the ilab experience
play

The iLab Experience a blended learning hands-on course concept you - PowerPoint PPT Presentation

The iLab Experience a blended learning hands-on course concept you set the focus Your Topics Structure 2019-05-14 Kick Off 04/23 1 IPv6 IPv6 04/30 BGP 2 Minilab 1+2+3 05/07 BGP 3 Your Exercise Topic Storm (IoT) 05/14 Minis


  1. Order of Presentations Team Topic 204 Becoming a beekeeper of ZigBee 202a Endless use cases for BLE Mesh Networks 202b LoRaWAN - The backbone of LoRa Networks 208 IoT orchestration with RabbitMQ 203 Sending a picture from a Raspberry Pi/Arduino via MQTT - Am I Safe in the Lab? 201 Risks & REST with CoAP 206 IoT - the ’S’ stands for security Break (into) your smart home 205 IoT Data Flows - Save the ISS! 207 The What, The How and The Why of Data

  2. reate your own exercise Kilian Schulte, Tobias Leibbrand| TEAM 202 Endless use cases for BLE Mesh Networks – Hospitals, Logistics, Transportation, Smart City, … 1

  3. Outline Lecture • Learn about the BLE Network Protocols (Communication, BLE Channels) • BLE Layer Architecture • Outlook: BLE Mesh Network and use cases • Exercise: Develop an own use case 2

  4. Outline PreLab • How are BLE Mesh Networks organized • Deeper look into the BLE Protocols • Learn about the four types of device models in a mesh network 3

  5. Outline Lab • Setup an own BLE Mesh Network for a use case of your choice • Deploy several BLE nodes • Testing (Run around the university) • Analyse how the devices are communicating 4

  6. What Will Your Students Learn? The Following Learning Goals are Covered in the Lecture PreLab Lab Understand BLE Network Protocols X X Learn about the BLE Layers X Understand BLE Mesh Networks X X Learn about pro and cons of BLE Networks X Setup and manage an own BLE Mesh Network X 5

  7. Teaser Practical Part Node / Observer Node / Relay Node / Sensor Node / Relay Webserver 6

  8. Order of Presentations Team Topic 204 Becoming a beekeeper of ZigBee 202a Endless use cases for BLE Mesh Networks 202b LoRaWAN - The backbone of LoRa Networks 208 IoT orchestration with RabbitMQ 203 Sending a picture from a Raspberry Pi/Arduino via MQTT - Am I Safe in the Lab? 201 Risks & REST with CoAP 206 IoT - the ’S’ stands for security Break (into) your smart home 205 IoT Data Flows - Save the ISS! 207 The What, The How and The Why of Data

  9. reate your own exercise Kilian Schulte, Tobias Leibbrand| TEAM 202 LoRaWAN – The backbone of LoRa Networks 1

  10. Outline Lecture • Difference LoRa / LoRaWAN • Real world example of a commercial LoRa Network (SWM) • Protocols + Architecture Components of LoRaWAN (Devices, Gateways, Network Server, Application Server) 2

  11. Outline Lecture 3 https://zakelijkforum.kpn.com/lora-forum-16/what-is-lora-and-lorawan-8314

  12. Outline Lecture 4 https://www.resiot.io/en/what-is-lorawan/attachment/schema-lora/

  13. Outline PreLab • Understand LoRaWAN Architecture Components in depth • Aspects of LoRaWAN: • Class A/B/C • Activation Methods: OTAA / ABP • Tools: loraserver.io (Open Source software components) 5

  14. Outline Lab • Setup an own LoRa Network with one / multiple devices using loraserver • Send data over the network and see how it is routet to the application • Play around with OTAA and the device classes learned in the PreLab 6

  15. What Will Your Students Learn? The Following Learning Goals are Covered in the Lecture PreLab Lab Understand the LoRaWAN Architecture Components X X Learn about the LoRaWAN MAC layer X Understand how LoRaWAN is used in the real world X Understand LoRaWAN device classes X X Understand LoRaWAN OTAA X X Setup an own complete LoRaWAN Network X 7

  16. Teaser Practical Part Network Server Gateway Application Server 8

  17. Order of Presentations Team Topic 204 Becoming a beekeeper of ZigBee 202a Endless use cases for BLE Mesh Networks 202b LoRaWAN - The backbone of LoRa Networks 208 IoT orchestration with RabbitMQ 203 Sending a picture from a Raspberry Pi/Arduino via MQTT - Am I Safe in the Lab? 201 Risks & REST with CoAP 206 IoT - the ’S’ stands for security Break (into) your smart home 205 IoT Data Flows - Save the ISS! 207 The What, The How and The Why of Data

  18. iLab2 - Your own exercise IoT orchestration with RabbitMQ 208 — Victor Oancea — Jurek Olden

  19. Why should this topic be chosen? Purpose Middleware is the glue of any IoT system IoT systems are dynamic, devices might fail Interesting Lab possibilities

  20. Reasons for Middleware Hetereogeneous System Message congestion Failures

  21. What will you learn? The following learning goals are covered in the Lecture PreLab Lab What is Middleware in an IoT context x Understand why Middleware is needed x x Introduce the publisher-subscriber queueing model and RabbitMQ x x x Learn about IoT communication protocols (MQTT, AMQP, STOMP) x x x Simulate some IoT devices x Configure RabbitMQ and set up an IoT system x Bring the system to its limits x

  22. Teaser practical part

  23. Order of Presentations Team Topic 204 Becoming a beekeeper of ZigBee 202a Endless use cases for BLE Mesh Networks 202b LoRaWAN - The backbone of LoRa Networks 208 IoT orchestration with RabbitMQ 203 Sending a picture from a Raspberry Pi/Arduino via MQTT - Am I Safe in the Lab? 201 Risks & REST with CoAP 206 IoT - the ’S’ stands for security Break (into) your smart home 205 IoT Data Flows - Save the ISS! 207 The What, The How and The Why of Data

  24. reate your own exercise Mariano Hernandez & Birtan Gültekin Team 203 Sending a picture from a Raspberry Pi/Arduino via MQTT - Am I Safe in the Lab? 1

  25. Outline Lecture • History of control in real time systems • Explain how Control Centers have worked since the 80’s. • Present real world examples (HL7, NTCIP, GOVTALK) • Show how new middleware standards have changed because of distributed computing 2

  26. Outline PreLab • Talk about the interoperability problem • Read about the joint comities that standardized the first protocols. • Present different kind of architectures • Explain how MQTT works 3

  27. Outline Lab • Setup a movement sensor with an Arduino/Raspberry Pi • Setup a camera with a Raspberry Pi • Create a publish-subscribe architecture • Show how one sensor can have many subscribers 4

  28. What Will Your Students Learn? The Following Learning Goals are Covered in the Lecture PreLab Lab Understand the interoperability issue X X Understand the evolution of IoT middleware X X X Understand the MQTT header X X Configure a Raspberry Pi, an Arduino, a MQTT broker and a X Subscriber Examine different use cases of the technology X 5

  29. Teaser Practical Part This is your playground: 6x Quad Core fast PC with 3-4 usable LAN interfaces per machine. 2x Cisco 881 Router 2x Ethernet switch 2x Work Place with KVM 6

  30. Order of Presentations Team Topic 204 Becoming a beekeeper of ZigBee 202a Endless use cases for BLE Mesh Networks 202b LoRaWAN - The backbone of LoRa Networks 208 IoT orchestration with RabbitMQ 203 Sending a picture from a Raspberry Pi/Arduino via MQTT - Am I Safe in the Lab? 201 Risks & REST with CoAP 206 IoT - the ’S’ stands for security Break (into) your smart home 205 IoT Data Flows - Save the ISS! 207 The What, The How and The Why of Data

  31. create your own exercise Florian Bauer and Simon Schäffner (204) Risks & REST with CoAP 1

  32. Outline Lecture • Get to know the CoAP protocol • Widely used IoT protocol with a REST architecture • Compare MQTT with CoAP architecture 2

  33. Outline PreLab • Deepen knowledge on CoAP architecture • Learn about CoAP packet format • Tools: CoAP Server library, CoAP Client, Wireshark 3

  34. Outline Lab • Setup a CoAP Server on an ESP microcontroller • Control light using CoAP client • Attack CoAP Server 4

  35. What Will Your Students Learn? The Following Learning Goals are Covered in the Lecture PreLab Lab Understand what CoAP is used for X X Understand the differences between MQTT and CoAP X X architecture Understand the CoAP packet format X X X Setup a CoAP Server on a microcontroller X X Setup a CoAP Client X X Attack a CoAP Server X X 5

  36. Teaser Practical Part 6

  37. Order of Presentations Team Topic 204 Becoming a beekeeper of ZigBee 202a Endless use cases for BLE Mesh Networks 202b LoRaWAN - The backbone of LoRa Networks 208 IoT orchestration with RabbitMQ 203 Sending a picture from a Raspberry Pi/Arduino via MQTT - Am I Safe in the Lab? 201 Risks & REST with CoAP 206 IoT - the ’S’ stands for security Break (into) your smart home 205 IoT Data Flows - Save the ISS! 207 The What, The How and The Why of Data

  38. iLab2 - Your own exercise IoT - the ’S’ stands for security Break (into) your smart home Ghania and David, Team 206 14. Mai 2019

  39. Why should this topic be chosen? Purpose What is the topic about? What content will your students learn? What is your background in the topic?

  40. Outline Lecture, PreLab and Lab Lecture IoT security vs. conventional security Attack vectors on IoT communication The Constrained Application Protocol Prelab and Lab Security issues associated with the Internet of Things A practical spoofing attack on the Constrained Application Protocol Secure configuration of CoAP with Datagram Transport Layer Security (DTLS)

  41. What will your students learn? The following learning goals are covered in the Lecture PreLab Lab Understand what IoT Security is x x x Learn in a practical way about security in IoT environment x Understand what CoAP is used for x x x Learning how to secure CoAP with DTLS or TLS (RFC 8323) x x Use attacks as basis to provide better defense x x Have fun time experimenting with all of the above x x x

  42. Teaser practical part Implement spoofing attack as described in the CoAP RFC 7252

  43. Sources CoAp RFC url: https://tools.ietf.org/html/rfc7252 Practical Internet of Things Security, Book by Brian Russell and Drew Van Duren, PACKT Publishing

  44. Order of Presentations Team Topic 204 Becoming a beekeeper of ZigBee 202a Endless use cases for BLE Mesh Networks 202b LoRaWAN - The backbone of LoRa Networks 208 IoT orchestration with RabbitMQ 203 Sending a picture from a Raspberry Pi/Arduino via MQTT - Am I Safe in the Lab? 201 Risks & REST with CoAP 206 IoT - the ’S’ stands for security Break (into) your smart home 205 IoT Data Flows - Save the ISS! 207 The What, The How and The Why of Data

  45. create your own exercise Dominik Winter & Vadim Goryainov IoT Data Flows Save the ISS! 1

  46. The Story • You are hired by the NASA to monitor the health state of bearings in the ISS space station! • The NASA was clever so it installed IoT sensors to record the vibration measurement signals of the bearings. • You must find a solution to detect failures of a bearing in advance so that technicians on the ISS can change them out before they break! 2

  47. References • You will work on a real NASA bearing data set [1] • Approach based on the paper [2]: Detection of weak transient signals based on wavelet packet transform and manifold learning for rolling element bearing fault diagnosis 3

  48. Outline Lecture • Background of Neural Networks and especially autoencoder networks • Basics of Tensorflow / Scikit-Learn / Pandas • Flow analysis and visualization methods with Node-RED 4

  49. Outline PreLab • Deepen the knowledge for (autoencoder) neural networks ○ Hyperparameter tuning, Optimizer ○ Convergence, Loss distribution ○ etc.. • Basics in Python/JavaScript required • Toolset: Tensorflow, Scikit-Learn, Node-RED 5

  50. Outline Lab • Save the ISS space station! • Hands-on the complete pipeline: ○ Analyze a dataset from the ISS’s bearing sensors ○ Train a model with Tensorflow/Scikit-Learn ○ Analyze data flows, implement a monitoring system and visualize everything with Node-RED 6

  51. What you will learn with us The Following Learning Goals are Covered in the Lecture PreLab Lab Learn backgrounds of neural networks, autoencoders X X Learn about the utilized machine learning frameworks X X Learn how to collect, connect, analyze and visualize IoT X X data flows with IBM’s Node-RED Analyze a real NASA dataset, build your own neural X network and train it to detect failures of bearings Implement a monitoring system for new incoming sensor X data and visualize it with Node-RED 7

  52. Node-RED 8

  53. Tensorflow import tensorflow as tf mnist = tf.keras.datasets.mnist load & preprocess (x_train, y_train),(x_test, y_test) = mnist.load_data() x_train, x_test = x_train / 255.0, x_test / 255.0 data model = tf.keras.models.Sequential([ build model tf.keras.layers.Flatten(input_shape=(28, 28)), tf.keras.layers.Dense(512, activation=tf.nn.relu), tf.keras.layers.Dropout(0.2), tf.keras.layers.Dense(10, activation=tf.nn.softmax) ]) model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy']) fit & evaluate model.fit(x_train, y_train, epochs=5) model.evaluate(x_test, y_test) 9

  54. Tensorboard 10

  55. Tensorboard 11

  56. Setup training data monitoring device training device test data 12

  57. Questions / Comments References: [1] http://data-acoustics.com/measurements/bearing-faults/bearing-4/ [2] Hai Qiu, Jay Lee, Jing Lin. “Wavelet Filter-based Weak Signature Detection Method and its Application on Roller Bearing Prognostics.” Journal of Sound and Vibration 289 (2006) 1066-1090 13

  58. Order of Presentations Team Topic 204 Becoming a beekeeper of ZigBee 202a Endless use cases for BLE Mesh Networks 202b LoRaWAN - The backbone of LoRa Networks 208 IoT orchestration with RabbitMQ 203 Sending a picture from a Raspberry Pi/Arduino via MQTT - Am I Safe in the Lab? 201 Risks & REST with CoAP 206 IoT - the ’S’ stands for security Break (into) your smart home 205 IoT Data Flows - Save the ISS! 207 The What, The How and The Why of Data

  59. reate your own exercise Ankita Kinnerkar, Viet Duong The What, The How and The Why of Data 1

  60. Outline Lecture • Iot data analysis – User behaviour analysis & energy consumption. • Introduce topics of preLab and explain. • Combination of data from an Iot device and data analtyics. 2

  61. Outline PreLab • Requirement : Basic coding skills . • To-Do : Steps for data cleaning and test knowledge based on the topic with multiple choice questions. • How to use tensorflow, prediction models usage. 3

  62. Outline Lab • Work with dataset of smart home. • Exploratory analysis for the dataset. • Feature Engineering. • Try out different models to achieve good results. • Performace evaluation metrics. • To work collaborately, team members use Google Collab. 4

  63. What Will Your Students Learn? The Following Learning Goals are Covered in the Lecture PreLab Lab Introduction to Data mining, the do and don’ts of mining X Exploratory analysis using pandas ,matplotlib X X Dealing with different types of datasets (Eg. Timeseries) X X X How to choose models based on your data X X X Use prediction/classification models for data X 5

  64. Teaser Practical Part 6

  65. All teams were great! Which team’s presentation did you like most?

  66. And why did you vote like that? What did you especially like? What could be improved?

  67. What did you especially like? What could be improved?

  68. Kick Off 04/23 1 IPv6 IPv6 04/30 BGP 2 Minilab 1+2+3 05/07 BGP 3 Your Exercise Topic Storm (IoT) 05/14 Minis Your Exercise Topic Voting Event 4 05/21 Your Exercise WWW Security YE1 5 IoT DIY HW WWW 05/28 6 Guest Composition IoT Smart Space SW & Measure 06/04 IoT1 7 VSL Hands-On (06/11) IoT2 Prepare Your Exercise 8 YE Didactics, Tools 06/18 9 Prepare Your Exercise 06/25 10 YE 1st Lecture 07/02 Your Exercise Giving good Feedback 11 (07/09) summer term 2019 You review 12 07/16 YE Review Presentation 13 07723 14 YE Final Presentation, Wrap-Up

Recommend


More recommend