Engineering Commons^™

“How Is My Child’S Asthma?” Digital Phenotype And Actionable Insights For Pediatric Asthma, Utkarshani Jaimini, Krishnaprasad Thirunarayan, Maninder Kalra, Revathy Venkataramanan, Dipesh Kadariya, Amit Sheth

Publications

Background: In the traditional asthma management protocol, a child meets with a clinician infrequently, once in 3 to 6 months, and is assessed using the Asthma Control Test questionnaire. This information is inadequate for timely determination of asthma control, compliance, precise diagnosis of the cause, and assessing the effectiveness of the treatment plan. The continuous monitoring and improved tracking of the child’s symptoms, activities, sleep, and treatment adherence can allow precise determination of asthma triggers and a reliable assessment of medication compliance and effectiveness. Digital phenotyping refers to moment-by-moment quantification of the individual-level human phenotype in situ using data from …

Transfer Learning With Deep Recurrent Neural Networks For Remaining Useful Life Estimation, Ansi Zhang, Honglei Wang, Shaobo Li, Yuxin Cui, Guanci Yang, Jianjun Hu

Faculty Publications

Prognostics, such as remaining useful life (RUL) prediction, is a crucial task in condition-based maintenance. A major challenge in data-driven prognostics is the difficulty of obtaining a sufficient number of samples of failure progression. However, for traditional machine learning methods and deep neural networks, enough training data is a prerequisite to train good prediction models. In this work, we proposed a transfer learning algorithm based on Bi-directional Long Short-Term Memory (BLSTM) recurrent neural networks for RUL estimation, in which the models can be first trained on different but related datasets and then fine-tuned by the target dataset. Extensive experimental results …

Damage Mechanism Evaluation Of Large-Scale Concrete Structures Affected By Alkali-Silica Reaction Using Pattern Recognition, Vafa Soltangharaei, Rafal Anay, Nolan Wesley Hayes, Lateef Assi, Yann Le Pape, Zhongguo John Ma, Paul Ziehl

Faculty Publications

Alkali-silica reaction has caused damage to concrete structures, endangering structural serviceability and integrity. This is of concern in sensitive structures such as nuclear power plants. In this study, acoustic emission (AE) was employed as a structural health monitoring strategy in large-scale, reinforced concrete specimens affected by alkali-silica reaction with differing boundary conditions resembling the common conditions found in nuclear containments. An agglomerative hierarchical algorithm was utilized to classify the AE data based on energy-frequency based features. The AE signals were transferred into the frequency domain and the energies in several frequency bands were calculated and normalized to the total energy …

In-Situ Electrochemical Analysis Of Microbial Activity, Ariane L. Martin, Pongsarun Satjaritanun, Sirivatch Shimpalee, Blake A. Devivo, John Weidner, Scott Greenway, J. Michael Henson, Charles E. Turick

Faculty Publications

Microbes have a wide range of metabolic capabilities available that makes them industrially useful organisms. Monitoring these metabolic processes is a crucial component in efcient industrial application. Unfortunately, monitoring these metabolic processes can often be invasive and time consuming and expensive, especially within an anaerobic environment. Electrochemical techniques, such as cyclic voltammetry (CV) and electrochemical impedance spectroscopy (EIS) ofer a non-invasive approach to monitor microbial activity and growth. EIS and CV were used to monitor Clostridium phytofermentans, an anaerobic and endospore-forming bacterium. C. phytofermentans ferments a wide range of sugars into hydrogen, acetate, and ethanol as fermentation by-products. For this …

A Bismuth Attack At Grain-Boundaries Of Ceria-Based Electrolytes, Tianrang Yang, Kevin Huang

Faculty Publications

Bismuth is a common additive of commercial silver pastes for enhancing metallization effect; silver paste is also commonly used in high-temperature electrochemical cells as a current collector or contact layer. We here report that the minor amount of bismuth in commercial silver pastes can transport to the interface of electrode/Gd-doped CeO₂ (GDC) electrolyte and seriously corrode grain-boundaries (GBs) of the GDC electrolyte, a commonly used intermediate-temperature electrolyte, causing significant ionic conductivity degradation. A comprehensive electron microscopic analysis reveals that the Bi-corrosion takes place along GBs of GDC electrolyte acting as “washing flux” agent, causing grain separation and thus blocking …

Investigation Of The Mechanical Behavior Of Non-Conventional Laminates: Anisotropy Of Tensile Strength In Coupons With Quasi-Isotropic Stiffness Characteristics, Israel Oluwatunmise Ayodele

Theses and Dissertations

Advanced composites have emerged as viable structural solutions over the years and have therefore become implemented in several applications, notably aerospace structures. In modern aircraft structures, they have been gradually introduced to both secondary and primary components. Laminated composites used in such applications have generally been restricted to those with straight fibers, that are aligned to only a handful of pre-selected fiber orientations; 0˚, 45˚, 90˚ and -45˚. Recent advances in the technology of laminated composites have however indicated the possibility to harness significantly higher structural gains by allowing the use of other fiber orientations, and even implementing curvilinear fibers …

Numerical Modeling Of Submarine Minibasin Flow And Morphodynamics, Elena Bastianon

Theses and Dissertations

Intraslope basins, or minibasins, are important morphological features of the continental slope in both modern and ancient sedimentary systems. Minibasins have an elliptical or spherical shape with a steep inlet or proximal zone followed by an almost horizontal basin floor, and an overflow zone near the downstream basin lip. These basins are filled with sediment transported by successive events of turbidity currents and other types of submarine flows. The work presented here focuses on turbidity current sedimentation in intraslope minibasins, which is often described in terms of the ‘fill-and- spill’ conceptual model. The ‘fill-and-spill’ model has been used previously to …

Exploring Machine Learning Techniques To Improve Peptide Identification, Fawad Kirmani

Theses and Dissertations

The goal of this work is to improve proteotypic peptide prediction with lower pro- cessing time and better efficiency. Proteotypic peptides are the peptides in protein sequence that can be confidently observed by mass-spectrometry based proteomics. One of the widely used method for identifying peptides is tandem mass spectrometry (MS/MS). The peptides that need to be identified are compared with the accurate mass and elution time (AMT) tag database. The AMT tag database helps in reducing the processing time and increases the accuracy of the identified peptides. Prediction of proteotypic peptides has seen a rapid improvement in recent years for …

Personalized Health Knowledge Graph, Amelie Gyrard, Manas Gaur, Saeedeh Shekarpour, Krishnaprasad Thirunarayan, Amit Sheth

Publications

Our current health applications do not adequately take into account contextual and personalized knowledge about patients. In order to design “Personalized Coach for Healthcare” applications to manage chronic diseases, there is a need to create a Personalized Healthcare Knowledge Graph (PHKG) that takes into consideration a patient’s health condition (personalized knowledge) and enriches that with contextualized knowledge from environmental sensors and Web of Data (e.g., symptoms and treatments for diseases). To develop PHKG, aggregating knowledge from various heterogeneous sources such as the Internet of Things (IoT) devices, clinical notes, and Electronic Medical Records (EMRs) is necessary. In this paper, we …

What Do You Have That Others Don't?: Succeeding In Academia Or Industry, Amit Sheth

Publications

No abstract provided.

Characterization Of The Spatial And Temporal Changes In River Geometry And Sand Load With Field Data Analysis And 1d Numerical Modeling, Zeyad Ayoob Sulaiman

Theses and Dissertations

The quantification of the changes in channel geometry and sand load that have occurred on the Missouri River after engineering works and that characterize the Altamaha River in the fluvial-tidal transition zone is the main objective of this research. Dam construction and channelization on the Missouri River resulted in flow regulation, sediment shortage by dam reservoir trapping, channel straightening and narrowing. Quantifying the morphodynamic response of the Lower Missouri River to these engineering projects at short and long-time scales is a difficult problem that we approach with the analysis of the available field data and with the aid of a …

Turning Up Antitumor Immunity Against Breast Cancer, Johnie Hodge

Theses and Dissertations

Breast cancer is the most common cancer in women worldwide, and is the second leading cause of cancer-related death in spite of significant advances in treatment and emphasis on early diagnosis. While treatment of localized disease is often successful, metastatic breast cancer, especially of the triple negative molecular subtype, carries a much poorer prognosis. The significant role of the immune system in the progression from localized to metastatic disease is becoming more and more appreciated. Tumor escape from immune surveillance and immune suppression in the tumor microenvironment have become therapeutic targets in addition to the traditional goals of directly killing …

Experimental Investigation Of Two-Phase (Gas/Liquid) Flow In Intermediate Sized, Horizontal And Inclined Pipes, Noble C. Anumbe

Theses and Dissertations

Multiphase flow models and correlations are indispensable tools for the design and operation of vital flow systems that power various industries. The development, validation and tuning of these flow models & correlations depend on the availability of reliable and accurate data. This dissertation reports on an experimental campaign that not only generated crucial two-phase flow data but also evaluated the effect of inclination angle on several flow parameters of interest. The report details the experimental investigation of upward, adiabatic, co-current two-phase (gas/liquid) flow through a 101.6 mm inner diameter (ID) pipe. Experimental data for the investigation were acquired using an …

Identification Of The Mechanisms Through Which Botanicals Attenuate Pathogenesis Of Human Diseases, Esraah Alharris

Theses and Dissertations

Plant products have been used for a long time in treatment of diseases. In fact, more than half of approved medicines are derived from plants or other natural products. Even though the synthetic drugs are effective in treating many human diseases, there is no cure against several clinical disorders. Moreover, a significant number of diseases can be prevented thereby causing less burden on societal healthcare costs as well as promoting healthy lifestyles. Thus, botanicals offer a unique opportunity to explore novel compounds to prevent and treat various clinical disorders as well as understand their mode of action so that new …

Ku-Band Ag Channel Modeling, Albert Smith

Theses and Dissertations

With the rise in use of Unmanned Aerial Systems (UAS), there is a need for safe and reliable integration into existing infrastructure. A proposed system for beyond line of sight control links for UAS is a Ku-band air-to-satellite communication system. To ensure this proposed system does not interfere with existing terrestrial infrastructure that operates in the Ku band, an examination of the Ku-band air-to-ground channel is required. The focus of this thesis is the modeling of the Ku-band AG channel. Tests consisting of transmitting a single tone continuous wave signal were conducted with a signal generator onboard NASA’s Viking S-3 …

The Restoration Of The Nile River And Its Delta, Egypt. Numerical Modeling, Basim Mohammed Naseef Al-Zaidi

Theses and Dissertations

The construction of the High Aswan Dam significantly reduced the flood flows and the sediment supply to the Egyptian portion of the Nile River. Consequences of this changes in river hydrology are diffuse channel bed erosion in the upstream part of the river, in- channel sedimentation in the downstream part of the system, delta recession, habitat deterioration, wetlands loss, water pollution, and environmental problems. The feasibility of a Nile River-Delta restoration project with controlled flow releases and sediment augmentations at Aswan is here investigated with the aid of site-specific one-dimensional morphodynamic models. The water source for the restoration project, based …

Topological Conduction And Investigation On Multi Occurrence Of Dirac Cone, Mustahseen Mobashwer Indaleeb

Theses and Dissertations

The unique phenomena in acoustic metamaterial at the Dirac-like cone, and at the exceptional spawning ring could transform the field of engineering with multiple new applications that were never possible before. Localized conical dispersion called Dirac cone at the Brillouin Zone boundaries are the well-known phenomena demonstrated by photonics and phononic metamaterials. However, Dirac cone-like dispersion at the center of the Brillouin zone (where wave number, k = 0) [1] is rare and only happens due to accidental degeneracy at finite frequencies in two-dimensional periodic crystals (PCs), with or without microarchitectures. Accidental degeneracies are generally the ‘sweet spots’ where the …

Ultrasonic Analysis And Tools For Quantitative Material State Awarness Of Engineered Materials, Subir Patra

Theses and Dissertations

The objective of this research is to devise new methods and tools to generate real time awareness of the material state of composite and metallic structures through ultrasonic nondestructive evaluation (NDE) and structural health monitoring (SHM) at its very early stage of failure. To device new methodology it is also important to verify the method through virtual experiments and hence computational NDE is getting popular in the recent years. In this thesis, while experimental methodology is developed to understand the material state at its early stage of failure, a new peridynamic based Peri-Elastodynamic (PED) computational method is also developed for …

Three-Way Catalysts In Passive Selective Catalytic Reduction Systems, Calvin Thomas

Theses and Dissertations

Conventional gasoline-powered engines operate with a stoichiometric air-fuel ratio (AFR), but greater fuel economy is achieved in lean burn engines by increasing the AFR. The primary drawback to these engines is the nitrogen oxide (NOX) emissions, which cannot be reduced over a conventional three-way catalyst (TWC). Passive selective catalytic reduction (SCR) is a promising approach for the control of NOX emissions in lean burn systems. By periodically decreasing the AFR to fuel-rich levels, ammonia (NH3) can be produced over a TWC and stored on a downstream SCR catalyst for the reduction of NOX during normal lean operation. While passive SCR …

Using Electronic Health Records To Characterize Prescription Patterns: Focus On Antidepressants In Nonpsychiatric Outpatient Settings, Joseph J. Deferio, Tomer T. Levin, Judith Cukor, Samprit Banerjee, Rozan Abdulrahman, Amit Sheth, Neel Mehta, Jyotishman Pathak

Publications

Objective To characterize nonpsychiatric prescription patterns of antidepressants according to drug labels and evidence assessments (on-label, evidence-based, and off-label) using structured outpatient electronic health record (EHR) data.

Methods A retrospective analysis was conducted using deidentified EHR data from an outpatient practice at a New York City-based academic medical center. Structured “medication–diagnosis” pairs for antidepressants from 35 325 patients between January 2010 and December 2015 were compared to the latest drug product labels and evidence assessments.

Results Of 140 929 antidepressant prescriptions prescribed by primary care providers (PCPs) and nonpsychiatry specialists, 69% were characterized as “on-label/evidence-based uses.” Depression diagnoses were associated …

Domain-Specific Use Cases For Knowledge-Enabled Social Media Analysis, Soon Jye Kho, Swati Padhee, Goonmeet Bajaj, Krishnaprasad Thirunarayan, Amit Sheth

Publications

No abstract provided.

Nonlocal Damage Mechanics For Quantification Of Health For Piezoelectric Sensor, Amit Shelke, Anowarul Habib, Umar Amjad, Ullrich Pietsch, Sourav Banerjee

Faculty Publications

In this paper, a novel method to quantify the incubation of damage on piezoelectric crystal is presented. An intrinsic length scale parameter obtained from nonlocal field theory is used as a novel measure for quantification of damage precursor. Features such as amplitude decay, attenuation, frequency shifts and higher harmonics of guided waves are commonly-used damage features. Quantification of the precursors to damage by considering the mentioned features in a single framework is a difficult proposition. Therefore, a nonlocal field theory is formulated and a nonlocal damage index is proposed. The underlying idea of the paper is that inception of the …

Tourism Review Sentiment Classification Using A Bidirectional Recurrent Neural Network With An Attention Mechanism And Topic-Enriched Word Vectors, Qin Li, Shaobo Li, Jie Hu, Sen Zhang, Jianjun Hu

Faculty Publications

Sentiment analysis of online tourist reviews is playing an increasingly important role in tourism. Accurately capturing the attitudes of tourists regarding different aspects of the scenic sites or the overall polarity of their online reviews is key to tourism analysis and application. However, the performances of current document sentiment analysis methods are not satisfactory as they either neglect the topics of the document or do not consider that not all words contribute equally to the meaning of the text. In this work, we propose a bidirectional gated recurrent unit neural network model (BiGRULA) for sentiment analysis by combining a topic …

End-To-End Convolutional Neural Network Model For Gear Fault Diagnosis Based On Sound Signals, Yong Yao, Honglei Wang, Shaobo Li, Zhongnhao Liu, Gui Gui, Yabo Dan, Jianjun Hu

Faculty Publications

Currently gear fault diagnosis is mainly based on vibration signals with a few studies on acoustic signal analysis. However, vibration signal acquisition is limited by its contact measuring while traditional acoustic-based gear fault diagnosis relies heavily on prior knowledge of signal processing techniques and diagnostic expertise. In this paper, a novel deep learning-based gear fault diagnosis method is proposed based on sound signal analysis. By establishing an end-to-end convolutional neural network (CNN), the time and frequency domain signals can be fed into the model as raw signals without feature engineering. Moreover, multi-channel information from different microphones can also be fused …

Statistically Guided Synthesis Of Mov-Based Mixed-Oxide Catalysts For Ethane Partial Oxidation, Juan D. Jimenez, Kathleen Mingle, Teeraya Bureerug, Cun Wen, Jochen A. Lauterbach

Faculty Publications

The catalytic performance of Mo8V2Nb1-based mixed-oxide catalysts for ethane partial oxidation is highly sensitive to the doping of elements with redox and acid functionality. Specifically, control over product distributions to ethylene and acetic acid can be afforded via the specific pairing of redox elements (Pd, Ni, Ti) and acid elements (K, Cs, Te) and the levels at which these elements are doped. The redox element, acid element, redox/acid ratio, and dopant/host ratio were investigated using a three-level, four-factor factorial screening design to establish relationships between catalyst composition, structure, and product distribution for ethane partial oxidation. Results show that the balance …

Statistically Guided Synthesis Of Mov- Based Mixed Oxide Catalysts For Ethane Partial Oxidation, Juan D. Jimenez, Kathleen Mingle, Teeraya Bureerug, Cun Wen, Jochen Lauterbach

Faculty Publications

The catalytic performance of Mo8V2Nb1-based mixed-oxide catalysts for ethane partial oxidation is highly sensitive to the doping of elements with redox and acid functionality. Specifically, control over product distributions to ethylene and acetic acid can be afforded via the specific pairing of redox elements (Pd, Ni, Ti) and acid elements (K, Cs, Te) and the levels at which these elements are doped. The redox element, acid element, redox/acid ratio, and dopant/host ratio were investigated using a three-level, four-factor factorial screening design to establish relationships between catalyst composition, structure, and product distribution for ethane partial oxidation. Results show that the balance …

Experimental Investigation Of Impact Localization In Composite Plate Using Newly Developed Imaging Method, Mohammad Faisal Haider, Asaad Migot, Md Yeasin Bhuiyan, Victor Giurgiutiu

Faculty Publications

This paper focuses on impact localization of composite structures, which possess more complexity in the guided wave propagation due to the anisotropic behavior of composite materials. In this work, a composite plate was manufactured by using a compression molding process with proper pressure and temperature cycle. Eight layers of woven composite prepreg were used to manufacture the composite plate. A structural health monitoring (SHM) technique was implemented with piezoelectric wafer active sensors (PWAS) to detect and localize the impact on the plate. There were two types of impact event that were considered in this paper (a) low energy impact event …

Product Innovation Design Based On Deep Learning And Kansei Engineering, Huafeng Quan, Shaobo Li, Jianjun Hu

Faculty Publications

Creative product design is becoming critical to the success of many enterprises. However, the conventional product innovation process is hindered by two major challenges: the difficulty to capture users’ preferences and the lack of intuitive approaches to visually inspire the designer, which is especially true in fashion design and form design of many other types of products. In this paper, we propose to combine Kansei engineering and the deep learning for product innovation (KENPI) framework, which can transfer color, pattern, etc. of a style image in real time to a product’s shape automatically. To capture user preferences, we combine Kansei …

Machine Learning For Internet Of Things Data Analysis: A Survey, Mohammad Saeid Mahdavinejad, Mohammadreza Rezvan, Mohammadamin Barekatain, Peyman Adibi, Payam Barnaghi, Amit Sheth

Publications

Rapid developments in hardware, software, and communication technologies have facilitated the emergence of Internet-connected sensory devices that provide observations and data measurements from the physical world. By 2020, it is estimated that the total number of Internet-connected devices being used will be between 25 and 50 billion. As these numbers grow and technologies become more mature, the volume of data being published will increase. The technology of Internet-connected devices, referred to as Internet of Things (IoT), continues to extend the current Internet by providing connectivity and interactions between the physical and cyber worlds. In addition to an increased volume, the …

A Practical Incremental Learning Framework For Sparse Entity Extraction, Hussein Al-Olimat, Steven Gustafson, Jason Mackay, Krishnaprasad Thirunarayan, Amit Sheth

Publications

This work addresses challenges arising from extracting entities from textual data, including the high cost of data annotation, model accuracy, selecting appropriate evaluation criteria, and the overall quality of annotation. We present a framework that integrates Entity Set Expansion (ESE) and Active Learning (AL) to reduce the annotation cost of sparse data and provide an online evaluation method as feedback. This incremental and interactive learning framework allows for rapid annotation and subsequent extraction of sparse data while maintaining high accuracy. We evaluate our framework on three publicly available datasets and show that it drastically reduces the cost of sparse entity …