Specific Emitter Identification using machine learnig

Project Title

Specific Emitter Identification using machine learnig

Project Area of Specialization Artificial IntelligenceProject Summary

pecific emitter identification is a technique that distinguishes different emitters using radio fingerprints. Feature extraction and classifier selection are critical factors affecting SEI performance. In this paper, we propose an SEI method using the Bispectrum-Radon transform (BRT) and a hybrid deep model. We propose BRT to characterize the unintentional modulation of pulses due to the superiority of bispectrum distributions in characterizing nonlinear features of signals. We then apply a hybrid deep model based on denoising autoencoders and a deep belief network to perform further deep feature extraction and discriminative identification. We design an automatic dependent surveillance-broadcast signal acquisition system to capture signals and to build dataset for validating our proposed SEI method. Theoretical analysis and experimental results show that the BRT feature outperformed traditional features in characterizing UMOP, and our proposed SEI method outperformed other feature and classifier combination methods.

Project Objectives

The classification and identification technique for radio transmitters with a similar modeland same producing lot is Specific Emitter Identification. The theme of this method is torepresent every target by the characteristics of signals of each single transmitter, and there-fore the signal envelop extraction technique by pattern dimension, Permutational Entropyand Dispersion Entropy of signal wrap square measure the most signal process tools. Thescheme behind this concept is to get the signal characteristics using different techniquesof features extraction once we come up with the features we can go for machine learningprocess we will prepare the data set of the feature of the signal the more the features themore trained machine we can get when the machine will be fully trained and will ableto run for real time execution of program the SDR will receive the signal and the trainedmachine will tell us which emitter is this.

Project Implementation Method

The classification and identification technique for radio transmitters with a similar model and same producing lot is Specific Emitter Identification. The theme of this method is to represent every target by the characteristics of signals of each single transmitter, and therefore the signal envelop extraction technique by pattern dimension, Permutational Entropy and Dispersion Entropy of signal wrap square measure the most signal process tools. The scheme behind this concept is to get the signal characteristics using different techniques of features extraction once we come up with the features we can go for machine learning process we will prepare the data set of the feature of the signal the more the features the more trained machine we can get when the machine will be fully trained and will able to run for real time execution of program the SDR will receive the signal and the trained machine will tell us which emitter is this.

Benefits of the Project

Specific Emitter identification now a days is very important because as the world is growing so fast so there should be some ways to protect, detect and to know about the things which are being happening to different devices. The major importance are:
{Military}
  Military wants to identify the emitters of rivals in war to protect their country, what if the military of a country comes to know which is the signal of the headquarter, obviously the emitter which is emitting more signals will be the headquarter so once they come to know about headquarter they can attack on it and can take control of it.
{phone cloning}
Mobile phone cloning is copying the identity of one mobile telephone to another mobile telephone. As there identity is same so the officials can have the problem to identify the real culprits by specific emitter identification we can identify the actual device by which an illegal activity is being performed.

Technical Details of Final Deliverable

The SDR will receive signal from the antenna, receiver will downconvert the signal andwill give the 8 bit I and Q then we will manipulate the I and Q of the signals for thefeature extraction, we will extract the features from Spurious Modulation, PermutationalEntropy and Dispersion Entropy after the features extraction phase we will maintain thedata sets,we will use python library scikit for Machine Learning we can use differentalgorithm for machine learning, as we are in a situation and wants a trained machine sowe will use supervised Machine learning algorithm cart or Random forest. For real timerunning of this application the most important thing is the speed of the whole process forthat purpose we will use such algorithm and features extraction method which is fast andcan work in real time systems properly

Final Deliverable of the Project HW/SW integrated systemCore Industry SecurityOther Industries Telecommunication Core Technology Artificial Intelligence(AI)Other TechnologiesSustainable Development Goals Peace and Justice Strong InstitutionsRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	10000
SDR	Equipment	1	10000	10000