The UCLA Electrical and Computer Engineering Department is dedicated to a mission to introduce Internet of Things (IoT) platforms that provide proven benefits to students at every level from Freshman students in their first quarter at to advanced graduate students. A specific mission focus is to address the acute and unmet need for platforms that enable scaling of instruction to large courses with all students engaged in IoT system development.
To accomplish this goal, UCLA has developed a capable set of resources to create and support IoT platforms. These resources include IoT Tutorials that have proven effective at every student level. These provide introduction to IoT for student backgrounds that range from students entering the engineering field to advanced graduate students.
Formal assessment of our IoT course offerings has confirmed effectiveness of this new IoT curriculum at all levels.
An important new capability is the integration of the STMicroelectronics SensorTile platform with BeagleBone.
These tutorials will guide you through an introduction to BeagleBone development and prepare you for the new SensorTile wireless sensor for IoT applications.
A critical advance has been made in integration of the SensorTile IoT platform provided by STMicroelectronics with the BeagleBone.
This provides the first low power, high performance, wireless sensor system integrated with embedded Linux platforms including the BeagleBone.
This provides also the first high performance 9 Degree of Freedom motion sensor with triaxial accelerometer, triaxial gyroscope, and triaxial magnetometer for the BeagleBone and related platforms.
Please see this link for information on this integration along with Tutorials providing user and developer guidance.
https://sites.google.com/view/ucla-stmicroelectronics-iot/home
Our team has been fortunate to have benefited from some of the early origins of IoT wtith development of Wireless Sensor Networks where we referred to this new field as “Internetworking the Physical World”. The book, Principles of Embedded Networked System Design by Professors Pottie and Kaiser provides references on this field and fundamental design principles.
Today, the IoT field is growing now at an unprecedented rate with many diverse applications from smartphone to wearable devices. The field of Wireless Health is expanding particularly rapidly with great potential impact on the entire world population. Our Wireless Health devices have been distributed to each continent on earth and are breakthroughs in areas from neurorehabilitation, to monitoring of human digestion, orthopaedics, and even athletics.
We are indebted to our collaborators at STMicroelectronics for their support and guidance of our programs.
These are the BeagleBone IoT Tutorials. Each has been developed to speed your progress and minimize any need for outside assistance – so that each student can proceed independently at any time. We recommend following these Tutorials in the order presented below.
These Tutorials support the BeagleBone Green Wireless platform that is an ideal, high performance, and broadly capable IoT device.
Students familiar with some concepts in the Tutorials should review the Tutorial to ensure their familiarity with all concepts.
1) An Introduction to the BeagleBone Platform
An introduction to the BeagleBone platform, instructions on how to access the BeagleBone with Windows and Mac platforms.
An introduction (or an important refresher for students with experience) in Linux operations on the BeagleBone platform.
3) Introduction to the VIM Editor
a) Introduction to the vim editor and its operations for software development on the BeagleBone.
b) Introduction to WiFi Configuration with SSH and SFTP Access
c) Introduction to methods of IoT platform configuration for WiFi network access as well as access to the operating system shell via SSH.
4) Introduction to GPIO, Interrupts, Analog and PWM Interfaces
Introduction to the BeagleBone access to General Purpose I/O (GPIO), Interrupts, Analog Sampling and PWM interfaces.
5) Introduction to I2C Interface and Motion Sensing
Introduction to the BeagleBone to the important I2C digital communication interface and its application to motion sensor data access by processes executing on the BeagleBone platform.
6) Introduction to Networking with TCP Socket Communication
Introduction to the BeagleBone network system applications with TCP Socket Communication systems.
7) Introduction to Event Timing and Platform Synchronization
Introduction to the BeagleBone general applications in development of event timing systems and clock synchronization for BeagleBone platforms.
8) Introduction to Kernel Module Development
Introduction to developing kernel module on the BeagleBone.
9) The SensorTile Wiki and Introduction to SensorTile - BeagleBone Integration
The Tutorials in this Wiki provide guidance in the development of the SensorTile wireless motion sensor and its operation with BeagleBone platforms. Together, these form an IoT system supporting wearable applications, audio applications, environmental monitoring, and vehicle applications.
1) IoT Machine Learning Reference Design with STMicroelectronics SensorTile and BeagleBone
This Reference Design provides development experience in Machine Learning with the SensorTile wireless sensor system, BeagleBone platform, and the Fast Artificial Neural Network (FANN) system.
Introduction or (or an important refresher for students with experience) for C code development including the gcc compiler.
2) A Troubleshooting Guide for BeagleBone Network Access and Firmware Update
This troubleshooting guide addresses problems you may encounter in SSH communication with your BeagleBone, use of the Eduroam WiFi network,driver installation, firmware update, and other issues.
Many UCLA students have collaborated in the development of Internet of Things (IoT) SensorTile systems in course projects. The senior capstone design course has included teams who have developed novel systems for motion classification with SensorTile data sources and machine learning methods.
This has included systems with single and dual SensorTile devices along with signal processing, signal feature extraction, neural network design, neural network training, and finally in-field performance analysis.
Reference Designs have been developed by these student teams that include design and development documentation as well as source code for your use.
These are available for evaluation and guidance with the objective that these may inspire other future development,
If you have questions regarding the Reference Designs, please contact kaiser@ee.ucla.edu.
1) STMicroelectronics SensorTile Reference Design: Basketball Freethrow Classifier by Machine Learning
This Reference Design developed by Alexander Graening and James Xu describes the comprehensive development of a system capable of detecting characteristics of the Basketball Freethrow motion. This relies on the complete set of signal acquisition from SensorTIle systems, signal processing, and machine learning. The SensorTile systems are used in pairs with attachment at upper and lower arm.
2) STMicroelectronics SensorTile Reference Design: Basketball Hookshot Classifier by Machine Learning
This Reference Design developed by Ziyue Yang and Zhitong Qian describes the comprehensive development of a system capable of detecting the characteristic motion of arm and hand associated with optimal and suboptimal Basketball Hookshot motion. The complete description of SensorTIle systems, signal processing, and machine learning development is included The SensorTile systems are used in pairs with attachment at upper and lower arm.
3) STMicroelectronics SensorTile Reference Design: Tennis Motion Classifier by Machine Learning
This Reference Design developed by Bonnie Lam and Gheorge Schreiber describes the another comprehensive development of a system capable of detecting Tennis motion swing types and swing quality. This also relies on the complete set of signal acquisition from SensorTIle systems, signal processing, and machine learning. Here the SensorTile is attached to the tennis racket.
This Reference Design developed by Guang Liew and Zhijie Yao describes another development based on dual SensorTile motion sensors each providing data sources for feature extraction. This system classifies proper and improper resistance training motions by SensorTile data sources and machine learning classifier systems.
This Reference Design developed by Loic Maxwell and Craig Young describes the development of a unique system that classifies the complex motions occurring in climbing. This classifies proper and improper motion applying dual SensorTile systems and a series of signal processing, feature extraction, and machine learning solutions.
This Reference Design developed by Michael Qi and July Zamora also applies dual SensorTile data sources to the important problem of classifying proper and improper motion required in shoulder rehabilitation. This also applies dual SensorTile devices along with end-to-end development from signal acquisition to machine learning system design and performance analysis.