Engineering Commons^™

Mobile-Polypnet: Lightweight Colon Polyp Segmentation Network For Low-Resource Settings, Ranit Karmakar, Saeid Nooshabadi

Michigan Tech Publications

Colon polyps, small clump of cells on the lining of the colon, can lead to colorectal cancer (CRC), one of the leading types of cancer globally. Hence, early detection of these polyps automatically is crucial in the prevention of CRC. The deep learning models proposed for the detection and segmentation of colorectal polyps are resource-consuming. This paper proposes a lightweight deep learning model for colorectal polyp segmentation that achieved state-of-the-art accuracy while significantly reducing the model size and complexity. The proposed deep learning autoencoder model employs a set of state-of-the-art architectural blocks and optimization objective functions to achieve the desired …

Kernel Matrix-Based Heuristic Multiple Kernel Learning, Stanton R. Price, Derek T. Anderson, Timothy C. Havens, Steven R. Price

Michigan Tech Publications

Kernel theory is a demonstrated tool that has made its way into nearly all areas of machine learning. However, a serious limitation of kernel methods is knowing which kernel is needed in practice. Multiple kernel learning (MKL) is an attempt to learn a new tailored kernel through the aggregation of a set of valid known kernels. There are generally three approaches to MKL: fixed rules, heuristics, and optimization. Optimization is the most popular; however, a shortcoming of most optimization approaches is that they are tightly coupled with the underlying objective function and overfitting occurs. Herein, we take a different approach …

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

Michigan Tech Publications

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 …

Overcoming Supply Disruptions During Pandemics By Utilizing Found Hardware For Open Source Gentle Ventilation, S. Oberloier, N. Gallup, J. M. Pearce

Michigan Tech Publications

This article details the design of an open source emergency gentle ventilator (gentle-vent) framework that can be used in periods of scarcity. Although it is not a medical device, the system utilizes a wide range of commonly-available components that are combined using basic electronics skills to achieve the desired performance. The main function of the gentle-vent is to generate a calibrated pressure wave at the pump to provide support to the patient's breathing. Each gentle-vent permutation was tested using a DIY manometer as it would be utilized in the field in low-resource settings and validated with an open source VentMon. …

Cascading Verification Initiated By Switching Attacks Through Compromised Digital Relays, Koji Yamashita, Zhiyuan Yang, Chee Wooi Ten, Soummya Kar, Andrew Ginter

Michigan Tech Publications

Attackers are able to enumerate all devices and computers within a compromised substation network. Digital relays deployed in the substation are the devices with IP addresses that can be discovered in the process of trial-and-error search. This paper is concerned with studies of cyberattacks manipulating digital relays to disruptively disconnect the associated breakers. The plausible enumeration of such disruptive attack for each relay in a substation is verified with the dynamic simulation studies with the special protection system for frequency, voltage, and rotor angle stability. A pertinent approach with smaller scale contingency analysis results is proposed to reduce the enormous …

Performance Prediction Of Underwater Acoustic Communications Based On Channel Impulse Responses, Evan Lucas, Zhaohui Wang

Michigan Tech Publications

Featured Application: Convolutional neural networks are used on the channel impulse response data to predict the performance of underwater acoustic communications. Abstract: Predicting the channel quality for an underwater acoustic communication link is not a straightforward task. Previous approaches have focused on either physical observations of weather or engineered signal features, some of which require substantial processing to obtain. This work applies a convolutional neural network to the channel impulse responses, allowing the network to learn the features that are useful in predicting the channel quality. Results obtained are comparable or better than conventional supervised learning models, depending on the …

Wireless Power Transfer In Autonomous Mobile Microgrids, Carl Greene

Dissertations, Master's Theses and Master's Reports

The ability to autonomously dock unmanned ground vehicles plays a key role in mobile micro-grids, where efficient power transfer is paramount. The approach utilized in this work allows for near-field wireless power transfer in remote locations with minimal support. Establishing a micro-grid power system connection autonomously using wireless power eliminates the arduous task of designing a complex, multiple degrees of freedom (MDOF) robotic arm. The work presented in this thesis focuses on both the hardware and software within the micro-grid system. This particular near-field wireless system consists of a primary and secondary set of modules, comprised of Litz wire coils, …

On-Ice Detection, Classification, Localization And Tracking Of Anthropogenic Acoustic Sources With Machine Learning, Steven J. Whitaker

Dissertations, Master's Theses and Master's Reports

Arctic acoustics have been of concern in recent years for the US navy. First-year ice is now the prevalent factor in ice coverage in the Arctic, which changes the previously understood acoustic properties. Due to the ice melting each year, anthropogenic sources in the Arctic region are more common: military exercises, shipping, and tourism. For the navy, it is of interest to detect, classify, localize, and track these sources to have situational awareness of these surroundings. Because the sources are on-water or on-ice, acoustic radiation propagates at a longer distance and so acoustics are the method by which the sources …

Adapting Deep Learning For Underwater Acoustic Communication Channel Modeling, Li Wei

Dissertations, Master's Theses and Master's Reports

The recent emerging applications of novel underwater systems lead to increasing demand for underwater acoustic (UWA) communication and networking techniques. However, due to the challenging UWA channel characteristics, conventional wireless techniques are rarely applicable to UWA communication and networking. The cognitive and software-defined communication and networking are considered promising architecture of a novel UWA system design. As an essential component of a cognitive communication system, the modeling and prediction of the UWA channel impulse response (CIR) with deep generative models are studied in this work.

Firstly, an underwater acoustic communication and networking testbed is developed for conducting various simulations and …

Model Predictive Control Of Energy Systems For Heat And Power Applications, Chethan Ramakrishna Reddy

Dissertations, Master's Theses and Master's Reports

Building and transportation sectors together account for two-thirds of the total energy consumption in the US. There is a need to make these energy systems (i.e., buildings and vehicles) more energy efficient. One way to make grid-connected buildings more energy efficient is to integrate the heating, ventilation and air conditioning (HVAC) system of the building with a micro-scale concentrated solar power (MicroCSP) sys- tem. Additionally, one way to make vehicles driven by internal combustion engine (ICE) more energy efficient is by integrating the ICE with a waste heat recovery (WHR) system. But, both the resulting energy systems need a smart …

An Experimental Study Towards Underwater Propulsion System Using Structure Borne Traveling Waves, Shreyas Suhas Gadekar

Dissertations, Master's Theses and Master's Reports

The method of generating steady-state structure-borne traveling waves underwater in an infinite media creates abundant opportunities in the field of propulsive applications, and they are gaining attention from several researchers. This experimental study provides a framework for harnessing traveling waves in a 1D beam immersed under quiescent water using two force input methods and providing a motion to an object floating on the surface of the water.

In this study, underwater traveling waves are tailored using structural vibrations at five different frequencies in the range of 10Hz to 300Hz. The resulting fluid motion provides a propulsive thrust that moves a …

Study Of Electric Vehicle Smart Charging And Energy Management For Vehicle-Grid Integration Systems, Zhouquan Wu

Dissertations, Master's Theses and Master's Reports

The emerging need of building an efficient Electric Vehicle (EV) charging infrastructure requires the investigation of all aspects of Vehicle-Grid Integration (VGI). This dissertation studies the optimal EV charging control and energy management of VGI system to address the economic benefits of EV charging customers and operation stability of distribution power grids. First of all, a centralized EV charging control method is developed under the transactive energy environment to minimize the EV charging cost and avoid the distribution power grid overloading. The quadratic programming is used to obtain optimized charging control actions. Case studies with hundreds of EVs are conducted …

Process Development, Physical, And Electrical Characterization Of Langmuir Blodgett Trough Deposited Polyaniline, Mehdi Malekrah

Dissertations, Master's Theses and Master's Reports

Conductive polymers have recently attracted a lot of attention in advanced technologies because of their unique characteristics. Among the conductive polymers, polyaniline (PANi) has been studied widely because of its environmental stability, simple processing, inexpensive source monomer, and, most importantly, its controllable wide conductivity range due to the doping (protonation) process. These characteristics of PANi make it a strong candidate for applications in numerous areas such as biosensors, transparent display, photovoltaic devices, batteries, and, more recently, flexible electronics. Even with the many studies that have been conducted in this field, however, future advances are still needed to optimize the processability, …

Hardware In The Loop Implementation And Simulations Of A Wave Energy Converter Using Typhoon Hil And Speedgoat, Pranav Nair

Dissertations, Master's Theses and Master's Reports

Several studies have indicated that electricity production is the prime source of greenhouse emissions, more than flying and driving combined. Hence, over the past few decades, there has been a significant rise in the need for clean energy to achieve the targets in emissions reduction. It has been observed that the share of renewable energy sources in the percentage of total electricity production is rising, but, according to climate experts, the transition needs to speed up. Hence, it is significant to study and develop underutilized renewable energy sources.

One of these underutilized renewable energy sources is wave energy. It has …

Stability Approximation Method For Pulse Loads In Power Electronic Systems, Eduardo A. Marmol D

Dissertations, Master's Theses and Master's Reports

Pulse loads on power electronic distribution systems are becoming very popular nowadays as the components of ships and airplanes are moving to more electric power. However, the pulse loads have a destabilizing effect on the power distribution system. Usually, the method used to study the stability of this type of system are small-signal analyses and are based on a system where the load is modeled as a constant. Since DC-DC systems with pulsed loads are very nonlinear, a small-signal analysis does not provide helpful information related to the stability of the system. The work presented in this thesis focuses on …

Self-Oscillating Induction Heater, Patrick Rice

Dissertations, Master's Theses and Master's Reports

This report develops a control system to keep an induction heater in resonance. When a metallic workpiece is inserted in the air core of the workcoil, the resonant frequency changes. Different workpiece materials affect the resonant frequency and power. This presents a problem since changing the resonant frequency of the circuit while keeping the frequency constant reduces the maximum power of the circuit. Finite element analysis is used to find the circuit parameters of the workcoil and workpiece interaction. A non-linear controller which oscillates based on the resonant frequency of an LC tank is created. Nyquist and describing function analysis …

Decarbonizing Rural Residential Buildings In Cold Climates: A Techno-Economic Analysis Of Heating Electrification, Filippo Padovani, Nelson Sommerfeldt, Francesca Longobardi, Joshua M. Pearce

Michigan Tech Publications

Given the need for decarbonization of the heating sector and the acute need of a propane replacement in the U.S. Upper Midwest, this study quantifies the techno-economic characteristics of sustainable heating electrification in isolated rural, residential buildings in cold climates without natural gas supply. Archetypal buildings are modeled under four levels of electrification. At each electrification level, a parametric solar photovoltaic (PV) sizing analysis is performed and the total life cycle cost, renewable fraction and greenhouse gas (GHG) emissions are calculated based on the primary energy supply for each building type. Cost optimal solutions are stress-tested with multi-dimensional sensitivity analyses. …

Sliding Mode Control Of A Nonlinear Wave Energy Converter Model, Tania Demonte Gonzalez, Gordon Parker, Enrico Anderlini, Wayne Weaver

Michigan Tech Publications

The most accurate wave energy converter models for heaving point absorbers include nonlinearities, which increase as resonance is achieved to maximize the energy capture. Over the power production spectrum and within the physical limits of the devices, the efficiency of wave energy converters can be enhanced by employing a control scheme that accounts for these nonlinearities. This paper proposes a sliding mode control for a heaving point absorber that includes the nonlinear effects of the dynamic and static Froude‐Krylov forces. The sliding mode controller tracks a reference velocity that matches the phase of the excitation force to ensure higher energy …

Progressive Poling Of Large Area, High R33 Electro-Optic Polymer Seo100c, Michael Maurer, Evan Gawron, Christopher Middlebrook

Michigan Tech Publications

SEO100c, an EO-polymer, has been reported of having an r33 in excess of 100 pm/V. Experimental poling research was performed on rib waveguide modulator for device design and development. Reported is the determination of the impact that temperature and voltage have on the poling of a SEO100c waveguide device in order to maximize the r33 while avoiding damage to the device structure ensuring high yield in manufacture. The poling process is shown to have a nonlinear relationship between r33 and poling field aiding in the selection of achievable poling voltages for required r33 values. Device thermal stability is quantified and …

Open Source Vacuum Oven Design For Low-Temperature Drying: Performance Evaluation For Recycled Pet And Biomass, Benjamin R. Hubbard, Lindsay I. Putman, Stephen Techtmann, Joshua M. Pearce

Michigan Tech Publications

Vacuum drying can dehydrate materials further than dry heat methods, while protecting sensitive materials from thermal degradation. Many industries have shifted to vacuum drying as cost-or time-saving measures. Small-scale vacuum drying, however, has been limited by the high costs of specialty scientific tools. To make vacuum drying more accessible, this study provides design and performance information for a small-scale open source vacuum oven, which can be fabricated from off-the-shelf and 3-D printed components. The oven is tested for drying speed and effectiveness on both waste plastic polyethylene terephthalate (PET) and a consortium of bacteria developed for bioprocessing of terephthalate wastes …

U.S. Potential Of Sustainable Backyard Distributed Animal And Plant Protein Production During And After Pandemics, Theresa K. Meyer, Alexis Pascaris, David Denkenberger, Joshua M. Pearce

Michigan Tech Publications

To safeguard against meat supply shortages during pandemics or other catastrophes, this study analyzed the potential to provide the average household’s entire protein consumption using either soybean production or distributed meat production at the household level in the U.S. with: (1) pasture-fed rabbits, (2) pellet and hay-fed rabbits, or (3) pellet-fed chickens. Only using the average backyard resources, soybean cultivation can provide 80-160% of household protein and 0- 50% of a household’s protein needs can be provided by pasture-fed rabbits using only the yard grass as feed. If external supplementation of feed is available, raising 52 chickens while also harvesting …

Open Source 3d-Printable Planetary Roller Screw For Food Processing Applications, Marcello C. Guadagno, Jacob M. Loss, Joshua M. Pearce

Michigan Tech Publications

Historically, open source agriculture (OSA) was based on grassroots technology generally manufactured by hand tools or with manual machining. The rise of distributed digital manufacturing provides an opportunity for much more rapid lateral scaling of open source appropriate technologies for agriculture. However, the most mature distributed manufacturing area is plastic, which has limited use for many OSA applications. To overcome this limitation with design, this study reports on of a completely 3D-printable planetary roller screw linear actuator. The device is designed as a parametric script-based computer aided design (CAD) package to allow for the easy adaption for a number of …

Authors From All Over The World Share Their Tech In Hardwarex To Battle Covid-19, Joshua M. Pearce

Michigan Tech Publications

No abstract provided.

Economics Of Grid-Tied Solar Photovoltaic Systems Coupled To Heat Pumps: The Case Of Northern Climates Of The U.S. And Canada, Joshua M. Pearce, Nelson Sommerfeldt

Michigan Tech Publications

Solar photovoltaic (PV) technology is now a profitable method to decarbonize the grid, but if catastrophic climate change is to be avoided, emissions from transportation and heating must also decarbonize. One approach to renewable heating is leveraging improvements in PV with heat pumps (HPs). To determine the potential for PV+HP systems in northern areas of North America, this study performs numerical simulations and economic analysis using the same loads and climate, but with local electricity and natural gas rates for Sault Ste. Marie, in both Canada and U.S. Ground-mounted, fixed-tilt, grid-tied PV systems are sized to match 100% of electric …

Sensing Methods For Two-Target And Four-Target Detection In Time-Constrained Vector Poisson And Gaussian Channels, Muhammad Fahad

Dissertations, Master's Theses and Master's Reports

In this dissertation we consider a sensor scheduling or resource management problem for a vector Poisson and Gaussian channels. The input is a binary random vector and the output is a set of conditionally independent Poisson or Gaussian random variables. The objective is to design a scaling matrix, which is a linear transformation whose purpose is to entangle the different inputs, under a total given energy/time constraint. The two metrics are adopted to quantify the performance of the designed scaling matrix: mutual information and Bayesian inference. In other words, it is an experimental design problem where the objective is to …

Real Time Adaptive Relay Settings For Microgrid Protection Verified Using Hardware In Loop, Aadam Harnekar

Dissertations, Master's Theses and Master's Reports

Microgrids with penetration of renewables is imposing new challenges for system protection. Renewables are characterized with high source impedance which limit the short circuit current. The value of short-circuit current is limited due to converters used which limit the current to a maximum of 1.1 to 1.5 times maximum rated load current. This can result in faults during the islanded mode of microgrid to go unnoticed if the relay settings are not adapted to account for it. The presence of such uncleared faults in the microgrid can result in exposing it to overcurrent for a long time which can damage …

Nonlinear Model Predictive Control Of Wave Energy Converter, Isha Malekar

Dissertations, Master's Theses and Master's Reports

In this report model predictive control (MPC) is applied to a simulated, spherical, point absorber wave energy converter to maximize energy extraction. Constraints are applied to the buoy's displacement and the power take-off (PTO) generator force. The WEC's "truth” model uses nonlinear Froude-Krylov (FK) hydrostatic and hydrodynamic forces. This is in contrast with previous studies where linear approximations are used in the form of a hydrostatic stiffness force and a wave excitation force. The nonlinear forces become significant when the vertical displacement of the buoy exceeds about 40% of the buoy's radius. Two versions of MPC are compared where optimal …

Towards Systems On Cloth: The Design, Manufacturing, And Validation Of Open-Source Embroidered Resistors, Somerset Schrock

Dissertations, Master's Theses and Master's Reports

This thesis is focused on advancing embroidered wearable electronics and textile electronics by creating open-source flexible resistors. Advancements in textile electronics could usher a new generation of smart devices that are entirely flexible. Current systems on cloth primarily use rigid components, which limits the flexibility and comfort of using the fabric devices. To advance this field, I propose a novel method of creating flexible electrical resistors with embroidery. To realize this technology, I created an open-source tool to create embroidery files for machine fabrication. This thesis details the methods and tools created for resistor fabrication. The resistors were tested to …

A Transdisciplinary Analysis Of Just Transition Pathways To 100% Renewable Electricity, Adewale Aremu Adesanya

Dissertations, Master's Theses and Master's Reports

The transition to using clean, affordable, and reliable electrical energy is critical for enhancing human opportunities and capabilities. In the United States, many states and localities are engaging in this transition despite the lack of ambitious federal policy support. This research builds on the theoretical framework of the multilevel perspective (MLP) of sociotechnical transitions as well as the concept of energy justice to investigate potential pathways to 100 percent renewable energy (RE) for electricity provision in the U.S. This research seeks to answer the question: what are the technical, policy, and perceptual pathways, barriers, and opportunities for just transition to …

Superresolution Enhancement With Active Convolved Illumination, Anindya Ghoshroy

Dissertations, Master's Theses and Master's Reports

The first two decades of the 21st century witnessed the emergence of “metamaterials”. The prospect of unrestricted control over light-matter interactions was a major contributing factor leading to the realization of new technologies and advancement of existing ones. While the field certainly does not lack innovative applications, widespread commercial deployment may still be several decades away. Fabrication of sophisticated 3d micro and nano structures, specially for telecommunications and optical frequencies will require a significant advancement of current technologies. More importantly, the effects of absorption and scattering losses will require a robust solution since this renders any conceivable application of metamaterials …