Emphasis : Machine Learning and Communications Algorithms
Collaborators: Glen Uehara, GD and ASU PhD program, Kristen Jaskie, Postdoc
Graduate Students: Leslie Miller, Tanay Patel, Nandika Goyal, Smylena Zebah Dsilva
Graduates of Program: Max Yarter GTRI, Aradhita Sarma Analog Devices, Rajesh Kumar ASU,
Undergraduate Researchers: Michael Esposito, Kaden McGuffie, Niki Kyriakou, Salil Naik, Movinya Gunatilaka
Faculty Advisor: Andreas Spanias, Professor ECEE, Director SenSIP Center
Sponsors: General Dynamics, National Science Foundation, Quantum Collaborative, ASU Knowledge Enterprise, CIA Government Labs
Presentation: Click Here To View
SenSIP Quantum Information Science and Machine Learning Student and Faculty Group
Current Projects:
Leslie Miller
1) Quantum Image Fusion Methods for Remote Sensing
Abstract— This project presents algorithms, simulations, and results using machine learning and quantum image fusion algorithms for radar and remote sensing applications. Previous efforts in the classification of synthetic aperture radar (SAR) images using quantum machine learning provided encouraging results but, nevertheless modest accuracy. In this paper, we propose a novel quantum image fusion technique used for identifying and classifying objects obtained from C-band SAR and optical images. More specifically, we design a four-qubit quantum circuit to process the SAR image dataset. This method enhances the spectral details otherwise not seen when using the raw SAR dataset. In addition to the quantum circuit, we design deep neural networks (NN) to improve classification results. The Visual Geometry Group 16 (VGG16), a convolutional neural network that is sixteen layers deep, is customized and used for classification. The merit of quantum fusion as well as the promising results in improving the overall system and lowering size, weight, power, and cost (SWaP-C) is described.
IEEE Citation: L. Miller, G. Uehara, A. Spanias, “Quantum Image Fusion Methods for Remote Sensing,” 2024 IEEE Aerospace Conference, Big Sky, MT, USA, 2024, pp. 1-8.
Aradhita Sharma
2) Quantum Linear Prediction For System Identification And Spectral Estimation Applications
Abstract—This project presents the design and implementation of quantum algorithms and circuits for linear prediction. The intended applications are system identification, spectral estimation, and speech processing. A frequency-domain method that uses the quantum Fourier transform is developed to estimate the autocorrelation sequence of the signal and a quantum circuit is designed to estimate the linear prediction parameters. The quantum linear prediction performance is evaluated using in system identification, autoregressive (AR) spectral estimation, and speech analysis simulations. More specifically, we evaluate the performance of the quantum linear predictor in terms of quantum noise effects, qubit precision, and overall computational requirements. Comparisons of quantum versus classical linear prediction are presented.
Keywords—Quantum linear prediction, quantum Fourier transform, HHL algorithm, qubits.
Fig: The modified HHL quantum circuit with pre and post processing blocks for speech signals.
IEEE Citation: A Sharma, G. Uehara, and A. Spanias, “Quantum Linear Prediction For System Identification And Spectral Estimation Applications,” 2023 57th Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA, USA, 2023.
Glen Uehara
3) Quantum Machine Learning for Photovoltaic Topology Optimization
Abstract—Photovoltaic array topology optimization was shown to improve efficiency in renewable energy plants. Previous studies demonstrated improvements via simulation at the level of 7-12% or more. In this project, we describe solar array topology optimization systems based on quantum machine learning algorithms. The idea of using quantum machine learning can be useful in cases where the objective is to optimize power output in large sites with several thousands of panels. We specifically propose and assess a quantum circuit for a neural network implementation for photovoltaic topology optimization. Results and comparisons are presented using classical and quantum neural network implementations. In addition, solar array topology optimization simulations and comparisons using a quantum neural network are described for different numbers of qubits.
Smart solar array monitoring system integrated with quantum machine learning topology reconfiguration algorithms.
IEEE Citation: G. Uehara, V. Narayanaswamy, C. Tepedelenlioglu, A. Spanias, “Quantum Machine Learning for Photovoltaic Topology Optimization,” 2022 IEEE 13th International Conference on Information, Intelligence, Systems & Applications (IISA), Hybrid Conference, July 2022.
Publications:
[1] G. Uehara, S. Rao, M. Dobson, C. Tepedelenlioglu, and A. Spanias, “Quantum Neural Network Parameter Estimation for PV Fault Detection.” In 2021 Twelfth IEEE International Conference on Information, Intelligence, Systems & Applications (IISA) 2021. – Click Here
[2] Uehara, Glen S., Andreas Spanias, and William Clark. “Quantum information processing algorithms with emphasis on machine learning.” 2021 12th International Conference on Information, Intelligence, Systems & Applications (IISA). IEEE, 2021. – Click Here
[3] G. Uehara, V. Narayanaswamy, C. Tepedelenlioglu, A. Spanias, “Quantum Machine Learning for Photovoltaic Topology Optimization,” 2022 IEEE 13th International Conference on Information, Intelligence, Systems & Applications (IISA), Hybrid Conference, July 2022. – Click Here
[4] M. Yarter, G. Uehara, A. Spanias, “Implementation and Analysis of Quantum Homomorphic Encryption,” 2022 IEEE 13th International Conference on Information, Intelligence, Systems & Applications (IISA), Hybrid Conference, July 2022. – Click Here
[5] M. Esposito, G. Uehara, A. Spanias, Quantum Machine Learning for Audio Classification with Applications to Healthcare, 2022 IEEE 13th International Conference on Information, Intelligence, Systems & Applications (IISA), Hybrid Conference, July 2022. – Click Here
[6] M. Yarter, G. Uehara, A. Spanias, “EDGE Cloud Voice Recognition Using Quantum Neural Networks,” IEEE MWCAS 2023, August 2023.
[7] Rajesh Kumar, Glen Uehara, Andreas Spanias, Measuring Performance of Quantum Simulators for Machine Learning, draft completed, to be submitted to IEEE.
[8] A. Sharma, G. Uehara, V. Narayanaswamy, L. Miller and A. Spanias, “Signal Analysis-Synthesis Using the Quantum Fourier Transform,” ICASSP 2023 – 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 2023, pp. 1-5, doi: 10.1109/ICASSP49357.2023.
Workforce Development:
Glen Uehara, Jean Larson, Wendy Barnard, Michael Esposito, Filippo Posta, Maxwell Yarter, Aradhita Sharma, Niki Kyriacou, Matthew Dobson, Andreas Spanias, “Undergraduate Research and Education in Quantum Machine Learning,” IEEE FIE 2022, Upsala, Oct. 2022. – Click Here
ASU SenSIP REU Site: Quantum Machine Learning Algorithm Design and Implementation – Click Here
AWARDS / HONORS related to Quantum Information Systems:
Impact Award for Quantum Machine Learning Work
Mathew Dobson, Quantum Energy & Quantum Edge Detection – More Info
Leslie Miller, Quantum Imaging, – More Info
Michael Esposito, Quantum COVID-19 Audio, – More Info
Aradhita Sharma, Quantum Signal Analysis Synthesis, – More Info
Thesis:
1. Barrett Honors Thesis in Quantum ML for Covid 19 Detection, M. Esposito, 2022.
2. Barrett Honors Thesis in Quantum ML for Imaging , L. Miller, 2023.
3. Masters Thesis, Rajesh Kumar, Measuring Performance of Quantum Simulators for Machine Learning, 2023.
4. Master Thesis Maxwell Yarter, Investigating Quantum Approaches to Algorithm Privacy and Speech Processing, 2023.
5. Master Thesis Aradhita Sharma, Development of Signal Analysis Synthesis Methods Quantum Fourier Transforms and Quantum Linear Prediction Algorithms, 2023.
SenSIP – Tec de Monterrey Workshop, April 2023
The purpose of this workshop is to explore areas of collaboration of SenSIP with Tec de Monterrey on Quantum Machine Learning
Reports:
Quantum Linear Prediction, Aradhita Sharma,Glen Uehara, Andreas Spanias, 2023.
Quantum Support Vector Machines for Energy, Niki Kyriakou,Glen Uehara and Andreas Spanias. 2023.
Quantum Machine Learning for Emotion Recognition, Kayden McGuffie, Glen Uehara and Andreas Spanias. 2023.
Quantum Image Edge Detection, Matthew Dobson, Glen Uehara and Andreas Spanias.2022.
Signal Analysis-Synthesis based on Quantum Fourier Transforms, Aradhita Sharma,Glen Uehara, Andreas Spanias, 2022
Quantum Cloud-Edge Computing for Audio Recognition, Max Yarter, Glen Uehara and Andreas Spanias. 2022.
Participation in the Quantum Collaborative,
With Quantum Collaborative, SenSIP and ITESM faculty and staff at the IBM Summit in November 2022 at NYC.