Digital Commons Network^™

Development Of Electrical Impedance Tomography Data Acquisition System And Deep Learning-Based Reconstruction Algorithms For Spatial Damage Detection, Damond Michael Li

Master's Theses

Electrical impedance tomography (EIT) is a non-destructive, non-invasive, and non-radioactive imaging technique used for reconstructing the internal conductivity distribution of a sensing domain. Performing EIT often requires large, stationary benchtop equipment that can be expensive and impractical. Other researchers have attempted to make portable EIT systems, but they all rely on external computation for image reconstruction/data analysis. This study outlines the development of a low-cost, portable, and wireless EIT data acquisition (DAQ) system that is capable of independently performing image reconstructions on-board. With the proposed system, EIT can be performed on carbon fiber reinforced polymers to spatially locate damages. Since …

Technical Note: Minimizing Cied Artifacts On A 0.35 T Mri-Linac Using Deep Learning, Austen N Curcuru, Deshan Yang, Hongyu An, Phillip S Cuculich, Clifford G Robinson, H Michael Gach

2020-Current year OA Pubs

BACKGROUND: Artifacts from implantable cardioverter defibrillators (ICDs) are a challenge to magnetic resonance imaging (MRI)-guided radiotherapy (MRgRT).

PURPOSE: This study tested an unsupervised generative adversarial network to mitigate ICD artifacts in balanced steady-state free precession (bSSFP) cine MRIs and improve image quality and tracking performance for MRgRT.

METHODS: Fourteen healthy volunteers (Group A) were scanned on a 0.35 T MRI-Linac with and without an MR conditional ICD taped to their left pectoral to simulate an implanted ICD. bSSFP MRI data from 12 of the volunteers were used to train a CycleGAN model to reduce ICD artifacts. The data from the …

Fully Automated Deep Learning Based Auto-Contouring Of Liver Segments And Spleen On Contrast-Enhanced Ct Images, Aashish C Gupta, Guillaume Cazoulat, Mais Al Taie, Sireesha Yedururi, Bastien Rigaud, Austin Castelo, John Wood, Cenji Yu, Caleb O'Connor, Usama Salem, Jessica Albuquerque Marques Silva, Aaron Kyle Jones, Molly Mcculloch, Bruno C Odisio, Eugene J Koay, Kristy K Brock

Faculty, Staff and Student Publications

Manual delineation of liver segments on computed tomography (CT) images for primary/secondary liver cancer (LC) patients is time-intensive and prone to inter/intra-observer variability. Therefore, we developed a deep-learning-based model to auto-contour liver segments and spleen on contrast-enhanced CT (CECT) images. We trained two models using 3d patch-based attention U-Net ([Formula: see text] and 3d full resolution of nnU-Net ([Formula: see text] to determine the best architecture ([Formula: see text]. BA was used with vessels ([Formula: see text] and spleen ([Formula: see text] to assess the impact on segment contouring. Models were trained, validated, and tested on 160 ([Formula: see text]), …

Functional Data Learning Using Convolutional Neural Networks, Jose Galarza, Tamer Oraby

School of Mathematical & Statistical Sciences Faculty Publications

In this paper, we show how convolutional neural networks (CNNs) can be used in regression and classification learning problems for noisy and non-noisy functional data (FD). The main idea is to transform the FD into a 28 by 28 image. We use a specific but typical architecture of a CNN to perform all the regression exercises of parameter estimation and functional form classification. First, we use some functional case studies of FD with and without random noise to showcase the strength of the new method. In particular, we use it to estimate exponential growth and decay rates, the bandwidths of …

Plant Disease Detection And Classification Using Deep Learning Methods: A Comparison Study, Pei-Wern Chin, Kok-Why Ng, Naveen Palanichamy

Journal of Informatics and Web Engineering

The presence issue of inaccurate plant disease detection persists under real field conditions and most deep learning (DL) techniques still struggle to achieve real-time performance. Hence, challenges in choosing a suitable deep-learning technique to tackle the problem should be addressed. Plant diseases have a detrimental effect on agricultural yield, hence early detection is crucial to prevent food insecurity. To identify and categorise the indications of plant diseases, numerous developed or modified DL architectures are utilised. This paper aims to observe the performance of the YOLOv8 model, which has better performance than its predecessors, on a small-scale plant disease dataset. This …

Prediction Of Student’S Academic Performance Through Data Mining Approach, Muhammad Mubashar Hussain, Shahzad Akbar, Syed Ale Hassan, Muhammad Waqas Aziz, Farwa Urooj

Journal of Informatics and Web Engineering

The universities and institutes produce a large amount of student data that can be used in a disciplinary way and useful information can be extracted by using an automated approach. Educational Data Mining (EDM) is an emerging discipline used in the educational environment to deal with big student data and extract useful information. The data mining of students’ data can help the At-risk students as well as the stakeholders by the early warning. This study aims to predict the performance of the students based on student-related data to increase the overall performance. In existing studies, insufficient attributes and complexity of …

The Hsp90-Myc-Cdk9 Network Drives Therapeutic Resistance In Mantle Cell Lymphoma, Fangfang Yan, Vivian Jiang, Alexa Jordan, Yuxuan Che, Yang Liu, Qingsong Cai, Yu Xue, Yijing Li, Joseph Mcintosh, Zhihong Chen, Jovanny Vargas, Lei Nie, Yixin Yao, Heng-Huan Lee, Wei Wang, Johnnelson R Bigcal, Maria Badillo, Jitendra Meena, Christopher Flowers, Jia Zhou, Zhongming Zhao, Lukas M Simon, Michael Wang

Faculty, Staff and Student Publications

Brexucabtagene autoleucel CAR-T therapy is highly efficacious in overcoming resistance to Bruton's tyrosine kinase inhibitors (BTKi) in mantle cell lymphoma. However, many patients relapse post CAR-T therapy with dismal outcomes. To dissect the underlying mechanisms of sequential resistance to BTKi and CAR-T therapy, we performed single-cell RNA sequencing analysis for 66 samples from 25 patients treated with BTKi and/or CAR-T therapy and conducted in-depth bioinformatics™ analysis. Our analysis revealed that MYC activity progressively increased with sequential resistance. HSP90AB1 (Heat shock protein 90 alpha family class B member 1), a MYC target, was identified as early driver of CAR-T resistance. CDK9 …

A Deep Learning Approach To Remove Contrast From Contrast-Enhanced Ct For Proton Dose Calculation, Xu Wang, Yao Hao, Ye Duan, Deshan Yang

2020-Current year OA Pubs

PURPOSE: Non-Contrast Enhanced CT (NCECT) is normally required for proton dose calculation while Contrast Enhanced CT (CECT) is often scanned for tumor and organ delineation. Possible tissue motion between these two CTs raises dosimetry uncertainties, especially for moving tumors in the thorax and abdomen. Here we report a deep-learning approach to generate NCECT directly from CECT. This method could be useful to avoid the NCECT scan, reduce CT simulation time and imaging dose, and decrease the uncertainties caused by tissue motion between otherwise two different CT scans.

METHODS: A deep network was developed to convert CECT to NCECT. The network …

Prediction Of Adverse Events Risk In Patients With Comorbid Post-Traumatic Stress Disorder And Alcohol Use Disorder Using Electronic Medical Records By Deep Learning Models, Oshin Miranda, Peihao Fan, Xiguang Qi, Haohan Wang, M Daniel Brannock, Thomas Kosten, Neal David Ryan, Levent Kirisci, Lirong Wang

Faculty, Staff and Students Publications

Background: Identifying co-occurring mental disorders and elevated risk is vital for optimization of healthcare processes. In this study, we will use DeepBiomarker2, an updated version of our deep learning model to predict the adverse events among patients with comorbid post-traumatic stress disorder (PTSD) and alcohol use disorder (AUD), a high-risk population.

Methods: We analyzed electronic medical records of 5565 patients from University of Pittsburgh Medical Center to predict adverse events (opioid use disorder, suicide related events, depression, and death) within 3 months at any encounter after the diagnosis of PTSD+AUD by using DeepBiomarker2. We integrated multimodal information including: lab tests, …

Deep Learning-Based Automatic Segmentation Of Cardiac Substructures For Lung Cancers, Xinru Chen, Raymond P Mumme, Kelsey L Corrigan, Yuki Mukai-Sasaki, Efstratios Koutroumpakis, Nicolas L Palaskas, Callistus M Nguyen, Yao Zhao, Kai Huang, Cenji Yu, Ting Xu, Aji Daniel, Peter A Balter, Xiaodong Zhang, Joshua S Niedzielski, Sanjay S Shete, Anita Deswal, Laurence E Court, Zhongxing Liao, Jinzhong Yang

Faculty, Staff and Student Publications

Purpose: Accurate and comprehensive segmentation of cardiac substructures is crucial for minimizing the risk of radiation-induced heart disease in lung cancer radiotherapy. We sought to develop and validate deep learning-based auto-segmentation models for cardiac substructures.

Materials and methods: Nineteen cardiac substructures (whole heart, 4 heart chambers, 6 great vessels, 4 valves, and 4 coronary arteries) in 100 patients treated for non-small cell lung cancer were manually delineated by two radiation oncologists. The valves and coronary arteries were delineated as planning risk volumes. An nnU-Net auto-segmentation model was trained, validated, and tested on this dataset with a split ratio of 75:5:20. …

Deep Learning Model Compression On Edge Devices For Audio, Afsana Rahman Mou

Theses and Dissertations

Audio classification plays a crucial role in interpreting and understanding soundscapes, enabling applications like voice assistants, sound event detection, and music analysis. However, deploying deep learning models for audio classification on edge devices presents significant challenges. These models often require substantial computational resources and memory, which are limited on edge devices. Balancing performance, efficiency, and accuracy remains a key hurdle in this field. In this research, we explore various deep learning architectures, including Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and Audio Spectrogram Transformer (AST), for the purpose of audio classification on the ESC 50 and Audio Set datasets. …

Crispr-Dipoff: An Interpretable Deep Learning Approach For Crispr Cas-9 Off-Target Prediction, Md Toufikuzzaman, Md Abul Hassan Samee, M Sohel Rahman

Faculty, Staff and Students Publications

CRISPR Cas-9 is a groundbreaking genome-editing tool that harnesses bacterial defense systems to alter DNA sequences accurately. This innovative technology holds vast promise in multiple domains like biotechnology, agriculture and medicine. However, such power does not come without its own peril, and one such issue is the potential for unintended modifications (Off-Target), which highlights the need for accurate prediction and mitigation strategies. Though previous studies have demonstrated improvement in Off-Target prediction capability with the application of deep learning, they often struggle with the precision-recall trade-off, limiting their effectiveness and do not provide proper interpretation of the complex decision-making process of …

Predicting Heart Disease Using Modified Googlenet Convolutional Neural Network Architecture Based On The Heart Sound, Abdullah R. Rashwan, Laila El Fangary, Safaa M. Azzam

Information Sciences Letters

Based on the data of the world health organization (WHO), diagnosing heart disease is a great task, as heart disease (HD) is the most prevalent disease worldwide. We suggested a method based on heart sounds to deal with this difficult issue because the heart sound (HS) is an essential component for detecting heart conditions. A feature extraction technique and a classifier are used in the suggested strategy. We use the GoogLeNet convolutional neural network (CNN) architecture with some modifications to separate the most crucial attributes of HS, and the heart condition is classified as diseased or not diseased based on …

Designing And Implementing An Ecg Reader And Heart Disease Classification Device Using Deep Learning (Comprehensive Review), Ghasaq Saad Jameel, M N. Al-Turfi, Dr. Hussain Falih Mahdi, Saba Nasser Hussain

Iraqi Journal for Computer Science and Mathematics

Cardiovascular cases remain a significant health care concern, necessitating new development methods for their prompt and accurate identification where a promising advancements is demonstrated using Deep Learning (DL) in automating heart anomalies detection, including irregular heartbeats, heart attacks, and abnormal heart rhythms, through the analysis of electrocardiogram (ECG) signals, which guided this article to explore the integration of DL methodologies in examining ECG data to enhance the diagnosis of various cardiac ailments and delves into the development of novel ECG devices designed to facilitate efficient data acquisition while ensuring patient comfort and accessibility.The devices used must provide real-time monitoring, seamless …

A Novel Deep Learning Approach For Classification Of Bird Sound Using Mel Frequency Cepstral Coefficients, Aymen Saad, Muhammad Mun’Im Ahmad Zabidi, Israa S. Kamil, Usman Ullah Sheikh

Iraqi Journal for Computer Science and Mathematics

Monitoring animal populationsis one important matter to better understand changes in their population, behavior, and biodiversity. Bird sounds are the main tool to classify bird species acoustically. The sounds of birds are an indicator for ecologists as it responds to changes in their environment. The recognition among a variety of bird species to get important features is computationally expensive. With the unbalanced classes and scarcity of training data, the performance accuracy is degrading.This paper aims to classify species ofbirds using lightweight convolutional neural networks (LWCNNs) basis on using a spectrogram image of Brazilian bird sounds as a dataset. For extracting …

Towards Sparse Imu Sensor-Based Estimation Of Walking Kinematics, Joint Moments, And Ground Reaction Forces In Multiple Locomotion Modes Via Deep Learning, Md Sanzid Bin Hossain

Graduate Thesis and Dissertation 2023-2024

Acquiring joint kinematics, joint moments, and ground reaction forces (GRFs) during walking is essential for assessing disease progression and health monitoring during rehabilitation. However, spatial and temporal constraints, expert processing, and high costs limit the current gold standard methods, such as optical motion capture systems and floor-embedded force plates. Experts have suggested wearables with machine learning methods to address this issue, but their large sensor count renders them impractical for daily use, and the use of generic algorithms limits their accuracy. As a result, learning kinematics and kinetics in everyday life outside of laboratory settings is challenging. Thus, there is …

Enhancing Scanning Tunneling Microscopy With Automation And Machine Learning, Darian Smalley

Graduate Thesis and Dissertation 2023-2024

The scanning tunneling microscope (STM) is one of the most advanced surface science tools capable of atomic resolution imaging and atomic manipulation. Unfortunately, STM has many time-consuming bottlenecks, like probe conditioning, tip instability, and noise artificing, which causes the technique to have low experimental throughput. This dissertation describes my efforts to address these challenges through automation and machine learning. It consists of two main sections each describing four projects for a total of eight studies.

The first section details two studies on nanoscale sample fabrication and two studies on STM tip preparation. The first two studies describe the fabrication of …

Disentangling Accelerated Cognitive Decline From The Normal Aging Process And Unraveling Its Genetic Components: A Neuroimaging-Based Deep Learning Approach, Yulin Dai, Yu-Chun Hsu, Brisa S Fernandes, Kai Zhang, Xiaoyang Li, Nitesh Enduru, Andi Liu, Astrid M Manuel, Xiaoqian Jiang, Zhongming Zhao, Alzheimer’S Disease Neuroimaging Initiative

Faculty, Staff and Student Publications

BACKGROUND: The progressive cognitive decline, an integral component of Alzheimer's disease (AD), unfolds in tandem with the natural aging process. Neuroimaging features have demonstrated the capacity to distinguish cognitive decline changes stemming from typical brain aging and AD between different chronological points.

OBJECTIVE: To disentangle the normal aging effect from the AD-related accelerated cognitive decline and unravel its genetic components using a neuroimaging-based deep learning approach.

METHODS: We developed a deep-learning framework based on a dual-loss Siamese ResNet network to extract fine-grained information from the longitudinal structural magnetic resonance imaging (MRI) data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) study. …

Deepwhalenet: A Climate Change-Aware Fft-Based Neural Network For Underwater Passive Acoustic Monitoring, Nicholas Ryan Rasmussen

Dissertations and Theses

In the face of escalating climate threats, the conservation of whale species has become increasingly critical. Traditional acoustic monitoring methods, burdened by extensive pre-processing and post-processing, need more adaptability and efficiency for effective marine mammal surveillance. This study introduces DeepWhaleNet, a novel deep-learning framework tailored for Underwater Passive Acoustic Monitoring (UPAM). DeepWhaleNet is designed to streamline whale detection by directly analyzing raw log-power spectrograms, thus extracting essential acoustic features to conserve these endangered species. The framework employs an extensive short-time Fourier transform (STFT) for input processing and a customized ResNet-18 architecture for classification, distinguishing whale vocalizations from ambient noise and …

Deep Learning Applications On Ionospheric Studies, Yang Pan

Physics Dissertations - Archive

Machine learning techniques, particularly deep learning techniques, have been vigorously pursued to tackle space physics problems and achieved some impressive results recently. The growth of deep learning technologies in different domains enables innovative solutions to those problems compared to conventional methods. Filling data gaps in instrumental observations is among the demanding issues, which benefits space physicists to study ionospheric phenomena with complete data coverage. Global total electron content (TEC) and regional ionospheric electron density (Ne) are among important physical parameters in ionospheric studies. Due to the limited coverage of global navigation satellite system (GNSS) ground receivers and sporadic …

Mitigating Safety Issues In Pre-Trained Language Models: A Model-Centric Approach Leveraging Interpretation Methods, Weicheng Ma

Dartmouth College Ph.D Dissertations

Pre-trained language models (PLMs), like GPT-4, which powers ChatGPT, face various safety issues, including biased responses and a lack of alignment with users' backgrounds and expectations. These problems threaten their sociability and public application. Present strategies for addressing these safety concerns primarily involve data-driven approaches, requiring extensive human effort in data annotation and substantial training resources. Research indicates that the nature of these safety issues evolves over time, necessitating continual updates to data and model re-training—an approach that is both resource-intensive and time-consuming. This thesis introduces a novel, model-centric strategy for understanding and mitigating the safety issues of PLMs by …

Leveraging Machine Learning & Deep Learning Methodologies To Detect Deepfakes, Aniruddha Tiwari

All Graduate Theses, Dissertations, and Other Capstone Projects

The rapid evolution of deep learning (DL) and machine learning (ML) techniques has facilitated the rise of highly convincing synthetic media, commonly referred to as deepfakes. These manipulative media artifacts, generated through advanced artificial intelligence algorithms, pose significant challenges in distinguishing them from authentic content. Given their potential to be disseminated widely across various online platforms, the imperative for robust detection methodologies becomes apparent. Accordingly, this study explores the efficacy of existing ML/DL-based approaches and aims to compare which type of methodology performs better in identifying deepfake content. In response to the escalating threat posed by deepfakes, previous research efforts …

Ai-Based Defect Detection In Aerospace Ultrasonic Signals, Rami Issac Lake

Graduate Research Theses & Dissertations

Ensuring the safety and integrity of materials and structures throughout the manufacturing cycle is a critical concern across various industries, including aerospace, automotive, oiland gas, and civil engineering. Non-Destructive Inspection (NDI) techniques allow for the examination of materials without causing damage or alteration, enabling the early detection of potential issues before materials are utilized in the field. The inspection of fuselage composites presents a particular challenge due to their complex structures, diverse materials, and differences in thickness, making defect detection a challenging yet crucial task. Moreover, defects of various types and causes can emerge across all depths of the material …

Artificial Intelligence Enabled Machinery Fault Detection And Diagnosis Using Vibro-Acoustic Signals, Srinivasa Rao Ippili

Theses and Dissertations--Mechanical and Aerospace Engineering

In various industries, the early detection of faults in rotating machinery is crucial to prevent system failures and ensure customer satisfaction. Typically, vibration measurement and diagnosis are employed for fault detection, but this process faces challenges in automation due to the complexity of installing and maintaining accelerometers, particularly in end-of-line quality control or pre-installed machinery health assessments. Acoustic signals, as a form of mechanical wave, offer an alternative for monitoring machinery while in operation. Unlike accelerometers, acoustic transducers are non-contact and easy to set up, enabling real-time data collection without interrupting equipment operation. However, utilizing acoustic signals in manufacturing poses …

Exploring 3d Genome Interaction And Epigenetic Regulation Via Swi/Snf Complex And Deep Learning Models, Ruoyun Wang

Dartmouth College Ph.D Dissertations

The three-dimensional organization of the genome is fundamental in regulating gene expression and maintaining cellular function. This organization's complexities, influenced by epigenetic marks and chromatin remodeling complexes, are crucial for understanding genomic regulation. Among these, the SWI/SNF complexes are key, facilitating chromatin accessibility and regulating gene activity across cell types. The first part of my dissertation focuses on SWI/SNF complexes, exploring their role in chromatin remodeling and their impact on 3D genome architecture. Utilizing next-generation sequencing (NGS) techniques, this section investigates the interplay between these complexes and chromatin structure. During my research on the SWI/SNF complex, I was intrigued by …

Enhancing Reservoir Modeling And Simulation Through Artificial Intelligence And Machine Learning: A Smart Proxy Modeling Approach, Andrew Timothy Jenkins

Graduate Theses, Dissertations, and Problem Reports (ETD)

The application of numerical reservoir simulation (NRS) has been a common approach within the oil and gas industry for decades, providing a means to model and forecast dynamic subsurface interactions, as a basis for reservoir management and development decisions. These techniques have expanded to application within carbon capture utilization and storage (CCUS) projects as domestic and global policy shift towards reducing carbon emissions while maintaining the energy needs of our modern society. NRS techniques have become a core process for permitting approval in Class VI (large-scale geological sequestration) wells due to the fundamental similarity of these types of subsurface processes. …

Custom Convolutional Neural Network Model For Identification Of Nutritional Deficiencies In Children, Shilpa Ankalaki, Vidyadevi G. Biradar, G. Kushal, N. Kavya

Open Access archive

Undernutrition occurs when there are deficiencies in essential vitamins, while overnutrition refers to consuming an excessive amount of nutrients, leading to issues such as obesity, diabetes, and related health problems. Malnutrition often stems from the economic and social status of parents. In children, malnutrition can significantly result in physical and mental growth issues. Therefore, there is a need for early prediction of malnutrition in children to mitigate its adverse effects. Children image comprises great amount of information which can be analyzed for distinguishing between a nourished or malnourished children. The success stories of convolutional neural networks in image classification are …

Predicting Application Security Attack Paths Using Correlation Analysis, Attack Tree, And Multi-Layer Perceptron, Santanam Kasturi

All-Inclusive List of Electronic Theses and Dissertations

The work proposed in this research is specific to application security and ties vulnerability data, data storage, statistical analysis, attack surface, attack tree, and predictive analytics as a comprehensive system for identifying attack patterns and predicting an attack path. The vulnerability information gathered using different detection and monitoring capabilities provides basic data for exposing a software applications attack surface. In a multi-tiered application that is web enabled and accessible through the internet starting with the UI / web layer (URL and web application headers) and going down to the Application Programming Interface (API) layer (application to API, API-API), and going …

Aboveground Biomass Density Estimation Using Deep Learning: Insight From Neon Ground-Truth Data And Simulated Gedi Waveform, Ashish Mahaur

Dissertations, Master's Theses and Master's Reports

Accurately estimating Aboveground Biomass Density (AGBD) is crucial for managing Earth's carbon cycle and informing climate strategies. NASA's GEDI mission advances global forest mapping, but traditional linear models often yield less reliable AGBD estimates. This study enhances AGBD estimation using deep learning models with NEON ground-truth data and simulated GEDI waveforms. We compared 1D CNNs, LSTMs, and pre-trained CNNs to traditional models. The ResNet152 model outperformed linear regression, achieving an R² of 0.68, demonstrating a 17% improvement. Our experiments also demonstrate the importance of large, diverse datasets, particularly for training deep learning models.

Security Information And Event Management Optimization Using Deep Federated Learning In Cloud-Based Autonomous Cyber-Physical Systems, Mohamed Mounir Moussa

Wayne State University Dissertations

The integration of cloud-based technologies into Connected and Autonomous Vehicles (CAVs) is reshaping the field by combining Deep Federated Learning (DFL), Security Information and Event Management (SIEM), and cloud-dew computing. This solution leverages cloud-based resource provisioning, which is crucial for allocating scalable and efficient computational resources in a dynamic manner. These resources are essential for managing the intricate data and computing requirements of distributed systems, especially in the intelligent vehicle sector. This provisioning facilitates the efficient control of route mapping and cybersecurity in Connected Autonomous Vehicles (CAVs), guaranteeing the ability to process and make decisions in real-time.The research evaluates the …