Open Access. Powered by Scholars. Published by Universities.®
- Institution
- Keyword
-
- Adversarial Machine Learning (1)
- Anti-saccade (1)
- Arrayed sensor (1)
- Athleticism (1)
- Bioinformatics (1)
-
- Biomedical Time-Series Analysis (1)
- Biomedical engineering (1)
- Chemical stimulation (1)
- Computational fluid dynamics (1)
- Computer science (1)
- Computer-vision (1)
- Concussion (1)
- Data Science (1)
- Deep Learning for Healthcare (1)
- Deep learning (1)
- Doppler (1)
- EEG Signal Classification (1)
- Electroencephalography (EEG) (1)
- Epileptic Seizure Detection (1)
- Explainable Artificial Intelligence (1)
- Eye Movement Control (1)
- Eye movement (1)
- Facial recognition (1)
- Few-shot (1)
- Flow (1)
- Frequency-Domain Robustness (1)
- Gait Analysis (1)
- Graphene nanoplatelets (1)
- Heart (1)
- High throughput screening (1)
- Publication
- Publication Type
Articles 1 - 9 of 9
Full-Text Articles in Vision Science
Adversarial Robustness In Biomedical Time-Series Models, Rohan Tiwari
Adversarial Robustness In Biomedical Time-Series Models, Rohan Tiwari
Bioengineering Theses
This study investigates adversarial vulnerabilities in deep learning models for biomedical time-series classification across two clinically important modalities: electrocardiography (ECG) and electroencephalography (EEG). Using the MIT-BIH Arrhythmia and CHB-MIT seizure datasets, I evaluate time-domain attacks (FGSM, PGD), Fourier-domain constrained attacks, and learned spectral perturbations designed to reveal modality-specific sensitivity patterns. Across both tasks, a consistent trend emerges low-frequency components (0–5 Hz) constitute a dominant axis of adversarial vulnerability, with perturbations in this range producing the steepest degradation in classification performance. In ECG models, protecting the physiologically relevant QRS band (5–20 Hz) significantly improves robustness, whereas EEG models remain highly sensitive …
A Deep Learning Approach For Semantic Segmentation And Its Application On Ctc., Samir Farag Harb
A Deep Learning Approach For Semantic Segmentation And Its Application On Ctc., Samir Farag Harb
Electronic Theses and Dissertations
This dissertation explores the modeling and analysis of medical images, focusing on the intricate task of colon segmentation and subsequent 3D reconstruction, which are critical steps in Computed Tomography Colonography (CTC) systems. The primary objective of this research is to develop precise segmentation approaches to enhance the accuracy of colon identification and reconstruction from abdominal CT scans. Three distinct segmentation approaches are proposed and evaluated: a Markov Random Field (MRF)-based approach, a convolutional neural network (CNN)-based deep learning (DL) approach, and a sequential episodic training with dual contrastive learning Approach (G-SET-DCL) that has a flavor of few-shot learning (FSL). To …
Development Of Light Actuated Chemical Delivery Platform On A 2-D Array Of Micropore Structure, Hojjat Rostami Azmand, Hojjat Rostami Azmand
Development Of Light Actuated Chemical Delivery Platform On A 2-D Array Of Micropore Structure, Hojjat Rostami Azmand, Hojjat Rostami Azmand
Dissertations and Theses
Localized chemical delivery plays an essential role in the fundamental information transfers within biological systems. Thus, the ability to mimic the natural chemical signal modulation would provide significant contributions to understand the functional signaling pathway of biological cells and develop new prosthetic devices for neurological disorders. In this paper, we demonstrate a light-controlled hydrogel platform that can be used for localized chemical delivery in a high spatial resolution. By utilizing the photothermal behavior of graphene-hydrogel composites confined within micron-sized fluidic channels, patterned light illumination creates the parallel and independent actuation of chemical release in a group of fluidic ports. The …
Implementation Of A Computer-Vision System As A Supportive Diagnostic Tool For Parkinson’S Disease, Diego Machado Reyes
Implementation Of A Computer-Vision System As A Supportive Diagnostic Tool For Parkinson’S Disease, Diego Machado Reyes
Honors Theses
Parkinson’s disease is the second most common neurodegenerative disorder, affecting nearly 1 million people in the US and it is predicted that the number will keep increasing. Parkinson’s disease is difficult to diagnose due to its similarity with other diseases that share the parkinsonian symptoms and the subjectivity of its assessment, thus increasing the probabilities of misdiagnosis. Therefore, it is relevant to develop diagnostic tools that are quantitatively based and monitoring tools to improve the patient’s quality of life. Computer-based assessment systems have shown to be successful in this field through diverse approaches that can be classified into two main …
Vector Flow Imaging In Pediatric Cardiology - Extracting And Validating Data, Mason Belue
Vector Flow Imaging In Pediatric Cardiology - Extracting And Validating Data, Mason Belue
Biomedical Engineering Undergraduate Honors Theses
In the field of bedside cardiac diagnostic imaging, Doppler Ultrasound (DU) is the gold standard for diagnosing heart conditions. The largest benefit of DU is its ability to noninvasively image cardiac flow and allow the estimation of blood velocity and quantification of anatomical disease. However, to get correct velocity estimation, the position of the transducer in relation to the flow field needs to be known. This is the problem of angle/direction dependency and limits DUs accuracy when imaging in areas where perfect alignment or exact position of the transducer in relation to flow field is not possible or known, such …
Seeing Eye To Eye: A Machine Learning Approach To Automated Saccade Analysis, Maigh Attre
Seeing Eye To Eye: A Machine Learning Approach To Automated Saccade Analysis, Maigh Attre
Honors Scholar Theses
Abnormal ocular motility is a common manifestation of many underlying pathologies particularly those that are neurological. Dynamics of saccades, when the eye rapidly changes its point of fixation, have been characterized for many neurological disorders including concussions, traumatic brain injuries (TBI), and Parkinson’s disease. However, widespread saccade analysis for diagnostic and research purposes requires the recognition of certain eye movement parameters. Key information such as velocity and duration must be determined from data based on a wide set of patients’ characteristics that may range in eye shapes and iris, hair and skin pigmentation [36]. Previous work on saccade analysis has …
Development Of An Eye Movement Based Predictive Model For Discrimination Of Parkinson's Disease From Other Parkinsonisms And Controls, Mary Anisa Kannan
Development Of An Eye Movement Based Predictive Model For Discrimination Of Parkinson's Disease From Other Parkinsonisms And Controls, Mary Anisa Kannan
Theses and Dissertations
Purpose: Due to the neurological aspects of Parkinson’s Disease (PD) and the sensitivity of eye movements to neurological issues, eye tracking has the potential to be an objective biomarker with higher accuracy in diagnosis than current clinical standards. Currently when PD is diagnosed clinically, there is an accuracy of 74% when diagnosed by a general practitioner and 82% when diagnosed by a movement disorder specialist. This study was designed to: 1. Assess eye movements as a potential biomarker for Parkinson’s Disease. 2. Determine if eye movements can distinguish between Parkinson’s Disease and commonly confounded movement disorders with parkinsonian symptoms. 3. …
A Microfluidic Tissue Array (Μfta) For Personalized Medicine Using Tumor Biopsies, A.H. R. Ahmed
A Microfluidic Tissue Array (Μfta) For Personalized Medicine Using Tumor Biopsies, A.H. R. Ahmed
Dissertations and Theses
Cancer is recognized as a complex disease with both genetic and epigenetic drivers that can vary from one individual to another. While very early research into cancer treated it as a clonal malfunction that could originate from as small as a single deregulated cell, the disease itself manifests itself with several more complexities beyond tumorigenic cells only. The tumor microenvironment itself – from the extracellular matrix to stromal cells - cooperate with tumor cells in a symbiotic manner towards metastatic progression. Clinical studies have provided more information regarding the degree of individualization possible, such that patients with similar genetic makeup …
Eye Movement Control: An Index For Athleticism, Brittany L. Oshea
Eye Movement Control: An Index For Athleticism, Brittany L. Oshea
Theses and Dissertations
Athletic potential is one of the most complex human traits. An elite athlete is produced from a complex interaction of an innumerable number of traits exhibited by the athlete. However, it’s not clear whether these traits are innate, allowing the athlete to excel, or, alternatively, are a consequence of practice. To be successful, athletes rely heavily on sensory information from the visual and vestibular systems. This study investigated the relationship eye movement control has with innate athleticism by comparing the saccadic and Vestibulo-Ocular Reflex (VOR) responses of former, no longer practicing, elite athletes against their age and gender matched counterparts …