Sector News Archives - Page 425 of 608 - SmartCitiesElectronics.com

Software accelerates AI deployment in audio, voice and sensing devices

Thu, Mar 12, 2020

Software for Cadence Tensilica HiFi digital signal processors (DSPs) has been optimised to execute TensorFlow Lite for Microcontrollers, part of the TensorFlow open-source platform for machine learning (ML) from Google. The edge-based ML running on the low power cores supports intelligence in audio, voice and sensing applications.

The HiFi DSPs are the first DSPs to support TensorFlow Lite for Microcontrollers, says Cadence. The software support for TensorFlow Lite on the HiFi DSP cores, promotes development of edge applications that use artificial intelligence (AI) and ML on TensorFlow and removes the need for hand-coding neural networks. This accelerates time to market, Cadence notes.

Implementing AI at the edge on devices that use voice and audio as a user interface, requires the inference model to be run on the device. This eliminates the latency associated with sending data to a cloud service and waiting for the response to be sent back to the device and also reduces power consumption associated with sending/receiving large amounts of data across a network.

It also serves to maintain privacy and minimise security issues since the data does not leave the device. As the device is not dependent on the cloud, it can be disconnected from the network and still operate.

A 600MHz Tensilica HiFi 4 DSP is included in NXP Semiconductor’s i.MX RT600 and delivers 4.8 Giga multiply-accumulates per second (GMACS). It has the compute power required for deploying voice, audio and other neural network-based applications at the edge. Joe Yu, vice president of microcontrollers at NXP Semiconductors, said: “Supporting the popular, end-to-end toolchain, TensorFlow, as well as other inferencing technologies, on the HiFi DSP will enable ML developers to take advantage of the compelling combination of compute and memory on this chip”.

Yipeng Liu, director of audio/voice IP at Cadence, added: “Support for TensorFlow Lite for Microcontrollers enables our licensees to innovate with ML applications like keyword detection, audio scene detection, noise reduction and voice recognition, with the assurance that they can run in an extremely low-power footprint”.

http://www.cadence.com

> Read More

Wideband mmWave synthesiser is for 5G radio beamforming and MIMO

Thu, Mar 12, 2020

The integrated 8V97003 wideband mmWave synthesiser is has the industry’s highest performance and features optimised for 5G and broadband wireless applications, says Renesas Electronics.

The 8V97003 can be used as a local oscillator (LO) for mmWave and beamforming, or a precision reference clock for a high-speed data converter in test and measurement, optical networking and data acquisition applications.

According to Bobby Matinpour, vice president of Timing Products, IoT and Infrastructure business unit at Renesas: “[The] single-chip . . . 8V97003 is particularly well-suited for emerging applications above the 6GHz carrier frequency, including broadband wireless, microwave backhaul, and 5G radios”.

The 8V97003 is claimed to deliver the industry’s best combination of wide frequency range (171.875MHz to 18GHz), low output phase noise (-60.6dBc at 20kHz to 100MHz at 6GHz) and high output power over its entire frequency range. Engineers can use a single 8V97003 in place of multiple synthesiser modules to reduce footprint and cost of the end product. The high output power eliminates the need for external driver which reduces complexity and power consumption without compromising performances, says Renesas. The low output phase noise makes it suitable for 5G and other wireless applications where it is claimed to enable superior system level signal-to-noise ratio (SNR) and error vector magnitude (EVM). As a reference clock for high-speed data converters, the 8V97003 maximises system performance by improving SNR and spurious-free-dynamic-range (SFDR).

Mass production quantities of the 8V97003 are available now in a 7.0 x 7.0mm, 48-lead VFQFPN package.

http://www.renesas.com

> Read More

Rohde & Schwarz introduces signalling tests for 5G NR in FR1 and FR2 mode

Thu, Mar 12, 2020

Signalling tests for FR1 and FR2 in non-standalone mode can now be performed with the R&S CMX500. To test 5G NR products which use a much higher bandwidth, and active antennae, over-the-air (OTA) measurements are necessary. Rohde & Schwarz has created a portfolio for 5G NR device testing, based on the CMX500 radio communication tester enabling non-standalone (NSA) and standalone (SA) signalling tests in both FR1 and FR2 frequency ranges.

To allow developers to test their mobile devices in 5G NR NSA and SA mode in line with 3GPP specifications, the test must accurately simulate both LTE and 5G NR networks. The CMX500 radio communication tester adds 5G capability to the company’s LTE test systems (CMW500 or CMWflexx), to allow testing from 2G to 5G on one platform. The extension box R&S CMX500 handles various FR1 and FR2, signalling and non-signalling as well as SA and NSA test scenarios, from R&D to certification testing, confirms Rohde & Schwarz.

A key functionality of the R&S CMX500 is signalling tests in FR2 with support for signalling tests in FR1. The tests performed in NSA mode feature both LTE and 5G connections. They verify LTE/5G signalling protocol behaviour, OTA RF/TX measurements, end-to-end data testing with LTE and 5G bearers as well as mmWave OTA signalling and RF measurements.

Signalling test in the new mmWave-based 5G frequency of FR2 requires an OTA test set up or environment. The test set up features the R&S ATS800R CATR rack- based antenna test system with OTA functionalities. Designed for FR2 R&D measurements, it optimises the available lab space by combining a, compact shielding chamber with T&M equipment in the same set up, to minimise footprint. The integrated reflector surface precision provides a sufficiently large quiet zone with high accuracy, says Rohde & Schwarz.

To control the 5G radio communication testers, the test set up includes the newly developed R&S CMsquares unified test software. This integrates the mobile network simulation with test configuration, parameterisation, real time measurements and test result management in a single environment for all relevant use cases from RF parametric testing over protocol analysis to data end-to-end throughput tests.

It provides easiest user guidance via dashboards and customisable workspaces which allow quick access to the various types of 5G measurements. It also has a built-in sequencer to run pre-configured 5G NR test scripts or to create 5G NR test scripts from scratch using a simple drag-and-drop workflow.

http://www.rohde-schwarz.com

> Read More

Simpleware ScanIP software enhances its machine learning operation

Thu, Mar 12, 2020

Synopsys introduces a machine learning (ML) -based auto segmentation module for 3D image processing in the Simpleware ScanIP software. The ML-based option speeds up operation by up to a factor of 20 to 50, says the company and precisely automates segmentation for medical device design and pre-surgical planning.

The new ScanIP software module, Simpleware AS Ortho, uses automated algorithms to shorten segmentation time and produce accurate results significantly faster for medical image data, says the company.

The ML-based auto segmentation module builds on Synopsys’ ScanIP software, a comprehensive solution for 3D image processing and segmenting images generated by computed tomography (CT) or magnetic resonance imaging (MRI) scanners.

The Simpleware AS Ortho module is specifically designed for segmentation needs in patients’ hips and knees. When applying this automated option with Synopsys’ ScanIP software to run analysis, users will easily see a 20 to 50 times faster rate of segmentation for clinical images, Synopsys reports.

The technology is scalable and helps to achieve more consistency and increased reliability in biomechanical compatibility. It can also dramatically streamline the workflow process in both pre-surgical planning and medical device design.

“Image segmentation of MRI and CT scans presents a significant challenge for our surgical and engineering multidisciplinary teams. We’re excited to collaborate with the Simpleware product group at Synopsys for solutions to this challenge,” said Johann Henckel, MD orthopedic surgeon at the Royal National Orthopaedic Hospital, in the UK. “What is currently a laborious process that occupies significant engineering resources and time can now be completed quickly, accurately and with less variability, promising a scalable solution for generating high-fidelity patient specific models, surgical tools and bespoke implants,” he said.

“The demand for image-based modeling of human anatomy tools with ML-enabled intelligence is rapidly growing, especially in markets that include patient specific workflows for medical devices, surgical guides and planning, and in silico clinical trials,” said Terry Ma, vice president of engineering at Synopsys.

Synopsys’ Simpleware AS Ortho (Auto Segmenter for Orthopedics) launches in March 2020 as a Simpleware ScanIP software add-on module for hips and knees. Synopsys plans further modules to provide automated segmentation options for other anatomical regions. For users wanting any customisation or workflows applied to different anatomies, Synopsys’ Simpleware Custom Modeler option is also available as a tailored and automated software option.

http://www.synopsys.com

> Read More

Software accelerates AI deployment in audio, voice and sensing devices

Wideband mmWave synthesiser is for 5G radio beamforming and MIMO

Rohde & Schwarz introduces signalling tests for 5G NR in FR1 and FR2 mode

Simpleware ScanIP software enhances its machine learning operation

About Smart Cities