Merge branch 'microsoft:main' into Bengali-Translation

.vscode/settings.json

@@ -0,0 +1,20 @@
+{
+    "cSpell.words": [
+        "ADCs",
+        "Geospatial",
+        "Kbps",
+        "Mbps",
+        "Seeed",
+        "Twilio",
+        "UART",
+        "UDID",
+        "Zigbee",
+        "antimeridian",
+        "geofence",
+        "geofences",
+        "geofencing",
+        "microcontrollers",
+        "mosquitto",
+        "sketchnote"
+    ]
+}

1-getting-started/lessons/1-introduction-to-iot/code/wio-terminal/nightlight/app.py

@@ -1,20 +0,0 @@
-from counterfit_shims_grove.counterfit_connection import CounterFitConnection
-import time
-from counterfit_shims_grove.grove_light_sensor_v1_2 import GroveLightSensor
-from counterfit_shims_grove.grove_led import GroveLed
-
-CounterFitConnection.init('127.0.0.1', 5000)
-
-light_sensor = GroveLightSensor(0)
-led = GroveLed(5)
-
-while True:
-    light = light_sensor.light
-    print('Light level:', light)
-
-    if light < 200:
-        led.on()
-    else:
-        led.off()
-
-    time.sleep(1)

1-getting-started/lessons/1-introduction-to-iot/pi.md

@@ -12,7 +12,7 @@ If you are using a Raspberry Pi as your IoT hardware, you have two choices - you
 
 Before you begin, you also need to connect the Grove Base Hat to your Pi.
 
-### Task
+### Task - setup
 
 Install the Grove base hat on your Pi and configure the Pi
 
@@ -29,7 +29,7 @@ Install the Grove base hat on your Pi and configure the Pi
 
 If you want to work directly on your Pi, you can use the desktop version of Raspberry Pi OS and install all the tools you need.
 
-#### Task
+#### Task - work directly on your Pi
 
 Set up your Pi for development.
 
@@ -79,7 +79,7 @@ Rather than coding directly on the Pi, it can run 'headless', that is not connec
 
 To code remotely, the Pi OS needs to be installed on an SD Card.
 
-##### Task
+##### Task - set up the Pi OS
 
 Set up the headless Pi OS.
 
@@ -115,7 +115,7 @@ The OS will be written to the SD card, and once compete the card will be ejected
 
 The next step is to remotely access the Pi. You can do this using `ssh`, which is available on macOS, Linux and recent versions of Windows.
 
-##### Task
+##### Task - connect to the Pi
 
 Remotely access the Pi.
 
@@ -147,7 +147,7 @@ Remotely access the Pi.
 
 Once you are connected to the Pi, you need to ensure the OS is up to date, and install various libraries and tools that interact with the Grove hardware.
 
-##### Task
+##### Task - configure software on the Pi
 
 Configure the installed Pi software and install the Grove libraries.
 
@@ -179,7 +179,7 @@ Configure the installed Pi software and install the Grove libraries.
 
 Once the Pi is configured, you can connect to it using Visual Studio Code (VS Code) from your computer - this is a free developer text editor you will be using to write your device code in Python.
 
-##### Task
+##### Task - configure VS Code for remote access
 
 Install the required software and connect remotely to your Pi.
 
@@ -199,7 +199,7 @@ The Hello World app for the Pi will ensure that you have Python and Visual Studi
 
 This app will be in a folder called `nightlight`, and it will be re-used with different code in later parts of this assignment to build the nightlight application.
 
-### Task
+### Task - hello world
 
 Create the Hello World app.
 

1-getting-started/lessons/1-introduction-to-iot/virtual-device.md

@@ -34,7 +34,7 @@ One of the powerful features of Python is the ability to install [pip packages](
 
 By default when you install a package it is available everywhere on your computer, and this can lead to problems with package versions - such as one application depending on one version of a package that breaks when you install a new version for a different application. To work around this problem, you can use a [Python virtual environment](https://docs.python.org/3/library/venv.html), essentially a copy of Python in a dedicated folder, and when you install pip packages they get installed just to that folder.
 
-#### Task
+#### Task - configure a Python virtual environment
 
 Configure a Python virtual environment and install the pip packages for CounterFit.
 
@@ -96,7 +96,7 @@ Configure a Python virtual environment and install the pip packages for CounterF
 
 Once the Python virtual environment is ready, you can write the code for the 'Hello World' application
 
-#### Task
+#### Task - write the code
 
 Create a Python application to print `"Hello World"` to the console.
 
@@ -119,7 +119,8 @@ Create a Python application to print `"Hello World"` to the console.
     ```sh
     code .
     ```
-    > 💁 If your terminal returns `command not found` on macOS it means VS Code has not been added to PATH, you can [add VS Code to PATH](https://code.visualstudio.com/docs/setup/mac#_launching-from-the-command-line) and run the command afterwards. VS Code is installed to PATH by default on Windows and Linux.
+
+    > 💁 If your terminal returns `command not found` on macOS it means VS Code has not been added to your PATH. You can add VS Code to yout PATH by following the instructions in the [Launching from the command line section of the VS Code documentation](https://code.visualstudio.com/docs/setup/mac?WT.mc_id=academic-17441-jabenn#_launching-from-the-command-line) and run the command afterwards. VS Code is installed to your PATH by default on Windows and Linux.
 
 1. When VS Code launches, it will activate the Python virtual environment. You will see this in the bottom status bar:
 
@@ -171,7 +172,7 @@ Create a Python application to print `"Hello World"` to the console.
 
 As a second 'Hello World' step, you will run the CounterFit app and connect your code to it. This is the virtual equivalent of plugging in some IoT hardware to a dev kit.
 
-#### Task
+#### Task - connect the 'hardware'
 
 1. From the VS Code terminal, launch the CounterFit app with the following command:
 

1-getting-started/lessons/1-introduction-to-iot/wio-terminal.md

@@ -8,7 +8,7 @@ The [Wio Terminal from Seeed Studios](https://www.seeedstudio.com/Wio-Terminal-p
 
 To use your Wio Terminal, you will need to install some free software on your computer. You will also need to update the Wio Terminal firmware before you can connect it to WiFi.
 
-### Task
+### Task - setup
 
 Install the required software and update the firmware.
 
@@ -32,7 +32,7 @@ The Hello World app for the Wio Terminal will ensure that you have Visual Studio
 
 The first step is to create a new project using PlatformIO configured for the Wio Terminal.
 
-#### Task
+#### Task - create a PlatformIO project
 
 Create the PlatformIO project.
 
@@ -122,7 +122,7 @@ The VS Code explorer will show a number of files and folders created by the Plat
 
 You're now ready to write the Hello World app.
 
-#### Task
+#### Task - write the Hello World app
 
 Write the Hello World app.
 

1-getting-started/lessons/3-sensors-and-actuators/README.md

@@ -28,15 +28,15 @@ Sensors are hardware devices that sense the physical world - that is they measur
 Some common sensors include:
 
 * Temperature sensors - these sense the air temperature, or the temperature of what they are immersed in. For hobbyists and developer, these are often combined with air pressure and humidity in a single sensor.
-* Buttons - they sense when they have been pressed
+* Buttons - they sense when they have been pressed.
-* Light sensors - these detect light levels, and can be for specific colors, UV light, IR light, or general visible light
+* Light sensors - these detect light levels, and can be for specific colors, UV light, IR light, or general visible light.
-* Cameras - these sense a visual representation of the world by taking a photograph or streaming video
+* Cameras - these sense a visual representation of the world by taking a photograph or streaming video.
-* Accelerometers - these sense movement in multiple directions
+* Accelerometers - these sense movement in multiple directions.
-* Microphones - these sense sound, either general sound levels, or directional sound
+* Microphones - these sense sound, either general sound levels, or directional sound.
 
 ✅ Do some research. What sensors does your phone have?
 
-All sensors have one thing in common - the convert whatever they sense into an electrical signal that can be interpreted by an IoT device. How this electrical signal is interpreted depends on the sensor, as well as the communication protocol used to communicate with the IoT device.
+All sensors have one thing in common - they convert whatever they sense into an electrical signal that can be interpreted by an IoT device. How this electrical signal is interpreted depends on the sensor, as well as the communication protocol used to communicate with the IoT device.
 
 ## Use a sensor
 
@@ -62,7 +62,7 @@ One example of this is a potentiometer. This is a dial that you can rotate betwe
 
 ***A potentiometer. Microcontroller by Template / dial by Jamie Dickinson - all from the [Noun Project](https://thenounproject.com)***
 
-The IoT device will send an electrical signal to the potentiometer at a voltage, such as 5 volts (5V). As the potentiometer is adjusted it changes the voltage that comes out of the other side. Imagine you have a potentiometer labelled as a dial that goes from 0 to [11](https://wikipedia.org/wiki/Up_to_eleven), such as a volume knob on an amplifier. When the potentiometer is in the full off position (0) then 0v (0 volts) will come out. When it is in the full on position (11), 5V (5 volts) will come out.
+The IoT device will send an electrical signal to the potentiometer at a voltage, such as 5 volts (5V). As the potentiometer is adjusted it changes the voltage that comes out of the other side. Imagine you have a potentiometer labelled as a dial that goes from 0 to [11](https://wikipedia.org/wiki/Up_to_eleven), such as a volume knob on an amplifier. When the potentiometer is in the full off position (0) then 0V (0 volts) will come out. When it is in the full on position (11), 5V (5 volts) will come out.
 
 > 🎓 This is an oversimplification, and you can read more on potentiometers and variable resistors on the [potentiometer Wikipedia page](https://wikipedia.org/wiki/Potentiometer).
 
@@ -74,9 +74,9 @@ The voltage that comes out the sensor is then read by the IoT device, and the de
 
 IoT devices are digital - they can't work with analog values, they only work with 0s and 1s. This means that analog sensor values need to be converted to a digital signal before they can be processed. Many IoT devices have analog-to-digital converters (ADCs) to convert analog inputs to digital representations of their value. Sensors can also work with ADCs via a connector board. For example, in the Seeed Grove ecosystem with a Raspberry Pi, analog sensors connect to specific ports on a 'hat' that sits on the Pi connected to the Pi's GPIO pins, and this hat has an ADC to convert the voltage into a digital signal that can be sent off the Pi's GPIO pins.
 
-Imagine you have an analog light sensor connected to an IoT device that uses 3.3V, and is returning a value of 1v. This 1v doesn't mean anything in the digital world, so needs to be converted. The voltage will be converted to an analog value using a scale depending on the device and sensor. One example is the Seeed Grove light sensor which outputs values from 0 to 1,023. For this sensor running at 3.3V, a 1v output would be a value of 300. An IoT device can't handle 300 as an analog value, so the value would be converted to `0000000100101100`, the binary representation of 300 by the Grove hat. This would then be processed by the IoT device.
+Imagine you have an analog light sensor connected to an IoT device that uses 3.3V, and is returning a value of 1V. This 1V doesn't mean anything in the digital world, so needs to be converted. The voltage will be converted to an analog value using a scale depending on the device and sensor. One example is the Seeed Grove light sensor which outputs values from 0 to 1,023. For this sensor running at 3.3V, a 1V output would be a value of 300. An IoT device can't handle 300 as an analog value, so the value would be converted to `0000000100101100`, the binary representation of 300 by the Grove hat. This would then be processed by the IoT device.
 
-✅ If you don't know binary then do a small amount of research to learn how numbers are represented by 0s and 1s. The [BBC Bitesize introduction to binary lesson](https://www.bbc.co.uk/bitesize/guides/zwsbwmn/revision/1) is a great place to start.
+✅ If you don't know binary, then do a small amount of research to learn how numbers are represented by 0s and 1s. The [BBC Bitesize introduction to binary lesson](https://www.bbc.co.uk/bitesize/guides/zwsbwmn/revision/1) is a great place to start.
 
 From a coding perspective, all this is usually handled by libraries that come with the sensors, so you don't need to worry about this conversion yourself. For the Grove light sensor you would use the Python library and call the `light` property, or use the Arduino library and call `analogRead` to get a value of 300.
 
@@ -92,9 +92,9 @@ The simplest digital sensor is a button or switch. This is a sensor with two sta
 
 Pins on IoT devices such as GPIO pins can measure this signal directly as a 0 or 1. If the voltage sent is the same as the voltage returned, the value read is 1, otherwise the value read is 0. There is no need to convert the signal, it can only be 1 or 0.
 
-> 💁 Voltages are never exact especially as the components in a sensor will have some resistance, so there is usually a tolerance. For example the GPIO pins on a Raspberry Pi work on 3.3V, and read a return signal above 1.8v as a 1, below 1.8v as 0.
+> 💁 Voltages are never exact especially as the components in a sensor will have some resistance, so there is usually a tolerance. For example the GPIO pins on a Raspberry Pi work on 3.3V, and read a return signal above 1.8V as a 1, below 1.8V as 0.
 
-* 3.3V goes into the button. The button is off so 0v comes out, giving a value of 0
+* 3.3V goes into the button. The button is off so 0V comes out, giving a value of 0
 * 3.3V goes into the button. The button is on so 3.3V comes out, giving a value of 1
 
 More advanced digital sensors read analog values, then convert them using on-board ADCs to digital signals. For example a digital temperature sensor will still use a thermocouple in the same way as an analog sensor, and will still measure the change in voltage caused by the resistance of the thermocouple at the current temperature. Instead of returning an analog value and relying on the device or connector board to convert to a digital signal, an ADC built into the sensor will convert the value and send it as a series of 0s and 1s to the IoT device. These 0s and 1s are sent in the same way as the digital signal for a button with 1 being full voltage and 0 being 0v.
@@ -155,13 +155,13 @@ Another option for converting digital signals from an IoT device to an analog si
 
 For example, you can use PWM to control the speed of a motor.
 
-imagine you are controlling a motor with a 5V supply. You send a short pulse to your motor, switching the voltage to high (5V) for two hundredths of a second (0.02s). In that time your motor can rotate one tenth of a rotation, or 36°. The signal then pauses for  two hundredths of a second (0.02s), sending a low signal (0v). Each cycle of on then off lasts 0.04s. The cycle then repeats.
+Imagine you are controlling a motor with a 5V supply. You send a short pulse to your motor, switching the voltage to high (5V) for two hundredths of a second (0.02s). In that time your motor can rotate one tenth of a rotation, or 36°. The signal then pauses for two hundredths of a second (0.02s), sending a low signal (0V). Each cycle of on then off lasts 0.04s. The cycle then repeats.
 
 ![Pule width modulation rotation of a motor at 150 RPM](../../../images/pwm-motor-150rpm.png)
 
 ***PWM rotation of a motor at 150RPM. motor by Bakunetsu Kaito / Microcontroller by Template - all from the [Noun Project](https://thenounproject.com)***
 
-This means in one second you have 25 5V pulses of 0.02s that rotate the motor, each followed by 0.02s pause of 0v not rotating the motor. Each pulse rotates the motor one tenth of a rotation, meaning the motor completes 2.5 rotations per second. You've used a digital signal to rotate the motor at 2.5 rotations per second, or 150 ([revolutions per minute](https://wikipedia.org/wiki/Revolutions_per_minute), a non-standard measure of rotational velocity).
+This means in one second you have 25 5V pulses of 0.02s that rotate the motor, each followed by 0.02s pause of 0V not rotating the motor. Each pulse rotates the motor one tenth of a rotation, meaning the motor completes 2.5 rotations per second. You've used a digital signal to rotate the motor at 2.5 rotations per second, or 150 ([revolutions per minute](https://wikipedia.org/wiki/Revolutions_per_minute), a non-standard measure of rotational velocity).
 
 ```output
 25 pulses per second x 0.1 rotations per pulse = 2.5 rotations per second
@@ -191,7 +191,7 @@ You can change the motor speed by changing the size of the pulses. For example,
 
 Digital actuators, like digital sensors, either have two states controlled by a high or low voltage, or have a DAC built in so can convert a digital signal to an analog one.
 
-One simple digital actuator is an LED. When a device sends a digital signal of 1, a high voltage is sent that lights the LED. When a digital signal of 0 is sent, the voltage drops to 0v and the LED turns off.
+One simple digital actuator is an LED. When a device sends a digital signal of 1, a high voltage is sent that lights the LED. When a digital signal of 0 is sent, the voltage drops to 0V and the LED turns off.
 
 ![A LED is off at 0 volts and on at 5V](../../../images/led.png)
 

1-getting-started/lessons/3-sensors-and-actuators/code-actuator/pi/nightlight/app.py

@@ -1,15 +1,15 @@
 import time
-from grove.grove_light_sensor_v1_2 import GroveLightSensor
+import seeed_si114x
 from grove.grove_led import GroveLed
 
-light_sensor = GroveLightSensor(0)
+light_sensor = seeed_si114x.grove_si114x()
 led = GroveLed(5)
 
 while True:
-    light = light_sensor.light
+    light = light_sensor.ReadVisible
     print('Light level:', light)
 
-    if light < 200:
+    if light < 300:
         led.on()
     else:
         led.off()

1-getting-started/lessons/3-sensors-and-actuators/code-actuator/virtual-device/nightlight/app.py

@@ -12,7 +12,7 @@ while True:
     light = light_sensor.light
     print('Light level:', light)
 
-    if light < 200:
+    if light < 300:
         led.on()
     else:
         led.off()

1-getting-started/lessons/3-sensors-and-actuators/code-actuator/wio-terminal/nightlight/app.py

@@ -12,7 +12,7 @@ while True:
     light = light_sensor.light
     print('Light level:', light)
 
-    if light < 200:
+    if light < 300:
         led.on()
     else:
         led.off()

1-getting-started/lessons/3-sensors-and-actuators/code-actuator/wio-terminal/nightlight/src/main.cpp

@@ -19,7 +19,7 @@ void loop()
     Serial.print("Light value: ");
     Serial.println(light);
 
-    if (light < 200)
+    if (light < 300)
     {
         digitalWrite(D0, HIGH);
     }

1-getting-started/lessons/3-sensors-and-actuators/code-sensor/pi/nightlight/app.py

@@ -1,10 +1,9 @@
 import time
-from grove.grove_light_sensor_v1_2 import GroveLightSensor
+import seeed_si114x
 
-light_sensor = GroveLightSensor(0)
+light_sensor = seeed_si114x.grove_si114x()
 
 while True:
-    light = light_sensor.light
+    light = light_sensor.ReadVisible
     print('Light level:', light)
-    
     time.sleep(1)

1-getting-started/lessons/3-sensors-and-actuators/code-sensor/wio-terminal/nightlight/app.py

@@ -12,7 +12,7 @@ while True:
     light = light_sensor.light
     print('Light level:', light)
 
-    if light < 200:
+    if light < 300:
         led.on()
     else:
         led.off()

1-getting-started/lessons/3-sensors-and-actuators/pi-actuator.md

@@ -12,7 +12,7 @@ The nightlight logic in pseudo-code is:
 
 ```output
 Check the light level.
-If the light is less than 200
+If the light is less than 300
     Turn the LED on
 Otherwise
     Turn the LED off
@@ -22,7 +22,7 @@ Otherwise
 
 The Grove LED comes as a module with a selection of LEDs, allowing you to chose the color.
 
-#### Task
+#### Task - connect the LED
 
 Connect the LED.
 
@@ -44,9 +44,9 @@ Connect the LED.
 
 ## Program the nightlight
 
-The nightlight can now be programmed using the Grove light sensor and the Grove LED.
+The nightlight can now be programmed using the Grove sunlight sensor and the Grove LED.
 
-### Task
+### Task - program the nightlight
 
 Program the nightlight.
 
@@ -70,16 +70,18 @@ Program the nightlight.
 
     The line `led = GroveLed(5)` creates an instance of the `GroveLed` class connecting to pin **D5** - the digital Grove pin that the LED is connected to.
 
+    > 💁 All the sockets have unique pin numbers. Pins 0, 2, 4, and 6 are analog pins, pins 5, 16, 18, 22, 24, and 26 are digital pins.
+
 1. Add a check inside the `while` loop, and before the `time.sleep` to check the light levels and turn the LED on or off:
 
     ```python
-    if light < 200:
+    if light < 300:
         led.on()
     else:
         led.off()
     ```
 
-    This code checks the `light` value. If this is less than 200 it calls the `on` method of the `GroveLed` class which sends a digital value of 1 to the LED, turning it on. If the light value is greater than or equal to 200 it calls the `off` method, sending a digital value of 0 to the LED, turning it off.
+    This code checks the `light` value. If this is less than 300 it calls the `on` method of the `GroveLed` class which sends a digital value of 1 to the LED, turning it on. If the light value is greater than or equal to 300 it calls the `off` method, sending a digital value of 0 to the LED, turning it off.
 
     > 💁 This code should be indented to the same level as the `print('Light level:', light)` line to be inside the while loop!
 
@@ -103,7 +105,7 @@ Program the nightlight.
     Light level: 290
     ```
 
-1. Cover and uncover the light sensor. Notice how the LED will light up if the light level is 200 or less, and turn off when the light level is greater than 200.
+1. Cover and uncover the sunlight sensor. Notice how the LED will light up if the light level is 300 or less, and turn off when the light level is greater than 300.
 
     > 💁 If the LED doesn't turn on, make sure it is connected the right way round, and the spin button is set to full on.
 

1-getting-started/lessons/3-sensors-and-actuators/pi-sensor.md

@@ -4,31 +4,33 @@ In this part of the lesson, you will add a light sensor to your Raspberry Pi.
 
 ## Hardware
 
-The sensor for this lesson is a **light sensor** that uses a [photodiode](https://wikipedia.org/wiki/Photodiode) to convert light to an electrical signal. This is an analog sensor that sends an integer value from 0 to 1,023 indicating a relative amount of light that doesn't map to any standard unit of measurement such as [lux](https://wikipedia.org/wiki/Lux).
+The sensor for this lesson is a **sunlight sensor** that uses [photodiodes](https://wikipedia.org/wiki/Photodiode) to convert visible and infrared light to an electrical signal. This is an analog sensor that sends an integer value from 0 to 1,023 indicating a relative amount of light, but this can be used to calculate exact values in [lux](https://wikipedia.org/wiki/Lux) by taking data from the separate infrared and visible light sensors.
 
-The light sensor is an eternal Grove sensor and needs to be connected to the Grove Base hat on the Raspberry Pi.
+The sunlight sensor is an eternal Grove sensor and needs to be connected to the Grove Base hat on the Raspberry Pi.
 
-### Connect the light sensor
+### Connect the sunlight sensor
 
-The Grove light sensor that is used to detect the light levels needs to be connected to the Raspberry Pi.
+The Grove sunlight sensor that is used to detect the light levels needs to be connected to the Raspberry Pi.
 
-#### Task
+#### Task - connect the sunlight sensor
 
-Connect the light sensor
+Connect the sunlight sensor
 
-![A grove light sensor](../../../images/grove-light-sensor.png)
+![A grove sunlight sensor](../../../images/grove-sunlight-sensor.png)
 
-1. Insert one end of a Grove cable into the socket on the light sensor module. It will only go in one way round.
+1. Insert one end of a Grove cable into the socket on the sunlight sensor module. It will only go in one way round.
 
-1. With the Raspberry Pi powered off, connect the other end of the Grove cable to the analog socket marked **A0** on the Grove Base hat attached to the Pi. This socket is the second from the right, on the row of sockets next to the GPIO pins.
+1. With the Raspberry Pi powered off, connect the other end of the Grove cable to one of the three the I<sup>2</sup>C sockets marked **I2C** on the Grove Base hat attached to the Pi. This socket is the second from the right, on the row of sockets next to the GPIO pins.
 
-![The grove light sensor connected to socket A0](../../../images/pi-light-sensor.png)
+    > 💁 I<sup>2</sup>C is a way sensors and actuators can communicate with an IoT device. It will be covered in more detail in a later lesson.
 
-## Program the light sensor
+![The grove sunlight sensor connected to socket A0](../../../images/pi-sunlight-sensor.png)
 
-The device can now be programmed using the Grove light sensor.
+## Program the sunlight sensor
 
-### Task
+The device can now be programmed using the Grove sunlight sensor.
+
+### Task - program the sunlight sensor
 
 Program the device.
 
@@ -36,38 +38,44 @@ Program the device.
 
 1. Open the nightlight project in VS Code that you created in the previous part of this assignment, either running directly on the Pi or connected using the Remote SSH extension.
 
+1. Run the following command to install a pip package for working with the sunlight sensor:
+
+    ```sh
+    pip3 install seeed-python-si114x
+    ```
+
+    Not all the libraries for the Grove Sensors are installed with the Grove install script you used in an earlier lesson. Some need additional packages.
+
 1. Open the `app.py` file and remove all code from it
 
 1. Add the following code to the `app.py` file to import some required libraries:
 
     ```python
     import time
-    from grove.grove_light_sensor_v1_2 import GroveLightSensor
+    import seeed_si114x
     ```
 
     The `import time` statement imports the `time` module that will be used later in this assignment.
 
-    The `from grove.grove_light_sensor_v1_2 import GroveLightSensor` statement imports the `GroveLightSensor` from the Grove Python libraries. This library has code to interact with a Grove light sensor, and was installed globally during the Pi setup.
+    The `import seeed_si114x` statement imports the `seeed_si114x` module that has code to interact with the Grove sunlight sensor.
 
 1. Add the following code after the code above to create an instance of the class that manages the light sensor:
 
     ```python
-    light_sensor = GroveLightSensor(0)
+    light_sensor = seeed_si114x.grove_si114x()
     ```
 
-    The line `light_sensor = GroveLightSensor(0)` creates an instance of the `GroveLightSensor` class connecting to pin **A0** - the analog Grove pin that the light sensor is connected to.
+    The line `light_sensor = seeed_si114x.grove_si114x()` creates an instance of the `grove_si114x` sunlight sensor class.
-
-    > 💁 All the sockets have unique pin numbers. Pins 0, 2, 4, and 6 are analog pins, pins 5, 16, 18, 22, 24, and 26 are digital pins.
 
 1. Add an infinite loop after the code above to poll the light sensor value and print it to the console:
 
     ```python
     while True:
-        light = light_sensor.light
+        light = light_sensor.ReadVisible
         print('Light level:', light)
     ```
 
-    This will read the current light level on a scale of 0-1,023 using the `light` property of the `GroveLightSensor` class. This property reads the analog value from the pin. This value is then printed to the console.
+    This will read the current sunlight level on a scale of 0-1,023 using the `ReadVisible` property of the `grove_si114x` class. This value is then printed to the console.
 
 1. Add a small sleep of one second at the end of the `loop` as the light levels don't need to be checked continuously. A sleep reduces the power consumption of the device.
 
@@ -81,16 +89,16 @@ Program the device.
     python3 app.py
     ```
 
-    You should see light values being output to the console. Cover and uncover the light sensor to see the values change:
+    You should see sunlight values being output to the console. Cover and uncover the sunlight sensor to see the values change:
 
     ```output
     pi@raspberrypi:~/nightlight $ python3 app.py 
-    Light level: 634
+    Light level: 259
-    Light level: 634
+    Light level: 265
-    Light level: 634
+    Light level: 265
-    Light level: 230
+    Light level: 584
-    Light level: 104
+    Light level: 550
-    Light level: 290
+    Light level: 497
     ```
 
 > 💁 You can find this code in the [code-sensor/pi](code-sensor/pi) folder.

1-getting-started/lessons/3-sensors-and-actuators/virtual-device-actuator.md

@@ -12,17 +12,17 @@ The nightlight logic in pseudo-code is:
 
 ```output
 Check the light level.
-If the light is less than 200
+If the light is less than 300
     Turn the LED on
 Otherwise
     Turn the LED off
 ```
 
-### Add the sensors to CounterFit
+### Add the actuator to CounterFit
 
 To use a virtual LED, you need to add it to the CounterFit app
 
-#### Task
+#### Task - add the actuator to CounterFit
 
 Add the LED to the CounterFit app.
 
@@ -48,7 +48,7 @@ Add the LED to the CounterFit app.
 
 The nightlight can now be programmed using the CounterFit light sensor and LED.
 
-#### Task
+#### Task - program the nightlight
 
 Program the nightlight.
 
@@ -75,13 +75,13 @@ Program the nightlight.
 1. Add a check inside the `while` loop, and before the `time.sleep` to check the light levels and turn the LED on or off:
 
     ```python
-    if light < 200:
+    if light < 300:
         led.on()
     else:
         led.off()
     ```
 
-    This code checks the `light` value. If this is less than 200 it calls the `on` method of the `GroveLed` class which sends a digital value of 1 to the LED, turning it on. If the light value is greater than or equal to 200 it calls the `off` method, sending a digital value of 0 to the LED, turning it off.
+    This code checks the `light` value. If this is less than 300 it calls the `on` method of the `GroveLed` class which sends a digital value of 1 to the LED, turning it on. If the light value is greater than or equal to 300 it calls the `off` method, sending a digital value of 0 to the LED, turning it off.
 
     > 💁 This code should be indented to the same level as the `print('Light level:', light)` line to be inside the while loop!
 
@@ -101,7 +101,7 @@ Program the nightlight.
     Light level: 253
     ```
 
-1. Change the *Value* or the *Random* settings to vary the light level above and below 200. You will see the LED turn on and off.
+1. Change the *Value* or the *Random* settings to vary the light level above and below 300. You will see the LED turn on and off.
 
 ![The LED in the CounterFit app turning on and off as the light level changes](../../../images/virtual-device-running-assignment-1-1.gif)
 

1-getting-started/lessons/3-sensors-and-actuators/virtual-device-sensor.md

@@ -12,7 +12,7 @@ The sensor is a **light sensor**. In a physical IoT device, it would be a [photo
 
 To use a virtual light sensor, you need to add it to the CounterFit app
 
-#### Task
+#### Task - add the sensors to CounterFit
 
 Add the light sensor to the CounterFit app.
 
@@ -38,11 +38,10 @@ Add the light sensor to the CounterFit app.
 
 The device can now be programmed to use the built in light sensor.
 
-### Task
+### Task - program the light sensor
 
 Program the device.
 
-
 1. Open the nightlight project in VS Code that you created in the previous part of this assignment. Kill and re-create the terminal to ensure it is running using the virtual environment if necessary.
 
 1. Open the `app.py` file

1-getting-started/lessons/3-sensors-and-actuators/wio-terminal-actuator.md

@@ -12,7 +12,7 @@ The nightlight logic in pseudo-code is:
 
 ```output
 Check the light level.
-If the light is less than 200
+If the light is less than 300
     Turn the LED on
 Otherwise
     Turn the LED off
@@ -22,7 +22,7 @@ Otherwise
 
 The Grove LED comes as a module with a selection of LEDs, allowing you to chose the color.
 
-#### Task
+#### Task - connect the LED
 
 Connect the LED.
 
@@ -48,7 +48,7 @@ Connect the LED.
 
 The nightlight can now be programmed using the built in light sensor and the Grove LED.
 
-### Task
+### Task - program the nightlight
 
 Program the nightlight.
 
@@ -67,7 +67,7 @@ Program the nightlight.
 1. Add the following code immediately before the `delay` in the loop function:
 
     ```cpp
-    if (light < 200)
+    if (light < 300)
     {
         digitalWrite(D0, HIGH);
     }
@@ -77,7 +77,7 @@ Program the nightlight.
     }
     ```
 
-    This code checks the `light` value. If this is less than 200 it sends a `HIGH` value to the `D0` digital pin. This `HIGH` is a value of 1, turning on the LED. If the light is greater than or equal to 200, a `LOW` value of 0 is sent to the pin, turning the LED off.
+    This code checks the `light` value. If this is less than 300 it sends a `HIGH` value to the `D0` digital pin. This `HIGH` is a value of 1, turning on the LED. If the light is greater than or equal to 300, a `LOW` value of 0 is sent to the pin, turning the LED off.
 
     > 💁 When sending digital values to actuators, a LOW value is 0v, and a HIGH value is the max voltage for the device. For the Wio Terminal, the HIGH voltage is 3.3V.
 
@@ -101,7 +101,7 @@ Program the nightlight.
     Light value: 344
     ```
 
-1. Cover and uncover the light sensor. Notice how the LED will light up if the light level is 200 or less, and turn off when the light level is greater than 200.
+1. Cover and uncover the light sensor. Notice how the LED will light up if the light level is 300 or less, and turn off when the light level is greater than 300.
 
 ![The LED connected to the WIO turning on and off as the light level changes](../../../images/wio-running-assignment-1-1.gif)
 

1-getting-started/lessons/4-connect-internet/README.md

@@ -27,7 +27,7 @@ In this lesson we'll cover:
 
 ## Communication protocols
 
-There are a number of popular communication protocols used by IoT devices to communicate with the Internet. The most popular are based around publish/subscribe messaging via some kind of broker. The IoT devices connect to the broker and publish telemetry and subscribe to commands, the cloud services also connect to the broker and subscribe to all the telemetry messages and publishes commands either to specific devices, or to groups of devices.
+There are a number of popular communication protocols used by IoT devices to communicate with the Internet. The most popular are based around publish/subscribe messaging via some kind of broker. The IoT devices connect to the broker and publish telemetry and subscribe to commands, the cloud services also connect to the broker and subscribe to all the telemetry messages and publish commands either to specific devices, or to groups of devices.
 
 ![IoT devices connect to a broker and publish telemetry and subscribe to commands. Cloud services connect to the broker and subscribe to all telemetry and send commands to specific devices.](../../../images/pub-sub.png)
 
@@ -39,7 +39,7 @@ MQTT is the most popular, and is covered in this lesson. Others include AMQP and
 
 [MQTT](http://mqtt.org) is a lightweight, open standard messaging protocol that can send messages between devices. It was designed in 1999 to monitor oil pipelines, before being released as an open standard 15 years later by IBM.
 
-MQTT has a single broker and multiple clients. All clients connect to the broker, and the broker routes messages to the relevant clients. Messages are routed using named topics, rather than being sent direct to an individual client. A client can publish to a topic, and any clients that subscribe to that topic will receive the message.
+MQTT has a single broker and multiple clients. All clients connect to the broker, and the broker routes messages to the relevant clients. Messages are routed using named topics, rather than being sent directly to an individual client. A client can publish to a topic, and any clients that subscribe to that topic will receive the message.
 
 ![IoT device publishing telemetry on the /telemetry topic, and the cloud service subscribing to that topic](../../../images/mqtt.png)
 
@@ -49,19 +49,19 @@ MQTT has a single broker and multiple clients. All clients connect to the broker
 
 ### Connect your IoT device to MQTT
 
-The first part in adding Internet control to your nightlight is connecting it to an MQTT broker.
+The first part of adding Internet control to your nightlight is connecting it to an MQTT broker.
 
 #### Task
 
 Connect your device to an MQTT broker.
 
-In this part of the lesson, you will connect your IoT nightlight to the Internet to allow it to be remotely controlled. Later in this lesson your IoT device will send a telemetry message over MQTT to a public MQTT broker with the light level, where it will be picked up by some server code that you will write. This code will check the light level and send a command message back to the device telling it to turn the LED on or off.
+In this part of the lesson, you will connect your IoT nightlight to the Internet to allow it to be remotely controlled. Later in this lesson, your IoT device will send a telemetry message over MQTT to a public MQTT broker with the light level, where it will be picked up by some server code that you will write. This code will check the light level and send a command message back to the device telling it to turn the LED on or off.
 
-The real-world use case for such a setup could be to gather data from multiple light sensors before deciding to turn on lights, in a location that has a lot of lights, such as a stadium. This could stop the lights being turned on if only one sensor was covered by cloud or a bird, but the other sensors detected enough light.
+The real-world use case for such a setup could be to gather data from multiple light sensors before deciding to turn on lights, in a location that has a lot of lights, such as a stadium. This could stop the lights from being turned on if only one sensor was covered by cloud or a bird, but the other sensors detected enough light.
 
 ✅ What other situations would require data from multiple sensors to be evaluated before sending commands?
 
-Rather than dealing with the complexities of setting up an MQTT broker as part of this assignment, you can use a public test server that runs [Eclipse Mosquitto](https://www.mosquitto.org), an open-source MQTT broker. This test broker is publicly available at [test.mosquitto.org](https://test.mosquitto.org), and doesn't require an accounts to be set up, making it a great tool for testing MQTT clients and servers.
+Rather than dealing with the complexities of setting up an MQTT broker as part of this assignment, you can use a public test server that runs [Eclipse Mosquitto](https://www.mosquitto.org), an open-source MQTT broker. This test broker is publicly available at [test.mosquitto.org](https://test.mosquitto.org), and doesn't require an account to be set up, making it a great tool for testing MQTT clients and servers.
 
 > 💁 This test broker is public and not secure. Anyone could be listening to what you publish, so should not be used with any data that needs to be kept private
 
@@ -76,7 +76,7 @@ Follow the relevant step below to connect your device to the MQTT broker:
 
 ### A deeper dive into MQTT
 
-Topics can have a hierarchy, and clients can subscribe to different levels of the hierarchy using wildcards. For example you can send temperature telemetry messages to `/telemetry/temperature` and humidity messages to `/telemetry/humidity`, then in your cloud app subscribe to `/telemetry/*` to receive both the temperature and humidity telemetry messages.
+Topics can have a hierarchy, and clients can subscribe to different levels of the hierarchy using wildcards. For example, you can send temperature telemetry messages to `/telemetry/temperature` and humidity messages to `/telemetry/humidity`, then in your cloud app subscribe to `/telemetry/*` to receive both the temperature and humidity telemetry messages.
 
 Messages can be sent with a quality of service (QoS), which determines the guarantees of the message being received.
 
@@ -327,9 +327,9 @@ Write the server code.
 
 One important consideration with telemetry is how often to measure and send the data? The answer is - it depends. If you measure often you can respond faster to changes in measurements, but you use more power, more bandwidth, generate more data and need more cloud resources to process. You need to measure often enough, but not too often.
 
-For a thermostat, measuring every few minutes is probably more than enough as temperatures don't change that often. If you only measure once a day then you could end up heating your house for nighttime temperatures in the middle of a sunny day, whereas if you measure every second you will have thousands of unnecessary duplicated temperature measurements that will eat into the users Internet speed and bandwidth (a problem for people with limited bandwidth plans), use more power which can be a problem for battery powered devices like remote sensors, and increase the cost of the providers cloud computing resources processing and storing them.
+For a thermostat, measuring every few minutes is probably more than enough as temperatures don't change that often. If you only measure once a day then you could end up heating your house for nighttime temperatures in the middle of a sunny day, whereas if you measure every second you will have thousands of unnecessarily duplicated temperature measurements that will eat into the users' Internet speed and bandwidth (a problem for people with limited bandwidth plans), use more power which can be a problem for battery powered devices like remote sensors, and increase the cost of the providers cloud computing resources processing and storing them.
 
-If you are monitoring a data around a piece of machinery in a factory that if it fails could cause catastrophic damage and millions of dollars in lost revenue, thn measuring multiple times a second might be necessary. It's better to waste bandwidth than miss telemetry that indicates that a machine needs to be stopped and fixed before it breaks.
+If you are monitoring data around a piece of machinery in a factory that if it fails could cause catastrophic damage and millions of dollars in lost revenue, then measuring multiple times a second might be necessary. It's better to waste bandwidth than miss telemetry that indicates that a machine needs to be stopped and fixed before it breaks.
 
 > 💁 In this situation, you might consider having an edge device to process the telemetry first to reduce reliance on the Internet.
 
@@ -339,7 +339,7 @@ Internet connections can be unreliable, with outages common. What should an IoT
 
 For a thermostat the data can probably be lost as soon as a new temperature measurement has been taken. The heating system doesn't care that 20 minutes ago it was 20.5°C if the temperature is now 19°C, it's the temperature now that determines if the heating should be on or off.
 
-For machinery you might want to keep the data, especially if it is used to look for trends. There are machine learning models that can detect anomalies in streams of data by looking over data from defined period of time (such as the last hour) and spotting anomalous data. This is often used for predictive maintenance, looking for indications that something might break soon so you can repair or replace before it happens. You might want every bit of telemetry for a machine sent so it can be processed for anomaly detection, so once the IoT device can reconnect it will send all the telemetry generated during the Internet outage.
+For machinery you might want to keep the data, especially if it is used to look for trends. There are machine learning models that can detect anomalies in streams of data by looking over data from defined period of time (such as the last hour) and spotting anomalous data. This is often used for predictive maintenance, looking for indications that something might break soon so you can repair or replace it before that happens. You might want every bit of telemetry for a machine sent so it can be processed for anomaly detection, so once the IoT device can reconnect it will send all the telemetry generated during the Internet outage.
 
 IoT device designers should also consider if the IoT device can be used during an Internet outage or loss of signal caused by location. A smart thermostat should be able to make some limited decisions to control heating if it can't send telemetry to the cloud due to an outage.
 
@@ -372,13 +372,13 @@ The next step for our Internet controlled nightlight is for the server code to s
 1. Add the following code to the end of the `handle_telemetry` function:
 
     ```python
-    command = { 'led_on' : payload['light'] < 200 }
+    command = { 'led_on' : payload['light'] < 300 }
     print("Sending message:", command)
     
     client.publish(server_command_topic, json.dumps(command))
     ```
 
-    This sends a JSON message to the command topic with the value of `led_on` set to true or false depending on if the light is less than 200 or not. If the light is less than 200, true is sent to instruct the device to turn the LED on.
+    This sends a JSON message to the command topic with the value of `led_on` set to true or false depending on if the light is less than 300 or not. If the light is less than 300, true is sent to instruct the device to turn the LED on.
 
 1. Run the code as before
 
@@ -421,7 +421,7 @@ If the commands need to be processed in sequence, such as move a robot arm up, t
 
 ## 🚀 Challenge
 
-The challenge in the last three lessons was to list as many IoT devices as you can that are in your home, school or workplace and decide if they are built around microcontrollers or single-board computers, or even a mixture of both, and thing about what sensors and actuators they are using.
+The challenge in the last three lessons was to list as many IoT devices as you can that are in your home, school or workplace and decide if they are built around microcontrollers or single-board computers, or even a mixture of both, and think about what sensors and actuators they are using.
 
 For these devices, think about what messages they might be sending or receiving. What telemetry do they send? What messages or commands might they receive? Do you think they are secure?
 

1-getting-started/lessons/4-connect-internet/code-commands/server/app.py

@@ -18,7 +18,7 @@ def handle_telemetry(client, userdata, message):
     payload = json.loads(message.payload.decode())
     print("Message received:", payload)
 
-    command = { 'led_on' : payload['light'] < 200 }
+    command = { 'led_on' : payload['light'] < 300 }
     print("Sending message:", command)
 
     client.publish(server_command_topic, json.dumps(command))

1-getting-started/lessons/4-connect-internet/code-mqtt/pi/nightlight/app.py

@@ -21,7 +21,7 @@ while True:
     light = light_sensor.light
     print('Light level:', light)
 
-    if light < 200:
+    if light < 300:
         led.on()
     else:
         led.off()

1-getting-started/lessons/4-connect-internet/code-mqtt/virtual-device/nightlight/app.py

@@ -24,7 +24,7 @@ while True:
     light = light_sensor.light
     print('Light level:', light)
 
-    if light < 200:
+    if light < 300:
         led.on()
     else:
         led.off()

3-transport/README.md

@@ -10,7 +10,7 @@ IoT can help with this supply chain by tracking the food in transit - ensuring d
 
 In these 4 lessons, you'll learn how to apply the Internet of Things to improve the supply chain by monitoring food as it is loaded onto a (virtual) truck, which is tracked as it moves to it's destination. You will learn about GPS tracking, how to store and visualize GPS data, and how to be alerted when a truck arrives at its destination.
 
-> 💁 These lessons will use some cloud resources. If you don't complete all the lessons in this project, make sure you follow the [Clean up your project](lessons/4-keep-your-plant-secure/README.md#clean-up-your-project) step in [lesson 4](lessons/6-keep-your-plant-secure/README.md).
+> 💁 These lessons will use some cloud resources. If you don't complete all the lessons in this project, make sure you [Clean up your project](../clean-up.md).
 
 ## Topics
 

4-manufacturing/README.md

@@ -0,0 +1,24 @@
+# Manufacturing and processing - using IoT to improve the processing of food
+
+Once food reaches a central hub or processing plant, it isn't always just shipped out to supermarkets. A lot of the time the food goes through a number of processing steps, such as sorting by quality. This is a process that used to be manual - it would start in the field when pickers would only pick ripe fruit, then at the factory the fruit would be ride a conveyer belt and employees would manually remove any bruised or rotten fruit. Having picked and sorted strawberries myself as a summer job during school, I can testify that this isn't a fun job.
+
+More modern setups rely on IoT for sorting. Some of the earliest devices like the sorters from [Weco](https://wecotek.com) use optical sensors to detect the quality of produce, rejecting green tomatoes for example. These can be deployed in harvesters on the farm itself, or in processing plants.
+
+As advances happen in Artificial Intelligence (AI) and Machine Learning (ML), these machines can become more advanced, using ML models trained to distinguish between fruit and foreign objects such as rocks, dirt or insects. These models can also be trained to detect fruit quality, not just bruised fruit but early detection of disease or other crop problems.
+
+> 🎓 The term *ML model* refers to the output of training machine learning software on a set of data. For example, you can train a ML model to distinguish between ripe and unripe tomatoes, then use the model on new images to see if the tomatoes are ripe or not.
+
+In these 4 lessons you'll learn how to train image-based AI models to detect fruit quality, how to use these from an IoT device, and how to run these on the edge - that is on an IoT device rather than in the cloud.
+
+> 💁 These lessons will use some cloud resources. If you don't complete all the lessons in this project, make sure you [Clean up your project](../clean-up.md).
+
+## Topics
+
+1. [Train a fruit quality detector](./4-manufacturing/lessons/1-train-fruit-detector/README.md)
+1. [Check fruit quality from an IoT device](./4-manufacturing/lessons/2-check-fruit-from-device/README.md)
+1. [Run your fruit detector on the edge](./4-manufacturing/lessons/3-run-fruit-detector-edge/README.md)
+1. [Trigger fruit quality detection from a sensor](./4-manufacturing/lessons/4-trigger-fruit-detector/README.md)
+
+## Credits
+
+All the lessons were written with ♥️ by [Jim Bennett](https://GitHub.com/JimBobBennett)

4-manufacturing/lessons/1-train-fruit-detector/README.md

@@ -0,0 +1,211 @@
+# Train a fruit quality detector
+
+Add a sketchnote if possible/appropriate
+
+This video gives an overview of the Azure Custom Vision service, a service that will be covered in this lesson.
+
+[![Custom Vision – Machine Learning Made Easy | The Xamarin Show](https://img.youtube.com/vi/TETcDLJlWR4/0.jpg)](https://www.youtube.com/watch?v=TETcDLJlWR4)
+
+## Pre-lecture quiz
+
+[Pre-lecture quiz](https://brave-island-0b7c7f50f.azurestaticapps.net/quiz/29)
+
+## Introduction
+
+The recent rise in Artificial Intelligence (AI) and Machine Learning (ML) is providing a wide range of capabilities to todays developers. ML models can be trained to recognize different things in images, including unripe fruit, and this can be used in IoT devices to help sort produce either as it is being harvested, or during processing in factories or warehouses.
+
+In this lesson you will learn about image classification - using ML models to distinguish between images of different things. You will learn how to train an image classifier to distinguish between fruit that is good, and fruit that is bad, either under or over ripe, bruised, or rotten.
+
+In this lesson we'll cover:
+
+* [Using AI and ML to sort food](#using-ai-and-ml-to-sort-food)
+* [Image classification via Machine Learning](#image-classification-via-machine-learning)
+* [Train an image classifier](#train-an-image-classifier)
+* [Test your image classifier](#test-your-image-classifier)
+
+## Using AI and ML to sort food
+
+Feeding the global population is hard, especially at a price that makes food affordable for all. One of the largest costs is labor, so farmers are increasingly turning to automation and tools like IoT to reduce their labor costs. Harvesting by hand is labor intensive (and often backbreaking work), and is being replaced by machinery, especially in richer nations. Despite the savings in cost of using machinery to harvest, there is a downside - the ability to sort food as it is being harvested.
+
+Not all crops ripen evenly. Tomatoes, for example, can still have some green fruits on the vine when the majority is ready for harvest. Although it is a waste to harvest these early, it is cheaper and easier for the farmer to harvest everything using machinery and dispose of the unripe produce later.
+
+✅ Have a look at different fruits or vegetables, either growing near you in farms or in your garden, or in shops, Are they all the same ripeness, or do you see variation?
+
+The rise of automated harvesting moved the sorting of produce from the harvest to the factory. Food would travel on long conveyer belts with teams of people picking over the produce removing anything that wasn't up to the required quality standard. Harvesting was cheaper thanks to machinery, but there was still a cost to manually sort food.
+
+![If a red tomato is detected it continues its journey uninterrupted. If a green tomato is detected it is flicked into a waste bin by a lever](../../../images/optical-tomato-sorting.png)
+
+***If a red tomato is detected it continues its journey uninterrupted. If a green tomato is detected it is flicked into a waste bin by a lever. tomato by parkjisun from the Noun Project - from the [Noun Project](https://thenounproject.com)***
+
+The next evolution was to use machines to sort, either built into the harvester, or in the processing plants. The first generation of these machines used optical sensors to detect colors, controlling actuators to push green tomatoes into a waste bin using levers or puffs of air, leaving red tomatoes to continue on a network of conveyor belts.
+
+The video below shows one of these machines in action.
+
+[![Automatic sorting of tomatoes via color](https://img.youtube.com/vi/AcRL91DouAU/0.jpg)](https://www.youtube.com/watch?v=AcRL91DouAU)
+
+In this video, as tomatoes fall from one conveyer belt to another, green tomatoes are detected and flicked into a bin using levers.
+
+✅ What conditions would you need in a factory or in a field for these optical sensors to work correctly?
+
+The latest evolutions of these sorting machines take advantage of AI and ML, using models trained to distinguish good produce from bad, not just by obvious color differences such as green tomatoes vs red, but by more subtle differences in appearance that can indicate disease or bruising.
+
+## Image classification via Machine Learning
+
+Traditional programming is where you take data, apply an algorithm to the data, and get output. For example, in the last project you took GPS coordinates and a geofence, applied an algorithm that was provided by Azure Maps, and got back a result of if the point was inside or outside the geofence. You input more data, you get more output.
+
+![Traditional development takes input and an algorithm and gives output. Machine learning uses input and output data to train a model, and this model can take new input data to generate new output](../../../images/traditional-vs-ml.png)
+
+Machine learning turns this around - you start with data and known outputs, and the machine learning tools work out the algorithm. You can then take that algorithm, called a *machine learning model*, and input new data and get new output.
+
+> 🎓 The process of a machine learning tool generating a model is called *training*. The inputs and known outputs are called *training data*.
+
+For example, you could give a model millions of pictures of unripe bananas as input training data, with the training output set as `unripe`, and millions of ripe banana pictures as training data with the output set as `ripe`. The ML tools will then generate a model. You then give this model a new picture of a banana and it will predict if the new picture is a ripe or an unripe banana.
+
+> 🎓 The results of ML models are called *predictions*
+
+![2 bananas, a ripe one with a prediction of 99.7% ripe, 0.3% unripe, and an unripe one with a prediction of 1.4% ripe, 98.6% unripe](../../../images/bananas-ripe-vs-unripe-predictions.png)
+
+ML models don't give a binary answer, instead they give probabilities. For example, a model may be given a picture of a banana and predict `ripe` at 99.7% and `unripe` at 0.3%. Your code would then pick the best prediction and decide the banana is ripe.
+
+The ML model used to detect images like this is called an *image classifier* - it is given labelled images, and then classifies new images based off these labels.
+
+## Train an image classifier
+
+To successfully train an image classifier you need millions of images. As it turns out, once you have an image classifier trained on millions or billions of assorted images, you can re-use it and re-train it using a small set of images and get great results, using a process called *transfer learning*.
+
+> 🎓 Transfer learning is where you transfer the learning from an existing ML model to a new model based off new data.
+
+Once an image classifier has been trained for a wide variety of images, it's internals are great at recognizing shapes, colors and patterns. Transfer learning allows the model to take what it has already learned in recognizing image parts, and use that to recognize new images.
+
+![Once you can recognize shapes, they can be put into different configurations to make a boat or a cat](../../../images/shapes-to-images.png)
+
+You can think of this as a bit like children's shape books, where once you can recognize a semi-circle, a rectangle and a triangle, you can recognize a sailboat or a cat depending on the configuration of these shapes. The image classifier can recognize the shapes, and the transfer learning teaches it what combination makes a boat or a cat - or a ripe banana.
+
+There are a wide range of tools that can help you do this, including cloud-based services that can help you train your model, then use it via web APIs.
+
+> 💁 Training these models takes a lot of computer power, usually via Graphics Processing Units, or GPUs. The same specialized hardware that makes games on your Xbox look amazing can also be used to train machine learning models. By using the cloud you can rent time on powerful computers with GPUs to train these models, getting access to the computing power you need, just for the time you need it.
+
+## Custom Vision
+
+Custom Vision is a cloud based tool for training image classifiers. It allows you to train a classifier using only a small number of images. You can upload images through a web portal, web API or an SDK, giving each image a *tag* that has the classification of that image. You then train the model, and test it out to see how well it performs. Once you are happy with the model, you can publish versions of it that can be accessed through a web API or an SDK.
+
+> 💁 You can train a custom vision model with as little as 5 images per classification, but more is better. You can get better results with at least 30 images.
+
+Custom Vision is part of a range of AI tools from Microsoft called Cognitive Services. These are AI tools that can be used either without any training, or with a small amount of training. They include speech recognition and translation, language understanding and image analysis. These are available with a free tier as services in Azure.
+
+> 💁 The free tier is more than enough to create a model, train it, then use it for development work. You can read about the limits of the free tier on the [Custom Vision Limits and quotas page on Microsoft docs](https://docs.microsoft.com/azure/cognitive-services/custom-vision-service/limits-and-quotas?WT.mc_id=academic-17441-jabenn).
+
+### Task - create a cognitive services resource
+
+To use Custom Vision, you first need to create two cognitive services resources in Azure using the Azure CLI, one for Custom Vision training and one for Custom Vision prediction.
+
+1. Create a Resource Group for this project called `fruit-quality-detector`
+
+1. Use the following command to create a free Custom Vision training resource:
+
+    ```sh
+    az cognitiveservices account create --name fruit-quality-detector-training \
+                                        --resource-group fruit-quality-detector \
+                                        --kind CustomVision.Training \
+                                        --sku F0 \
+                                        --yes \
+                                        --location <location>
+    ```
+
+    Replace `<location>` with the location you used when creating the Resource Group.
+
+    This will create a Custom Vision training resource in your Resource Group. It will be called `fruit-quality-detector-training` and use the `F0` sku, which is the free tier. The `--yes` option means you agree to the terms and conditions of the cognitive services.
+
+1. Use the following command to create a free Custom Vision prediction resource:
+
+    ```sh
+    az cognitiveservices account create --name fruit-quality-detector-prediction \
+                                        --resource-group fruit-quality-detector \
+                                        --kind CustomVision.Prediction \
+                                        --sku F0 \
+                                        --yes \
+                                        --location <location>
+    ```
+
+    Replace `<location>` with the location you used when creating the Resource Group.
+
+    This will create a Custom Vision prediction resource in your Resource Group. It will be called `fruit-quality-detector-prediction` and use the `F0` sku, which is the free tier. The `--yes` option means you agree to the terms and conditions of the cognitive services.
+
+### Task - create an image classifier project
+
+1. Follow the [Create a new Project section of the Build a classifier quickstart on the Microsoft docs](https://docs.microsoft.com/azure/cognitive-services/custom-vision-service/getting-started-build-a-classifier?WT.mc_id=academic-17441-jabenn#create-a-new-project) to create a new Custom Vision project. The UI may change and these docs are always the most up to date reference.
+
+    Call your project `fruit-quality-detector`.
+
+    When you create your project, make sure to use the `fruit-quality-detector-training` resource you created earlier. Use a *Classification* project type, a *Multiclass* classification type, and the *Food* domain.
+
+    ![The settings for the custom vision project with the name set to fruit-quality-detector, no description, the resource set to fruit-quality-detector-training, the project type set to classification, the classification types set to multi class and the domains set to food](../../../images/custom-vision-create-project.png)
+
+### Task - train your image classifier project
+
+To train an image classifier, you will need multiple pictures of fruit, both good and bad quality to tag as good and bad, such as an ripe and an overripe banana.
+
+> 💁 These classifiers can classify images of anything, so if you don't have fruit to hand of differing quality, you can use two different types of fruit, or cats and dogs!
+
+Ideally each picture should be just the fruit, with either a consistent background, or a wide variety of backgrounds. Ensure there's nothing in the background that is specific to ripe vs unripe fruit.
+
+> 💁 It's important not to have specific backgrounds, or specific items that are not related to the thing being classified for each tag, otherwise the classifier may just classify based on the background. There was a classifier for skin cancer that was trained on moles both normal and cancerous, and the cancerous ones all had rulers against them to measure the size. It turned out the classifier was almost 100% accurate at identifying rulers in pictures, not cancerous moles.
+
+1. Gather pictures for your classifier. You will need at least 5 pictures for each label to train the classifier, but the more the better. You will also need a few additional images to test the classifier. These images should all be different images of the same thing. For example:
+
+    * Using 2 ripe bananas, take some pictures of each one from a few different angles, taking at least 7 pictures (5 to train, 2 to test), but ideally more.
+
+        ![Photos of 2 different bananas](../../../images/banana-training-images.png)
+
+    * Repeat the same process using 2 unripe bananas
+
+    You should have at least 10 training images, with at least 5 ripe and 5 unripe, and 4 testing images, 2 ripe, 2 unripe. You're images should be png or jpegs, small than 6MB. If you create them with an iPhone for example they may be high-resolution HEIC images, so will need to be converted and possibly shrunk. The more images the better, and you should have a similar number of ripe and unripe.
+
+    If you don't have both ripe and unripe fruit, you can use different fruits, or any two objects you have available. You can also find some example images in the [images](./images) folder of ripe and unripe bananas that you can use.
+
+1. Follow the [Upload and tag images section of the Build a classifier quickstart on the Microsoft docs](https://docs.microsoft.com/azure/cognitive-services/custom-vision-service/getting-started-build-a-classifier?WT.mc_id=academic-17441-jabenn#upload-and-tag-images) to upload your training images. Tag the ripe fruit as `ripe`, and the unripe fruit as `unripe`.
+
+    ![The upload dialogs showing the upload of ripe and unripe banana pictures](../../../images/image-upload-bananas.png)
+
+1. Follow the [Train the classifier section of the Build a classifier quickstart on the Microsoft docs](https://docs.microsoft.com/azure/cognitive-services/custom-vision-service/getting-started-build-a-classifier?WT.mc_id=academic-17441-jabenn#train-the-classifier) to train the image classifier on your uploaded images.
+
+    You will be given a choice of training type. Select **Quick Training**.
+
+The classifier will then train. It will take a few minutes for the training to complete.
+
+> 🍌 If you decide to eat your fruit whilst the classifier is training, make sure you have enough images to test with first!
+
+## Test your image classifier
+
+Once your classifier is trained, you can test it by giving it a new image to classify.
+
+### Task - test your image classifier
+
+1. Follow the [Test and retrain a model with Custom Vision Service documentation on the Microsoft docs](https://docs.microsoft.com/azure/cognitive-services/custom-vision-service/test-your-model?WT.mc_id=academic-17441-jabenn#test-your-model) to test your image classifier. Use the testing images you created earlier, not any of the images you used for training.
+
+    ![A unripe banana predicted as unripe with a 98.9% probability, ripe with a 1.1% probability](../../../images/banana-unripe-quick-test-prediction.png)
+
+1. Try all the testing images you have access to and observe the probabilities.
+
+---
+
+## 🚀 Challenge
+
+Image classifiers use machine learning to make predictions about what is in an image, based of probabilities that particular features of an image mean that it matches a particular label. It doesn't understand what is in the image - it doesn't know what a banana is or understand what makes a banana a banana instead of a boat.
+
+What do you think would happen if you used a picture of a strawberry with a model trained on bananas, or a picture of an inflatable banana, or a person in a banana suit, or even a yellow cartoon character like someone from the Simpsons?
+
+Try it out and see what the predictions are. You can find images to try with using [Bing Image search](https://www.bing.com/images/trending).
+
+## Post-lecture quiz
+
+[Post-lecture quiz](https://brave-island-0b7c7f50f.azurestaticapps.net/quiz/30)
+
+## Review & Self Study
+
+* When you trained your classifier, you would have seen values for *Precision*, *Recall*, and *AP* that rate the model that was created. Read up on what these values are using [the Evaluate the classifier section of the Build a classifier quickstart on the Microsoft docs](https://docs.microsoft.com/azure/cognitive-services/custom-vision-service/getting-started-build-a-classifier?WT.mc_id=academic-17441-jabenn#evaluate-the-classifier)
+* Read up on how to improve your classifier from the [How to improve your Custom Vision model on the Microsoft docs](https://docs.microsoft.com/azure/cognitive-services/custom-vision-service/getting-started-improving-your-classifier?WT.mc_id=academic-17441-jabenn)
+
+## Assignment
+
+[Train your classifier for multiple fruits and vegetables](assignment.md)

4-manufacturing/lessons/1-train-fruit-detector/assignment.md

@@ -0,0 +1,16 @@
+# Train your classifier for multiple fruits and vegetables
+
+## Instructions
+
+In this lesson you trained an image classifier to be able to distinguish between ripe and unripe fruits, but only using one type of fruit. A classifier can be trained to recognize multiple fruits, with varying rates of success depending on the type of fruit and the difference between ripe and unripe.
+
+For example, with fruits that change color when they ripen, image classifiers might be less effective than a color sensor as they usually work on grey scale images instead of full color.
+
+Train your classifier with other fruits to see how well it works, especially when fruits look similar. For example, apples and tomatoes.
+
+## Rubric
+
+| Criteria | Exemplary | Adequate | Needs Improvement |
+| -------- | --------- | -------- | ----------------- |
+| Train the classifier for multiple fruits | Was able to train the classifier for multiple fruits | Was able to train the classifier for one additional fruit | Was unable to train the classifier for more fruits |
+| Determine how well the classifier works | Was able to comment correctly on how well the classifier worked with different fruits | Was able to observe and offer suggestions as to how well it was working | Was unable to comment on how well the classifier worked |

4-manufacturing/lessons/2-check-fruit-from-device/README.md

@@ -0,0 +1,33 @@
+# Check fruit quality from an IoT device
+
+Add a sketchnote if possible/appropriate
+
+![Embed a video here if available](video-url)
+
+## Pre-lecture quiz
+
+[Pre-lecture quiz](https://brave-island-0b7c7f50f.azurestaticapps.net/quiz/31)
+
+## Introduction
+
+In this lesson you will learn about
+
+In this lesson we'll cover:
+
+* [Thing 1](#thing-1)
+
+## Thing 1
+
+---
+
+## 🚀 Challenge
+
+## Post-lecture quiz
+
+[Post-lecture quiz](https://brave-island-0b7c7f50f.azurestaticapps.net/quiz/32)
+
+## Review & Self Study
+
+## Assignment
+
+[](assignment.md)

4-manufacturing/lessons/2-check-fruit-from-device/assignment.md

@@ -0,0 +1,9 @@
+#
+
+## Instructions
+
+## Rubric
+
+| Criteria | Exemplary | Adequate | Needs Improvement |
+| -------- | --------- | -------- | ----------------- |
+| |  |  |  |

4-manufacturing/lessons/3-run-fruit-detector-edge/README.md

@@ -0,0 +1,33 @@
+# Run your fruit detector on the edge
+
+Add a sketchnote if possible/appropriate
+
+![Embed a video here if available](video-url)
+
+## Pre-lecture quiz
+
+[Pre-lecture quiz](https://brave-island-0b7c7f50f.azurestaticapps.net/quiz/33)
+
+## Introduction
+
+In this lesson you will learn about
+
+In this lesson we'll cover:
+
+* [Thing 1](#thing-1)
+
+## Thing 1
+
+---
+
+## 🚀 Challenge
+
+## Post-lecture quiz
+
+[Post-lecture quiz](https://brave-island-0b7c7f50f.azurestaticapps.net/quiz/34)
+
+## Review & Self Study
+
+## Assignment
+
+[](assignment.md)

4-manufacturing/lessons/3-run-fruit-detector-edge/assignment.md

@@ -0,0 +1,9 @@
+#
+
+## Instructions
+
+## Rubric
+
+| Criteria | Exemplary | Adequate | Needs Improvement |
+| -------- | --------- | -------- | ----------------- |
+| |  |  |  |

4-manufacturing/lessons/4-trigger-fruit-detector/README.md

@@ -0,0 +1,33 @@
+# Trigger fruit quality detection from a sensor
+
+Add a sketchnote if possible/appropriate
+
+![Embed a video here if available](video-url)
+
+## Pre-lecture quiz
+
+[Pre-lecture quiz](https://brave-island-0b7c7f50f.azurestaticapps.net/quiz/35)
+
+## Introduction
+
+In this lesson you will learn about
+
+In this lesson we'll cover:
+
+* [Thing 1](#thing-1)
+
+## Thing 1
+
+---
+
+## 🚀 Challenge
+
+## Post-lecture quiz
+
+[Post-lecture quiz](https://brave-island-0b7c7f50f.azurestaticapps.net/quiz/36)
+
+## Review & Self Study
+
+## Assignment
+
+[](assignment.md)

4-manufacturing/lessons/4-trigger-fruit-detector/assignment.md

@@ -0,0 +1,9 @@
+#
+
+## Instructions
+
+## Rubric
+
+| Criteria | Exemplary | Adequate | Needs Improvement |
+| -------- | --------- | -------- | ----------------- |
+| |  |  |  |

README.md

@@ -79,6 +79,10 @@ We have two choices of IoT hardware to use for the projects depending on persona
 | 12 | [Transport](./3-transport) | Store location data | Learn how to store IoT data to be visualized or analysed later | [Store location data](./3-transport/lessons/2-store-location-data/README.md) |
 | 13 | [Transport](./3-transport) | Visualize location data | Learn about visualizing location data on a map, and how maps represent the real 3d world in 2 dimensions | [Visualize location data](./3-transport/lessons/3-visualize-location-data/README.md) |
 | 14 | [Transport](./3-transport) | Geofences | Learn about geofences, and how they can be used to alert when vehicles in the supply chain are close to their destination | [Geofences](./3-transport/lessons/4-geofences/README.md) |
+| 15 | [Manufacturing](./4-manufacturing) | Train a fruit quality detector | Learn about training an image classifier in the cloud to detect fruit quality | [Train a fruit quality detector](./4-manufacturing/lessons/1-train-fruit-detector/README.md) |
+| 16 | [Manufacturing](./4-manufacturing) | Check fruit quality from an IoT device | Learn about using your fruit quality detector from an IoT device | [Check fruit quality from an IoT device](./4-manufacturing/lessons/2-check-fruit-from-device/README.md) |
+| 17 | [Manufacturing](./4-manufacturing) | Run your fruit detector on the edge | Learn about running your fruit detector on an IoT device on the edge | [Run your fruit detector on the edge](./4-manufacturing/lessons/3-run-fruit-detector-edge/README.md) |
+| 18 | [Manufacturing](./4-manufacturing) | Trigger fruit quality detection from a sensor | Learn about triggering fruit quality detection from a sensor | [Trigger fruit quality detection from a sensor](./4-manufacturing/lessons/4-trigger-fruit-detector/README.md) |
 
 ## Offline access
 

hardware.md

@@ -23,7 +23,7 @@ All the device code for Arduino is in C++. To complete all the assignments you w
 
 These are specific to using the Wio terminal Arduino device, and are not relevant to using the Raspberry Pi.
 
-* [Grove camera kit](https://www.seeedstudio.com/Grove-Serial-Camera-Kit.html)
+* [ArduCam Mini 2MP Plus - OV2640](https://www.arducam.com/product/arducam-2mp-spi-camera-b0067-arduino/)
 * [Grove speaker plus](https://www.seeedstudio.com/Grove-Speaker-Plus-p-4592.html)
 
 ## Raspberry Pi
@@ -48,7 +48,7 @@ These are specific to using the Raspberry Pi, and are not relevant to using the
   * Any USB speaker, or speaker with a 3.5mm cable
   or
   * [USB Speakerphone](https://www.amazon.com/USB-Speakerphone-Conference-Business-Microphones/dp/B07Q3D7F8S/ref=sr_1_1?dchild=1&keywords=m0&qid=1614647389&sr=8-1)
-* [Grove Light sensor](https://www.seeedstudio.com/Grove-Light-Sensor-v1-2-LS06-S-phototransistor.html)
+* [Grove Sunlight sensor](https://www.seeedstudio.com/Grove-Sunlight-Sensor.html)
 
 ## Sensors and actuators
 
@@ -58,8 +58,6 @@ Most of the sensors and actuators needed are used by both the Arduino and Raspbe
 * [Grove humidity and temperature sensor](https://www.seeedstudio.com/Grove-Temperature-Humidity-Sensor-DHT11.html)
 * [Grove capacitive soil moisture sensor](https://www.seeedstudio.com/Grove-Capacitive-Moisture-Sensor-Corrosion-Resistant.html)
 * [Grove relay](https://www.seeedstudio.com/Grove-Relay.html)
-* [Grove 125KHz RFID reader](https://www.seeedstudio.com/Grove-125KHz-RFID-Reader.html)
-* [RFID tags (125KHz)](https://www.seeedstudio.com/RFID-tag-combo-125khz-5-pcs-p-700.html)
 * [Grove GPS (Air530)](https://www.seeedstudio.com/Grove-GPS-Air530-p-4584.html)
 * [Grove - Ultrasonic Distance Sensor](https://www.seeedstudio.com/Grove-Ultrasonic-Distance-Sensor.html)
 

images/icons/noun_tomato_1285672.svg

@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg" data-name="Layer 1" viewBox="0 0 96 116.8875" x="0px" y="0px"><title>18</title><path d="M97.28,40.76A31.82,31.82,0,0,0,77.71,17.64c-1.4.77-4.47,2.39-7.48,3.64a15.14,15.14,0,0,1-7.81,1,18.06,18.06,0,0,0,2.17,2.18c2.15,2,2.8,6.45,2.8,6.45a20.36,20.36,0,0,1-2.3.45c-7.63.34-17.59-5.15-17.59-5.15-2.15-.11-6.28,1.64-9.68,3.11s-10.65,2-10.65,2A34.79,34.79,0,0,1,30,25.59C31.76,22.87,34,19.81,34,19.81c-2.5-1.09-4.93-3.91-6.09-5.39C8.43,20.62-2.47,42.28,3.75,62.49a48.65,48.65,0,0,0,52,34C91.82,92.46,100.84,56.46,97.28,40.76Z" transform="translate(-2 -3.24)"/><path d="M40.05,18.67C37.93,20.38,32.66,27,32.66,27s4.75-1.44,6.25-2.14c6-2.76,9.64-2.66,9.64-2.66a62.36,62.36,0,0,0,13.63,5.2c-.67-2.17-2.1-1.76-4-6.09-1.06-2.41,1.48-2.06,5.58-2.11C70.26,19.1,79,12.8,79,12.8c-3.24-.87-9.09,3.14-13.09,3a67.33,67.33,0,0,1-10.25-1.61c-2.67-1.35-2-6.31-1.43-8.7A1.74,1.74,0,0,0,53,3.42a8.21,8.21,0,0,0-3.26,0,1.63,1.63,0,0,0-.85.42C45.68,7,46.38,13.3,46.38,13.3a4,4,0,0,0,3.71,3.62c3.4.26,4.42-.85,4.42-.85s-1.77,3.46-7,2c-2-.56-3.21-2.36-3.93-4.47L40.37,14c-6.34-.44-12.43-8.1-12.43-8.1A17.59,17.59,0,0,0,40.05,18.67Z" transform="translate(-2 -3.24)"/><text x="0" y="108.51" fill="#000000" font-size="5px" font-weight="bold" font-family="'Helvetica Neue', Helvetica, Arial-Unicode, Arial, Sans-serif">Created by parkjisun</text><text x="0" y="113.51" fill="#000000" font-size="5px" font-weight="bold" font-family="'Helvetica Neue', Helvetica, Arial-Unicode, Arial, Sans-serif">from the Noun Project</text></svg>