Engineering Commons^™

Artificial Intelligence-Enabled Exploratory Cyber-Physical Safety Analyzer Framework For Civilian Urban Air Mobility, Md. Shirajum Munir, Sumit Howlader Dipro, Kamrul Hasan, Tariqul Islam, Sachin Shetty

VMASC Publications

Urban air mobility (UAM) has become a potential candidate for civilization for serving smart citizens, such as through delivery, surveillance, and air taxis. However, safety concerns have grown since commercial UAM uses a publicly available communication infrastructure that enhances the risk of jamming and spoofing attacks to steal or crash crafts in UAM. To protect commercial UAM from cyberattacks and theft, this work proposes an artificial intelligence (AI)-enabled exploratory cyber-physical safety analyzer framework. The proposed framework devises supervised learning-based AI schemes such as decision tree, random forests, logistic regression, K-nearest neighbors (KNN), and long short-term memory (LSTM) for predicting and …

Toward Real-Time, Robust Wearable Sensor Fall Detection Using Deep Learning Methods: A Feasibility Study, Haben Yhdego, Christopher Paolini, Michel Audette

Electrical & Computer Engineering Faculty Publications

Real-time fall detection using a wearable sensor remains a challenging problem due to high gait variability. Furthermore, finding the type of sensor to use and the optimal location of the sensors are also essential factors for real-time fall-detection systems. This work presents real-time fall-detection methods using deep learning models. Early detection of falls, followed by pneumatic protection, is one of the most effective means of ensuring the safety of the elderly. First, we developed and compared different data-segmentation techniques for sliding windows. Next, we implemented various techniques to balance the datasets because collecting fall datasets in the real-time setting has …

Patch-Wise Training With Convolutional Neural Networks To Synthetically Upscale Cfd Simulations, John P. Romano, Alec C. Brodeur, Oktay Baysal

Mechanical & Aerospace Engineering Faculty Publications

This paper expands the authors’ prior work[1], which focuses on developing a convolutional neural network (CNN) model capable of mapping time-averaged, unsteady Reynold’s-averaged Navier-Stokes (URANS) simulations to higher resolution results informed by time-averaged detached eddy simulations (DES). The authors present improvements over the prior CNN autoencoder model that result from hyperparameter optimization, increased data set augmentation through the adoption of a patch-wise training approach, and the predictions of primitive variables rather than vorticity magnitude. The training of the CNN model developed in this study uses the same URANS and DES simulations of a transonic flow around several NACA 4-digit airfoils …

Acm Web Conference 2023, Usha Lokala, Kaushik Roy, Utkarshani Jaimini, Amit Sheth

Publications

Improving the performance and explanations of ML algorithms is a priority for adoption by humans in the real world. In critical domains such as healthcare, such technology has significant potential to reduce the burden on humans and considerably reduce manual assessments by providing quality assistance at scale. In today’s data-driven world, artificial intelligence (AI) systems are still experiencing issues with bias, explainability, and human-like reasoning and interpretability. Causal AI is the technique that can reason and make human-like choices making it possible to go beyond narrow Machine learning-based techniques and can be integrated into human decision-making. It also offers intrinsic …

A Survey Of Using Machine Learning In Iot Security And The Challenges Faced By Researchers, Khawlah M. Harahsheh, Chung-Hao Chen

Electrical & Computer Engineering Faculty Publications

The Internet of Things (IoT) has become more popular in the last 15 years as it has significantly improved and gained control in multiple fields. We are nowadays surrounded by billions of IoT devices that directly integrate with our lives, some of them are at the center of our homes, and others control sensitive data such as military fields, healthcare, and datacenters, among others. This popularity makes factories and companies compete to produce and develop many types of those devices without caring about how secure they are. On the other hand, IoT is considered a good insecure environment for cyber …

Atlas-Based Shared-Boundary Deformable Multi-Surface Models Through Multi-Material And Two-Manifold Dual Contouring, Tanweer Rashid, Sharmin Sultana, Mallar Chakravarty, Michel Albert Audette

Electrical & Computer Engineering Faculty Publications

This paper presents a multi-material dual “contouring” method used to convert a digital 3D voxel-based atlas of basal ganglia to a deformable discrete multi-surface model that supports surgical navigation for an intraoperative MRI-compatible surgical robot, featuring fast intraoperative deformation computation. It is vital that the final surface model maintain shared boundaries where appropriate so that even as the deep-brain model deforms to reflect intraoperative changes encoded in ioMRI, the subthalamic nucleus stays in contact with the substantia nigra, for example, while still providing a significantly sparser representation than the original volumetric atlas consisting of hundreds of millions of voxels. The …

Control Implemented On Quantum Computers: Effects Of Noise, Nondeterminism, And Entanglement, Kip Nieman, Keshav Kasturi Rangan, Helen Durand

Chemical Engineering and Materials Science Faculty Research Publications

Quantum computing has advanced in recent years to the point that there are now some quantum computers and quantum simulators available to the public for use. In addition, quantum computing is beginning to receive attention within the process systems engineering community for directions such as machine learning and optimization. A logical next step for its evaluation within process systems engineering is for control, specifically for computing control actions to be applied to process systems. In this work, we provide some initial studies regarding the implementation of control on quantum computers, including the implementation of a single-input/single-output proportional control law on …

Machine Learning In Requirements Elicitation: A Literature Review, Cheligeer Cheligeer, Jingwei Huang, Guosong Wu, Nadia Bhuiyan, Yuan Xu, Yong Zeng

Engineering Management & Systems Engineering Faculty Publications

A growing trend in requirements elicitation is the use of machine learning (ML) techniques to automate the cumbersome requirement handling process. This literature review summarizes and analyzes studies that incorporate ML and natural language processing (NLP) into demand elicitation. We answer the following research questions: (1) What requirement elicitation activities are supported by ML? (2) What data sources are used to build ML-based requirement solutions? (3) What technologies, algorithms, and tools are used to build ML-based requirement elicitation? (4) How to construct an ML-based requirements elicitation method? (5) What are the available tools to support ML-based requirements elicitation methodology? Keywords …

Extending Instantaneous De-Mixing Algorithms To Anechoic Mixtures, Swarnadeep Bagchi, Ruairí De Fréin

Conference papers

The AdRess algorithm separates sources that are mixed using stereo, pan-mixing in a computationally efficient way. Pan-mixing gives the sources a location in the stereo field by introducing a relative attenuation between the versions of the sources that appear on each channel. AdRess achieves separation by constructing only a frequency-attenuation matrix. We introduce a new algorithm called Delayed-AdRess (D-AdRess), where, in addition to the frequency-attenuation matrix, two other matrices namely, frequency-delay and time-delay are used to separate sources from anechoic mixtures. By anechoic mixtures, we mean mixing scenarios where both attenuation and delays are experienced by the source signals.

A Study Of Non-Datapath Cache Replacement Algorithms, Steven G. Lyons Jr.

FIU Electronic Theses and Dissertations

Conventionally, caching algorithms have been designed for the datapath — the levels of memory that must contain the data before it gets made available to the CPU. Attaching a fast device (such as an SSD) as a cache to a host that runs the application workload are recent developments. These host-side caches open up possibilities for what are referred to as non-datapath caches to exist. Non-Datapath caches are referred to as such because the caches do not exist on the traditional datapath, instead being optional memory locations for data. As these caches are optional, a new capability is available to …

Analysis Of Power Quality Constrained Consumer-Friendly Demand Response In Low Voltage Distributions Network, Chittesh Veni Chandran

Dissertations

Load management using demand response (DR) in a low voltage distribution network (LVDN) offers an economically profitable business platform with peak load management. However, the inconvenience caused to the consumer in depriving their devices and the low levels of associated incentive have contributed to lower consumer acceptance for DR programs in the community. However, with the increasing number of controllable consumer loads, a residential-level DR program is highly plausible in the short to medium term. Further, additional DR capabilities (including ancillary services) are likely to improve the remuneration potential for participants in DR. Considering the perspective of a distribution network …

Phonetic Algorithm Performance, Aaron Schneidereit

Senior Honors Projects

AARON SCHNEIDEREIT (Computer Science BS) Phonetic Algorithm Performance Sponsors: Noah Daniels (Computer Science and Statistics) Phonetic Algorithms are used for classifying words based on their pronunciation. These algorithms are used in many text-to-speech technologies and spell-checkers to ensure that a word can be correctly recognized despite minor spelling/pronunciation errors. The process of encoding a word to its phonetic surname is known as Phonetic Matching. Since 1918, there have only been a handful of phonetic algorithms that have been created. The main three algorithms that other phonetic algorithms are built from are Soundex, New York State Identification and Intelligence System (NYSIIS), …

Phonetic Algorithm Performance, Aaron Schneidereit

Senior Honors Projects

AARON SCHNEIDEREIT (Computer Science BS) Phonetic Algorithm Performance Sponsors: Noah Daniels (Computer Science and Statistics) Phonetic Algorithms are used for classifying words based on their pronunciation. These algorithms are used in many text-to-speech technologies and spell-checkers to ensure that a word can be correctly recognized despite minor spelling/pronunciation errors. The process of encoding a word to its phonetic surname is known as Phonetic Matching. Since 1918, there have only been a handful of phonetic algorithms that have been created. The main three algorithms that other phonetic algorithms are built from are Soundex, New York State Identification and Intelligence System (NYSIIS), …

A Simple, Realistic Walled Phantom For Intravascular And Intracardiac Applications., Hareem Nisar, John Moore, Roberta Piazza, Efthymios Maneas, Elvis C S Chen, Terry M Peters

Robarts Imaging Publications

PURPOSE: This work aims to develop a simple, anatomically and haptically realistic vascular phantom, compatible with intravascular and intracardiac ultrasound. The low-cost, dual-layered phantom bridges the gap between traditional wall-only and wall-less phantoms by showing both the vessel wall and surrounding tissue in ultrasound imaging. This phantom can better assist clinical tool training, testing of intravascular devices, blood flow studies, and validation of algorithms for intravascular and intracardiac surgical systems.

METHODS: Polyvinyl alcohol cryogel (PVA-c) incorporating a scattering agent was used to obtain vessel and tissue-mimicking materials. Our specific design targeted the inferior vena cava and renal bifurcations which were …

Survey Of 8 Uav Set-Covering Algorithms For Terrain Photogrammetry, Joshua Hammond, Cory Vernon, Trent Okeson, Benjamin Barrett, Samuel Arce, Valerie Newell, Joseph Janson, Kevin Franke, John Hedengren

Faculty Publications

Remote sensing with unmanned aerial vehicles (UAVs) facilitates photogrammetry for environmental and infrastructural monitoring. Models are created with less computational cost by reducing the number of photos required. Optimal camera locations for reducing the number of photos needed for structure-from-motion (SfM) are determined through eight mathematical set-covering algorithms as constrained by solve time. The algorithms examined are: traditional greedy, reverse greedy, carousel greedy (CG), linear programming, particle swarm optimization, simulated annealing, genetic, and ant colony optimization. Coverage and solve time are investigated for these algorithms. CG is the best method for choosing optimal camera locations as it balances number of …

Optimization Of Railroad Bearing Health Monitoring System For Wireless Utilization, Jonas Cuanang, Constantine Tarawneh, Martin Amaro Jr., Jennifer Lima, Heinrich D. Foltz

Mechanical Engineering Faculty Publications and Presentations

In the railroad industry, systematic health inspections of freight railcar bearings are required. Bearings are subjected to high loads and run at high speeds, so over time the bearings may develop a defect that can potentially cause a derailment if left in service operation. Current bearing condition monitoring systems include Hot-Box Detectors (HBDs) and Trackside Acoustic Detection Systems (TADS™). The commonly used HBDs use non-contact infrared sensors to detect abnormal temperatures of bearings as they pass over the detector. Bearing temperatures that are about 94°C above ambient conditions will trigger an alarm indicating that the bearing must be removed from …

Conference Roundup: Smart Cataloging - Beginning The Move From Batch Processing To Automated Classification, Rachel S. Evans

Articles, Chapters and Online Publications

This article reviewed the Amigos Online Conference titled “Work Smarter, Not Harder: Innovating Technical Services Workflows” keynote session delivered by Dr. Terry Reese on February 13, 2020. Excerpt:

"As the developer of MarcEdit, a popular metadata suite used widely across the library community, Reese’s current work is focused on the ways in which libraries might leverage semantic web techniques in order to transform legacy library metadata into something new. So many sessions related to using new technologies in libraries or academia, although exciting, are not practical enough to put into everyday use by most librarians. Reese’s keynote, titled Smart Cataloging: …

Cyber-Physical Security With Rf Fingerprint Classification Through Distance Measure Extensions Of Generalized Relevance Learning Vector Quantization, Trevor J. Bihl, Todd J. Paciencia, Kenneth W. Bauer Jr., Michael A. Temple

Faculty Publications

Radio frequency (RF) fingerprinting extracts fingerprint features from RF signals to protect against masquerade attacks by enabling reliable authentication of communication devices at the “serial number” level. Facilitating the reliable authentication of communication devices are machine learning (ML) algorithms which find meaningful statistical differences between measured data. The Generalized Relevance Learning Vector Quantization-Improved (GRLVQI) classifier is one ML algorithm which has shown efficacy for RF fingerprinting device discrimination. GRLVQI extends the Learning Vector Quantization (LVQ) family of “winner take all” classifiers that develop prototype vectors (PVs) which represent data. In LVQ algorithms, distances are computed between exemplars and PVs, and …

Using Cost-Sensitive Learning And Feature Selection Algorithms To Improve The Performance Of Imbalanced Classification, Fang Feng, Kuan-Ching Li, Jun Shen, Qingguo Zhou, Xuhui Yang

Faculty of Engineering and Information Sciences - Papers: Part A

Imbalanced data problem is widely present in network intrusion detection, spam filtering, biomedical engineering, finance, science, being a challenge in many real-life data-intensive applications. Classifier bias occurs when traditional classification algorithms are used to deal with imbalanced data. As already known, the General Vector Machine (GVM) algorithm has good generalization ability, though it does not work well for the imbalanced classification. Additionally, the state-of-the-art Binary Ant Lion Optimizer (BALO) algorithm has high exploitability and fast convergence rate. Based on these facts, we have proposed in this paper a Cost-sensitive Feature selection General Vector Machine (CFGVM) algorithm based on GVM and …

Disaster Damage Categorization Applying Satellite Images And Machine Learning Algorithm, Farinaz Sabz Ali Pour, Adrian Gheorghe

Engineering Management & Systems Engineering Faculty Publications

Special information has a significant role in disaster management. Land cover mapping can detect short- and long-term changes and monitor the vulnerable habitats. It is an effective evaluation to be included in the disaster management system to protect the conservation areas. The critical visual and statistical information presented to the decision-makers can help in mitigation or adaption before crossing a threshold. This paper aims to contribute in the academic and the practice aspects by offering a potential solution to enhance the disaster data source effectiveness. The key research question that the authors try to answer in this paper is how …

Relational Sequential Decision Making, Kaushik Roy

Publications

Markov Decision Processes(MDPs) are the standard for sequential decision making. Comprehensive theory and methods have been developed to deal with solving MDPs in the propositional setting. Real world domains however are naturally represented using objects and relationships. To this effect, relational adaptations of algorithms to solve MDPs have been proposed in recent years. This paper presents a study of these techniques both in the model based and model free setting.

An Integrated Approach For Remanufacturing Job Shop Scheduling With Routing Alternatives., Ling Ling Li, Cong Bo Li, Li Li, Ying Tang, Qing Shan Yang

Henry M. Rowan College of Engineering Faculty Scholarship

Remanufacturing is a practice of growing importance due to increasing environmental awareness and regulations. However, the stochastic natures inherent in the remanufacturing processes complicate its scheduling. This paper undertakes the challenge and presents a remanufacturing job shop scheduling approach by integrating alternative routing assignment and machine resource dispatching. A colored timed Petri net is introduced to model the dynamics of remanufacturing process, such as various process routings, uncertain operation times for cores, and machine resource conflicts. With the color attributes in Petri nets, two types of decision points, recovery routing selection and resource dispatching, are introduced and linked with places …

Rubik's Cube: A Visual And Tactile Learning Of Algorithms And Patterns, Lawrence Muller

Open Educational Resources

This is a classroom activity report on teaching algorithms as part of a second course in computer programming. Teaching an algorithm in an introductory level programming class is often a dry task for the instructor and the rewards for the student are abstract. To make the learning of algorithms and software more rewarding, this assignment employs a Rubik’s cube.

Dynamic Light Scattering Optical Coherence Tomography To Probe Motion Of Subcellular Scatterers., Nico J J Arezza, Marjan Razani, Michael C Kolios

Medical Biophysics Publications

Optical coherence tomography (OCT) is used to provide anatomical information of biological systems but can also provide functional information by characterizing the motion of intracellular structures. Dynamic light scattering OCT was performed on intact, control MCF-7 breast cancer cells and cells either treated with paclitaxel to induce apoptosis or deprived of nutrients to induce oncosis. Autocorrelations (ACs) of the temporal fluctuations of OCT intensity signals demonstrate a significant decrease in decorrelation time after 24 h in both the paclitaxel-treated and nutrient-deprived cell groups but no significant differences between the two groups. The acquired ACs were then used as input for …

The Role Of Artificial Intelligence In Business Decision Making, Chase Rainwater

Operations Management Presentations

When we think of artificial intelligence, we often are drawn to the self-driving cars, voice-based home technologies and automated online interactions that fill the news and drive our daily activities. However, the root of these advancements, machine learning, is a predictive analytics technique that has much broader applicability. With the age of “big data” and the buzz around “data science” continuing to grow, decision-makers are asking themselves if emerging technologies, such as machine learning, can help improve business processes.

In this seminar we will demystify the fundamental concepts that comprise machine learning. The differences between supervised and unsupervised learning, as …

Icdar 2019 Time-Quality Binarization Competition, Rafael Dueire Lins, Ergina Kavallieratou, Elisa Barney Smith, Rodrigo Barros Bernardino, Darlisson Marinho De Jesus

Electrical and Computer Engineering Faculty Publications and Presentations

The ICDAR 2019 Time-Quality Binarization Competition assessed the performance of seventeen new together with thirty previously published binarization algorithms. The quality of the resulting two-tone image and the execution time were assessed. Comparisons were on both in "real-world" and synthetic scanned images, and in documents photographed with four models of widely used portable phones. Most of the submitted algorithms employed machine learning techniques and performed best on the most complex images. Traditional algorithms provided very good results at a fraction of the time.

Transparency And Algorithmic Governance, Cary Coglianese, David Lehr

All Faculty Scholarship

Machine-learning algorithms are improving and automating important functions in medicine, transportation, and business. Government officials have also started to take notice of the accuracy and speed that such algorithms provide, increasingly relying on them to aid with consequential public-sector functions, including tax administration, regulatory oversight, and benefits administration. Despite machine-learning algorithms’ superior predictive power over conventional analytic tools, algorithmic forecasts are difficult to understand and explain. Machine learning’s “black-box” nature has thus raised concern: Can algorithmic governance be squared with legal principles of governmental transparency? We analyze this question and conclude that machine-learning algorithms’ relative inscrutability does not pose a …

The Global Disinformation Order: 2019 Global Inventory Of Organised Social Media Manipulation, Samantha Bradshaw, Philip N. Howard

Copyright, Fair Use, Scholarly Communication, etc.

Executive Summary

Over the past three years, we have monitored the global organization of social media manipulation by governments and political parties. Our 2019 report analyses the trends of computational propaganda and the evolving tools, capacities, strategies, and resources.

1. Evidence of organized social media manipulation campaigns which have taken place in 70 countries, up from 48 countries in 2018 and 28 countries in 2017. In each country, there is at least one political party or government agency using social media to shape public attitudes domestically.

2.Social media has become co-opted by many authoritarian regimes. In 26 countries, computational propaganda …

A Mathematical Framework On Machine Learning: Theory And Application, Bin Shi

FIU Electronic Theses and Dissertations

The dissertation addresses the research topics of machine learning outlined below. We developed the theory about traditional first-order algorithms from convex opti- mization and provide new insights in nonconvex objective functions from machine learning. Based on the theory analysis, we designed and developed new algorithms to overcome the difficulty of nonconvex objective and to accelerate the speed to obtain the desired result. In this thesis, we answer the two questions: (1) How to design a step size for gradient descent with random initialization? (2) Can we accelerate the current convex optimization algorithms and improve them into nonconvex objective? For application, …

Combining Algorithms For More General Ai, Mark Robert Musil

Undergraduate Research & Mentoring Program

Two decades since the first convolutional neural network was introduced the AI sub-domains of classification, regression and prediction still rely heavily on a few ML architectures despite their flaws of being hungry for data, time, and high-end hardware while still lacking generality. In order to achieve more general intelligence that can perform one-shot learning, create internal representations, and recognize subtle patterns it is necessary to look for new ML system frameworks. Research on the interface between neuroscience and computational statistics/machine learning has suggested that combined algorithms may increase AI robustness in the same way that separate brain regions specialize. In …