18
Semantic Signal Processing for Re-hosting CR/SDR Implementations SP/Radio Primitive Recognition Jiadi Yu, Yingying Chen 1

Semantic Signal Processing for Re-hosting CR/SDR Implementations

Embed Size (px)

DESCRIPTION

Semantic Signal Processing for Re-hosting CR/SDR Implementations. SP/Radio Primitive Recognition Jiadi Yu, Yingying Chen. SSP Framework. Parse cognitive-linguistics-based representation and generate implementation code in the target platform. - PowerPoint PPT Presentation

Citation preview

Page 1: Semantic Signal Processing for Re-hosting CR/SDR Implementations

Semantic Signal Processing for Re-hosting CR/SDR Implementations

SP/Radio Primitive Recognition

Jiadi Yu, Yingying Chen

1

Page 2: Semantic Signal Processing for Re-hosting CR/SDR Implementations

SSP Framework

Abstract conceptual primitives (“Thing, Place, Path, Action, Cause”) from existing implementations of signal processing modules/systems in source code

Represent the implementation profile of signal processing modules/systems based on cognitive linguistics

Parse cognitive-linguistics-based representation and generate implementation code in the target platform

2

Page 3: Semantic Signal Processing for Re-hosting CR/SDR Implementations

Radio-Level Abstraction– Abstract primitives at Radio-level

• Analyze the Code-level primitives to recognize Radio-level primitives

Algebraic calculation: +, -, *, /Logic calculation: xor, nor, andType conversionsRelational Operator:

==,! =Conditional control: if… else…, while :

Code levelSignal SourcesSignal SinksFiltersSignal ModulationSignal DemodulationSource codingSynchronizationEqualizationAGCOFDM locks :

Radio level

Primitives of Semantic Radio

3

Page 4: Semantic Signal Processing for Re-hosting CR/SDR Implementations

Radio-Level Abstraction (cont’)

SourcesCode

Radio levelXML

Presentation

Code level XML

Presentation

Inference EngineKnowledge

Base

RadioPrimitives

Radio LevelAbstraction

TargetCode

Code level

Abstraction

SP module recognition

4

Page 5: Semantic Signal Processing for Re-hosting CR/SDR Implementations

Learning Based Inference Engine– Inference engine is able to understand the what level

primitives in the semantic presentation need to parsing

– Inference engine is able to know what primitives need to generate target code and what primitives just use code from code library

– Machine knows how to implement any-level primitives in the target code

5

Page 6: Semantic Signal Processing for Re-hosting CR/SDR Implementations

Learning Based Inference Engine

Inference Engine

Radio/CodePresentation

TargetCodeParser

Higher-level

Reinforcement learning

Knowledge Base

Learning Agent

InformationInquiry

CodeGenerate

Conceptual Primitives

lower-level

SP module recognition

6

Page 7: Semantic Signal Processing for Re-hosting CR/SDR Implementations

SP/Radio Primitive Recognition • Objective

– Automated recognition of functionality of a SP/Radio primitive

– Automated recognition of functions from knowledge library to perform desired action

– Recognize the equivalence of two different implementations

7

Page 8: Semantic Signal Processing for Re-hosting CR/SDR Implementations

Primitive Recognition - Potential Approaches

– Context-based• Function names

• Comments

– Behavior pattern• Tree-based pattern recognition

• Machine learning -based pattern recognition

8

Page 9: Semantic Signal Processing for Re-hosting CR/SDR Implementations

Context-based Recognition

• Information retrieval

from Function names/Comments

– Function names

Direct comparison

Fuzzy matching and identification

– Comments Keyword-based

Machine learning models

9

Page 10: Semantic Signal Processing for Re-hosting CR/SDR Implementations

• The representation architecture based on cognitive linguistics of the signal processing implementation is a Tree Structure.

Tree-based Pattern Recognition

• Each signal processing module can be represented as a behavior pattern using lower-level primitives

• Each signal processing module can be represented as a tree architecture.

10

Page 11: Semantic Signal Processing for Re-hosting CR/SDR Implementations

Tree-based Pattern Recognition

Primitive Recognition

Tree architecture

analyze

Knowledge base

Tree representation Source

Target

11

Page 12: Semantic Signal Processing for Re-hosting CR/SDR Implementations

An Example of QPSK

• two QPSK implementations

Tree representatio

n

Binary Tree representatio

n

12

Page 13: Semantic Signal Processing for Re-hosting CR/SDR Implementations

Tree-based Pattern Recognition(Cont’)

• Advantage 

Direct comparison Accuracy can be high

• Disadvantage

Compare with all modules/functions of Knowledge base Slow, high computational cost

13

Page 14: Semantic Signal Processing for Re-hosting CR/SDR Implementations

Machine Learning-based Pattern Recognition

– Based on the correlation between the radio primitive and identified features

– Potential Features

• Lower-level primitives– Example: lookup table

• Hierarchical architecture- Example: QPSK includes a lookup table primitive

• Numerical attributes- Example: integers, real numbers

• Input/output variable types and ranges- Example: Input/output parameters of a filter is array

14

Page 15: Semantic Signal Processing for Re-hosting CR/SDR Implementations

A Simple Filter Example

The basic elementfor the simplefilter include:

LOOPACCUMLATION MULTIPLYARRAY

void main(){for(i = 0; i < N ; i = i + 1){

k = N - i;temp = tap[i] * input[k];sum = sum + temp;

}} The code segments probably

implement functionality of  a filter 15

Page 16: Semantic Signal Processing for Re-hosting CR/SDR Implementations

Machine Learning-based Pattern Recognition

(Cont’)

• Advantage 

Fast & simple

• Disadvantage

Accuracy can be low

16

Page 17: Semantic Signal Processing for Re-hosting CR/SDR Implementations

ML and Tree-based Pattern Recognition

• Low computational cost and high accuracy

ML-based Pattern Recognition

Tree-based Pattern Recognition

First step

Second step

similar primitives

Primitive Recognition

Source Target

17

Page 18: Semantic Signal Processing for Re-hosting CR/SDR Implementations

Thank You

Comments & Questions?

18