Engineering Commons^™

A Fiber-Optic Sensor-Embedded And Machine Learning Assisted Smart Helmet For Multi-Variable Blunt Force Impact Sensing In Real Time, Yiyang Zhuang, Taihao Han, Qingbo Yang, Ryan O'Malley, Aditya Kumar, Rex E. Gerald, Jie Huang

Materials Science and Engineering Faculty Research & Creative Works

Early on-site diagnosis of mild traumatic brain injury (mTBI) will provide the best guidance for clinical practice. However, existing methods and sensors cannot provide sufficiently detailed physical information related to the blunt force impact. In the present work, a smart helmet with a single embedded fiber Bragg grating (FBG) sensor is developed, which can monitor complex blunt force impact events in real time under both wired and wireless modes. The transient oscillatory signal "fingerprint" can specifically reflect the impact-caused physical deformation of the local helmet structure. By combination with machine learning algorithms, the unknown transient impact can be recognized quickly …

Sequential Frame-Interpolation And Dct-Based Video Compression Framework, Yeganeh Jalalpour, Wu-Chi Feng, Feng Liu

Computer Science Faculty Publications and Presentations

Video data is ubiquitous; capturing, transferring, and storing even compressed video data is challenging because it requires substantial resources. With the large amount of video traffic being transmitted on the internet, any improvement in compressing such data, even small, can drastically impact resource consumption. In this paper, we present a hybrid video compression framework that unites the advantages of both DCT-based and interpolation-based video compression methods in a single framework. We show that our work can deliver the same visual quality or, in some cases, improve visual quality while reducing the bandwidth by 10--20%.

Machine Learning With Gradient-Based Optimization Of Nuclear Waste Vitrification With Uncertainties And Constraints, Lagrande Gunnell, Kyle Manwaring, Xiaonan Lu, Jacob Reynolds, John Vienna, John Hedengren

Faculty Publications

Gekko is an optimization suite in Python that solves optimization problems involving mixed-integer, nonlinear, and differential equations. The purpose of this study is to integrate common Machine Learning (ML) algorithms such as Gaussian Process Regression (GPR), support vector regression (SVR), and artificial neural network (ANN) models into Gekko to solve data based optimization problems. Uncertainty quantification (UQ) is used alongside ML for better decision making. These methods include ensemble methods, model-specific methods, conformal predictions, and the delta method. An optimization problem involving nuclear waste vitrification is presented to demonstrate the benefit of ML in this field. ML models are compared …

Development Of A High-Resolution Digital Elevation Model Of A Pilot Study Area In Basin 6, Located Near The Waste Isolation Pilot Plant (Wipp), New Mexico, Usa, Gisselle A. Gutierrez-Zuniga

FIU Electronic Theses and Dissertations

The purpose of this study is to develop a high-resolution DEM of a topographically representative sub-basin west of the WIPP transuranic waste repository. This will support accurate delineation of surface hydrological features and development of hydrological models to assess potential impact of climate, karst surface features and incompatible land use activities on regional groundwater recharge that may result in long-term vulnerability of the karst topography and thus the integrity and performance of the WIPP.

A UAV was used to collect over 5,000 images of a representative basin west of the WIPP. Images were processed using commercial software and methods were …

Design Of Secure Communication Schemes To Provide Authentication And Integrity Among The Iot Devices, Vidya Rao Dr.

Technical Collection

The fast growth in Internet-of-Things (IoT) based applications, has increased the number of end-devices communicating over the Internet. The end devices are made with fewer resources and are low battery-powered. These resource-constrained devices are exposed to various security and privacy concerns over publicly available Internet communication. Thus, it becomes essential to provide lightweight security solutions to safeguard data and user privacy. Elliptic Curve Cryptography (ECC) can be used to generate the digital signature and also encrypt the data. The method can be evaluated on a real-time testbed deployed using Raspberry Pi3 devices and every message transmitted is subjected to ECC. …

Application Of Machine Learning And Cyber Security In Smart Grid, Soham Dutta Dr.

Technical Collection

Unplanned islanding of microgrids is a major hindrance in providing continuous power supply to the critical loads. The detection of these islanding instants needs to be very fast so that the distributed generators (DG) are able to take control actions in minimum time. Due to high quality data at a rapid rate, micro phasor measurement unit (μ-PMU) are becoming widely popular in distribution system and micro grids. These μ-PMUs can be leveraged for island detection. However, the working of μ-PMU is hugely dependent on communication network for data transmission which is prone to cyber-attacks. In view of the above facts, …

Predictability Of Mechanical Behavior Of Additively Manufactured Particulate Composites Using Machine Learning And Data-Driven Approaches, Steven Malley, Crystal Reina, Somer Nacy, Jérôme Gilles, Behrad Koohbor

Henry M. Rowan College of Engineering Departmental Research

Additive manufacturing and data analytics are independently flourishing research areas, where the latter can be leveraged to gain a great insight into the former. In this paper, the mechanical responses of additively manufactured samples using vat polymerization process with different weight ratios of magnetic microparticles were used to develop, train, and validate a neural network model. Samples with six different compositions, ranging from neat photopolymer to a composite of photopolymer with 4 wt.% of magnetic particles, were manufactured and mechanically tested at quasi-static strain rate and ambient environmental conditions. The experimental data were also synthesized using a data-driven approach based …

Finite Element-Based Machine Learning Model For Predicting The Mechanical Properties Of Composite Hydrogels, Yasin Shokrollahi, Pengfei Dong, Peshala T. Gamage, Nashaita Patrawalla, Vipuil Kishore, Hozhabr Mozafari, Linxia Gu

Department of Mechanical and Materials Engineering: Faculty Publications

In this study, a finite element (FE)-based machine learning model was developed to predict the mechanical properties of bioglass (BG)-collagen (COL) composite hydrogels. Based on the experimental observation of BG-COL composite hydrogels with scanning electron microscope, 2000 microstructural images with randomly distributed BG particles were created. The BG particles have diameters ranging from 0.5 μm to 1.5 μm and a volume fraction from 17% to 59%. FE simulations of tensile testing were performed for calculating the Young’s modulus and Poisson’s ratio of 2000 microstructures. The microstructural images and the calculated Young’s modulus and Poisson’s ratio by FE simulation were used …

Additive Manufacturing Of Complexly Shaped Sic With High Density Via Extrusion-Based Technique – Effects Of Slurry Thixotropic Behavior And 3d Printing Parameters, Ruoyu Chen, Adam Bratten, Joshua Rittenhouse, Tian Huang, Wenbao Jia, Ming-Chuan Leu, Haiming Wen

Mechanical and Aerospace Engineering Faculty Research & Creative Works

Additive manufacturing of dense SiC parts was achieved via an extrusion-based process followed by electrical-field assisted pressure-less sintering. The aim of this research was to study the effect of the rheological behavior of SiC slurry on the printing process and quality, as well as the influence of 3D printing parameters on the dimensions of the extruded filament, which are directly related to the printing precision and quality. Different solid contents and dispersant- Darvan 821A concentrations were studied to optimize the viscosity, thixotropy and sedimentation rate of the slurry. The optimal slurry was composed of 77.5 wt% SiC, Y2O3 and Al2O3 …

Predicting Defects In Laser Powder Bed Fusion Using In-Situ Thermal Imaging Data And Machine Learning, Sina Malakpour Estalaki, Cody S. Lough, Robert G. Landers, Edward C. Kinzel, Tengfei Luo

Mechanical and Aerospace Engineering Faculty Research & Creative Works

Variation in the local thermal history during the Laser Powder Bed Fusion (LPBF) process in Additive Manufacturing (AM) can cause micropore defects, which add to the uncertainty of the mechanical properties (e.g., fatigue life, tensile strength) of the built materials. In-situ sensing has been proposed for monitoring the AM process to minimize defects, but successful minimization requires establishing a quantitative relationship between the sensing data and the porosity, which is particularly challenging with a large number of variables (e.g., laser speed, power, scan path, powder property). Physics-based modeling can simulate such an in-situ sensing-porosity relationship, but it is computationally costly. …

Digital Twin For Hvac Load And Energy Storage Based On A Hybrid Ml Model With Cta-2045 Controls Capability, Rosemary E. Alden, Evan S. Jones, Huangjie Gong, Abdullah Al Hadi, Dan Ionel

Power and Energy Institute of Kentucky Faculty Publications

Building modeling, specifically heating, ventilation, and air conditioning (HVAC) load and equivalent energy storage calculations, represent a key focus for decarbonization of buildings and smart grid controls. Widely used white box models, due to their complexity, are too computationally intensive to be employed in high resolution distributed energy resources (DER) platforms without simulation time delays. In this paper, an ultra-fast one-minute resolution Hybrid Machine Learning Model (HMLM) is proposed as part of a novel procedure to replicate white box models as an alternative to widespread experimental big data collection. Synthetic output data from experimentally calibrated EnergyPlus models for three existing …

A Novel Convolutional Neural Network Based Dysphonic Voice Detection Algorithm Using Chromagram, Rumana Islam, Mohammed Tarique

Electrical and Computer Engineering Publications

This paper presents a convolutional neural network (CNN) based non-invasive pathological voice detection algorithm using signal processing approach. The proposed algorithm extracts an acoustic feature, called chromagram, from voice samples and applies this feature to the input of a CNN for classification. The main advantage of chromagram is that it can mimic the way humans perceive pitch in sounds and hence can be considered useful to detect dysphonic voices, as the pitch in the generated sounds varies depending on the pathological conditions. The simulation results show that classification accuracy of 85% can be achieved with the chromagram. A comparison of …

Machine Learning-Based Peripheral Artery Disease Identification Using Laboratory-Based Gait Data, Ali Al-Ramini, Mahdi Hassan, Farahnaz Fallahtafti, Mohammad Ali Takallou, Hafizur Rahman, Basheer Qolomany, Iraklis I. Pipinos, Fadi M. Alsaleem, Sara A. Myers

Department of Mechanical and Materials Engineering: Faculty Publications

Peripheral artery disease (PAD) manifests from atherosclerosis, which limits blood flow to the legs and causes changes in muscle structure and function, and in gait performance. PAD is underdiagnosed, which delays treatment and worsens clinical outcomes. To overcome this challenge, the purpose of this study is to develop machine learning (ML) models that distinguish individuals with and without PAD. This is the first step to using ML to identify those with PAD risk early. We built ML models based on previously acquired overground walking biomechanics data from patients with PAD and healthy controls. Gait signatures were characterized using ankle, knee, …

Machine Learning-Based Peripheral Artery Disease Identification Using Laboratory-Based Gait Data, Ali Al-Ramini, Mahdi Hassan, Farahnaz Fallahtafti, Mohammad Ali Takallou, Basheer Qolomany, Iraklis I. Pipinos, Fadi Alsaleem, Sara A. Myers

Department of Mechanical and Materials Engineering: Faculty Publications

Peripheral artery disease (PAD) manifests from atherosclerosis, which limits blood flow to the legs and causes changes in muscle structure and function, and in gait performance. PAD is underdiagnosed, which delays treatment and worsens clinical outcomes. To overcome this challenge, the purpose of this study is to develop machine learning (ML) models that distinguish individuals with and without PAD. This is the first step to using ML to identify those with PAD risk early. We built ML models based on previously acquired overground walking biomechanics data from patients with PAD and healthy controls. Gait signatures were characterized using ankle, knee, …

Artificial Intelligence In Civil Infrastructure Health Monitoring—Historical Perspectives, Current Trends, And Future Visions, Tarutal Ghosh Mondal, Genda Chen

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

Over the past 2 decades, the use of artificial intelligence (AI) has exponentially increased toward complete automation of structural inspection and assessment tasks. This trend will continue to rise in image processing as unmanned aerial systems (UAS) and the internet of things (IoT) markets are expected to expand at a compound annual growth rate of 57.5% and 26%, respectively, from 2021 to 2028. This paper aims to catalog the milestone development work, summarize the current research trends, and envision a few future research directions in the innovative application of AI in civil infrastructure health monitoring. A blow-by-blow account of the …

Sers Spectroscopy With Machine Learning To Analyze Human Plasma Derived Sevs For Coronary Artery Disease Diagnosis And Prognosis, Xi Huang, Bo Liu, Shenghan Guo, Weihong Guo, Ke Liao, Guoku Hu, Wen Shi, Mitchell Kuss, Michael J. Duryee, Daniel R. Anderson, Yongfeng Lu, Bin Duan

Department of Electrical and Computer Engineering: Faculty Publications

Coronary artery disease (CAD) is one of the major cardiovascular diseases and represents the leading causes of global mortality. Developing new diagnostic and therapeutic approaches for CAD treatment are critically needed, especially for an early accurate CAD detection and further timely intervention. In this study, we successfully isolated human plasma small extracellular vesicles (sEVs) from four stages of CAD patients, that is, healthy control, stable plaque, non-ST-elevation myocardial infarction, and ST-elevation myocardial infarction. Surface-enhanced Raman scattering (SERS) measurement in conjunction with five machine learning approaches, including Quadratic Discriminant Analysis, Support Vector Machine (SVM), K-Nearest Neighbor, Artificial Neural network, were then …

Sers Spectroscopy With Machine Learning To Analyze Human Plasma Derived Sevs For Coronary Artery Disease Diagnosis And Prognosis, Xi Huang, Bo Liu, Shenghan Guo, Weihong Guo, Ke Liao, Guoku Hu, Wen Shi, Mitchell Kuss, Michael J. Duryee, Daniel R. Anderson, Yongfeng Lu, Bin Duan

Department of Electrical and Computer Engineering: Faculty Publications

Coronary artery disease (CAD) is one of the major cardiovascular diseases and represents the leading causes of global mortality. Developing new diagnostic and therapeutic approaches for CAD treatment are critically needed, especially for an early accurate CAD detection and further timely intervention. In this study, we successfully isolated human plasma small extracellular vesicles (sEVs) from four stages of CAD patients, that is, healthy control, stable plaque, non-ST-elevation myocardial infarction, and ST-elevation myocardial infarction. Surface-enhanced Raman scattering (SERS) measurement in conjunction with five machine learning approaches, including Quadratic Discriminant Analysis, Support Vector Machine (SVM), K-Nearest Neighbor, Artificial Neural network, were then …

Ag-Iot For Crop And Environment Monitoring: Past, Present, And Future, Nipuna Chamara, Md Didarul Islam, Geng Bai, Yeyin Shi, Yufeng Ge

Department of Biological Systems Engineering: Papers and Publications

CONTEXT: Automated monitoring of the soil-plant-atmospheric continuum at a high spatiotemporal resolution is a key to transform the labor-intensive, experience-based decision making to an automatic, data-driven approach in agricultural production. Growers could make better management decisions by leveraging the real-time field data while researchers could utilize these data to answer key scientific questions. Traditionally, data collection in agricultural fields, which largely relies on human labor, can only generate limited numbers of data points with low resolution and accuracy. During the last two decades, crop monitoring has drastically evolved with the advancement of modern sensing technologies. Most importantly, the introduction …

Natural Language Processing For Novel Writing, Leqing Qu, Okan Ersoy

Department of Electrical and Computer Engineering Technical Reports

No abstract provided.

Machine Learning Assisted High-Sensitivity And Large-Dynamic-Range Curvature Sensor Based On No-Core Fiber And Hollow-Core Fiber, Chen Zhu, Yiyang Zhuang, Jie Huang

Electrical and Computer Engineering Faculty Research & Creative Works

Simultaneously Increasing the Sensitivity and Dynamic Range of an Optical Fiber Sensor is Desired and Yet Challenging. in This Article, We Demonstrate an Optical Fiber Curvature Sensor based on a No-Core Fiber (NCF) Cascaded with a Hollow-Core Fiber (HCF), Realizing Simultaneously High Sensitivity and a Large Dynamic Range with the Assistance of Machine Learning Analysis. the Sensor is Fabricated by Simply Fusion Splicing a Section of NCF and HCF to Two Single-Mode Fibers (SMFs), Forming the SMF-NCF-HCF-SMF Hybrid Structure. It is Shown that the Multimode Interference in the NCF Can Increase the Sensitivity of the Device for Curvature Measurements, Compared …

Snow Parameters Inversion From Passive Microwave Remote Sensing Measurements By Deep Convolutional Neural Networks, Heming Yao, Yanming Zhang, Lijun Jiang, Hong Tat Ewe, Michael Ng

Electrical and Computer Engineering Faculty Research & Creative Works

This paper proposes a novel inverse method based on the deep convolutional neural network (ConvNet) to extract snow's layer thickness and temperature via passive microwave remote sensing (PMRS). The proposed ConvNet is trained using simulated data obtained through conventional computational electromagnetic methods. Compared with the traditional inverse method, the trained ConvNet can predict the result with higher accuracy. Besides, the proposed method has a strong tolerance for noise. The proposed ConvNet composes three pairs of convolutional and activation layers with one additional fully connected layer to realize regression, i.e., the inversion of snow parameters. The feasibility of the proposed method …

Ground Moving Target Detection For Airborne Radar Using Machine Learning Approaches, Rafi Ahmed

FIU Electronic Theses and Dissertations

Airborne radar faces many challenges to suppress unknown interferences from ground reflections to detect slow-moving targets. In this dissertation work, a feature-based machine learning approach is proposed to effectively classify target and interference such as ground clutter without actually removing them using traditional methods. Multiple features are considered for developing the target/clutter classification algorithms of airborne radars with digital arrays. The features we use for classification include the clutter proximity measures and target geometric feature.

The proximity feature is extracted to distinguish target, and clutter in location in the Doppler-angle domain for airborne radar. The Euclidean distance between a signal …

Classification Of Teleseismic Shear Wave Splitting Measurements: A Convolutional Neural Network Approach, Yanwei Zhang, Stephen S. Gao

Geosciences and Geological and Petroleum Engineering Faculty Research & Creative Works

Shear wave splitting (SWS) analysis is widely used to provide critical constraints on crustal and mantle structure and dynamic models. In order to obtain reliable splitting measurements, an essential step is to visually verify all the measurements to reject problematic measurements, a task that is increasingly time consuming due to the exponential increase in the amount of data. In this study, we utilized a convolutional neural network (CNN) based method to automatically select reliable SWS measurements. The CNN was trained by human-verified teleseismic SWS measurements and tested using synthetic SWS measurements. Application of the trained CNN to broadband seismic data …

Predicting Compressive Strength Of Alkali-Activated Systems Based On The Network Topology And Phase Assemblages Using Tree-Structure Computing Algorithms, Rohan Bhat, Taihao Han, Sai Akshay Ponduru, Arianit Reka, Jie Huang, Gaurav Sant, Aditya Kumar

Electrical and Computer Engineering Faculty Research & Creative Works

Alkali-activated system is an environment-friendly, sustainable construction material utilized to replace ordinary Portland cement (OPC) that contributes to 9% of the global carbon footprint. Moreover, the alkali-activated system has exhibited superior strength at early ages and better corrosion resistance compared to OPC. The current state of analytical and machine learning models cannot produce highly reliable predictions of the compressive strength of alkali-activated systems made from different types of aluminosilicate-rich precursors owing to substantive variation in the chemical compositions and reactivity of these precursors. In this study, a random forest model with two constraints (i.e., topological network and thermodynamic constraints) is …

Machine Learning Prediction Of Glass Transition Temperature Of Conjugated Polymers From Chemical Structure, Amirhadi Alesadi, Zhiqiang Cao, Zhaofan Li, Song Zhang, Haoyu Zhao, Xiaodan Gu, Wenjie Xia

Faculty Publications

Predicting the glass transition temperature (T_g) is of critical importance as it governs the thermomechanical performance of conjugated polymers (CPs). Here, we report a predictive modeling framework to predict T_g of CPs through the integration of machine learning (ML), molecular dynamics (MD) simulations, and experiments. With 154 T_g data collected, an ML model is developed by taking simplified “geometry” of six chemical building blocks as molecular features, where side-chain fraction, isolated rings, fused rings, and bridged rings features are identified as the dominant ones for T_g. MD simulations further unravel the fundamental roles …

Cardio-Net: A Matlab-Based Software For The Display And Diagnostic Utilization Of Vectorcardiograms, Ali H. Mannaa, Domenico Gatti

Medical Student Research Symposium

Background: The 12-lead technique is the standard in ECG, however alternate cardiography modalities such as vectorcardiography (VCG) exist . While the VCG modality offers unique clinical metrics and certain advantages over ECG, it is hardly utilized due to it being more difficult to obtain than ECG. Here we introduce Cardio-Net, a MATLAB-based software that uses standard 12-lead ECG data to generate and visualize VCGs. Furthermore, we demonstrate the diagnostic potential of VCG by utilizing a recurrent neural network (RNN) to accurately classify vectorcardiograms.

Methods: MATLAB version 2019b and the following toolboxes were used for data processing: Deep learning, …

Improving Pain Assessment Using Vital Signs And Pain Medication For Patients With Sickle Cell Disease: Retrospective Study, Swati Padhee, Gary K. Nave Jr, Tanvi Banerjee, Daniel M. Abrams, Nirmish Shah

Computer Science and Engineering Faculty Publications

Background: Sickle cell disease (SCD) is the most common inherited blood disorder affecting millions of people worldwide. Most patients with SCD experience repeated, unpredictable episodes of severe pain. These pain episodes are the leading cause of emergency department visits among patients with SCD and may last for several weeks. Arguably, the most challenging aspect of treating pain episodes in SCD is assessing and interpreting a patient's pain intensity level. Objective: This study aims to learn deep feature representations of subjective pain trajectories using objective physiological signals collected from electronic health records. Methods: This study used electronic health record data collected …

Coevolution Of Machine Learning And Process-Based Modelling To Revolutionize Earth And Environmental Sciences: A Perspective, Mojtaba Sadegh

Civil Engineering Faculty Publications and Presentations

Machine learning (ML) applications in Earth and environmental sciences (EES) have gained incredible momentum in recent years. However, these ML applications have largely evolved in ‘isolation’ from the mechanistic, process-based modelling (PBM) paradigms, which have historically been the cornerstone of scientific discovery and policy support. In this perspective, we assert that the cultural barriers between the ML and PBM communities limit the potential of ML, and even its ‘hybridization’ with PBM, for EES applications. Fundamental, but often ignored, differences between ML and PBM are discussed as well as their strengths and weaknesses in light of three overarching modelling objectives in …

Data-Driven And Multiscale Modeling Of Dna-Templated Dye Aggregates, Austin Biaggne, Lawrence Spear, German Barcenas, Maia Ketteridge, William B. Knowlton, Bernard Yurke, Lan Li

Materials Science and Engineering Faculty Publications and Presentations

Dye aggregates are of interest for excitonic applications, including biomedical imaging, organic photovoltaics, and quantum information systems. Dyes with large transition dipole moments (μ) are necessary to optimize coupling within dye aggregates. Extinction coefficients (ε) can be used to determine the μ of dyes, and so dyes with a large ε (>150,000 M⁻¹) should be engineered or identified. However, dye properties leading to a large ε are not fully understood, and low-throughput methods of dye screening, such as experimental measurements or density functional theory (DFT) calculations, can be time-consuming. In order to screen large datasets of molecules …

Runtime Energy Savings Based On Machine Learning Models For Multicore Applications, Vaibhav Sundriyal, Masha Sosonkina

Electrical & Computer Engineering Faculty Publications

To improve the power consumption of parallel applications at the runtime, modern processors provide frequency scaling and power limiting capabilities. In this work, a runtime strategy is proposed to maximize energy savings under a given performance degradation. Machine learning techniques were utilized to develop performance models which would provide accurate performance prediction with change in operating core-uncore frequency. Experiments, performed on a node (28 cores) of a modern computing platform showed significant energy savings of as much as 26% with performance degradation of as low as 5% under the proposed strategy compared with the execution in the unlimited power case.