Linkdump: August 2019

A googly eyed robot in a library

Read more »

App note: Ferrite bead demystified

an_analog_AN1368

App note from Analog Devices hinting for proper selection of ferrite bead for you applications. Link here (PDF)

An effective method for filtering high frequency power supply noise and cleanly sharing similar supply rails is the use of ferrite beads. A ferrite bead is a passive device that filters high frequency noise energy over a broad frequency range. It becomes resistive over its intended frequency range and dissipates the noise energy in the form of heat. The ferrite bead is connected in series with the power supply rail and is often combined with capacitors to ground on either side of the bead. This forms a low-pass filter network, further reducing the high frequency power supply noise.

Read more »

Update: Deep-Learning for Detecting Diabetic Retinopathy #Google #Diabetes #Ophthalmology #HealthcareAI #MachineLearning #DeepLearning #ComputerVision @googleAI

Update on Google’s diabetic retinopathy project below! Take a look at the original post here.

Photo from Google AI Blog Post “Improving the Effectiveness of Diabetic Retinopathy Models”. Caption: “On the left is a fundus image graded as having proliferative (vision-threatening) DR by an adjudication panel of ophthalmologists (ground truth). On the top right is an illustration of our deep learning model’s predicted scores (“P” = proliferative, the most severe form of DR). On the bottom right is the set of grades given by physicians without assistance (“Unassisted”) and those who saw the model’s predictions (“Grades Only”).”

 

For the last several years Google has been working with clinics in India to develop a deep learning model to predict the severity of diabetic retinopathy (DR). In more advanced stages, DR can lead to vision loss and requires clinical intervention. Best practice suggests regular screening before the patient’s vision is impaired. In India, there are many patients that need this type of screening and a shortage of eye care specialists. That’s where deep learning comes in!

Back in 2016, Google trained a deep neural network classifier trained on anonymized retinal images to identify ‘Referrable DR’. The results were published in JAMA with the intent to improve the model and performance measurements. The last several years have shown improvements in model evaluation and proving out use cases. Several months ago the first prospective study for the project was published titled “Performance of a Deep-Learning Algorithm vs Manual Grading for Detecting Diabetic Retinopathy in India”.

The study utilized several different neural networks aimed at predicting the severity of DR from fundus images. During the study, additional improvements were made to the model with the addition of higher quality images, hyperparameter tuning and the use of the Inception-v4 neural network architecture.

During the course of the prospective data collection period, we made additional improvements to the model, including tuning the models with adjudicated data as reported by Krause et al. The improvements can be summarized as (1) larger training sets, (2) better hyperparameter exploration (tuning), (3) larger input image resolution, and (4) using the improved Inception-v4 neural network architecture. We graded the images using the model from Krause et al retrospectively at the conclusion of the study.
The study results indicate that the deep learning algorithm is able to automate DR grading to expand screening programs.
This study shows that the automated DR system generalizes to this population of Indian patients in a prospective setting and demonstrates the feasibility of using an automated DR grading system to expand screening programs.

Read more »

Friday Product Post: May the 4 Be With You

Hi. Welcome to September! Welcome to here! You look nice today. No, I have never written one of these before, thank you for noticing.

Before we get to the new stuff, of which there is a considerable quantity, let's talk about the free stuff. Today kicks off the second of our Two Weeks of Free party, which means you can now choose from among three fresh, new sensors, and pay $0 for your selection. How can this be, you ask? It's easy: purchase either the Artemis RedBoard (yes, the new one) or the Qwiic RedBoard, and pick one of three sensors for free! This week of free will end next Friday, September 13 (oooh), at 11:59 p.m. MT. You can also find out more (including important rules and stuff) at our Two Weeks of Free page!

SparkFun RedBoard Artemis

added to your cart!

SparkFun RedBoard Artemis

In stock DEV-15444

The RedBoard Artemis takes the incredibly powerful Artemis module from SparkFun and wraps it up in an easy to use and familia…

$19.95
SparkFun RedBoard Qwiic

added to your cart!

SparkFun RedBoard Qwiic

23 available DEV-15123

The SparkFun RedBoard Qwiic is an Arduino-compatible development board with a built in Qwiic connector, eliminating the need …

$19.95
4

Here are this week's free sensors to go with your new Qwiic or Artemis RedBoard:

SparkFun Distance Sensor Breakout - 4 Meter, VL53L1X (Qwiic)

added to your cart!

SparkFun Distance Sensor Breakout - 4 Meter, VL53L1X (Qwiic)

In stock SEN-14722

This SparkFun Distance Sensor Breakout utilizes the VL53L1X next generation ToF sensor module to give you the highly accurate…

$21.95
6
SparkFun UV Light Sensor Breakout - VEML6075 (Qwiic)

added to your cart!

SparkFun UV Light Sensor Breakout - VEML6075 (Qwiic)

In stock SEN-15089

The VEML6075 UV Light Sensor Breakout is SparkFun’s latest ultraviolet sensing solution.

$6.95
SparkFun Qwiic OpenLog

added to your cart!

SparkFun Qwiic OpenLog

In stock DEV-15164

The SparkFun Qwiic OpenLog can store, or "log", huge amounts of serial data and act as a black box of sorts all over I2C.

$16.95

Use code FD19P4 for the Distance Sensor Breakout, FD19P5 for the UV Light Sensor Breakout, and FD19P6 for the Qwiic OpenLog.

Get to it, and enjoy! Now let's talk about new stuff. There's a lot of it.


In the next iteration of the Model B line, Raspberry Pi has given us the very powerful Model B 4, with the goal of a full desktop experience. The 2GB and 4GB DDR4 RAM boards have the ability to run two 4k monitors at once via two micro HDMI ports, and feature the long-asked-for, true Gigabit Ethernet. This creates a much higher-performing multimedia experience with the new Pi! In addition to two USB2 ports, the Raspberry Pi 4 also has two USB 3 ports, making data transfers that much quicker over USB.

Raspberry Pi 4 Model B (2 GB)

added to your cart!

Raspberry Pi 4 Model B (2 GB)

In stock DEV-15446

The 2 GB Raspberry Pi 4 features the ability to run two 4k resolution monitors, to run true Gigabit Ethernet operations, all …

$49.95
Raspberry Pi 4 Model B (4 GB)

added to your cart!

Raspberry Pi 4 Model B (4 GB)

In stock DEV-15447

The 4 GB Raspberry Pi 4 features the ability to run two 4k resolution monitors, to run true Gigabit Ethernet operations, all …

$59.95

The micro:bit is a pocket-sized computer that lets you get creative with digital technology. Between the micro:bit and our shield-like bit boards, you can do almost anything while coding, customizing and controlling your micro:bit from almost anywhere! This week we have three new accessory boards to add functionality to your micro:bit.

SparkFun gator:RTC - micro:bit Accessory Board

added to your cart!

SparkFun gator:RTC - micro:bit Accessory Board

In stock COM-15486

The gator:RTC is a supplemental data logging tool with a RV-3028 real time clock (RTC) module from Micro Crystal, using a con…

$14.95

The gator:RTC is a supplemental data logging tool to be used in conjunction with the gator:log, part of SparkFun's gator:bit series of gator-clippable accessories designed for easy interface with the micro:bit or other microcontrollers. This tool allows a student to focus more on the experiment than on watching a thermometer or stopwatch.

SparkFun gator:UV - micro:bit Accessory Board

added to your cart!

SparkFun gator:UV - micro:bit Accessory Board

In stock SEN-15273

The SparkFun gator:UV micro:bit Accessory Board is an ultraviolet sensing solution created to interface with the micro:bit as…

$6.95

The SparkFun gator:UV is an ultraviolet sensing solution created to interface with the micro:bit as easily as possible. It can be easily interfaced with the micro:bit or other microcontrollers via the SparkFun gator:bit! This sensor board is a great solution for monitoring the UV light exposure in your next experiment! The gator:UV is designed around the VEML6070, an advanced UV light sensor that communicates over an I2C bus, incorporating a photodiode, amplifiers, and analog/digital circuits all into a single chip.

SparkFun gator:log - micro:bit Accessory Board

added to your cart!

SparkFun gator:log - micro:bit Accessory Board

In stock DEV-15270

The gator:log is the perfect data logging tool for your next experiment.

$12.95

The gator:log is the perfect data logging tool for your next micro:bit experiment. With the automation of the data collection process, gone are the days of rushing around with a pen and composition notebook to simultaneously record data and your observations. Now, you only need to sit back and observe your experiment.


Raspberry Pi Wall Adapter Power Supply - 5.1VDC, 3.0A, 15.3W (USB-C)

added to your cart!

Raspberry Pi Wall Adapter Power Supply - 5.1VDC, 3.0A, 15.3W (USB-C)

In stock TOL-15448

The is the official USB Type-C Power Supply for the Raspberry Pi Model 4 B.

$8.00

Last but potentially not least, depending on your needs: this is the official USB Type-C Power Supply for the Raspberry Pi 4 Model B. This is a wall adapter with a USB Type-C Connector that fulfills the 15.3W power requirements of the Raspberry Pi 4. It can also be used for other devices which require up to 5.1VDC and 3A. This model comes in white, as you can see here.

Great! We did it, guys!! That's everything for now. We’d love to see what projects you’ve made – shoot us a tweet @sparkfun, or let us know on Instagram or Facebook.

comments | comment feed

Read more »

Arduino Nano Prototyping Case #3DThursday #3DPrinting

NewImage

Shared by Venomouse on Thingiverse:

Arduino Nano Prototyping case.

I got sick of breadboards and dodgy wires.

Figured this would help rapid prototyping ?

Download the files and learn more


649-1
Every Thursday is #3dthursday here at Adafruit! The DIY 3D printing community has passion and dedication for making solid objects from digital models. Recently, we have noticed electronics projects integrated with 3D printed enclosures, brackets, and sculptures, so each Thursday we celebrate and highlight these bold pioneers!

Have you considered building a 3D project around an Arduino or other microcontroller? How about printing a bracket to mount your Raspberry Pi to the back of your HD monitor? And don’t forget the countless LED projects that are possible when you are modeling your projects in 3D!

Read more »

Make Workshop: Rocket Stove Welding Practice Kit

Practicing your welding is a task that is often overlooked. In school, they have exercises that you repeat till you’re good, but in a makerspace, you just kind of have to jump into projects and get better as you go. Richard at 42Fab.com has come up with some basic projects […]

Read more on MAKE

The post Make Workshop: Rocket Stove Welding Practice Kit appeared first on Make: DIY Projects and Ideas for Makers.

Read more »

Great Women Artists, the Largest Published Collection of Female Artists #ArtTuesday

NewImage

Adding this to the wishlist I’ve shared with my brother’s for the times they feel like sending me a gift. We’d also like to draw your attention to the fantastic cover art and how it works so brilliant with that strikethrough text. From Colossal:

Great Women Artists celebrates the centuries-long lineage of artistic brilliance amongst artists who happen to be female. Featuring a vast array of aesthetics and movements spanning 500 years, included artists range from Nina Chanel Abney and Eva Hesse to Shoplifter and Sofonisba Anguissola.

Read more from Colossal and Phaidon


Screenshot 4 2 14 11 48 AMEvery Tuesday is Art Tuesday here at Adafruit! Today we celebrate artists and makers from around the world who are designing innovative and creative works using technology, science, electronics and more. You can start your own career as an artist today with Adafruit’s conductive paints, art-related electronics kits, LEDs, wearables, 3D printers and more! Make your most imaginative designs come to life with our helpful tutorials from the Adafruit Learning System. And don’t forget to check in every Art Tuesday for more artistic inspiration here on the Adafruit Blog!

Read more »

Drones Save 450 Baby Deer From Harvest in Switzerland #drone #droneday

Fawn 1024x578

Here is awwwesome story out of Switzerland. Thermal imaging drones used to detect baby dear before farmers harvest. Via Dronelife:

The technology is now being used to save animals, too. In Graubünden in eastern Switzerland, drones with thermal imaging cameras were able to spot and rescue 450 newborn deer playing a high-stakes game of hide and seek in meadows and pastures due to be harvested.

Throughout the season across the area, around 1,100 missions saved 450 fawns during pre-harvest inspections using drones and thermal cameras. The fawns tend to lower themselves to the ground when a mower approaches, giving farmers little chance to spot them in time.

Read more!


Welcome to drone day on the Adafruit blog. Every Monday we deliver the latest news, products and more from the Unmanned Aerial Vehicles (UAV), quadcopter and drone communities. Drones can be used for video & photography (dronies), civil applications, policing, farming, firefighting, military and non-military security work, such as surveillance of pipelines. Previous posts can be found via the #drone tag and our drone / UAV categories.

Read more »