Artemis Machine Learing and Shields for the Real World

30VDC / 300VAC Power Shield ... USE CAUTION WHEN CONNECTING POWER TO THIS SHIELD . MAKE SURE POWER IS OFF BEFORE CONNECTING WIRES TO IT .This shield has capacitors and Diodes to ensure there is no back feeding of the Power module and also has a TVS diode to ensure that there are not any errant spikes entering the System..It also has a 5 VDC power regulator and a 3.3 Power regulator to feed the shield with extra 3.3 VDC for more current capability 1A.

The Screw Shield has an opening to allow the power regulator to poke through. The Regulator is about 1.5" high so it interferes with the upper shield without the hole. This allows the screw shield to be securely put in place and make contact with the lower shield through its pins.

When Soldering Put the Parts together and solder the Bottom first ..Make sure everything is square and aligned

SENSORS

https://www.sparkfun.com/products/10124

https://www.sparkfun.com/products/12756

https://www.sparkfun.com/products/9868

https://www.digikey.com/products/en/development-boards-kits-programmers/accessories/783?k=JST&k=QWIIC&pkeyword=JST

SPARKFUN REDBOARD ARTEMIS ATP PROGRAMMING USING ARDUINO

PROGRAMMING and the Tensorflow machine learning setup

https://github.com/tensorflow/io

https://www.tensorflow.org/s/results?q=kafka

https://nodered.org/

https://kafka.apache.org/quickstart

https://github.com/kaiwaehner/kafka-connect-iot-mqtt-connector-example

Install Code

open a terminal in Your Linux machine and start installing

sudo apt-get install snap
snap install mosquitto
sudo apt-add-repository ppa:mosquitto-dev/mosquitto-ppa
pip install --upgrade pip
pip install tensorflow

https://www-us.apache.org/dist/kafka/2.3.0/kafka_2.12-2.3.0.tgz
tar-xzf kafka_2.12-2.3.0.tgz
cd kafka_2.12-2.3.0
tar -xzf kafka_2.12-2.3.0.tgz.part
sudo rm -r kafka_2.12-2.3.0.tgz.part
cd kafka_2.12-2.3.0

https://linuxize.com/post/how-to-install-python-3-7-on-ubuntu-18-04/

Installing Python 3.7 on Ubuntu with Apt

Installing Python 3.7 on Ubuntu with apt is a relatively straightforward process and will only take a few minutes:

Start by updating the packages list and installing the prerequisites:

sudo apt update
sudo apt install software-properties-common

Copysudo apt update
sudo apt install software-properties-common

• Start by updating the packages list and installing the prerequisites:
  Copy
  sudo apt update
sudo apt install software-properties-common

Next, add the deadsnakes PPA to your sources list:

sudo add-apt-repository ppa:deadsnakes/ppa

Copysudo add-apt-repository ppa:deadsnakes/ppa
When prompted press Enter to continue:

Press [ENTER] to continue or Ctrl-c to cancel adding it.

CopyPress [ENTER] to continue or Ctrl-c to cancel adding it.
Next, add the deadsnakes PPA to your sources list:
Copy
sudo add-apt-repository ppa:deadsnakes/ppa
When prompted press Enter to continue:
Copy
Press [ENTER] to continue or Ctrl-c to cancel adding it.
Once the repository is enabled, install Python 3.7 with:

sudo apt install python3.7

Copy

sudo apt install python3.7
Once the repository is enabled, install Python 3.7 with:
Copy
sudo apt install python3.7
At this point, Python 3.7 is installed on your Ubuntu system and ready to be used. You can verify it by typing:

python3.7 --version

Copy

python3.7 --version
Python 3.7.3

• At this point, Python 3.7 is installed on your Ubuntu system and ready to be used. You can verify it by typing:
  Copy
  python3.7 --version

Python 3.7.3
You also need to install more dependancies

sudo apt-get install openjdk-8-jre

Installing Tensor FLow

pip install --upgrade pip

https://www.tensorflow.org/install/pip

https://www.tensorflow.org/tutorials

Ok once you have all the dependencies and programs installed we are going to try this..See below picture its from https://github.com/kaiwaehner/hivemq-mqtt-tensorflow-kafka-realtime-iot-machine-learning-training-inference

I've tried various different configurations over the last few weeks and I am a huge fan of opensource Programming etc so using Confluence ,AMAZON etc was totally out.

So instead of using the HiveMQTT broker were going to use the Mosquitto MQTT broker and install it into our Linux machine.. You can use a Raspberry Pi if you don't have a Linux computer running Ubuntu. I am sensing data at the moment from various devices and converting it to MQTT in node red from another server for data while I am waiting for my Artemis device to show up.