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 …

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 …

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 …

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 …

Characterization And Estimation Of Musculoskeletal Pain Using Machine Learning, Boluwatife Faremi

Master's Theses

Traditional scales utilized for recording pain are known to be highly subjective and biased due to inaccuracies in recollecting actual pain intensities. As a result, machine learning (ML) models that are trained using these scores as ground truth are reported to have low performance for objective pain classification because of the huge disparity between what was felt in moments of pain and the scores recorded afterward.

In the present study, two devices were designed for gathering real-time, continuous in-session subjective pain scores and the recording of the autonomic nervous system (ANS) altered endodermal (EDA) activity. 24 participants were recruited to …

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 …

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, …

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 …

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 …

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 …

Development Of A Myoelectric Detection Circuit Platform For Computer Interface Applications, Nickolas Andrew Butler

Master's Theses

Personal computers and portable electronics continue to rapidly advance and integrate into our lives as tools that facilitate efficient communication and interaction with the outside world. Now with a multitude of different devices available, personal computers are accessible to a wider audience than ever before. To continue to expand and reach new users, novel user interface technologies have been developed, such as touch input and gyroscopic motion, in which enhanced control fidelity can be achieved. For users with limited-to-no use of their hands, or for those who seek additional means to intuitively use and command a computer, novel sensory systems …

Microfluidic Electrical Impedance Spectroscopy, John J. Foley

Master's Theses

The goal of this study is to design and manufacture a microfluidic device capable of measuring changes in impedance valuesof microfluidic cell cultures. Tocharacterize this, an interdigitated array of electrodes was patterned over glass, where it was then bonded to a series of fluidic networks created in PDMS via soft lithography. The device measured ethanol impedance initially to show that values remain consistent over time. Impedance values of water and 1% wt. saltwater were compared to show that the device is able to detect changes in impedance, with up to a 60% reduction in electrical impedance in saltwater. Cells were …

Adaptation Of Vt-Dbr Lasers For Lidar, Luke Horowitz

Master's Theses

Vernier Tuned Distributed Bragg Reflector (VT-DBR) lasers have had great success in the field of Swept-Source Optical Coherence Tomography (SS-OCT) due to their continuous and nearly 40 nm wavelength tuning range in a single longitudinal mode. Fast sweeps allow for real time imaging with micrometer resolution at a distance of a few centimeters. While this laser has proven quite useful as a medical imaging tool via OCT, it has yet to similarly prove itself for general light detection and ranging (LIDAR) applications due to range limitations that arise from a finite laser coherence length. The goal of this thesis is …

Extended-Use Ecg Monitor, Daniel Aaron Soski

Master's Theses

In this thesis, a prototype ECG monitor was developed that is integrated into an elastic shirt and takes a 3-lead ECG for over 5 days. The high-quality measurements can be used to identify markers indicative of various detrimental heart conditions. Measurements recorded by the device are encrypted and stored onto a micro-SD card. Current Holter monitors are expensive and have functional lives less than 48 hours; however, extended duration monitoring has been proven more useful in diagnosis. The device designed demonstrates that ECG measurements can be taken over longer durations without sacrificing quality, comfort, or device cost.

Computer-Aided Diagnoses (Cad) System: An Artificial Neural Network Approach To Mri Analysis And Diagnosis Of Alzheimer's Disease (Ad), Berizohar Padilla Cerezo

Master's Theses

Alzheimer’s disease (AD) is a chronic and progressive, irreversible syndrome that deteriorates the cognitive functions. Official death certificates of 2013 reported 84,767 deaths from Alzheimer’s disease, making it the 6th leading cause of death in the United States. The rate of AD is estimated to double by 2050. The neurodegeneration of AD occurs decades before symptoms of dementia are evident. Therefore, having an efficient methodology for the early and proper diagnosis can lead to more effective treatments.

Neuroimaging techniques such as magnetic resonance imaging (MRI) can detect changes in the brain of living subjects. Moreover, medical imaging techniques are the …

Hand (Motor) Movement Imagery Classification Of Eeg Using Takagi-Sugeno-Kang Fuzzy-Inference Neural Network, Rory Larson Donovan

Master's Theses

Approximately 20 million people in the United States suffer from irreversible nerve damage and would benefit from a neuroprosthetic device modulated by a Brain-Computer Interface (BCI). These devices restore independence by replacing peripheral nervous system functions such as peripheral control. Although there are currently devices under investigation, contemporary methods fail to offer adaptability and proper signal recognition for output devices. Human anatomical differences prevent the use of a fixed model system from providing consistent classification performance among various subjects. Furthermore, notoriously noisy signals such as Electroencephalography (EEG) require complex measures for signal detection. Therefore, there remains a tremendous need to …

Silent Communication Device, Christopher Wayne Schutter

Master's Theses

Oral communication has constituted as a necessary aspect of how people interact with one another, but there are always situations where this form of communication can create distractions, irritation, or even danger. Take for example, a student in a laboratory who needs to communicate effectively with a lab partner without creating a distraction to those trying to work around said student or a soldier on a battlefield who needs to relay information effectively to his or her comrades without revealing his or her position to the enemy. It becomes apparent that people need a more exclusive form of communication in …

Hall Effect Modeling In Fem Simulators And Comparison To Experimental Results In Silicon And Printed Sensors, Leonardo A. Frem

Master's Theses

Finite element method simulation models for thin-film semiconductor-based Hall sensors were developed using secondary data in order to understand their behavior under strong magnetic fields. Given a device geometry and charge carrier density and mobility, the models accurately calculated sensor resistance, Hall voltage under a normally-incident constant magnetic field, and expected offset from a population of Hall devices. The model was successfully matched against data from integrated chip Hall sensors from St. Jude Medical. Additionally, the feasibility of creating Hall effect devices with common carbon ink was explored experimentally. The material properties obtained from testing these ink-based devices through the …

Quantification Of Blood Flow Velocity Using Color Sensing, Aditya Deepak Sanghani

Master's Theses

Blood flow velocity is an important parameter that can give information on several pathologies including atherosclerosis, glaucoma, Raynaud’s phenomenon, and ischemic stroke [2,5,6,10]. Present techniques of measuring blood flow velocity involve expensive procedures such as Doppler echocardiography, Doppler ultrasound, and magnetic resonance imaging [11,12]. They cost from $8500-$20000. It is desired to find a low-cost yet equally effective solution for measuring blood flow velocity. This thesis has a goal of creating a proof of concept device for measuring blood flow velocity.

Finger blood flow velocity is investigated in this project. The close proximity to the skin of the finger’s arteries …

Characterization Of Two Vernier-Tuned Distributed Bragg Reflector (Vt-Dbr) Lasers Used In Swept Source Optical Coherence Tomography (Ss-Oct), Greg M. Bergdoll

Master's Theses

Insight Photonic Solutions Inc. has continued to develop their patented VT-DBR laser design; these wavelength tunable lasers promise marked image-quality and acquisition time improvements in SS-OCT applications.

To be well suited for SS-OCT, tunable lasers must be capable of producing a highly linear wavelength sweep across a tuning range well-matched to the medium being imaged; many different tunable lasers used in SS-OCT are compared to identify the optimal solution.

This work electrically and spectrally characterizes two completely new all-semiconductor VT-DBR designs to compare, as well. The Neptune VT-DBR, an O-band laser, operates around the 1310 nm range and is a …

Sweep Stability Characterization Of A Vernier-Tuned Distributed Bragg Reflector (Vt-Dbr) All-Semiconductor Tunable Swept Laser System At 1550 Nm For Sensing Applications, Roric Christian Martens Biersach

Master's Theses

The short-term jitter and longer-term wander of the frequency sweep profile of a Vernier-Tuned Distributed Bragg Reflector (VT-DBR) laser at 1550 nm used in optical coherence tomography (OCT) and other sensing applications is characterized in this work. The VT-DBR has demonstrated success in source-swept OCT (SSOCT), performing both intensity and phase-sensitive OCT.

The purpose of this paper is to investigate one of the unique aspects of the VT-DBR laser that makes it successful in OCT: the stability of the linear optical frequency sweep. A highly stable linear optical frequency sweep implies benefits for further fiber sensing applications including fiber Bragg …

Ecg Classification With An Adaptive Neuro-Fuzzy Inference System, Brad Thomas Funsten

Master's Theses

Heart signals allow for a comprehensive analysis of the heart. Electrocardiography (ECG or EKG) uses electrodes to measure the electrical activity of the heart. Extracting ECG signals is a non-invasive process that opens the door to new possibilities for the application of advanced signal processing and data analysis techniques in the diagnosis of heart diseases. With the help of today’s large database of ECG signals, a computationally intelligent system can learn and take the place of a cardiologist. Detection of various abnormalities in the patient’s heart to identify various heart diseases can be made through an Adaptive Neuro-Fuzzy Inference System …

Design And Fabrication Techniques Of Devices For Embedded Power Active Contact Lens, Errol Heradio Leon

Master's Theses

This thesis designed and fabricated various devices that were interfaced to an IC for an active contact lens that notifies the user of an event by detection of an external wireless signal. The contact lens consisted of an embedded antenna providing communication with a 2.4GHz system, as well as inductive charging at an operating frequency of 13.56 MHz. The lens utilized a CBC005 5µAh thin film battery by Cymbet and a manufactured graphene super capacitor as a power source. The custom integrated circuit (IC) was designed using the On Semiconductor CMOS C5 0.6 µm process to manage …

Design, Characterization And Application Of A Multiple Input Stethoscope Apparatus, Spencer Geng Wong

Master's Theses

For this project, the design, implementation, characterization, calibration and possible applications of a multiple transducer stethoscope apparatus were investigated. The multi-transducer sensor array design consists of five standard stethoscope diaphragms mounted to a rigid frame for a-priori knowledge of their relative spatial locations in the x-y plane, with compliant z-direction positioning to ensure good contact and pressure against the subject’s skin for reliable acoustic coupling. When this apparatus is properly placed on the body, it can digitally capture the same important body sounds investigated with standard acoustic stethoscopes; especially heart sounds. Acoustic signal inputs from each diaphragm are converted to …

Eye "R" Glasses: Development Of An Infrared Sensor System For Detecting The Human Body, Rick Wong

Master's Theses

Throughout the years, sensors have been an integral part of automation, alert, and medical systems. Many of these systems measure physiological characteristics of the human body to alert themselves of their current conditions. Drowsy driver systems, for instance, measure the eyes and facial movements with a camera to determine if the driver is falling asleep at the wheel. Electroencephalography (EEG), electrooculography (EOG), and electromyography (EMG) employ electrodes on the human body to measure electrical activity of a patient’s REM sleep cycle patterns. Pulse oximeters use optical light through a process called photoplethysmography (PPG) to measure heart rate.

As diverse as …