Dr. Peng Wang Profile

Dr. Peng Wang

SPIE Involvement:

Author

Publications (7)

Proceedings Article | 30 May 2022 Presentation

Transitory cross entropy for model training on unbalanced datasets

Venkateswara Dasari, Billy Geerhart, Peng Wang

Proceedings Volume PC12117, PC1211703 (2022) https://doi.org/10.1117/12.2618556

KEYWORDS: Data modeling

Read Abstract +

Proceedings Article | 12 April 2021 Presentation + Paper

Deep learning to predict the modulation schemes of real OFDM signals

Peng Wang, Manuel Vindiola, Michael Markowski, James Buxton

Proceedings Volume 11751, 117510B (2021) https://doi.org/10.1117/12.2585313

KEYWORDS: Orthogonal frequency division multiplexing, Data modeling, Modulation, Neural networks

Read Abstract +

Proceedings Article | 12 April 2021 Presentation + Paper

Efficient normalization techniques to optimize AI models for deployment in tactical edge

Billy Geerhart, Venkat Dasari, Peng Wang, David Alexander

Proceedings Volume 11751, 117510F (2021) https://doi.org/10.1117/12.2585788

KEYWORDS: Artificial intelligence, Sensors, Databases, Data modeling

Read Abstract +

Proceedings Article | 12 April 2021 Presentation + Paper

Deep neural network model optimizations for resource constrained tactical edge computing platforms

Venkat Dasari, Billy Geerhart, Peng Wang, David Alexander

Proceedings Volume 11751, 117510E (2021) https://doi.org/10.1117/12.2585784

KEYWORDS: Neural networks, Optimization (mathematics), Tactical intelligence, Artificial intelligence, Situational awareness sensors

Read Abstract +

Proceedings Article | 22 April 2020 Presentation + Paper

Deep learning for modulation and coding rate classification of OFDM

Peng Wang, Manuel Vindiola, Michael Markowski

Proceedings Volume 11419, 114190K (2020) https://doi.org/10.1117/12.2557300

KEYWORDS: Modulation, Orthogonal frequency division multiplexing, Signal to noise ratio, Data modeling, Performance modeling, Matrices, Quadrature amplitude modulation, Forward error correction, Machine learning, Neural networks

Read Abstract +

Machine Learning (ML) technologies have been widely used for blind signal classification problem (Modulation Classification) to automatically identify the modulation schemes of Radio Frequency (RF) signal from complex- valued IQ (In-phase Quadrature) samples. Traditional ML methods usually have two stages where the first stage is to manually extract the features of the IQ symbols by subject matter experts and the second stage is to feed the features to an ML algorithm (e.g., a support vector machine) to develop the classifier. The state- of-art technology is to apply Deep Learning (DL) technologies such as Convolutional Neural Network (CNN) or Recurrent Neural Network (RNN) directly to the complex-value IQ symbols to train a multi-class classifier. In this effort we are focused on the modulation and coding rate classification problems for multi-carrier Orthogonal Frequency-Division Multiplexing (OFDM) signals. The generated OFDM data set consists of over 480k instances across four different modulations and three different coding rates which include BPSK + 1=2, BPSK+3=4, QPSK+1=2, QPSK+3=4, QAM16+1=2, QAM16+3=4, QAM64+2=3 and QAM64+3=4. Deep Learning (DL) models can successfully catch the features of OFDM modulations and identify the modulation scheme from the baseband IQ symbols. Four DL models including Residual Neural Network 34(Resnet34), Resnet18, Squeezenet and Long Short-Term Memory (LSTM) trained over the data set can achieve over 94% overall accuracy for signals across 􀀀10dB to 10dB with step size of 4dB. Among them, Squeezenet and LSTM models have much smaller model sizes which can be easily loaded in resource-limited edge computing platforms. To the best of our knowledge, coding rate classification of OFDM signals has not been studied in previous works. Therefore, three different DL models including a single-stage coding rate classifier, a combination of modulation and coding rate classifier, and a two-stage coding rate classifier are developed to identify the coding rate. However, coding rates can only be identified for low-order modulation schemes BPSK and QPSK but not for high-order modulation schemes QAM16 and QAM64. Further investigation is needed to understand the coding rate classification for high-order QAM signals.