Engineering Commons^™

Analog Implementation Of The Hodgkin-Huxley Model Neuron, Zachary D. Mobille, George H. Rutherford, Jordan Brandt-Trainer, Rosangela Follmann, Epaminondas Rosa

Annual Symposium on Biomathematics and Ecology Education and Research

No abstract provided.

Nonlinear Observer For Visual-Inertial Navigation Using Intermittent Landmark Measurements, Miaomiao Wang

Western Research Forum

The development of reliable orientation, position and linear velocity estimation algorithms for the 3D visual-inertial navigation system (VINS) is instrumental in many applications, such as autonomous underwater vehicles (AUVs), and unmanned aerial vehicles (UAVs). It is extremely important when the global position system (GPS) is not available in GPS-denied environments. Recently, observers design for VINS using landmark position measurements from Kinect sensors or stereo cameras has been increasingly investigated in the literature.

The aim of this work is to design a nonlinear observer for VINS under the assumption that landmark position measurements are intermittent. In practice, the landmark measurements are …

Virtual Eye: A Spatial-Temporal Bottom-Up Eye Sensitivity Model, Todd Goodall

MODVIS Workshop

Video quality and compression models use the

spatial contrast sensitivity function (CSF), which is solved

based on a linear system approximation. This function measures

the eye’s sensitivity to sinusoid gratings, ignoring the subtle

connectivity and inhomogeniety of cell density across the

visual field. Non-linear aspects of the eye, such as the change

in frequency sensitivity with changing illumination, are not

captured by this simple approximation. We propose Virtual

Eye, a bottom-up approach that models the spatio-temporal

dynamics of the eye across the visual field. Each functional

retinal cell layer in the eye is modeled using non-uniform spatial

cell responses, which …

The Challenge For Vision Of Fluctuating Real-World Illumination, David H. Foster

MODVIS Workshop

No abstract provided.

An Assessment Of The Decision Making Units’ Efficiency In Service Systems (The Case Of Cellular Telecom), Maoloud Dabab, Timothy R. Anderson

Student Research Symposium

Most tools and models on performance and quality of service management are generic and do not solve the complex technical systems, which the most critical component on the network and where these tools should be applied. The objective of this research is to assess the cellular performance and Base Transceiver Station (BTS) efficiency by proposing a robust model that is derived from multiple Key Performance Indicators (KPIs) based on technical and financial aspects. The novelty of this research provides a comprehensive multidimensional model for tuning the BTS parameters, which can lead to developing a standard global mobile network KPI. The …

Reliable Explanations Via Adversarial Examples On Robust Networks, Walt Woods, Jack H. Chen, Christof Teuscher

Student Research Symposium

Neural Networks (NNs) are increasingly used as the basis of advanced machine learning techniques in sensitive fields such as autonomous vehicles and medical imaging. However, NNs have been found vulnerable to a class of imperceptible attacks, called adversarial examples, which arbitrarily alter the output of the network. To close the schism between needing reliability in real-world applications and the fragility of NNs, we propose a new method for stabilizing networks, and show that as an added bonus, our technique results in reliable, high-fidelity explanations for the NN's decision. Compared to the state-of-the-art, this technique increased the area under the curve …

Explanation Methods For Neural Networks, Jack H. Chen, Christof Teuscher

Student Research Symposium

Neural Networks (NNs) have become a basis of almost all state-of-the-art machine learning algorithms and classifiers. While NNs have been shown to generalize well to real-world examples, researchers have struggled to show why they work on an intuitive level. We designed several methods to explain the decisions of two state-of-the-art NN classifiers, ResNet and an All-CNN, in the context of the Japanese Society of Radiological Technology (JSRT) lung nodule dataset and the CIFAR-10 image dataset. Leading explanation methods LIME and Grad-CAM generate variations of heat maps which represent the regions of the input determined salient by the NN. We analyze …

An Unsupervised Channel Selection Method For Ssvep-Based Brain Computer Interfaces, Ethan Webster, Hadi Habibzadeh, Tolga Soyata

CURCE Annual Undergraduate Conference

Brain-computer interfaces (BCIs) provide an alternative communication channel for people with motor deficits that prevent normal communication. The underlying premise of a BCI is that a neuroimaging process such as electroencephalography (EEG) can be used to measure the user’s brain activity as signals. The obtained signals are analyzed to determine the user’s intended actions and a computer system can be used to replace voluntary muscle activity as a means of communication. The information transfer rate (ITR) of an algorithm used for determining the user’s intentions greatly affects the perceived practicality of the BCI system. Such algorithms are divided into two …

Mechanical Systems That Function Like Living Organisms, Dallas Rice

Kansas State University Undergraduate Research Conference

The purpose of this research was to explore the relationship between the human body and technologically advanced mechanical systems or robotics. More specifically, we looked at how robotics plays a part in prosthetics for other living organisms. During the research we looked at the anatomy of the human body, focusing on the nervous system, bone structure and movements, tissue and muscle relationships, and the neurological response of the brain. We also looked at how the human body reacts and responds to artificial limbs as a way to identify the best ways to introduce unnatural mechanical systems to the body. Different …

Dqn: Deep Q-Learning For Autonomous Navigation, Leonardo Garrido Alvarez

Kansas State University Undergraduate Research Conference

This project deals with autonomous mobile robots trained using reinforcement learning, a branch of machine learning (the science of improving problem-solving performance based on experience) based on choosing actions to maximize rewards from various environments. This is a form of behavioral learning that is observed in nature and thus more biologically plausible than cognitive models based on labeled data provided by a teacher (supervised learning). We developed an experimental test bed by implementing Deep Q-Networks (DQN), a form of reinforcement learning, for goal-oriented navigation and obstacle avoidance tasks using a TurtleBot3 Burger robot and in the gazebo simulation environment for …

Low Cost Vehicular Autonomy Using Radar And Gps, Nathan Jessurun, Ryan Gordon, Danielle Fredette

The Research and Scholarship Symposium (2013-2019)

This presentation describes a subset of the systems devised for this year's autonomous golf cart senior design project. Our goal is to explore the possibilities of low cost autonomy using only radar and GPS for environmental sensing and navigation. Although autonomous and semi-autonomous ground vehicles are a relatively new reality, prototypes have been a subject of engineering research for decades, often utilizing an array of sensors and sensor fusion techniques. State of the art autonomous ground vehicle prototypes typically use a combination of LIDAR and other distance sensors (such as radar or sonar) as well as cameras and GPS, sometimes …

(Poster) Combining Design And Entrepreneurial Mindset Development: Improved Multifunctional Charging Station, Allison Zwickl, Payton Staman, Evan Parduhn, Jake Smith, David Olawale, Stephen Spicklemire, Rashedul Sarker

ASEE IL-IN Section Conference

It has become imperative to find ways to organize different devices of varying functions and sizes. This problem was introduced to us through customers who believed the current designs on the market could use improvement, or through the lack of organization that they have when charging multiple devices. A solution is a modular concept with a base station that will include a wireless pad and a few charging cords. Additionally customers can purchase specialized add ons that fit into the base station. The housing station will seamlessly charge a plethora of devices including; smart-phones, smart-watches, and speakers in a centralized …

(Poster) Internal Restoration And Modernization Of A 1948 Wwii Era Jukebox, Miles Furr, Cristiana Olarinre, Joel Carpenter, Elijah Knox, George Ricco, Paul Talaga, Suranga Dharmarathne

ASEE IL-IN Section Conference

Using Six Sigma guidelines under the sponsorship of The University of Indianapolis in cooperation with the client, Brugh Industrial Engineering, this project is to modernize the functionality and interface of a Rockola Model 1428 Jukebox while maintaining its vintage appeal. The process of modernization includes meeting today's industrial safety standards, incorporating ethernet protocol, and utilizing a programmable logic controller, PLC. The jukebox is a showcase of current automation technology. Lighting has been upgraded from fluorescent and incandescent bulbs to addressable nano pixel LEDs. The amplifier, coin system, and record selection system were revitalized to OEM operation standards. All switches within …

Development Of A Set Of Pre-Class Videos For Electromagnetic Theory, Benjamin Mcpheron, Josiah D. Kunz

ASEE IL-IN Section Conference

One important aspect of experiential learning is allowing students time to reflect on new concepts before the application of the material. Most commonly, this is attempted by assigning readings from a textbook, but research suggests that few students complete these readings. This discouraging fact has prompted the use of other resources, such as videos, to supplement pre-class readings in order to introduce new material. Previous work has been completed by this author to produce pre-class videos for use in an introductory circuits course. This paper extends that work to the development of pre-class videos for a senior level electrical engineering …

Interactive Simulations In Signals And Systems, Anthony Richardson

ASEE IL-IN Section Conference

Several interactive simulations that promote a better understanding of concepts traditionally encountered in an undergraduate Signals and Systems course are described. The simulations were developed to support the text “Signals & Systems: Theory and Applications” by Ulaby and Yagle. The text and all simulation programs are available for free download (ss2.eecs.umich.edu) as part of the Free Electrical Engineering Textbook Initiative from the University of Michigan.

All simulations use graphical control elements that allow the student to interact with the simulation. Many of the simulations use either real audio or image data so that the student can vary parameters of the …

Course And Exam Statistics In Electrical Engineering, D Blandford, Mark Randall, Jessica Lofton

ASEE IL-IN Section Conference

This paper examines the course and national exam records for about fifty students in electrical engineering. The data includes the following: SAT/ACT scores, high school math and science grades, high school GPA, high school class rank, and grades for math, science, and engineering courses in the first two years of the major for undergraduates in electrical engineering. The data is analyzed seeking a correlation with success in the major which is measured by the cumulative GPA at or near graduation.

Two types of correlation data are presented. First, correlation with individual data items and success in the major is established. …

A Voice Activated Prosthetic Mode Of Control, Will Picken

UNO Student Research and Creative Activity Fair

There are many options for a prosthetic mode of control. The most commonly created modes of control involve surface EMG (sEMG) and require that the user have well defined muscle activation in order to trigger the movement of the prosthetic. Unfortunately, many prosthetic users do not have the required muscle tone or strength to trigger these sensors, so the need for a control mechanism that doesn’t rely on sEMG is clear. This study focuses on the development of a low-cost, voice activated prosthetic mode of control compatible with the prosthetics developed by Dr. Zuniga and his research team.

The printed …