Engineering topics

Alam, Muhammad

Publications and source records attributed to Alam, Muhammad.

2 records

DOE OSTI2024

FIU Project 2: Environmental Remediation Science & Technology [Slides]

FIU’s research under this project involves conducting basic and applied science to fill knowledge gaps and validate potential remediation technologies for contaminated soil and groundwater and the assessment of the fate and transport of contaminants in the environment. The aim of FIU’s research is to reduce the potential for contaminant mobility or toxicity in the surface and subsurface through the development and application of state-of-the-art scientific and environmental remediation technologies at the Hanford Site, Savannah River Site (SRS), and the Waste Isolation Pilot Plant (WIPP), which is the Nation’s only mined geologic repository for permanent disposal of transuranic waste. FIU collaborates with scientists from Pacific Northwest National Laboratory (PNNL), Savannah River National Laboratory (SRNL), Savannah River Ecology Laboratory (SREL), Los Alamos National Laboratory (LANL) and the DOE Carlsbad Field Office (CBFO) in order to plan and execute research that is synergistic with the work being conducted at the sites, and that supports the resolution of critical science and engineering needs which leads to a better understanding of the long-term behavior of subsurface contaminants. The knowledge gained through this research will be used to transform experimental and modeling innovations into practical applications deployed at the sites to support EM’s primary goal of expediting the closure of major contaminated soil and groundwater sites and waste units. Collaborative relationships between FIU and the national laboratories have provided large benefits over the years to FIU, the national laboratories, the DOE complex, and the DOE EM mission. By working closely with the national laboratories, FIU’s research is not only closely aligned with the cleanup mission priorities at the DOE sites, but complements and supports ongoing work at the national laboratories for screening of new remedial technologies. This coordination and leveraging of research efforts results in time- and cost-savings, and will accelerate progress of the DOE EM environmental restoration mission.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2022

Training a Quantum Annealing Based Restricted Boltzmann Machine on Cybersecurity Data

A restricted Boltzmann machine (RBM) is a generative model that could be used in effectively balancing a cybersecurity dataset because the synthetic data a RBM generates follows the probability distribution of the training data. RBM training can be performed using contrastive divergence (CD) and quantum annealing (QA). QA-based RBM training is fundamentally different from CD and requires samples from a quantum computer. We present a real-world application that uses a quantum computer. Specifically, we train a RBM using QA for cybersecurity applications. The D-Wave 2000Q has been used to implement QA. RBMs are trained on the ISCX data, which is a benchmark dataset for cybersecurity. For comparison, RBMs are also trained using CD. CD is a commonly used method for RBM training. Our analysis of the ISCX data shows that the dataset is imbalanced. We present two different schemes to balance the training dataset before feeding it to a classifier. The first scheme is based on the undersampling of benign instances. The imbalanced training dataset is divided into five sub-datasets that are trained separately. A majority voting is then performed to get the result. Our results show the majority vote increases the classification accuracy up from 90.24% to 95.68%, in the case of CD. For the case of QA, the classification accuracy increases from 74.14% to 80.04%. In the second scheme, a RBM is used to generate synthetic data to balance the training dataset. We show that both QA and CD-trained RBM can be used to generate useful synthetic data. Balanced training data is used to evaluate several classifiers. Among the classifiers investigated, K-Nearest Neighbor (KNN) and Neural Network (NN) perform better than other classifiers. They both show an accuracy of 93%. Our results show a proof-of-concept that a QA-based RBM can be trained on a 64-bit binary dataset. The illustrative example suggests the possibility to migrate many practical classification problems to QA-based techniques. Further, we show that synthetic data generated from a RBM can be used to balance the original dataset.

97 MATHEMATICS AND COMPUTING↗