Biomedical Commons^™

Hardware-In-The-Loop Evaluation Of Sensor-Source Selection For Prosthetic Locomotion Intent Recognition, Victoria Asencio-Clemens

Master's Theses

Active lower-limb prostheses use intent-recognition systems to identify a user’s locomotion mode and select an appropriate control strategy, but sensor configurations that perform well offline may be unsuitable for resource-constrained embedded hardware. Existing sensor-selection methods generally prioritize classification accuracy without directly accounting for processing latency, memory usage, or other hardware-dependent requirements. To address this limitation, this thesis develops a hardware-in-the-loop source-selection framework for embedded classification of level walking, ramp ascent, ramp descent, stair ascent, and stair descent using multimodal biomechanical data from transtibial amputee participants. Subject-specific linear support vector machine classifiers were evaluated using trial-held-out validation, and candidate configurations from …

Design And Parametric Testing Of A Transimpedance Amplifier For Low-Power Biomedical Applications, Stanlon Tan, William Chung, Brandon Wu

Electrical Engineering

This project developed and evaluated an optical sensing system for detecting changes associated with glucose concentration. The system combined a laser-diode, cuvette sample holder, photodiode, resistive-feedback transimpedance amplifier, high-resolution analog-to-digital converter, and microcontroller. Parametric testing evaluated the effects of input current and feedback resistance on transimpedance gain, output range, and linearity. Firmware was developed to configure the ADC, average repeated conversions, monitor measurement variation, convert raw digital counts into voltage using a source-meter calibration equation, and compare sample measurements with a water reference. A cuvette enclosure maintained alignment between the laser-diode, sample, and photodiode while reducing external optical interference. Testing …

Practical Multimodal Wearable Sensing For Functional Upper Extremity Primitive Classification With Application To Stroke Rehabilitation, Nicholas Weiss

Master's Theses

Stroke often causes long-term weakness and impaired motor control in the upper extremity (UE), making everyday tasks such as reaching, grasping, and moving objects more difficult. Restoring functional arm use is therefore a central goal of post-stroke rehabilitation. Measuring affected arm use continuously and objectively is important because isolated clinical assessments may not fully capture how the affected arm is used during therapy or daily life. Wearable sensors offer a promising approach for monitoring, but raw sensor signals are difficult to interpret directly. Functional movement primitives address this issue by describing UE behavior as smaller, task-agnostic movement units.

This thesis …

Dot Product Engine Based Neuromorphic Hardware For Continuous-Time Biomedical Signal Classification, Sanjeev Srinivasan

Master's Theses

Accurate diagnosis of pathological conditions from biomedical signals, such as electrocardiograms (ECGs) is often performed offline, making it time-consuming, costly, and inefficient, especially when abnormal patterns are rare and long-term monitoring generates large amounts of data. To address this, this work proposes a compact, scalable, and programmable neuromorphic system designed for real-time preliminary arrhythmia detection and classification using ECG signals, that can be extended to other biomedical signals. The proposed design processes ECG signals using a delta modulation-based spike encoder, followed by classification with a dot-product engine (DPE) based spiking neural network (SNN) processor and winner-take-all (WTA) circuit. The architecture …

Optimizing And Training An Svm-Based Breast Cancer Tumor Classifier, Kevin Lopatka

Master's Theses

With advancements in technology, turning to machine learning has become a popular choice for aiding clinicians in the diagnoses of breast cancer malignancies. While the neural networking approach has been vetted thoroughly, this work aims to take advantage of traditional machine learning techniques; mainly support vector machine learning and the optimizing of feature extraction. The discrete-wavelet transform is used in the feature extraction stage of machine learning. Previous works that use this feature extraction technique are analyzed and expanded upon by utilizing a variety of different wavelets as well as other color-spaces with the goal of achieving higher result metrics …

Hypoxic Incubator: Improving Robustness/Reliability And Demonstrating Physiological Efficacy, Damon Dennis Tan

Master's Theses

The Microphysiological Systems Laboratory aims to develop colorectal cancer tumor models under a hypoxic environment to assess model response to pharmaceutical compounds in vitro. To perform relevant studies, researchers have attempted to use different hypoxic inducing strategies such as a nitrogen pod and hypoxic incubator to recreate in vivo physiological responses to hypoxia. However, studies would be interrupted due to incubator functionality failure. To ensure successful and physiologically relevant studies, I improved and verified the robustness and reliability of a hypoxic incubator previously designed and manufactured in the lab. Through the testing and iterating design processes, I engineered and implemented …

Machine Learning-Based Stress Detection Using Smartphones And Wearable Sensors, Robert Burns, Kassandra Martinez-Mejia

College of Engineering Summer Undergraduate Research Program

Stress and mental health have been considered increasing global concerns in modern society, including some of the illnesses responsible for a large proportion of comorbidities and deaths worldwide, such as depression and cardiovascular disease. Recently, smartphones, smartwatches, and smart wristbands have become an integral part of our lives and have reached widespread usage [1]. This raised the question of whether we can detect and prevent stress with smartphones and wearable sensors wirelessly. The challenge of such an approach is that the weak ECG signal is prone to errors, and the battery life of the smart devices is limited. In this …

Dual Base Sige Is-Hbt For Use In Biosensing Applications, Liam Stephen Hayes

Master's Theses

The proposed research is for a novel SiGe-based Ion-Sensitive Dual Hetero-junction Bipolar Transistor (IS-HBT) to be used in both trans-dermal biological sensing as well as Lab-on-Chip (LOC) applications. The end goals for the device designed are two: For one, the research done for this work will be used to substantiate the claims made by Zafar et al. [1] that an HBT-style structure is better suited for biosensing application rather than a conventional Field Effect Transistor (FET) based geometries. Secondly, it provides the final element to be integrated along with a selectivity membrane, as well as with a reverse-iontophoresis system to …

2-Channel Eeg Neurofeedback System, Tim Erwin, Donna Nikjou, Sebastian Turkewitz

Electrical Engineering

This work describes the design of an EEG-based neurofeedback system which provides users with real-time feedback on their level of focus or relaxation. By analyzing the spectral content of the brain activity measured via scalp electrodes, focus and relaxation levels can be quantified. Based on these measurements, live feedback in the form of moving bar graphs is provided to users, allowing them to gain awareness of their mental-state and more efficiently learn how to consciously relax or focus. This project covers the design of the system, including amplification and filtering stages, digitization, and signal processing. The system interfaces with a …

Generative Data Augmentation: Using Dcgan To Expand Training Datasets For Chest X-Ray Pneumonia Detection, Ryan D. Maier

Master's Theses

Recent advancements in computer vision have demonstrated remarkable success in image classification tasks, particularly when provided with an ample supply of accurately labeled images for training. These techniques have also exhibited significant potential in revolutionizing computer-aided medical diagnosis by enabling the segmentation and classification of medical images, leveraging Convolutional Neural Networks (CNNs) and similar models. However, the integration of such technologies into clinical practice faces notable challenges. Chief among these is the obstacle of acquiring high-quality medical imaging data for training purposes. Patient privacy concerns often hinder researchers from accessing large datasets, while less common medical conditions pose additional hurdles …

Providing Cadence Feedback In Real-Time To Guide Cardiovascular Workouts, Levi O. Rash

Master's Theses

Cardiovascular workouts offer numerous health benefits, yet beginners often find it challenging to initiate them. Existing wearable technologies, although providing valuable feedback such as heart rate zones, often disrupt the workout flow and distract users due to the need for interaction with the wearable display. In response, we propose an alternative feedback mechanism: cadence, measured in steps per minute. This feedback mechanism uses multiplicative control to produce the correct cadence for the user’s target heart rate (HR). To model the HR and cadence relationship, a first-order system was used. The prototype implementation of this system was completed in Arduino, using …

Cardio Trainer, Levi Rash, Cristian Rodriguez

Electrical Engineering

The Cardio Trainer Device is a wearable device that guides the user through a physical exercise based on the user’s heartbeat measurements. Users interface with the device via a wearable band. The band determines the heartbeat of the user in real time and, using that reading, gives the user verbal instructions to optimize their workout. These verbal instructions then serve to control the physical exertion of the user and are delivered through an audio device. Users input personal physical metrics to the Cardio Trainer Device that tailor the performance of the device in a manner of ways: rate of instruction, …

Identifying And Minimizing Underspecification In Breast Cancer Subtyping, Jonathan Cheuk-Kiu Tang

Master's Theses

In the realm of biomedical technology, both accuracy and consistency are crucial to the development and deployment of these tools. While accuracy is easy to measure, consistency metrics are not so simple to measure, especially in the scope of biomedicine where prediction consistency can be difficult to achieve. Typically, biomedical datasets contain a significantly larger amount of features compared to the amount of samples, which goes against ordinary data mining practices. As a result, predictive models may fail to find valid pathways for prediction during training on such datasets. This concept is known as underspecification.

Underspecification has been more accepted …

Diy Cell Incubator, Hayden James Jeanor

Electrical Engineering

The purpose of creating a cell Incubator is for the development of cell and tissue production in laboratory settings. Large scale research projects and the medical community grow cells for various reasons, including experiments and creating tissue for patients. However, they cannot simply depend on growing cells in a petri dish that sit on a rack at room temperature. To grow heathy cells in the fastest way possible, they use cell incubators. Cell incubators create an atmosphere within the incubation bay that is designed to promote cell growth. The three main components that need to be constantly regulated, using a …

Smart Bottle Ble Integration, Joshua M. Rizzolo

Electrical Engineering

In 1975, four percent of children aged five to nineteen were categorized as overweight or obese. As of 2016, this figure climbed above 18 percent [1]. Researchers at California Polytechnic State University San Luis Obispo (Cal Poly) want to investigate the effect of overeating in early childhood on later childhood obesity. This research requires collecting feeding pattern data on infants, which proves challenging. Parents cannot be relied on to regularly collect clean data due to factors including work schedule, multitasking, and general exhaustion. Thus, we have developed a tool to automatically collect data on feeding frequency and duration, as well …

Bicep Muscle Rep Counter With Semg, Matthew Max Garcia

Electrical Engineering

The Bicep Muscle Rep Counter with SEMG is a device that was made to develop three repetition thresholds or difficulty levels from a fully-flexed bicep brachii muscle and signal to the user when consequent bicep muscle contractions pass said thresholds or levels. This device can be used when performing a bicep-focused movement or when generally flexing the bicep muscle. Essentially, this device serves to make sure each repetition of a muscle contraction passes a percentage value calculated from the electrical activity outputted from a max contraction.

The device is not designed for and does not produce data for muscle growth, …

Neural Network Based Diagnosis Of Breast Cancer Using The Breakhis Dataset, Ross E. Dalke

Master's Theses

Breast cancer is the most common type of cancer in the world, and it is the second deadliest cancer for females. In the fight against breast cancer, early detection plays a large role in saving people’s lives. In this work, an image classifier is designed to diagnose breast tumors as benign or malignant. The classifier is designed with a neural network and trained on the BreakHis dataset. After creating the initial design, a variety of methods are used to try to improve the performance of the classifier. These methods include preprocessing, increasing the number of training epochs, changing network architecture, …

Insole Fall Prevention Device, Nick M. Hughes, Andrew M. Slaboda

Biomedical Engineering

Falls among the aging population occur every single day, with 1 in every 5 resulting in some injury and 300,000 hospitalized every year with a hip fracture [1]. The most popular and effective way to mitigate these falls is through physical therapist intervention. However, with the increased popularity in telerehab, many patients at risk for falls cannot accurately convey their gait tendencies to their physical therapists from the comfort of their home or while not in direct contact with the PT. A device like an insole, implanted with force sensors, which measures different parts of a patient’s foot, could convey …

Verification Of A Digital Microfluidics Platform, Karanpartap Singh

Electrical Engineering

The electrowetting effect describes the change in contact angle between a solid surface and electrolyte in response to an applied electric potential difference. Given a planar array of individually-actuated electrodes, electrowetting can be used to transport, mix, and separate picoliter to microliter-sized droplets of liquid on a dielectric layer. Applications of this phenomenon range from lab-on-a-chip and other microfluidic devices to liquid lenses capable of altering their topology and focus within milliseconds.

This project extends prior work simulating the dependence of droplet velocity on actuation voltage and demonstrates observed physics on a physical platform. The simulation portion of this project …

Smart Motor Syringe System, Connor Wilson

Electrical Engineering

In this document a proof-of-concept design is developed and implementation to showcase the latest development in an ongoing effort to produce a series of automated syringe pumps.

Integration Of Electrical Impedance Spectroscopy For Multichannel Cell Culture Measurement, Conard Chan

Master's Theses

ELECTROCHEMICAL IMPEDANCE SPECTROSCOPY (EIS) has been widely used to study the electrical properties of biological material due to its non-invasive nature and experimental reliability. However, most of the precision impedance analyzers used in EIS only provide single- or two-channel measurements which are inadequate for larger-scale multiplexed measurements, such as those found in modern microfluidic cell culture experiments. The Biomedical Microsystems Laboratory has developed a 16-channel cell culture platform with integrated electrode arrays for monitoring cell growth and electrical properties (i.e., the so-called “electrical phenotype”). In this paper, a system consisting of a 16-channel solid-state analog multiplexer (MUX)paired with a low-cost, …

Classifying Electrocardiogram With Machine Learning Techniques, Hillal Jarrar

Master's Theses

Classifying the electrocardiogram is of clinical importance because classification can be used to diagnose patients with cardiac arrhythmias. Many industries utilize machine learning techniques that consist of feature extraction methods followed by Naive- Bayesian classification in order to detect faults within machinery. Machine learning techniques that analyze vibrational machine data in a mechanical application may be used to analyze electrical data in a physiological application. Three of the most common feature extraction methods used to prepare machine vibration data for Naive-Bayesian classification are the Fourier transform, the Hilbert transform, and the Wavelet Packet transform. Each machine learning technique consists of …

Portable Ventilator, Bradley C. Weeks, Jack W. Brewer, Sanders Sanabria

Electrical Engineering

The current COVID-19 pandemic has heavily impacted the healthcare system in the United States and elsewhere. The need for patients to have access to a hospital with a ventilator along with a shortage of ventilators for recovery and at-home care as a result of minimal hospital vacancy for patients has been greatly stressed. The presented problem is both an unmet demand and supply of portable and effective ventilators. Existing ventilators have many shortcomings that should be addressed: size, weight, cost, and complexity of current ventilators confines users to stay in a medical facility whilst being monitored by professionals. This both …

Biological Semantic Segmentation On Ct Medical Images For Kidney Tumor Detection Using Nnu-Net Framework, Andres Bergsneider

Master's Theses

Healthcare systems are constantly challenged with bottlenecks due to human-reliant operations, such as analyzing medical images. High precision and repeatability is necessary when performing a diagnostics on patients with tumors. Throughout the years an increasing number of advancements have been made using various machine learning algorithms for the detection of tumors helping to fast track diagnosis and treatment decisions. “Black Box” systems such as the complex deep learning networks discussed in this paper rely heavily on hyperparameter optimization in order to obtain the most ideal performance. This requires a significant time investment in the tuning of such networks to acquire …

Smart Motor Syringe System, Conard Chan, Jenny Chiao

Electrical Engineering

Syringe pumps are widely used in many research applications especially in the applications that need precise control. Today most medical research utilizes syringes to control the fluid being pumped to the experiment objects. In most cases microscopic or nano-scopic motion control is required to acquire optimal results, such application includes purification of DNA/RNA from contaminants[1]. The high precision required to control the syringe pump makes it difficult to perform manually. This paper focuses on the design of an intelligent syringe pump motor control system to achieve reliable and precise control for biomedical experiments. This project improves medical research quality with …

Electrocardiographic (Ecg) Biometric Identification, Ryan Morosa, Charbel Ghantous

Electrical Engineering

Electrocardiography (ECG) is being used a lot more in biometrics for applications where protection of privacy is important. Other methods like facial recognition can be falsified by using different colored contacts to manipulate identification. For this reason, ECG is a viable option for biometric identification since it relies solely on the heartbeat to classify characteristics of an individual. The Pan-Tompkins method was used for feature extraction, and both ELM and correlation were used for classification. ELM through MATLAB achieved an average accuracy of 85%. Correlation achieved an average accuracy of 89.2%.

Eeg Midi Controller, Jack Ellison, Eric Bettencourt

Electrical Engineering

One of the greatest challenges for aspiring musicians is the amount of practice and commitment required to become fluent in a traditional instrument. Taken a step further, individuals who have impaired motor skills may be incapable of even executing the physical demands required to practice one. While this device does not create notes directly from a user's brain waves, exploring and designing EEG based musical hardware capable of using a person’s thoughts to control musical devices could pave the way for greater advances. It can also open many doors into psycho-acoustic research, treating the mind's response to hearing music and …

Neural Network Pruning For Ecg Arrhythmia Classification, Isaac E. Labarge

Master's Theses

Convolutional Neural Networks (CNNs) are a widely accepted means of solving complex classification and detection problems in imaging and speech. However, problem complexity often leads to considerable increases in computation and parameter storage costs. Many successful attempts have been made in effectively reducing these overheads by pruning and compressing large CNNs with only a slight decline in model accuracy. In this study, two pruning methods are implemented and compared on the CIFAR-10 database and an ECG arrhythmia classification task. Each pruning method employs a pruning phase interleaved with a finetuning phase. It is shown that when performing the scale-factor pruning …

Pulsed Electrical Field Ablation Modulation, Camille Lousie Dozois, Jason Tyler Arias, Courtnee Lin Madsen

Biomedical Engineering

This document comprises the steps taken by the senior project team to create a Proof-of-Concept Review for a Variable Pulsed Electric Field Ablation Catheter. First, the team did a significant amount of background research on related literature to better understand the current status of the project topic. After sufficient background information was obtained, project objectives and deliverables were finalized. Once customer requirements and the indications for use were completed, engineering specifications for the product and project were documented. All key customer requirements and engineering specs were related to the variable pulse functionality, maneuverability, as well as overall dimensioning of the …

Blood Glucose Predictor, Jessica Patterson

Electrical Engineering

For my senior project, I perform data analysis using statistical methods to determine body metrics that correlate with blood glucose levels. Working with Dr. Tina Smilkstein, I take repeat measurements from 6 different volunteers to establish trends in bodily metric data. The data taken includes weight, body fat, pulse rate, VO2, blood glucose, blood pressure, hours slept, and quality of sleep. Using these values, I use the program MiniTab to view results.

A few examples of correlations with blood glucose found in this project are:

• Systolic blood pressure for females had a regression line of 124.0 -0.3366*Blood Pressure. This indicates …