Stander Symposium: School of Engineering

Follow

• 

  Evaluating the perception of University support for International Graduate Students in Engineering

  Camryn Justice

  Within the School of Engineering, 336 out of 587 graduate and law students are international, making up a significant portion of the student body. Unlike their domestic counterparts, who often transition from the university’s undergraduate programs, these students face unique challenges. While existing support systems, such as the graduate affairs committee, provide some assistance, significant barriers remain. Anecdotal complaints highlight a growing need for stronger support structures. This raises important questions: What strategies can be implemented to better support international graduate students? If resources already exist, what prevents students from utilizing them? By identifying and addressing these barriers, we can contribute to a better understanding of the experience of international graduate students at our university.

• 

  Experience the Thrill of Engineering at the Sumo Bot Showdown!

  Badar Al Mandhari, Michael Berkemeier, Daniel Bridge, Mark Brune, Andrew Burke, Cameron Cope, Tanner Cuttone, Charles Dalton, Jason Fish, Carla Garcia, Matthew Garrelts, Daniel Gubser, Adam Johnson, Thomas Kilbane, Kahra Loding, Adomas Mazeika, Owen Mott, Julian Pabon, Samuel Schiyer, Adin Stoller, Luke Wilson

  Dive into the dynamic world of robotics at our exhilarating Sumo Bot Competition! This spectacular event showcases the talent and creativity of students who have mastered the art of engineering design and automated systems. Watch as these miniature mechanical warriors go head-to-head in a battle of wits, strategy, and power. Designed entirely by students, each sumo bot is a marvel of modern engineering, programmed to outmaneuver and outlast its competitors in the sumo ring. Whether you're a tech enthusiast or new to the world of robotics, this competition promises an entertaining and enlightening experience for all ages. Join us to celebrate the spirit of innovation and cheer on the next generation of engineers as they put their skills to the ultimate test. Don’t miss out on the fun—come and be a part of the action!

• 

  Experimental Investigation of the Second-Mode Boundary-Layer Instability Over a Flat Plate with a Wavy Wall

  Megan Sieve

  This study experimentally investigates the effect of wavy walls on the second-mode boundary-layer instability in the hypersonic regime. The experiments were performed in the Air Force Research Laboratory’s Mach-6 Ludwieg Wind Tunnel on flat-plate test articles. Two different flat-plate test articles were used: a smaller test article used in previous studies and one larger that was constructed for these specific experiments. Findings include the initial test results of the larger test article without a wavy-wall insert and results from three different wavy-wall samples taken using the smaller test article. The initial larger flat plate test results showed that the boundary-layer transition onset behavior varied between the fluctuating surface pressure power spectra measurements and the surface heat-flux measurements. The spectral measurements indicated transition onset upstream of the heat-flux measurements. The wavy-wall test results showed that the wavy-wall inserts shifted the second-mode frequencies lower. Additionally, the higher-amplitude wavy walls provided spectra that indicated a second-mode frequency locking tendency, which was shown to trend well with the freestream unit Reynolds number. Supporting computations indicated good agreement with the frequency-modulating effects of the wavy walls.

• 

  Experimental Validation of Solar Panel Tilt Optimization and Microclimate Variations of Solar Prairies

  Alex Zawacki

  Two projects explore the optimization and ecological impacts of solar energy systems. The first investigates solar panel tilt optimization to enhance energy efficiency, while the second examines microclimatic variations in a solar prairie at the University of Dayton.The solar panel tilt optimization project aims to maximize energy output by identifying the ideal tilt angle based on location, season, and atmospheric conditions. Conducted at Kettering Labs, the study collects empirical data on real-world solar panel performance. Initial data were gathered with panels at a flat orientation (0° tilt) to establish a baseline for comparison. Future testing will analyze energy production across different tilt angles to identify configurations that maximize solar irradiance year-round. Data from theoretical models and real-world measurements will inform recommendations for fixed solar installations in regions with fluctuating sunlight conditions.The second project examines how solar infrastructure influences local ecosystems. Conducted at the University of Dayton’s Curran Place solar prairie, Thermochron iButton temperature loggers recorded hourly temperature variations at three locations: underneath solar panels, in the aisle between rows, and in buffer zones. Results confirm that areas beneath panels experience more extreme temperature fluctuations—higher daytime temperatures and colder nighttime temperatures—compared to other locations. Summer 2023 data showed temperatures underneath panels were 2–5°C higher during the day and 2–3°C colder at night. These fluctuations may impact insect habitats and species survival.Together, these studies provide insights into the intersection of solar technology and environmental sustainability. The tilt optimization project seeks to improve energy production, while the solar prairie project highlights ecological effects. Findings are relevant to both the solar energy industry and conservation efforts, emphasizing the need to integrate environmental considerations into renewable energy system design.

• 

  Flight Test Validation of Tandem Propeller Performance with Vertical Offset

  Michael Foster

  Positioning the aft rotors of a multirotor above the plane of the fore rotors, relative to the freestream, can improve power consumption efficiency in edgewise flight. To validate the results of a previous wind tunnel study at the University of Dayton Low Speed Wind Tunnel (UD-LSWT) with flight tests, a custom-built multirotor was developed. The multirotor accommodated multiple vertical offset configurations of the aft rotors and utilized GPS to sustain altitude and velocity in edgewise flight, thereby ensuring repeatable flight paths. The mass of the multirotor was held constant throughout the tests to isolate the effects of vertical offset on performance. Flight tests were performed for multiple flight speed and vertical offset configurations under calm ambient conditions, as recorded by a custom-built anemometer and wind-direction sensor. Wind tunnel experiments were conducted to further investigate certain trends identified in flight testing and to validate their underlying causes.Flight test data confirmed the findings of the previous wind tunnel data, demonstrating a clear correlation between vertical offset of the rear rotors and improved power consumption efficiency. Specifically, at advance ratios between 0.15 and 0.45, a vertical offset of 20% of the propeller diameter led to more than a 15% reduction in power consumption as compared to a baseline configuration without offset. Additional increases in the vertical offset above 20% of the propeller diameter yielded only minimal further efficiency gains. These findings affirm the practicality of using vertical rotor offset to improve multirotor efficiency while maintaining a compact design.

• 

  Hybrid (Lithium-Aluminum/ Oxygen or Air) Fuel Cell

  Nil Nareshbhai Panchal

  HYBRID AIR FUEL CELLABSTRACTThe work represented in this paper is the extended work of the latest published work on “Oxygen or Air Fuel Cell” (Sarwan S. Sandhu, “A High Temperature Lithium-Aluminum Alloy/Oxygen or Air Fuel Cell.”, RA Journal of Applied Research (ISSN: 2394-6709); DOI: 10.47191/rajar/v11i1.01; Volume: 11 Issue: 01 January-2025.) The hybrid fuel cell sketched above will be explained in the work to be presented. The predicted data for the open-circuit and operational cell voltage; for example, at the cell temperature of 405⁰C and geometric current density of 0.10 amp∙〖cm〗_geom^(-2) are presented. Currently, I am working on defining the elementary reaction steps. In the future, the species transport coupled with the electrochemical kinetics model for the cathode electrode of the fuel cell.

• 

  Impact of Arm Dominance and Practice Type on Movement Task Performance Post Spinal Cord Injury

  Rebekah Revadelo

  Task specific training can be an effective rehabilitation technique for people with spinal cord injuries (SCI) and virtual reality (VR) is a useful tool for presenting movement tasks in a controlled and systematic way. Upper extremity rehabilitation is especially important for people with SCI, which fits with many VR movement tasks. We sought to assess how blocked-task and random-task practice techniques would impact task performance for 7 SCI subjects playing the VR game Beat Saber. Subjects were instructed to cut through blocks in a specified direction in time to the beat of a song. Performance analysis of Cut Offset Error and Cut Angle Error were recorded for the dominant and nondominant side across 4 trials in the order Blocked 1, Random 1, Random 2, Blocked 2. We hypothesized that performance would decrease between baseline and the first random trial but improve between the first and last blocked trials. We expected improvements on both sides, however, changes were driven by the nondominant side, while the dominant side was steady across trials. For Cut Offset Error, the nondominant side improved between the Random 1 and Blocked 2 trials. For Cut Angle Error, the nondominant side improved between the Blocked 1 and Blocked 2 trials. Results suggest that this practice method can help people with SCI to maintain equal bilateral ability, which is important for their mobility and independence.

• 

  Influence of Additives and Impurities on the Dielectric Properties of Jet Fuel

  C James Nesbit

  The dielectric constant of jet fuel is critical in modern aircraft for onboard fuel volume gauging. This project seeks to understand the effects that additives and impurities have on dielectric constant (i.e., relative permittivity) and density of jet fuels across various temperatures and concentrations. These measurements were performed using the newly developed Stanhope-Seta JetDC, an instrument designed to provide dielectric constant data at operating conditions for commercial aircraft fuel gauging systems. The JetDC performed dielectric constant and density measurements from 0 to 30 degrees Celsius. A derived quantity, known as the gauging slope, which is often referred to as a Clausius-Mossotti slope, was then calculated from these measurements. The gauging slope is used by the aircraft industry to determine fuel mass in onboard tanks. Since aircraft use pitch and yaw as flight controls, conventional fuel floats are ineffective for fuel gauging. Gauging slope calculations were performed for three common fuel additives at various concentrations in a representative Jet A fuel. The fuel additives studied were fuel system icing inhibitor (FSII), corrosion inhibitor/lubricity improver (CI/LI), and static dissipater additive (SDA). It was found that FSII had an effect on the dielectric constant, and thus the gauging slope. No statistically significant effects were observed for CI/LI and SDA additives over the range of concentrations tested.

• 

  Integration of 2D materials with silicon photonics

  Ifeanyi Njoku

  This project aims to develop and fabricate a non-volatile memory (NVM) device based on 2D ferroelectric material integrated with silicon photonics. Here, we integrate the 2D ferroelectric material copper indium phosphorus sulfide (CuInP2S6, CIPS) on a photonic microring resonator (MRR) device for high-speed optical computing applications. Ring resonators are used for their advantage of better tunability and easier design. MRRs are vital in silicon photonic integrated circuits (PICs) because they allow precise control of light's amplitude and phase by leveraging resonance by altering the refractive index of the MRR material, which shifts its resonance wavelength, enabling functions like modulation and switching. However, this shift is temporary, as the refractive index returns to its original state once the applied voltage is removed. A ferroelectric material is required to make this change persistent (i.e., to store data), as it can retain the refractive index shift even in the absence of voltage, enabling non-volatile data storage in photonic systems. This is because ferroelectrics exhibit stable, reversible spontaneous polarization switchable by an external electric field. While CIPS has been studied in the literature as a 2D ferroelectric material for various electronic applications, its integration with silicon PICs for memory applications remains unexplored. This project addresses this gap by developing a novel high-speed ferroelectric NVM device integrating CIPS on MRRs.

• 

  Investigating conductive inks in hybrid electronics at flex-to-stretch interfaces

  Josafat Jimenez

  Electrical traces made from conductive liquid-metal inks and silver flake composite inks are fabricated on stretchable substrates. Uniaxial strain is applied to the samples to test resistance response of 2 mm-wide traces for both inks to investigate electrical loss and failure modes under high strains, up to and beyond 200 %.

• 

  Laser powder Bed Fusion process modelling using ANSYS Fluent

  Rahul Rathun

  Metal Laser Powder Bed Fusion (PBF-LB/M) is a complex phenomenon that involves heat transfer, mass transfer, phase change, fluid flow, and other physics fields. In this research we are using ANSYS Fluent as thermal CFD software to setup and solve multiple physical field equations to model the process of PBF-LB/M. This developed computational model and analyze variations in input process parameters such as laser power, scan speed, beam diameter, and non material behavior. Considering all these input process parameter variations, it is possible to predict the melt pool dimensions, temperature distribution, liquid-gas interface with greater accuracy. In this research, we considered Inconel-718, to predict the melt pool morphology for varying process conditions. The predicted dimensions of the melt pool will be validated against well known NIST experimental dataset. Therefore, the developed fluent thermal-CFD will be presented as a high fidelity computational model to predict the process and structure of PBF-LB/M manufacturing systems.

• 

  Localization of Melt Pond Regions in the Arctic Using Transformer Models

  Aqsa Sultana

  Recent breakthroughs in Natural Language Processing (NLP) have inspired the use of transformers in computer vision, where they have shown significant promise in tasks like image classification. This study focuses on applying transformers for pixel-wise classification in images. By using pure transformers as encoders, images are divided into patches, and these patches are embedded into tokens, which are fed as input to a Vision Transformer. The self-attention mechanism within transformers allows the model to focus on important patches relative to their neighbors, enabling it to capture long-range dependencies and contextual relationships across the image.However, challenges arise when dealing with the complexity of image datasets, scalability of models, and limitations in capturing long-range contextual information. To address these issues, we turn to the Swin Transformer. The Swin Transformer processes images hierarchically, building feature maps progressively by merging image features at deeper layers. Initially, image patches are grouped into regular windows, which are processed separately using self-attention. In the following layers, the window partitioning is shifted, enabling the model to perform self-attention across the boundaries of these windows, thereby enhancing its ability to capture finer details and long-range dependencies.We evaluate the performance of Swin Transformers on Arctic melt pond data, using high-resolution datasets from the Healy-Oden Trans Arctic Expedition (HOTRAX) and NASA’s Operation IceBridge. Our results demonstrate the effectiveness of the Swin Transformer in localizing melt ponds and achieving precise segmentation in complex Arctic imagery.

• 

  Mechanical Design of an Aircraft with a Bio-Inspired Rotating Empennage

  Benjamin Schaiper

  An aircraft without a vertical stabilizer and using a novel rotating empennage is currently under study at the Air Force Research Lab. The project aims to produce a highly maneuverable tailless fighter aircraft that is inspired by the flight of hunting birds. Flying creatures do not have a vertical stabilizer and exhibit remarkable maneuverability by rotating their tail feathers for lateral stability and pitch control. In the tailless bio-inspired aircraft, lateral control is gained by providing the empennage with an additional degree of freedom. The bio-inspired rotating empennage (BIRE) concept aircraft has the capability to rotate the empennage about the roll axis, in addition to tilting each horizontal stabilizer about the pitch axis. The selected platform for the BIRE project is a single-engine, supersonic, tactical aircraft, based on the F-16 Fighting Falcon. The design of the mechanical drive and structural components is ongoing. This poster will illustrate the concept and current state of development.

• 

  Nonlinear Dynamics of Soft Electro-Active Materials Under AC Voltages

  Nathan Benham

  Dielectric elastomers are a compelling class of electro-active materials that show great promise for large-deformation actuation, sensing, and energy-generation applications. In a recent series of papers, the faculty mentor and coworkers developed analytical models to explore the quasi-static and dynamic response of circular dielectric elastomer membranes to DC (constant) and AC (time-varying) voltages, respectively. These models led to the uncovering of rich and atypical nonlinear dynamic behavior not previously reported in the literature. However, these novel findings have yet to be experimentally verified. Thus, the goal of this Honors Thesis is to (a) develop an experimental setup for electro-mechanically testing circular dielectric elastomer membranes under AC and DC voltages, and (b) deploy it to investigate three key questions: (1) How significant is the influence of constitutive model calibration on the predicted quasi-static (DC) voltage-stretch response? (2a) Can AC voltage pulses be leveraged to achieve large stable stretches without dielectric breakdown? (2b) Can proportional-integral-derivative (PID) control be leveraged to tune AC voltage waveforms to achieve moderate-to-large unstable stretches without dielectric breakdown? The results of this research are expected to advance the understanding of the nonlinear dynamics of soft electroactive materials. If successful, this research could impact the design of actuators, sensors, and isolators used in robotics, measurements, and vibration control.

• 

  Novel High-Speed Mechanical Press Designs Optimized for Improved Ram Dwell Limited by Joint Force Considerations

  Tianze Xu

  A mechanical press shapes parts by driving a ram into metal to deform it into a desired form. Because this process is widely used—from forming pop cans to shaping car fenders—mechanical presses play a crucial role in global manufacturing. The objective of this research is to develop alternative drivetrain designs for mechanical presses that generate specialized ram motions while meeting industry demands for optimal joint forces. By focusing on mechanical presses, this study leverages their advantages over other forming methods, including higher speeds, lower costs, enhanced accuracy, greater precision, and improved energy efficiency. Even small improvements can significantly reduce processing time and energy consumption. The research evaluates five drivetrain designs under realistic industrial conditions to enhance the dwell phase and achieve the required joint forces. Two of these designs are currently prevalent in industry, while the remaining three offer potential advancements.

• 

  Observations of Memristive Behavior for Ba0.6Sr0.4TiO3 and Ba0.7Sr0.3TiO3 Through Current Voltage Curve Analysis

  Tristan Quach

  As indicated by the consistent validation of Moore’s Law, decreasing the size of electronics has been a perpetual goal for decades. Memristors have a unique way of decreasing the size of devices by performing the functions of what would normally need a group of devices. This is done by making use of the multiple states of a memristor. Additional useful qualities of memristors include in-memory computing, low power consumption, and nonvolatile memory. There are many possible dielectrics that can be used for memristive devices, but barium-based dielectrics show promise. Sixty-forty and seventy-thirty compositions of barium strontium titanate (BST) are dielectrics of interest. Analysis of the current-voltage curve is made from voltage sweeps to observe memristive behavior of these dielectric materials. The sixty-forty composition of BST largely does not show memristive behavior. The same voltage values throughout the voltage sweep do not significantly alter the current value, indicating that the devices are not switching between the high and low resistance states. The seventy-thirty composition of BST largely shows memristive behavior on only the positive side of the voltage sweep, clearly switching from high resistance state to low resistance state. However, the seventy-thirty composition shows similar behavior to the sixty-forty composition on the negative side of the voltage sweep.

• 

  Pathways to a Greener Cement Industry in Nepal: Forecasting Energy and CO₂ for 2030 SDG Compliance

  Sobit Sapkota

  Nepal's cement industry, a major contributor to the nation's economic growth, faces pressingchallenges in aligning its expansion with climate and energy sustainability goals. This studyemploys the Markov Chain Grey Model (MCGM) integrated with scenario analysis to forecastthe industry's energy consumption and CO2 emissions through 2030. Findings reveal that under abusiness-as-usual scenario, energy use is set to surge by 107%, with CO2 emissions rising by220%—an alarming 63% above the target for the 2030 Sustainable Development Goals (SDGs).However, in an optimized scenario incorporating energy efficiency improvements and low-carbon technologies, energy demand could be limited to a 26% increase, with CO2 emissionsmeeting the SDG threshold. The results highlight the critical need for strategic policy support,advanced technologies, and sector-wide commitment to achieve climate targets and manageenergy demand effectively. By enhancing the forecasting precision of the MCGM, this studyprovides actionable insights for climate policy and sustainable energy strategies, offering apathway for Nepal's cement industry to contribute meaningfully to national and global climateobjectives.

• 

  Phase-Change-Material Trimmed, Fixed-Wavelength Slow Wave Loop-Terminated Mach-Zehnder Interferometer Sensors for Low-Cost Chem-Bio Sensing Applications

  Jianhao Shen

  We experimentally demonstrated a compact slow wave enhanced loop-terminated Mach-Zehnder interferometer (LT-MZI) sensor with phase sensitivity of 277,750 rad/RIU-cm. The sensor employs phase change materials (PCMs) to actively trim interferometer fringes post-fabrication, enabling alignment with fixed-wavelength sources for low-cost on-chip chem-bio sensing. Traditional chip-integrated sensors face challenges due to fabrication-induced wavelength mismatches and dependance on external tunable lasers or alignment-sensitive coupling. Here, antimony selenide (Sb2Se3) PCMs integrated on the LT-MZI reference arm enable non-volatile phase tuning via amorphous-to-crystalline transitions, eliminating the need for energy-intensive, continuously powered thermal tuning elements. The LT-MZI leverages slow light propagation in a 2-dimensional photonic crystal waveguide (2D PCW) structure to amplify phase shifts, achieving enhanced sensitivity. A 2×2 multimode interference (MMI) splitter divides light into reference and sensing arms, which recombine at a second MMI connected to a loop mirror. The LT-MZI’s loop mirror doubles the effective interaction length, further increasing sensitivity compared to standard MZIs. 3D-FDTD simulations confirmed spectral fringe trimming via PCM phase transitions, allowing alignment to fixed-wavelength lasers. This platform addresses fabrication tolerances and enables multiplexed, low-cost sensors. Ongoing work focuses on continuous PCM phase control for precise fringe stabilization. The approach is scalable to diverse interferometric and resonator-based sensors, promising compact, high-sensitivity systems for real-world chem-bio applications.

• 

  Portable Power Charger Design with Solar Panels

  Lucas Terry

  When camping, access to electricity is often unreliable. The aim of this project is to design and prototype a solar panel battery charging system for small electronics in remote locations. The system requirements are to have two stable DC voltage outputs (5 V and 13.8 V), be able to withstand continual use, and have a small footprint. The design techniques are formed by power electronic principles and implemented to create two isolated circuits for converting and stabilizing the current generated by the solar panels. The device prototype is tested to verify it functions as intended. The final deliverables of this project are a functional device, test data in various weather conditions, and a live demonstration of the device granted the goals of the project are successfully achieved.

• 

  Precision in Focus: Demonstrating the Capabilities and Accuracy of Camera Arrays

  Qingyu Ren

  This poster presents a novel camera array system that achieves sub-millimeter accuracy (<1mm) through absolute synchronization across all imaging sensors. The system is primarily designed for capturing moving objects, its robust feature extraction algorithms allow it to reliably process and work with blurred inputs when they occur. With a lightweight architecture that facilitates seamless integration with drone platforms, the system offers versatile applicability across diverse domains including aerial surveying, surveillance, and industrial inspection. Experimental evaluations confirm that even under conditions that introduce image blur, the system maintains high precision and performance.

• 

  Preparation, Cure, Characterization, and Mechanical Properties of Reactive Flame-Retardant Cyanate Ester/Epoxy Resin Blends and Their Carbon Fiber Reinforced Composites

  Mustafa Mukhtar

  Cyanate esters are used in aerospace and microelectronics because of their excellent thermal stability, superior mechanical characteristics, and favorable dielectric properties. Cyanate ester resins are typically mixed with lower-cost epoxy monomers to adjust cost, toughness, and processing capabilities. Despite the high performance of these thermosetting polymers, flame retardancy remains a challenge. This study explores blends of thermosetting cyanate ester and epoxy resin (EP/CE) enhanced with a reactive phosphorus-based flame retardant, poly(m-phenylene methylphosphonate) (PMP). Two different CE monomers were investigated (LVT and LECy). This innovative combination, previously unexplored, is designed to deliver improved flame resistance while retaining some advantages of both cyanate ester and epoxy resins. The two CE monomers were blended with the same epoxy monomer (DGEBA) in a 1:1 ratio. The effect of phosphorus concentration was analyzed using thermogravimetric analysis (TGA) and microscale combustion calorimetry (MCC). Carbon fiber composites with a Vf of approximately 0.5 were successfully fabricated. Dynamical Mechanical Analysis (DMA) of the composite laminates showed that PMP reduced the average Tg by up to 39°C at 3 wt% phosphorus. The flammability of the laminates was assessed with cone calorimetry, which confirmed a reduction in peak HRR by approximately 27%. The mechanical properties were assessed through three-point flexure testing. PMP integration only marginally affected flexural strength (6–15%) and modulus (7–13%).

• 

  Quantifying Droplet Breakup Regimes in High-Speed Flow Fields with Diffuse Background Illumination

  Joseph Kastner

  Understanding the dynamics of droplet breakup in high-speed flow fields is critical for many aerospace applications such as liquid fuel injection into high-speed crossflow or weather encounters with high-speed vehicles. In such applications, thermophysical properties such as surface tension, viscosity, etc. as well flow parameters (Mach number) will drive the droplet breakup regime. The objective of this work is to implement diffuse background illumination (DBI) to quantify sessile droplet breakup. A shock tube will be employed to simulate high-speed flow conditions by generating shock waves of various strengths. Both head on and side imaging will be implemented to provide further insight to the breakup dynamics. Weber number will be used to identify breakup regimes. Center of mass calculations will be performed using the high-speed imaging data.

• 

  Quantitative Analytical Methods for Real Time Lie Detection Using Eye Gaze and Biometric Sensors

  Sean Davy, Nathaniel Doll, Lexie Kemble, Meredith Tropeano, Audrey Zelczak

  This poster provides a summary of an IRB approved research study on the optical response of the human eye using a GazePoint eye tracking system and biometrics hardware. Pupil dilation, gaze position, blink rate, and reaction time were recorded for human subjects in response to various visual and auditory stimuli on a computer screen. In addition, EEG, heart rate, blood pressure, and galvanic skin response were recorded using a suite of simultaneous biosensors. The experimental tasks were designed with varying levels of complexity and included both memory-recall and computational tasks for truth and deception scenarios. The overall aim of this study was to identify establish baseline physiological data sets across multiple demographics, which can be used in the future to advance forensic diagnostic methodologies using quantitative analysis and machine learning for various types of neuroscience applications, including lie detection.

• 

  Sea Ice Data Generation Using Diffusion Models

  Aqsa Sultana

  The increasing frequency of extreme weather events due to global warming poses significant threats to ecosystems and human life. One of the primary indicators of climate change in the Arctic is the formation of melt ponds on sea ice. However, the lack of large-scale, annotated Arctic sea ice datasets presents a major challenge in training deep learning models for predicting the dynamics of these melt ponds. In this study, we propose the use of diffusion models, a class of generative models, to synthesize Arctic sea ice data for the analysis of melt pond formation.Diffusion models generate realistic new data by learning the distribution of existing data and iteratively transforming a simple distribution into a more complex one through a noise-adding process. During training, noise (such as Gaussian noise) is added to the data, and the model learns how to reverse this process. After training, the model can generate new, realistic data by starting from random noise and gradually transforming it to match the distribution of the original data. During inference, the model uses conditioning information alongside the noise input to guide the generation of samples that adhere to specified conditions.For training the model, we used high-resolution aerial imagery from the Arctic region, collected during the Healy-Oden Trans Arctic Expedition (HOTRAX) in 2005, and NASA’s Operation IceBridge DMS L1B Geolocated and Orthorectified data from 2016. To evaluate the quality of the synthetic images, we employ the Chromatic Similarity Index (CSI), a metric for assessing chromatic similarity between the original and generated images. This approach demonstrates the potential of diffusion models for generating synthetic Arctic sea ice data to further understand melt pond dynamics.

• 

  Self-Supervised Contrastive Learning for BCI system

  Abdulbasit Alhinqari

  As the demand for various AI applications continues to grow in importance for futuristic aspects of life, non-invasive Brain-Computer Interfaces (BCIs) are expected to become one of the top priorities. BCIs enable humans to control surrounding equipment and devices through a direct communication link from the brain. These systems often rely on the classification of Electroencephalogram (EEG) signals, which are recordings of human brain activity. Given this potential, an increasing number of researchers and scientists are focusing on this field.Traditionally, various algorithms have relied on manual feature extraction to classify EEG datasets. However, recent advancements in Convolutional Neural Networks (CNNs) and deep learning architectures have demonstrated significant success in tasks such as computer vision, natural language processing, and contextual analysis, largely due to their ability to perform automatic feature extraction. Despite their success in other domains, these methods still struggle to generalize effectively on EEG signals due to their non-stationary and random nature.This work focuses on EEG-based BCI systems that leverage CNNs and deep learning tools. Specifically, it explores the application of self-supervised contrastive learning techniques for the classification of motor imagery (MI) actions.