180 likes | 264 Views
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.
E N D
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 Represent the implementation profile of signal processing modules/systems based on cognitive linguistics Abstract conceptual primitives (“Thing, Place, Path, Action, Cause”) from existing implementations of signal processing modules/systems in source code
Radio-Level Abstraction • Abstract primitives at Radio-level • Analyze the Code-level primitives to recognize Radio-level primitives Primitives of Semantic Radio Code level Radio level Algebraic calculation: +, -, *, / Logic calculation: xor, nor, and Type conversions Relational Operator: ==,!= Conditional control: if… else…, while : Signal Sources Signal Sinks Filters Signal Modulation Signal Demodulation Source coding Synchronization Equalization AGC OFDM locks :
Radio-Level Abstraction (cont’) Radio Level Abstraction Inference Engine Radio Primitives Radio level XML Presentation Knowledge Base Target Code Code level XML Presentation Code level Abstraction Sources Code SP module recognition
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
Learning Based Inference Engine Knowledge Base SP module recognition Inference Engine Learning Agent Conceptual Primitives Radio/Code Presentation Parser Higher-level Reinforcement learning Code Generate Target Code lower-level Information Inquiry
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
Primitive Recognition - Potential Approaches • Context-based • Function names • Comments • Behavior pattern • Tree-based pattern recognition • Machine learning -based pattern recognition
Context-based Recognition • Information retrieval from Function names/Comments • Function names Direct comparison Fuzzy matching and identification • Comments Keyword-based Machine learning models
Tree-based Pattern Recognition • The representation architecture based on cognitive linguistics of the signal processing implementation is a Tree Structure. • 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.
Tree-based Pattern Recognition Primitive Recognition Source Tree representation Tree architecture analyze Target Knowledge base
An Example of QPSK • two QPSK implementations Binary Tree representation Tree representation
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
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
A Simple Filter Example The basic element for the simple filter include: • LOOP • ACCUMLATION • MULTIPLY • ARRAY 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
Machine Learning-based Pattern Recognition(Cont’) • Advantage Fast & simple • Disadvantage Accuracy can be low
ML and Tree-based Pattern Recognition • Low computational cost and high accuracy Primitive Recognition Second step First step Tree-based Pattern Recognition ML-based Pattern Recognition Source Target similar primitives
Thank You Comments & Questions?