (AI)-based Level 2+ advanced driver assistance systems (ADAS) through to Level 5 autonomous driving.   

“Our efforts in conjunction with NVIDIA are singularly focused on elevating the security of data in AI-based autonomous driving applications and ultimately, to enhance the safety of drivers,” said Anthony Le, vice president of marketing, Macronix America.

The ArmorFlash memory on the Drive AGX Xavier and Pegasus platforms can provide trusted identification, authentication and encryption features for autonomous driving security requirements.

ArmorFlash offers a combination of mature security technologies, including unique ID, authentication and encryption features. This blend of features enables superior levels of security in a high-density memory device to prevent data from being compromised, claims Macronix.

The ArmorFlash device provides trusted NVM storage of encrypted and integrity-protected assets. The ArmorFlash supports secure communication channel and protocol with the Nvidia Xavier system on a chip (SoC) via cryptographic operations, integrity checks and additional measures against certain security protocol attacks.

The global ADAS market is expected to exceed $67 billion by 2025, fuelled by a compounded annual growth rate of 19 per cent, according to Grand View Research. The research company attributes the growth to increasing government initiatives mandating driver assistance system to lower road accidents and cites expanding adoption of ADAS in small cars as a factor boosting market demand.

http://www.macronix.com

> Read More

Speech inference is optimised for Intel FPGA PAC to save power demands

To save electricity consumption and to reduce data centre infrastructure, Myrtle announces that its artificial intelligence (AI) can run on the new, high-performance Intel FPGA Programmable Acceleration Card (Intel FPGA PAC) D5005 accelerator. The result is to reduce costs and remove growth constraints for businesses offering speech services such as transcription, translation, synthesis or voice assistance in on-premise or cloud-based data centres, says the AI specialist.

Intel and Myrtle have worked together to optimise a recurrent neural network (RNN) for speech inference on the Intel FPGA PAC D5005. The collaboration can run more than 4,000 voice channels concurrently on one FPGA, leading to a six-fold improvement in performance per watt compared with general purpose GPUs with a latency of one 30th that of a GPU, reports Myrtle.

“The industry has to take new approaches to produce machine learning solutions that meet customers’ stringent latency, power and cost constraints”, said Peter Baldwin, CEO, Myrtle. He added that these performance metrics on Intel’s latest PCA will allow customers preserve their investment in hardware as machine learning models evolve.

Myrtle specialises in hardware-software codesign. The quantisation, sparsity and compression of machine learning models has been recognised by the MLPerf consortium. Myrtle dominates MLPerf speech transcription and has open sourced its code to help the industry benchmark new edge and data centre hardware more consistently, says the company.

Myrtle creates high-performance, energy-efficient computing solutions for deep learning inferencing on next-generation data centre hardware. Myrtle’s RNN technology enables companies to cost-efficiently implement and scale speech applications on cloud or on-premise infrastructure.

Myrtle is a partner in Intel’s design solutions network (DSN).

http://www.myrtle.ai

> 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