Engineering Commons^™

Learning From Machines: Insights In Forest Transpiration Using Machine Learning Methods, Morgan Thornwell

Dissertations and Theses

Machine learning has been used as a tool to model transpiration for individual sites, but few models are capable of generalizing to new locations without calibration to site data. Using the global SAPFLUXNET database, 95 tree sap flow data sites were grouped using three clustering strategies: by biome, by tree functional type, and through use of a k-means unsupervised clustering algorithm. Two supervised machine learning algorithms, a random forest algorithm and a neural network algorithm, were used to build machine learning models that predicted transpiration for each cluster. The performance and feature importance in each model were analyzed and compared …

Investigating The Performance Of A Novel Multi-Element Airfoil Concept Using Numerical Analysis, Ahmed Elbaz

Mechanical Engineering

Separation control is one of the trending topics recently for Vertical Axis Wind Turbine (VAWT) applications, flow separation that occur on the suction side of an airfoil is a major limitation for VAWTs starting and power coefficient; passive control of flow separation has been attracting wind energy research community recently. The principle objective of this paper is to investigate the effect of the multi-element airfoil on the aerodynamic characteristics at wide range of angles of attack at a Reynolds number of 140,000. The multi element airfoil modification has been implemented by replacing the baseline airfoil with two airfoil members within …

Control And Planning For Mobile Manipulators Used In Large Scale Manufacturing Processes, Joshua T. Nguyen

LSU Master's Theses

Sanding operations in industry is one of the few manufacturing tasks that has yet to achieve automation. Sanding tasks require skilled operators that have developed a sense of when a work piece is sufficiently sanded. In order to achieve automation in sanding with robotic systems, this developed sense, or intelligence, that human operators have needs to be understood and implemented in order to achieve, at the minimum, the same quality of work. The system will also need to have the equivalent reach of a human operator and not be constrained to a single, small workspace. This thesis developed solutions for …

Interfacial Interactions Of Uranium And Hdpe In Agricultural Soil And Their Bioacummulation In Mentha Arvensis, Casey Miller, Andrew Neidhart, Kendra Hess, Abdul-Mehdi S. Ali, Angelica Benavidez, Michael Spilde, Laura Green, José M. Cerrato, Jorge Gonzalez Estrella, Eliane El Hayek

Civil Engineering ETDs

We investigated the adsorption, precipitation, and phytoavailability of uranium after reactions with soil, high-density polyethylene particles, and Mentha arvensis through the integration of batch experiments, plant exposure, microscopy, and spectroscopy. Soluble U (initially 100 µM) decreased by 98.6% (1.09 µM) at pH 5 and 86.2% (13.81 µM) at pH 7.5 after 0.1 h of reaction with 10 g of soil in solution. Heterogenous U precipitates were observed in weathered HDPE surfaces for experiments without soil at both pH conditions. This suggests the weathering of the microplastic surfaces enhanced the nucleation of the U precipitates. Plants exposed to both U and …

Towards Multiplexed And Multimodal Biosensor Platforms In Real-Time Monitoring Of Metabolic Disorders, Sung Sik Chu, Hung Anh Nguyen, Jimmy Zhang, Shawana Tabassum, Hung Cao

Electrical Engineering Faculty Publications and Presentations

Metabolic syndrome (MS) is a cluster of conditions that increases the probability of heart disease, stroke, and diabetes, and is very common worldwide. While the exact cause of MS has yet to be understood, there is evidence indicating the relationship between MS and the dysregulation of the immune system. The resultant biomarkers that are expressed in the process are gaining relevance in the early detection of related MS. However, sensing only a single analyte has its limitations because one analyte can be involved with various conditions. Thus, for MS, which generally results from the co-existence of multiple complications, a multi-analyte …

Bioremediation Of Petroleum-Based Contaminants By Alkane-Degrading Bacterium Alcanivorax Borkumensis, Amber Julaine Pete

LSU Doctoral Dissertations

The world’s dependence on petroleum hydrocarbons has led to significant environmental implications. For example, oil spills cause lasting environmental damage, and the increase of plastics in the marine environment has been growing, specifically, microplastics that can be difficult to detect due to their small size. Petroleum hydrocarbons occur naturally in nearly all marine environments, which has allowed hundreds of microorganisms to evolve to utilize these hydrocarbons as their primary energy source. These microbes are classified as hydrocarbonoclastic and are utilized to remove spilled oil biodegradation. Over the last ten years, progress has been made in the biodegradation of oil spills …

Pulsatility Is A Predictive Marker Of Improved Cardiac Function In Patients With Liquid Matrix-Treated Left Ventricular Assist Devices, Philemon Mikail, Rinku Skaria, Marvin Slepian, Janny Garcia, Richard Smith, Zain Khalpey

The VAD Journal

Objective: Left ventricular assist devices (LVADs) are utilized as a bridge to transplant or as destination therapy for patients with end-stage heart failure. Although cardiac offloading from these devices rarely leads to complete remodeling and functional recovery, the use of mesenchymal cells to modulate heart failure has been explored in recent years due to its intrinsic regenerative properties. Current methods of evaluating cardiac function have too much variability, difficulty of access, or require too frequent follow up to create universal weaning protocols. We hypothesized that the administration of amniotic allograft liquid matrix (LM) containing amnion-derived mesenchymal stem cells (aMSCs) in …

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 …

Improving The Factual Accuracy Of Abstractive Clinical Text Summarization Using Multi-Objective Optimization, Amanuel Alambo, Tanvi Banerjee, Krishnaprasad Thirunarayan, Mia Cajita

Computer Science and Engineering Faculty Publications

While there has been recent progress in abstractive summarization as applied to different domains including news articles, scientific articles, and blog posts, the application of these techniques to clinical text summarization has been limited. This is primarily due to the lack of large-scale training data and the messy/unstructured nature of clinical notes as opposed to other domains where massive training data come in structured or semi -structured form. Further, one of the least explored and critical components of clinical text summarization is factual accuracy of clinical summaries. This is specifically crucial in the healthcare domain, cardiology in particular, where an …

A Comparative Study On Representativeness And Stochastic Efficacy Of Miniature Tensile Specimen Testing, Sreekar Karnati, Sriram Praneeth Isanaka, Yunlu Zhang, Frank W. Liou, Jason L. Schulthess

Mechanical and Aerospace Engineering Faculty Research & Creative Works

In this article, a miniature dog bone tensile coupon design was tested against the existing ASTM standard specimen design. Specimens were prepared from commercially sourced austenitic stainless steel 304 alloy, and a defect-ridden additively manufactured 304L alloy was studied. By utilizing a tensile specimen design that is 1/230th volume of the smallest ASTM E8-04 (2016), Standard Test Methods for Tension Testing of Metallic Materials, dog bone specimen, coupled to a digital image correlation (DIC) setup, case studies were performed to compare tensile property measurements and strain field evolution. Whereas yield strength measurements were observed to be similar, post-yield, the ultimate …

Application Of Probabilistic Methods To Turbine Engine Disk Life Prediction And Risk Assessment, Paul Copp, Ashley Whitney-Rawls, Jace Carter, Tarun Goswami

Biomedical, Industrial & Human Factors Engineering Faculty Publications

Turbine engine disk life prediction and understanding the associated risk remains a significant challenge for today’s designer. Despite advances made in materials testing and characterization, as well as, the application of damage tolerance and linear elastic fracture mechanics modeling, there remains a void in properly assessing loading, geometry, and material design property variability. Add to this the application of advanced hybrid and composite material systems and the need to accurately deal with material variability is even greater. There still remain incidents of failure of critical components which were not properly accounted for by the existing analytical methods, testing, and inspections …

Demonstrating Configuration Of Software Defined Networking In Real Wireless Testbeds, Saish Urumkar, Gianluca Fontanesi, Avishek Nag, Sachin Sharma

Conference papers

Currently, several wireless testbeds are available to test networking solutions including Fed4Fire testbeds such as w-ilab. t and CityLab in the EU, and POWDER and COSMOS in the US. In this demonstration, we use the w-ilab.t testbed to set up a wireless ad-hoc Software-Defined Network (SDN). OpenFlow is used as an SDN protocol and is deployed using a grid wireless ad-hoc topology in w-ilab.t. In this paper, we demonstrate: (1) the configuration of a wireless ad-hoc network based on w-ilab.t and (2) the automatic deployment of OpenFlow in an ad-hoc wireless network where some wireless nodes are not directly connected …

Experimenting An Edge-Cloud Computing Model On The Gpulab Fed4fire Testbed, Vikas Tomer, Sachin Sharma

Conference papers

There are various open testbeds available for testing algorithms and prototypes, including the Fed4Fire testbeds. This demo paper illustrates how the GPULAB Fed4Fire testbed can be used to test an edge-cloud model that employs an ensemble machine learning algorithm for detecting attacks on the Internet of Things (IoT). We compare experimentation times and other performance metrics of our model based on different characteristics of the testbed, such as GPU model, CPU speed, and memory. Our goal is to demonstrate how an edge-computing model can be run on the GPULab testbed. Results indicate that this use case can be deployed seamlessly …

Predictive Thermal Modeling And Characterization Of Ultrasonic Consolidation Process For Thermoplastic Composites, Madeline Kirby

LSU Master's Theses

Ultrasonic consolidation (USC) of thermoplastic composites (TPCs) is a highly attractive and promising method to manufacture high-performance composites. This work focuses on USC of dry carbon fiber (CF) fabrics with high-temperature polyphenylene sulfide (PPS) films. Experimental trials to assess feasibility of the process are time-consuming. Consequently, a predictive thermal model would facilitate process parameters selection to reduce expensive trial-and-error approaches. This paper presents a 2D finite element model of samples under consolidation, incorporating equations for viscoelastic heating, matrix phase change, and material properties. Theoretical temperature profiles for nodes of interest were compared to the corresponding experimental temperature curves for various …

Surface-Wave Coupling In Double Floquet Sheets Supporting Phased Temporal Wood Anomalies, Ya-Wen Tsai, Yao-Ting Wang, Emanuele Galiffi, Andrea Alù, Ta-Jen Yen

Advanced Science Research Center

We investigate symmetry-selective surface-mode excitation in a general periodically time-modulated double-layer system, where the modulation of the two layers has a constant phase difference. By deriving a semi-analytic transfer matrix formalism of a Drude-dispersive double-layer structure with periodic time-modulation, we calculate the scattering amplitudes and the corresponding transmission coefficient. Our results show that the phase-difference between the modulation of the two sheets plays an essential role in significantly enhancing and selectively exciting either the even or odd surface mode with high efficiency. We verify our calculations with full-wave time-domain simulations, showing that efficient switching between the surface-wave excitation of the …

Influence Of Aluminum Addition On The Laser Powder Bed Fusion Of Copper-Aluminum Mixtures, Nada Kraiem, Loic Constantin, A. Mao, Fei Wang, Bai Cui, Jean-François Silvain, Yongfeng Lu

Department of Electrical and Computer Engineering: Faculty Publications

The high optical reflectivity of copper (Cu) in the near infrared (NIR) domain and its elevated heat dissipation make Cu a challenging metal for laser powder bed fusion (LPBF), even with high energy densities (EDs). In this study, we demonstrated that adding aluminum (Al) powder by as little as 0.75, 1.5, and 3 wt.% substantially enhances Cu processability, leading to denser (up to 98%) and smoother (Ra = 3.3 𝜇m) Cu-Al parts as compared to 95% and 18 𝜇m, respectively, for the parts printed using pure Cu. In addition, this method reduces the ED required by a factor of two …

Enabling Successful Human-Robot Interaction Through Human-Human Co-Manipulation Analysis, Soft Robot Modeling, And Reliable Model Evolutionary Gain-Based Predictive Control (Mega-Pc), Spencer W. Jensen

Theses and Dissertations

Soft robots are inherently safer than traditional robots due to their compliance and high power density ratio resulting in lower accidental impact forces. Thus they are a natural option for human-robot interaction. This thesis specifically looked at human-robot co-manipulation which is defined as a human and a robot working together to move an object too large or awkward to be safely maneuvered by a single agent. To better understand how humans communicate while co-manipulating an object, this work looked at haptic interaction of human-human dyadic co-manipulation trials and studied some of the trends found in that interaction. These trends point …

Simulation And Localization Of Autonomous Underwater Vehicles Leveraging Lie Group Structure, Easton Robert Potokar

Theses and Dissertations

Autonomous underwater vehicles (AUVs) have the potential to dramatically improve safety, quality of life and general scientific knowledge. Our coasts, lakes and rivers are filled with various forms of marine infrastructure including dams, bridges, ship hulls, communication lines, and oil rigs. Each of these structures requires regular inspection, and current methods utilize divers, which is dangerous, expensive, and time consuming. AUVs have the potential to alleviate these difficulties and enable more regular inspection of these structures. Furthermore, there are significant scientific discoveries in the fields of geology, marine biology and medicine that AUV exploration of our oceans will enable. Since …

The Message Design Of Raiders Of The Lost Ark On The Atari 2600 & A Fan’S Map, Quick Start, And Strategy Guide, Miguel Ramlatchan, William I. Ramlatchan

Distance Learning Faculty & Staff Books

The message design and human performance technology in video games, especially early video games have always been fascinating to me. From an instructional design perspective, the capabilities of the technology of the classic game consoles required a careful balance of achievable objectives, cognitive task analysis, guided problem solving, and message design. Raiders on the Atari is an excellent example of this balance. It is an epic adventure game, spanning 13+ distinct areas, with an inventory of items, where those hard to find items had to be used by the player to solve problems during their quest (and who would have …

Anthropogenic Stressors Compound Climate Impacts On Inland Lake Dynamics: The Case Of Hamun Lakes, Arash Modaresi Rad, Jason Kreitler, John T. Abatzoglou, Kendra Fallon, Kevin R. Roche, Mojtaba Sadegh

Civil Engineering Faculty Publications and Presentations

Inland lakes face unprecedented pressures from climatic and anthropogenic stresses, causing their recession and desiccation globally. Climate change is increasingly blamed for such environmental degradation, but in many regions, direct anthropogenic pressures compound, and sometimes supersede, climatic factors. This study examined a human-environmental system – the terminal Hamun Lakes on the Iran-Afghanistan border – that embodies amplified challenges of inland waters. Satellite and climatic data from 1984 to 2019 were fused, which documented that the Hamun Lakes lost 89% of their surface area between 1999 and 2001 (3809 km² versus 410 km²), coincident with a basin-wide, multi-year …

Performance Modeling And Analysis Of A Thermoelectric Building Envelope For Space Heating, Xiaoli Liu, Ming Qu, Kazuaki Yazawa, Jorge Kohanoff, Piotr Chudzinski, Lorenzo Stella, Brian Norton, Niall Holmes Dr., Ruchita Jani, Hongxi Yin

Conference papers

To provide energy-efficient space heating and cooling, a thermoelectric building envelope (TBE) embeds thermoelectric devices in building walls. The thermoelectric device in the building envelope can provide active heating and cooling without requiring refrigerant use and energy transport among subsystems. Thus, the TBE system is energy and environmentally friendly. A few studies experimentally investigated the TBE under limited operating conditions, and only simplified models for the commercial thermoelectric module (TEM) were developed to quantify its performance. A holistic approach to optimum system performance is needed for the optimal system design and operation. The study developed a holistic TBE-building system model …

Mdam-Drnet: Dual Channel Residual Network With Multi-Directional Attention Mechanism In Strawberry Leaf Diseases Detection, Tingjing Liao, Ruoli Yang, Peirui Zhao, Wenhua Zhou, Mingfang He, Liujun Li

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

The growth of strawberry plants is affected by a variety of strawberry leaf diseases. Yet, due to the complexity of these diseases' spots in terms of color and texture, their manual identification requires much time and energy. Developing a more efficient identification method could be imperative for improving the yield and quality of strawberry crops. To that end, here we proposed a detection framework for strawberry leaf diseases based on a dual-channel residual network with a multi-directional attention mechanism (MDAM-DRNet). (1) In order to fully extract the color features from images of diseased strawberry leaves, this paper constructed a color …

Integrated Socio-Environmental Vulnerability Assessment Of Coastal Hazards Using Data-Driven And Multi-Criteria Analysis Approaches, Ahad Hasan Tanim, Erfan Goharian, Hamid Moradkhani

Faculty Publications

Coastal hazard vulnerability assessment has been centered around the multi-variate analysis of geo-physical and hydroclimate data. The representation of coupled socio-environmental factors has often been ignored in vulnerability assessment. This study develops an integrated socio-environmental Coastal Vulnerability Index (CVI), which simultaneously combines information from five vulnerability groups: biophysical, hydroclimate, socio-economic, ecological, and shoreline. Using the Multi-Criteria Decision Making (MCDM) approach, two CVI (CVI-50 and CVI-90) have been developed based on average and extreme conditions of the factors. Each CVI is then compared to a data-driven CVI, which is formed based on Probabilistic Principal Component Analysis (PPCA). Both MCDM and PPCA …

Neural Networks For Interference Mitigation In Satellite Communication Systems, Martha E. Cash

LSU Master's Theses

The objective of this thesis is to utilize the power of machine learning to develop a neural network-aided receiver in a DVBS-2X satellite communication system to improve the downlink transmission quality in the presence of interference. An emphasis is placed on mitigating the effects caused by non-linear distortions, carrier frequency offset, and additive white Gaussian noise. This thesis proposes a feed-forward neural network with two hidden layers to compensate for the distortions in the received signal. The proposed system model uses 16-APSK modulation scheme. The neural network is tested under varying degrees of non-linear distortion, frequency offsets, and varying levels …

Reactions In The Microannulus Of A Wellbore System With Produced Water From The Permian Basin, Ernesto J. Perea

Civil Engineering ETDs

The objective of this study is to determine the effect of the products from steel corrosion and cement dissolution after reaction with produced water (PW) on the permeability of a wellbore microannulus. The wellbore microannulus is the interface between wellbore cement and steel casing and is often identified as a leakage pathway in wellbore systems. The need to better understand the impact of PW on well integrity aids in the assessment of environmental impacts of energy production. Static batch reactors were used to expose a cement – steel microannulus to two PW solutions, a simulated PW, and a field sampled …

Rapid Response Protocol (Rrp) For Monitoring Water Quality Parameters For Wildfire Disturbance, Paige G. Tunby

Civil Engineering ETDs

The increase in wildfire frequency and intensity has been driven by the sensitivity of fire regimes to climate changes and fire suppression. Wildfires impact hydrological and environmental processes and ecosystem service due to the mobilization of wildfire debris by precipitation. Data on post-fire water quality dynamics have been measured in a few study cases from burned watersheds where sensors were deployed to monitor non-fire-related water quality issues. This has led to a dearth of data for understanding the effects of wildfire disturbances on fluvial networks. To close the gap in available water quality data, we have created a rapid response …

Mdam-Drnet: Dual Channel Residual Network With Multi-Directional Attention Mechanism In Strawberry Leaf Diseases Detection, Tingjing Liao, Ruoli Yang, Peirui Zhao, Wenhua Zhou, Mingfang He, Liujun Li

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

The growth of strawberry plants is affected by a variety of strawberry leaf diseases. Yet, due to the complexity of these diseases' spots in terms of color and texture, their manual identification requires much time and energy. Developing a more efficient identification method could be imperative for improving the yield and quality of strawberry crops. To that end, here we proposed a detection framework for strawberry leaf diseases based on a dual-channel residual network with a multi-directional attention mechanism (MDAM-DRNet). (1) In order to fully extract the color features from images of diseased strawberry leaves, this paper constructed a color …

Characterization Of Electrophoretic Deposited Zinc Oxide Nanopartices For The Fabrication Of Next-Generation Nanoscale Electronic Applications, Fawwaz Abduh A. Hazzazi

LSU Doctoral Dissertations

Several reports state that it is crucial to analyze nanoscale semiconductor materials and devices with potential benefits to meet the need for next-generation nanoelectronics, bio, and nanosensors. The progress in the electronics field is as significant now, with modern technology constantly evolving and a greater focus on more efficient robust optoelectronic applications. This dissertation focuses on the study and examination of the practicality of Electrophoretic Deposition (EPD) of zinc oxide (ZnO) nanoparticles (NPs) for use in semiconductor applications.

The feasibility of several synthesized electrolytes, with and without surfactants and APTES surface functionalization, is discussed. The primary objective of this study …

Analysis Of Sequential Adsorption-Oxidation Of Vocs On Atomic Layer-Deposited Ptni/Zro2-Sio2dual-Function Materials, Busuyi O. Adebayo, Han Yu, Ali A. Rownaghi, Xinhua Liang, Fateme Rezaei

Chemical and Biochemical Engineering Faculty Research & Creative Works

To develop efficient dual-function materials (DFMs) for capture and destruction of volatile organic compounds (VOCs), we prepared a series of composite materials comprising PtNi nanoparticles supported on ZrO₂-promoted SiO₂(PtNi/ZrO₂-SiO₂) via atomic layer deposition (ALD) method and investigated them for sequential adsorption and desorption/catalytic oxidation of benzene, as a model VOC compound. ZrO₂was first deposited on a unimodal SiO₂support, followed by deposition of Pt and Ni nanoparticles with varried amount. Dynamic adsorption experiments were conducted using a 500 ppmv-laden feed at 25 °C and 1 atm, followed by in …

Scale Up Of A Novel Method To Maximize Malonyl-Coa In Escherichia Coli, Clifford Harris Leblanc Iv

LSU Master's Theses

The instability of oil’s price along with its limited availability and impact on the environment motivate the search for an alternative feedstock that can sustain the profitability of chemical companies. Industrial biotechnology can promote renewable sources of energy and products by using microorganisms to produce a wide range of chemical compounds. The three-carbon metabolite, malonyl-CoA, can serve as a precursor to a variety of industrial chemicals. The major hurdle with using malonyl-CoA in industry is that its intracellular concentration in Escherichia Coli is very low. Previous attempts to increase the intracellular level of malonyl-CoA have ranged from genetic engineering of …