Engineering Commons^™

A Real-Time Gaze Estimation Framework For Mobile Devices, Yu Feng, Nathan Goulding-Hotta, Asif Khan, Hans Reyserhove, Yuhao Zhu

Frameless

Tracking eyes becomes an important component to unleash new ways of human-machine interactions in augmented and virtual reality (AR/VR). To make the eye tracking system responsible, eye tracking systems need to operate at a real-time rate (> 30Hz). However, from our experiments, modern gaze tracking algorithms operate at most 5 Hz on mobile processors. In this talk, we present a real-time eye tracking algorithm that operates at 30 Hz on a mobile processor. Our algorithm achieves sub-0.5° gaze accuracy, while requiring only 30K parameters, which is one to two orders of magnitude smaller than state-of-the-art algorithms.

Development Of A Compliant Gripper Driven By 3 Dof Soft Robot, Derek M. Price Ii, Ricardo Ramirez, Pt Angel Tran

Symposium of Student Scholars

Industrial robots are moving toward automation, which makes it increasingly necessary to replace the functions traditionally performed by humans with robotics. Pick and place operation is a prime example of such automation. Robots that pick up and place objects mimic the human action of picking an object up and placing it in a targeted location. It has led to the development of robotic end-effectors that have a human-like feel. Grippers can be articulated in various ways depending on their application area and well-defined desired tasks. As compliant and soft links deflect more under the same load than their rigid body …

Ai Based Optimization Of Odometry Performance On Mobile Robots, Sunny Leveson Jones, Charles Koduru

Symposium of Student Scholars

Robots have become a large part of the modern world and have been used to navigate through complex environments, with various optimal speeds and pathing requirements. To improve this, we have developed an AI-based predictive pathing optimizer that takes in data regarding the requested route and implements optimal speeds. The algorithm will compare time lost to the time gained by moving at a higher velocity. This has been developed by implementing continual circular patterns onto a mobile robot, which allows for rapid analysis of both the accuracy and the speed of the cycle. This optimization is proposed to increase the …

Relativistic Magnetron Powered By Electrons In A High-Energy State, Dmitrii Andreev

Electrical and Computer Engineering ETDs

A traditional relativistic magnetron is an efficient, high-power source of cm-wave radiation. Typically, a cathode sits inside the interaction region and produces a quickly expanding cathode plasma. However, rapid radial expansion leads to unwanted frequency drift and pulse shortening. Recently, researchers at Technion, in collaboration with the University of New Mexico, proposed to use a split cathode to form a low-energy “squeezed” state by injecting electrons externally into a potential well and squeezing them with a sufficiently strong magnetic field. Technion’s long-pulse experiments achieved a low-energy state, at the output power and efficiency comparable to a physical cathode inside the …

A Model-Based Fault Diagnosis In Dynamic Systems Via Asynchronous Motors System Identification Or Testing, And Control Engineering Observers, Kenelt Pierre

USF Tampa Graduate Theses and Dissertations

Induction machines are the workhorse of many military and commercialtypes of equipment. They are asynchronous machines referred to in this dissertation as induction motors. They are widely used due to their reliability in Naval Unmanned Systems like Remotely Operated Vehicles (ROV), Unmanned Untethered Underwater Vehicles (UUV), Autonomous Undersea Vehicles (AUV), and platforms like Missiles and Satellites. These induction motors are mainly controlled using variable speed drive functions, i.e., thrusters, propellers, and actuators. Though they are very robust, to harness the full technical benefits of induction motors, state-of-the-art drivers or controllers must be used to control such motors.

In model-based fault …

Improving The Work Efficiency Of An Air Conditioning System Based On A Chiller, N Usmonov, A Khazratov, J Usmonov

Technical science and innovation

This article deals with evaporative cooling devices used in air conditioning systems. Various ways of lowering the air temperature to the dew point have been identified as a result of improvements to the devices considered. It is also indicated that the circulating water temperature in the system can be lowered to the air temperature on the wet bulb thermometer. As is known, recirculating water is often used as a cooling water in process units to reduce water consumption in industrial plants. Circulating water is heated by recirculation and the heated water is cooled in ventilated cooling towers. This method of …

Preprocessing Of Speech Signals For The System Of Recognition And Spectral Analysis Of Speech, Sherzod Nematov, Y Kamolova

Technical science and innovation

Having a digital representation of a speech signal, we can think about metrics, that is, the parameters of this signal, with the help of which the program can recognize sounds, words and sentences with approximately the same result that a healthy hearing aid and a healthy human brain give.

An Investigation Into Magnetic Gears And Magnetic Springs For Marine Hydrokinetic Power Generators, Hossein Baninajar

Dissertations and Theses

Marine hydrokinetic generators often use mechanical gears to convert the low-speed motion into the high-speed rotary motion that is required for conventional electrical generators. While mechanical gearboxes have a high torque density and can reach high efficiencies, they suffer from serious reliability issues. Recently, magnetic gearing technology has been proposed as a means of making hydrokinetic generators more reliable. As magnetic gears use magnetic field modulation to create speed change, they offer a high reliability, nonfriction, power transmission mechanism that limits the wear to only the bearings and makes the magnetic gears almost maintenance-free. During an over-torque condition, a magnetic …

A Preliminary Comparative Study Of Molecular Visualization Software For Education, Ruoming Shen

Modeling, Simulation and Visualization Student Capstone Conference

Chemistry and biology are sciences vital for understanding metabolic processes, developing disease treatments, and improving environmental conditions. With extensive knowledge of biochemistry, we can take advantage of a material’s unique chemical composition and properties in various applications. Visualization software is essential for analyzing complex chemical and biological structures and predicting their interactions with each other. This paper presents a preliminary study of three open source molecular visualization software tools - Visual Molecular Dynamics (VMD), Jmol, and Mol*, and evaluates their strengths and deficiencies. This paper utilizes the March Molecule of the Month, Vascular Endothelial Growth Factor (VEGF), from the Protein …

Image Processing Algorithms For Detection Of Anomalies In Orthopedic Surgery Implants, Alexander William Wiese

Theses and Dissertations

Orthopedic implant procedures for hip implants are performed on 300,000 patients annually in the United States, with 22.3 million procedures worldwide. While most such operations are successfully performed to relieve pain and restore joint function for the duration of the patient's life, advances in medicine have enabled patients to outlive the life of their implant, increasing the likelihood of implant failure. There is significant advantage to the patient, the surgeon, and the medical community in early detection of implant failures.The research work presented in this thesis demonstrates a non-invasive digital image processing technique for the automated detection of specific arthroplasty …

Dc Microgrid Fault Detection Using Multiresolution Analysis Of Traveling Waves, Rudy Montoya

Mechanical Engineering ETDs

Fast detection and isolation of faults in a DC microgrid is of particular importance. Fast tripping protection (i) increases the lifetime of power electronics (PE) switches by avoiding high fault current magnitudes and (ii) enhances the controllability of PE converters. This thesis proposes a traveling wave (TW) based scheme for fast tripping protection of DC microgrids. The proposed scheme utilizes a discrete wavelet transform (DWT) to calculate the high-frequency components of DC fault currents. Multiresolution analysis (MRA) using DWT is utilized to detect TW components for different frequency ranges. The Parseval energy calculated from the MRA coefficients are then used …

Distributed Control And Learning Of Connected And Autonomous Vehicles Approaching And Departing Signalized Intersections, Joshua Onyeka Ogbebor

LSU Master's Theses

This thesis outlines methods for achieving energy-optimal control policies for autonomous vehicles approaching and departing a signalized traffic intersection. Connected and autonomous vehicle technology has gained wide interest from both research institutions and government agencies because it offers immense promise in advancing efficient energy usage and abating hazards that beset the current transportation system. Energy minimization is itself crucial in reducing the greenhouse emissions from fossil-fuel-powered vehicles and extending the battery life of electric vehicles which are presently the major alternative to fossil-fuel-powered vehicles. Two major forms of fuel minimization are studied. First, the eco-driving problem is solved for a …

Zero-Power Ac Current Sensor, Omar Aragonez

Mechanical Engineering ETDs

In this study, a magnetic piezoelectric cantilever powered AC current and frequency sensor is proposed. This paper covers the configuration of the experimental setup, finite element modeling of the magnetic coupling, and the optimal spatial location of the magnetic proof mass in relation to the wire for smart grid applications. Solid and stranded copper wires of various gauges were used and carried current up to 30A. The magnets act as a proof mass to lower the frequency while also coupling to the magnetic field generated by the current carrying wire. The frequency of the AC current produces a sinusoidal force …

Wave-Optics Investigation Of Branch-Point Density, Jeffrey R. Beck, Jeremy Bos, Terry J. Brennan, Mark F. Spencer

Michigan Tech Publications, Part 1

We use wave-optics simulations to investigate branch-point density (i.e., the number of branch points within the pupil-phase function) in terms of the grid sampling. The goal for these wave-optics simulations is to model plane-wave propagation through homogeneous turbulence, both with and without the effects of a finite inner scale modeled using a Hill spectrum. In practice, the grid sampling provides a gauge for the amount of branch-point resolution within the wave-optics simulations, whereas the Rytov number, Fried coherence diameter, and isoplanatic angle provide parameters to setup and explore the associated deep-turbulence conditions. Via Monte Carlo averaging, the results show that …

Electric Vehicles: Lowering Greenhouse Gas Emissions, Tyler Hansen

Student Research Symposium

The amount of greenhouse gasses in the earth’s atmosphere has led to rapid climate change. In order to remedy this, the amount of annual greenhouse gas emissions needs to be decreased. As of 2019, transportation accounted for 29 percent of the Nation’s total greenhouse gas emissions. Therefore, one important way to decrease greenhouse gas emissions in the U.S will be a switch from traditional vehicles powered by gasoline and diesel, to electric vehicles. Despite challenges of infrastructure, resources, and consumer access, a national switch to electric vehicles is possible and necessary.

Practical Considerations And Applications For Autonomous Robot Swarms, Rory Alan Hector

LSU Doctoral Dissertations

In recent years, the study of autonomous entities such as unmanned vehicles has begun to revolutionize both military and civilian devices. One important research focus of autonomous entities has been coordination problems for autonomous robot swarms. Traditionally, robot models are used for algorithms that account for the minimum specifications needed to operate the swarm. However, these theoretical models also gloss over important practical details. Some of these details, such as time, have been considered before (as epochs of execution). In this dissertation, we examine these details in the context of several problems and introduce new performance measures to capture practical …

Machine Learning Based Medical Image Deepfake Detection: A Comparative Study, Siddharth Solaiyappan, Yuxin Wen

Engineering Faculty Articles and Research

Deep generative networks in recent years have reinforced the need for caution while consuming various modalities of digital information. One avenue of deepfake creation is aligned with injection and removal of tumors from medical scans. Failure to detect medical deepfakes can lead to large setbacks on hospital resources or even loss of life. This paper attempts to address the detection of such attacks with a structured case study. Specifically, we evaluate eight different machine learning algorithms, which include three conventional machine learning methods (Support Vector Machine, Random Forest, Decision Tree) and five deep learning models (DenseNet121, DenseNet201, ResNet50, ResNet101, VGG19) …

A Novel Composite Hybrid Energy Storage System For Hybrid And Electric Vehicles, Marium Rasheed

Student Research Symposium

This work introduces a composite hybrid energy storage system (CHESS) architecture that combines energy-dense and capacitively-coupled power-dense battery packs in a unique configuration that requires minimal energy balancing using low-power DC-DC converters. A power-dense battery is coupled to an energy-dense battery using a relatively small supercapacitor module that naturally distributes the system current between the two packs, requiring no additional contactors or full-power processing DC-DC converters. A design procedure is developed to size the system for plug-in hybrid and battery electric vehicles (PHEVs and BEVs). The procedure results in designs that achieve weight reduction for a PHEV/BEV battery-energy-storage system (ESS) …

Nuclear Fusion: Powering The Future, Maxwel Head

Student Research Symposium

There has always been a concern for power generation for the world. With limited fossil fuels and the inefficiency of our current, renewable, power generation, a solution to our issue has been in the works for many years. Engineers, scientists, and civil workers are hard at work attempting to apply nuclear fusion to create massive amounts of power for the foreseeable future. Research was conducted using internet and library resources to find primary and secondary sources. For this study, interviews and news reports and case studies were reviewed to provide diverse information. To summarize what was found, engineers are hard …

Financial Literacy In America, John Cappelli

Student Research Symposium

After graduation most people do not have enough financial knowledge to be successful. This research project looks at how financial literacy courses impact students of different backgrounds. Research was conducted using online databases to evaluate primary and secondary sources including surveys and Add something specific about the sources you used. From this research I found that US high school graduates are lacking in financial education. In conclusion I think that all US highschools need to include mandatory financial education courses in order to ensure students have at least a basic understanding before having to make major decisions.

Representing And Analyzing The Dynamics Of An Agent-Based Adaptive Social Network Model With Partial Integro-Differential Equations, Hiroki Sayama

Northeast Journal of Complex Systems (NEJCS)

We formulated and analyzed a set of partial integro-differential equations that capture the dynamics of our adaptive network model of social fragmentation involving behavioral diversity of agents. Previous results showed that, if the agents’ cultural tolerance levels were diversified, the social network could remain connected while maintaining cultural diversity. Here we converted the original agent-based model into a continuous equation-based one so we can gain more theoretical insight into the model dynamics. We restricted the node states to 1-D continuous values and assumed the network size was very large. As a result, we represented the whole system as a set …

Paying The Pied Passer: Discussing The Appropriate Contract To Award Nfl Quarterbacks, Alex Gohr

Student Research Symposium

No NFL team has ever won the Super Bowl while simultaneously paying their starting quarterback more than 13% of the maximum budget allowed for player salaries. This paper explores the effects of quarterbacks on an NFL roster and the consequences of the size of their contracts have on the performance of the team as a whole entity. This research was derived from databases of NFL statics and expert opinions on the matter of player contracts. From the research conducted, it is concluded that quarterbacks must voluntarily take less money for the opportunity to continue to compete for championships or, alternatively, …

Intra-Hour Solar Forecasting Using Cloud Dynamics Features Extracted From Ground-Based Infrared Sky Images, Guillermo Terrén-Serrano

Electrical and Computer Engineering ETDs

Due to the increasing use of photovoltaic systems, power grids are vulnerable to the projection of shadows from moving clouds. An intra-hour solar forecast provides power grids with the capability of automatically controlling the dispatch of energy, reducing the additional cost for a guaranteed, reliable supply of energy (i.e., energy storage). This dissertation introduces a novel sky imager consisting of a long-wave radiometric infrared camera and a visible light camera with a fisheye lens. The imager is mounted on a solar tracker to maintain the Sun in the center of the images throughout the day, reducing the scattering effect produced …

Plant Identification In A Combined-Imbalanced Leaf Dataset, Viraj K. Gajjar, Anand K. Nambisan, Kurt Louis Kosbar

Electrical and Computer Engineering Faculty Research & Creative Works

Plant identification has applications in ethnopharmacology and agriculture. Since leaves are one of a distinguishable feature of a plant, they are routinely used for identification. Recent developments in deep learning have made it possible to accurately identify the majority of samples in five publicly available leaf datasets. However, each dataset captures the images in a highly controlled environment. This paper evaluates the performance of EfficientNet and several other convolutional neural network (CNN) architectures when applied to a combination of the LeafSnap, Middle European Woody Plants 2014, Flavia, Swedish, and Folio datasets. To normalize the impact of imbalance resulting from combining …

Novel Platforms For Large-Scale Adherent Culture Of Mammalian Cells, Ashkan Yekrangsafakar

LSU Doctoral Dissertations

With recent advances in biotechnology, there is a strong and urgent need for robust platforms to culture mammalian cells on a large scale to produce biopharmaceuticals. To this end, various bioreactors have been developed over the past decades, but their capacity and efficiency are often limited by insufficient mass transfer rate and excessive shear stress. In this work, multiple novel bioreactors for the large-scale adherent culture of anchorage-dependent cells were developed.

Hollow MicroCarriers (HMC) was developed as an alternative solution for the microcarrier-based culture system in a stirred-tank bioreactor. In the conventional microcarrier technique, cells are exposed to the harmful …

Toward Suicidal Ideation Detection With Lexical Network Features And Machine Learning, Ulya Bayram, William Lee, Daniel Santel, Ali Minai, Peggy Clark, Tracy Glauser, John Pestian

Northeast Journal of Complex Systems (NEJCS)

In this study, we introduce a new network feature for detecting suicidal ideation from clinical texts and conduct various additional experiments to enrich the state of knowledge. We evaluate statistical features with and without stopwords, use lexical networks for feature extraction and classification, and compare the results with standard machine learning methods using a logistic classifier, a neural network, and a deep learning method. We utilize three text collections. The first two contain transcriptions of interviews conducted by experts with suicidal (n=161 patients that experienced severe ideation) and control subjects (n=153). The third collection consists of interviews conducted by experts …

An Analytical Methodology To Security Constraints Management In Power System Operation, Shubo Zhang

ETD Archive

In a deregulated electricity market, Independent System Operators (ISOs) are responsible for dispatching power to the load securely, efficiently, and economically. ISO performs Security Constrained Unit Commitment (SCUC) to guarantee sufficient generation commitment, maximized social welfare and facilitating market-driven economics. A large number of security constraints would render the model impossible to solve under time requirements. Developing a method to identify the minimum set of security constraints without overcommitting is necessary to reduce Mixed Integer Linear Programming (MILP) solution time. To overcome this challenge, we developed a powerful tool called security constraint screening. The proposed approach effectively filters out non-dominating …

Manipulating Image Luminance To Improve Eye Gaze And Verbal Behavior In Autistic Children, Louanne Boyd, Vincent Berardi, Deanna Hughes, Franceli L. Cibrian, Jazette Johnson, Viseth Sean, Eliza Delpizzo-Cheng, Brandon Mackin, Ayra Tusneem, Riya Mody, Sara Jones, Karen Lotich

Engineering Faculty Articles and Research

Autism has been characterized by a tendency to attend to the local visual details over surveying an image to understand the gist–a phenomenon called local interference. This sensory processing trait has been found to negatively impact social communication. Although much work has been conducted to understand these traits, little to no work has been conducted to intervene to provide support for local interference. Additionally, recent understanding of autism now introduces the core role of sensory processing and its impact on social communication. However, no interventions to the end of our knowledge have been explored to leverage this relationship. This work …

Image And Video Segmentation Of Appearance-Volatile Objects, Yongqing Liang

LSU Master's Theses

Segmentation is a process of partitioning a digital image or frame into multiple regions or objects. The goal of segmentation is to identify and locate the objects of interest with their boundaries. Recent segmentation approaches often follow such a pipeline: they first train the model on a collected dataset and then evaluate the trained model on a given image or video. They assume that the appearance of object is consistent in training and testing sets. However, the appearance of object may change in different photography conditions. How to effectively segment the objects with volatile appearance remains under-explored. In this work, …

Lyapunov-Based Economic Model Predictive Control For Detecting And Handling Actuator And Simultaneous Sensor/Actuator Cyberattacks On Process Control Systems, Henrique Oyama, Dominic Messina, Keshav Kasturi Rangan, Helen Durand

Chemical Engineering and Materials Science Faculty Research Publications

The controllers for a cyber-physical system may be impacted by sensor measurement cyberattacks, actuator signal cyberattacks, or both types of attacks. Prior work in our group has developed a theory for handling cyberattacks on process sensors. However, sensor and actuator cyberattacks have a different character from one another. Specifically, sensor measurement attacks prevent proper inputs from being applied to the process by manipulating the measurements that the controller receives, so that the control law plays a role in the impact of a given sensor measurement cyberattack on a process. In contrast, actuator signal attacks prevent proper inputs from being applied …