The element14 ESSENTIALS of AI at the Edge covers the definitions, basic concepts, and components of AI in edge computing, as well as a systems analysis. To extend the knowledge covered in the main module, this supplementary guide discusses the types of related components or development boards used for prototyping or product development.
The MaaXBoard is an NXP i.MX 8M processor-based single board computer used for embedded computing and smart edge IoT applications. The i.MX 8M family of application processors are based on the Arm® Cortex®-A53 and Cortex-M4 cores, which provide audio, voice, and video processing for applications that scale from consumer home audio to industrial building automation and embedded computers. The MaaXBoard is production ready, FCC, CE, and RoHS certified. It is available in quantities from one to thousands. The MaaXBoard contains everything necessary to support and create a Linux, Android, Windows 10 IoT Core, or other OS based system. The platform offers several on-board peripherals, including 2 GB of DDR4 memory, a Gigabit Ethernet port, dual USB 3.0 host ports, HDMI output, MIPI-DSI, MIPI-CSI, Wi-Fi, Bluetooth Low Energy, and MicroSD card slot. A Raspberry Pi HAT compatible expansion connector also provides interfaces for UART, SPI, I2C, and GPIO.
These combined capabilities make it an ideal platform for investigating AI, IoT, and multimedia applications. Each MaaXBoard is shipped with a custom passive Heatsink and Quick Start guide to assist developers with getting started on their hardware or software development project. A user-supplied 5V/3A USB Type-C power supply is required to power the board. A 16GB microSD card and an HDMI cable are recommended for booting the MaaXBoard and connecting it to an LCD monitor.
The SBC-S32V234 is an evaluation board and development platform engineered for high-performance, safe computation-intensive front vision, surround vision, sensor fusion, and Driver Monitoring Systems (DMS) and Occupant Monitoring Systems applications. Developed in partnership with MicroSys and based on the 64-bit Arm® Cortex®-A53 S32V processors, the SBC-S32V234 has an efficient form factor while covering many of the uses cases available for the S32V234 processors. The SBC-S32V234 is the recommended starting evaluation board for S32V processors. The S32V234 processors offer both S32V234-EVB2 and SBC-S32V234 board options with similar functionality; consider using the cost-competitive and small form factor SBC-S32V234 evaluation board if your use case is covered by all its features.
NXP's MCU-based solution for Amazon's Alexa Voice Service (AVS) leverages the i.MX RT106A audio crossover processor, enabling developers to easily add Alexa voice assistant capabilities to their products. This turnkey design with ultra-small form factor comes integrated with Amazon-qualified software for an out-of-the-box AVS experience. NXP's MCU-based AVS solution provides OEMs with a fully integrated, self-contained, software and hardware solution that includes both the MCU and an NXP smart audio amplifier with speaker protection. It comes with all far-field audio processing algorithms including noise suppression, echo cancellation, beamforming and barge-in capabilities, to enable use in acoustically difficult environments. Also included is the Amazon Alexa client application and a machine learning inference engine for Alexa wake word identification.
This easy-to-use AVS implementation facilitates the demand for ubiquitous voice control embedded in a diverse variety of products across home, commercial and industrial applications. It eliminates the need to deploy dedicated stand-alone voice control devices such as smart speakers or smart displays.
STEVAL-STWINKT1 STWIN SensorTile Wireless Industrial Node, Development Kit and Reference Design for Industrial IoT Applications
The STMicroelectronics's STWIN SensorTile wireless industrial node is a development kit and reference design that simplifies prototyping and testing of advanced industrial IoT applications, such as condition monitoring and predictive maintenance. The kit features a core system board with a range of embedded industrial-grade sensors and an ultra-low-power microcontroller for vibration analysis of 9-DoF motion sensing data across a wide range of vibration frequencies, including very high frequency audio and ultrasound spectra, and high precision local temperature and environmental monitoring. The development kit is complemented with a rich set of software packages and optimized firmware libraries, as well as a cloud dashboard application, all provided to help speed up design cycles for end-to-end solutions. The kit supports BLE wireless connectivity through an on-board module, and Wi-Fi connectivity through a special plugin expansion board (STEVAL-STWINWFV1). Wired connectivity is also supported via an on-board RS485 transceiver. The core system board also includes an STMod+ connector for compatible, low cost, small form factor daughter boards associated with the STM32 family, such as the LTE Cell pack. Apart from the core system board, the kit is provided complete with a 480 mAh Li-Po battery, an STLINK-V3MINI debugger, and a plastic box.
The STEVAL-MKSBOX1V1 (SensorTile.box) is a ready-to-use box kit with wireless IoT and wearable sensor platform to help you use and develop apps based on remote motion and environmental sensor data, regardless of your level of expertise. The SensorTile.box board fits into a small plastic box with a long-life rechargeable battery, and the ST BLE Sensor app on your smartphone connects via Bluetooth to the board and allows you to immediately begin using the wide range of default IoT and wearable sensor applications. In Expert Mode, you can build customs apps from your selection of SensorTile.box sensors, operating parameters, data and output types, and special functions and algorithms available. This multi sensor kit therefore allows you to design wireless IoT and wearable sensor applications quickly and easily, without performing any programming.
SensorTile.box includes a firmware programming and debugging interface that allows professional developers to engage in more complex firmware code development using the STM32 Open Development Environment, which includes a sensing AI function pack with neural network libraries. It has an easy-to-use app with immediate functionality for the following motion and environmental sensor applications: Pedometer optimized for belt positioning, Baby crying detection with Cloud AI learning, Barometer / environmental monitoring, Vehicle / goods tracking, Vibration monitoring, Compass and inclinometer Sensor data logger. The compact board has the following high precision sensors: Digital temperature sensor (STTS751), 6-axis inertial measurement unit (LSM6DSOX), 3-axis accelerometers (LIS2DW12 and LIS3DHH), 3-axis magnetometer (LIS2MDL), Altimeter / pressure sensor (LPS22HH), Microphone / audio sensor (MP23ABS1), and Humidity sensor (HTS221).
Consumer Edition (CE) specification. Ultra96-V2 is available in more countries around the world as it has been designed with a certified radio module from Microchip. Additionally, Ultra96-V2 is available in both commercial and industrial temperature grade options. Additional power control and monitoring is possible with the included Infineon Pmics. Like Ultra96, the Ultra96-V2 boots from the provided Delkin 16 GB microSD card. Engineers have options of connecting to Ultra96-V2 through a Webserver using integrated wireless access point capability or to use the provided PetaLinux desktop environment which can be viewed on the integrated Mini DisplayPort video output. Multiple application examples and on-board development options are provided as examples. Ultra96-V2 provides four user-controllable LEDs. Engineers may also interact with the board through the 96Boards-compatible low-speed and high-speed expansion connectors by adding peripheral accessories such as those included in the MikroE Click Mezzanine for 96Boards (available as an accessory). Micron LPDDR4 memory provides 2 GB of RAM in a 512M x 32 configuration. Wireless options include 802.11b/g/n Wi-Fi and Bluetooth 5 Low Energy. The radio module is Agency Certified in over 75 countries. UARTs are accessible on a header as well as through the expansion connector. JTAG is available through a header. The convenient JTAG/UART Pod (available as an accessory) provides both JTAG and UART connections via USB. I2C is available through the expansion connector.
The ZCU102 Evaluation Kit enables designers to jumpstart designs for automotive, industrial, video, and communications applications. This kit features a Zynq® UltraScale+™ MPSoC with a quad-core Arm® Cortex®-A53, dual-core Cortex-R5F real-time processors, and a Mali™-400 MP2 graphics processing unit based on Xilinx's 16nm FinFET+ programmable logic fabric. The ZCU102 supports all major peripherals and interfaces, enabling development for a wide range of applications. It is optimized for quick application prototyping with Zynq UltraScale+ MPSoC. It has DDR4 SODIM—4GB 64-bit w/ ECC attached to processing system (PS) and DDR4 Component—512MB 16-bit attached to programmable logic (PL). It als contains PCIe® Root Port Gen2 x4, USB3, Display Port and SATA, 4x SFP+ interfaces for Ethernet, 2x FPGA Mezzanine Card (FMC) interfaces for I/O expansion, including 16 16.3Gb/s GTH transceivers and 64 user-defined differential I/O signals.
The Zynq® UltraScale+™ RFSoC ZCU111 Evaluation Kit enables designers to jumpstart RF-Class analog designs for wireless, cable access, early-warning (EW)/radar and other high-performance RF applications. This kit features a Zynq Ultrascale+ RFSoC supporting 8x 4GSPS 12-bit ADCs, 8x 6.5GSPS 14-bit DAC, and 8 soft-decision forward error correction (SD-FECs). Complete with ARM Cortex A53 and ARM Cortex-R5 subsystems, UltraScale+ programmable logic, and the highest signal processing bandwith in a Zynq UltraScale+ device, this kit provides a rapid, comprehensive RF Analog-to-Digital signal chain prototyping platform. It has DDR4 Component - 4GB, 64-bit, 2666 MT/s, attached to Programmable Logic (PL), and DDR4 SODIMM - 4GB 64-bit, 2400 MT/s, attached to Processor Subsystem (PS). It also contains Ganged SFP28 cage to support up to 4 SFP/SFP+/zSFP+/SFP28 modules, USB3, DisplayPort and SATA, FPGA Mezzanine Card (FMC+) interface for I/O expansion, including 12 x 32.75 Gb/s GTY transceivers and 34 user defined differential I/O signals.
Bringing computer vision and AI to your IoT and edge device prototypes are now easier than ever with enhanced capabilities of the Intel® Neural Compute Stick 2. Whether you're developing a smart camera, a drone with gesture-recognition capabilities, an industrial robot, or the next, must-have smart home device, the Intel® NCS2 offers what you need to prototype smarter. It's built on the latest Intel® Movidius™ Myriad™ X VPU which features the neural compute engine—a dedicated hardware accelerator for deep neural network inferences. With more compute cores than the original version and access to the Intel® Distribution of OpenVINO™ toolkit, the Intel® NCS2 delivers 8x performance boost over the previous generation.
LSM6DSRX iNEMO Inertial Module with Machine Learning Core, Finite State Machine and Advanced Digital Functions for High Accuracy Applications
The LSM6DSRX is a system-in-package featuring a 3D digital accelerometer and a 3D digital gyroscope with an extended full-scale range for the gyroscope, up to 4000 dps, and high stability over temperature and time. The LSM6DSRX supports main OS requirements, offering real, virtual and batch sensors with 9 kbytes with FIFO compression up to three times for dynamic data batching. The LSM6DSRX has a full-scale acceleration range of ±2/±4/±8/±16 g and an angular rate range of ±125/±250/±500/±1000/±2000/±4000 dps. The LSM6DSRX embeds a broad range of advanced functions supporting Android wearable sensors and programmable sensors (suitable for activity recognition). The LSM6DSRX embeds a Machine Learning Core able to identify if a data pattern matches an activity in a user-defined set of classes, reducing power consumption and increasing performance of the sensor. The LSM6DSRX is available in a plastic land grid array (LGA) package.
The 505567-0371 is part of the Molex Micro-Lock Plus Wire to Board Connector System, providing electrical and mechanical reliability in a high-temperature design that meets industry requirements. Used in automotive and consumer electronics applications, it features a positive lock, an inner lock for dual row versions and outer lock for single row versions, dual contact terminal design, and tin-bismuth terminals prevents whiskering for a clean and uninterrupted signal. It can withstand up to 105°C operating temperature.
The 203955-0201 is part of the Molex SlimStack Board-to-Board Connectors, which are deal for compact applications in the automotive, industrial, medical and mobile device industries. SlimStack Board-to-Board Connectors offer a wide selection of low-profile, narrow width options in various mated heights and circuit sizes. The 203955-0201 is a 0.40mm pitch SlimStack board-to-board PCB receptacle mates with 203956 series SlimStack board-to-board plug. It is a FB5 Floating Series, with 5.00mm Mated Height, 3.80mm Mated Width, and 20 Circuits.
The 501331-0407 is part of the Pico-Clasp 1.00mm-pitch wire-to-board connector system, which ranges in circuit sizes from 2 to 50 and provides wide header versions, ideal for space constraint applications. The wide range of design options including gold and tin plating, allows additional design flexibility and the simplicity to stay within the product family. The 501331-0407 is a PCB header with a 1.00mm Pitch in a Single Row and vertical orientation. It is Surface Mounted, Tin Plated, with Inner Friction Lock, and 4 Circuits.
*Trademark. Xilinx, ST Microelectronics, Molex®, NXP Semiconductors, & Intel are trademarks of their corresponding companies: Xilinx Inc., STMicroelectronics International N.V., Molex Corp., NXP Semiconductors N.V., & Intel Corp. Other logos, product and/or company names may be trademarks of their respective owners.