Adlink takes pallets to the edge with robotic communication

Digital and analogue assets can communicate and collaborate, says Adlink, using its Edge and Vortex DDS edge IoT products. 

The company’s edge IoT products can add intelligence to conveyors. They also find missing inventory, automate bin picking, determine fill levels and connect robots  − all in real-time. Daniel Collins, Adlink IoT director for North America said: “By bringing artificial intelligence (AI) to the edge we’re helping to automate warehouse logistics in a quick and cost-effective way that increases productivity and employee ergonomics. One of our customers decreased the time it takes to build a pallet by 41 per cent, increasing total daily throughput by 200 per cent without disrupting the way employees are used to working.”

The Adlink Edge and Adlink Vortex DDS make pallets and robots intelligent so they can communicate with the world around them, enabling customers to increase pallet profitability, quality inspection, automation, and productivity within the distribution center and manufacturing floor. 

The company will debut its Edge IoT Smart Pallet Experience at Pack Expo, Las Vegas (23 to 25 September) in the Las Vegas Convention Center, Level 1, Lower South Hall booth 6387.

The immersive experience will demonstrate machine vision, AI and robotics technology for warehouse distribution and manufacturing with partners Amazon Web Services (AWS), Intel’s IoT group, and robot maker Rover Robotics. A game-like exhibit will encourage attendees to use hands-on edge IoT technology, stacking pallets against the clock for a chance to win a $100 Visa gift card.

Adlink Technology specialises in edge computing and has a mission to reduce the complexity of building IoT systems. Adlink provides the analogue digital link to make machine connectivity simple through edge hardware and edge software to form edge IoT solutions for manufacturing, networking and communications, medical, transportation, power, oil and gas, and government and defence industries. 

Its edge IoT includes embedded building blocks and intelligent computing platforms, fully featured edge platforms, data connectivity and extraction devices, secure software for data movement, and edge IoT apps to monitor, manage, and analyse data-streaming assets and devices.  

(Picture credit: AlexLMX)

http://www.adlinktech.com
> Read More

Intel Xeon Scalable processors are equipped for AI training

Up to 56 processor cores per socket and built in artificial intelligence training acceleration distinguish the next generation of Intel Xeon Scalable processors. Codenamed Cooper Lake, the processors will be available from the first half of next year. The high core-count processors will use the Intel Xeon platinum 9200 series capabilities for high performance computing (HPC) and AI customers.

The second generation, Intel Xeon Scalable processors will deliver twice the processor core count (up to 56 cores), higher memory bandwidth, and higher AI inference and training performance compared to the standard Intel Xeon Platinum 8200 platforms, confirms Intel. The family will be the first x86 processor to deliver built-in AI training acceleration through new bfloat16 support added to Intel Deep Learning (DL) Boost. 

Intel DL Boost augments the existing Intel Advanced Vector Extensions 512 (Intel AVX-512) instruction set. This “significantly accelerates inference performance for deep learning workloads optimised to use vector neural network instructions (VNNI),” said Jason Kennedy, director of Datacenter Revenue Products and marketing at Intel.

He cites workloads such as image classification, language translation, object detection, and speech recognition, which can be lightened using the accelerated performance. Early tests have shown image recognition 11 times faster using a similar configuration than with current-generation Intel Xeon Scalable processors, reports Intel. Current projections estimate 17 times faster inference throughput benefit with Intel Optimized Caffe ResNet-50 and Intel DL Boost for CPUs.  

The processor family will be platform-compatible with the 10nm Ice Lake processor.

The Intel Xeon Platinum 9200 processors are available for purchase today as part of a pre-configured systems from select OEMs, including Atos, HPE, Lenovo, Penguin Computing, Megware and authorised Intel resellers. 

http://www.intel.com
> Read More

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

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