This project leverages a very up and coming topic in the field of wireless communications; the software defined radio. One of the key objective of this sensing and detection project is to identify and determine modulation schemes of signals encountered in an open environment.
Available, Multi-purpose Hardware
Using only open-source software and commercial off the shelf hardware
will allow the highest level of availability for the user. Additionally,
our system will only require a laptop and a radio frequency front end!
Easy-to-Use Interface
An easy to use interface will allow for clear and quickly
available results. Users need not waste time processing
unclear data.
Awareness
Full radio frequency awareness will be provided by the use of
high-bandwidth radio (DC - 6GHz).
Project Details
Specifics about our project.
Adaptive Spectrum Sensor is a signal detector, looking for wireless signals that might indicate danger to US soldiers. As of today, the Army does not have the ability to identify signal types in the operator’s immediate vicinity. Such a capability would make the warfighter notably safer while deployed in potentially hostile environments.
Adaptive Spectrum Sensor consists of a commercial, off-the-shelf (COTS) laptop paired with two COTS software-defined radios, and software based on the GNURadio and TensorFlow open-sourced libraries. The ability to identify modulation types of wireless signals is very processing intensive and difficult, but has been made much more efficient with machine learning. We used our own signal processing software along with an implementation of a popular white paper to construct our system.
Scott is a senior electrical engineering major from San Diego, California. He hopes to graduate next May with a bachelors of engineering in electrical engineering and a bachelors of engineering in systems engineering. He participated in the co-op program at Stevens, which gave him the opportunity to work with companies such as Port Authority of New York and New Jersey, Credit Agricole COrporate and Investment Bank, and MITRE. He is concentrating in wireless communications and space systems engineering, and have accepted a full time position with MITRE in Aberdeen, Maryland.
Joseph Pang
BE Electrical Engineering
Joseph is a 4/4 student and is pursuing Electrical Engineering at Stevens. Currently he is working at G3 Technologies and will work full-time for the company upon
graduation.
Vijayrahul Raja
BE Computer Engineering
Vijay is a 4/4 student pursuing both of his Bachelor's and Master's in Computer Engineering. He has been working as an IT intern at the Liberty Science Center since last year.He has also worked in various technical positions like developing and testing. HIs interest lies in both the hardware, software components of a processor and he also has a strong passion towards Networks and Security. He would like to work for big companies in the near future.
Kunal Patel
BE Computer Engineering
Kunal is a 5/5 student at Stevens pursuing a Bachelor's Degree in Computer Engineering, and plan on getting his Master's in Software Engineering in the near future. At Stevens, he participated in the co-op program, in which he gained significant work experience in IT and database management. He has worked at Mindray, Credit Agricole, Nomura, and Hunter Douglas. At Mindray, he worked on a database called ExtraView and helped design it. At Credit Agricole he worked for the BCP team a conducted quarterly tests. At Nomura he worked under the PeopleSoft team and learned SQL there.Finally, at Hunter Douglas, he was in IT,so he helped support the company's computers and programs.
Andrew Gutherie
BE Computer Engineering
Andrew is a 4/4 student at Stevens pursuing a Bachelor's Degree in Computer Engineering with a concentration in software engineering. He had two internships as IT and plan on seeking full time employment after graduation.
GNU Radio is a free & open-source software development toolkit that provides signal processing blocks to implement software radios. It can be used with readily-available low-cost external RF hardware to create software-defined radios, or without hardware in a simulation-like environment. It is widely used in hobbyist, academic and commercial environments to support both wireless communications research and real-world radio systems.As GNURadio already has extensive libraries for signal processing applications, this implementation will give the most resources and developmental flexibility to the team from the outset.
, all the signal processing and identification is done by a computer using Python code from GNURadio. In this implementation, the SDR front end serves only as the antenna and sampler. A computer will implement all of the software for this program, including the software components to identify high RSSI signals, modulation types, and center frequencies of relevant signals. Finally, an interface will allow the user to send commands to the program, and display the relevant information back to the user.
A common model/system for SDRs is the SDR itself contains an antenna and the ability to sample signals at a given sample rate, and then a processor attached to the radio performs processing in terms of modulation and demodulation, FFTs, filtering, and other functions normally done on an FPGA in a traditional radio. SDRs still have FPGAs in a more flexible configuration that can still be controlled with software. SDRs are becoming especially useful learning and analyzing tools.
Currently our project is capable of performing the full basic set of its original functions.
It is capable of finding a signal from a broad-spectrum scan and determining the modulation types.
It can find signals and determine the type of modulation in under a second as well with a eighty percent accuracy.
The only signals of the base set that it can not identify are those that are functionally indistinguishable,
but this does not have a real impact on the code’s functionality.
The design of the RF portion of the project has evolved to using two USRPs instead of one.
One USRP is used to scan the given spectrum and identify signals, and the second USRP hones in on the signal and captures samples,
which are then forwarded to the machine learning portion of the project. Current editions of this part of the project are promising and working,
and optimizations are being made in terms of statistical analysis and latency. By using the mean and standard deviation of the received RF power,
we can have our system adapt to any noisy or quiet environment,
and reducing the latency of the process widens the application scope for our product.
The flow chart below shows the major signal flow for our prototype.
The MITRE Corporation
Lorem ipsum dolor sit amet consectetur.
MITRE is a not-for-profit organization that operates research and development centers sponsored by the federal government. It provides practical solutions for some the nation's critical challenges in aviation, defense and intelligence, homeland security and so on.
For this project, our sponsor, MITRE, is private contractor of the military. They are providing assistance with the project, and have the same goals the military does.
based radio, as well as established an environment to program in and an environment to share our work. From MITRE we received the receivers which are what we will use to receive the data to be analyzed. The other resources we have available to us are contacts in MITRE who are designated to provide assistance to us, our project advisor, and the money allocated to our group for the sake of completing the project.
The team would like to thank MITRE Corporation for offering equipment, code and technical expertise, specifically Ryan Nilsen, Adam Parks, Marcin Wojcik, and Bill Urrego. The team would also like to thank Professor Bruce McNair for continued advice, direction, and expertise.
Universal Software Radio Peripheral
Lorem ipsum dolor sit amet consectetur.
This project will be implemented using one or more Universal Software Radio Peripherals (USRP). Two platforms were available to our group: USRP X300 and USRP N210 (both designed by Ettus Research). Each has its own advantages and disadvantages. For our project, we will be handling the USRP N210.
Some specification about the USRP N210 model is that it provides high-bandwidth, high-dynamic range processing capability. The modular design allows the USRP N210 to operate from DC to 6 GHz, while a multiple-in, multiple-out (MIMO) expansion port allows multiple USRP N210 series devices to be synchronized. It can also stream up to 50 Mega-samples/second (MS/s) to and from host applications.
Users can implement custom functions in the larger FPGA fabric which can process up to 100 MS/s in both the transmit and receive directions.
For the programming aspect of this project, N210 are compatible with the USRP Hardware Driver (UHD) like all other USRP models. They are compatible with other third-party software frameworks, including GNU Radio companion software, LabVIEW, and Matlab. The UHD architecture, provides this powerful compatibility along with the ability to use APIs of C++ and Python, which will be mostly used for developing and analyzing our system of interest.
Language and Toolkits
Python is an interpreted, object-oriented, high-level programming language with dynamic semantics. Python can be interfaced to other languages by the Simplified Wrapper Interface Generator. This allows Python code to run with speed comparable to other languages, like C++.
We also used the Tkinter Python standard GUI package to show a visual representation of our input and output functionalities and results.
TensorFlow is an open source software library for machine learning across a range of tasks, and developed by Google. TensorFlow builds and trains neural networks to detect and decipher patterns and correlations, analogous to the learning and reasoning which humans use.
GNU Radio is a free & open-source software toolkit that provides signal processing blocks to implement software radios. It can be used with external RF hardware to create SDRs, or without hardware in a simulation-like environment. It is widely used in research and real-world systems.
