Physical Sciences and Mathematics Commons^™

Hybridize Functions: A Tool For Automatically Refactoring Imperative Deep Learning Programs To Graph Execution, Raffi Khatchadourian, Tatiana Castro Vélez, Mehdi Bagherzadeh, Nan Jia, Anita Raja

Publications and Research

Efficiency is essential to support responsiveness w.r.t. ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code—supporting symbolic, graph-based Deep Neural Network (DNN) computation. While scalable, such development is error-prone, non-intuitive, and difficult to debug. Consequently, more natural, imperative DL frameworks encouraging eager execution have emerged but at the expense of run-time performance. Though hybrid approaches aim for the “best of both worlds,” using them effectively requires subtle considerations to make code amenable to safe, accurate, and efficient graph execution—avoiding performance bottlenecks and semantically inequivalent results. We discuss the engineering aspects of a …

Hybridize Functions: A Tool For Automatically Refactoring Imperative Deep Learning Programs To Graph Execution, Raffi Khatchadourian, Tatiana Castro Vélez, Mehdi Bagherzadeh, Nan Jia, Anita Raja

Publications and Research

Efficiency is essential to support responsiveness w.r.t. ever-growing datasets, especially for Deep Learning (DL) systems. DL frameworks have traditionally embraced deferred execution-style DL code—supporting symbolic, graph-based Deep Neural Network (DNN) computation. While scalable, such development is error-prone, non-intuitive, and difficult to debug. Consequently, more natural, imperative DL frameworks encouraging eager execution have emerged but at the expense of run-time performance. Though hybrid approaches aim for the "best of both worlds," using them effectively requires subtle considerations to make code amenable to safe, accurate, and efficient graph execution—avoiding performance bottlenecks and semantically inequivalent results. We discuss the engineering aspects of a …

Unpaired Virtual Histological Staining Of Tissue From Autofluorescence Using Regularized Cycle-Consistent Adversarial Networks, Zhesi Wen

Theses and Dissertations

We present a regularized CycleGAN with a Dense Residual U-Net to virtually stain autofluorescence images of tissue into H&E-like images. Our method outperforms standard architectures, reduces artifacts, and achieves superior FID scores, enabling efficient, label-free, and accurate digital pathology for unpaired datasets using multi-channel fluorescence inputs.

Controlling A Mobile Inverted Pendulum And Optimizing Leaning Angle To Apply Force Using Reinforcement Learning, Aryan Mediratta

2025 Spring Honors Capstone Projects - Archive

Reinforcement Learning is a Machine Learning paradigm that involves simulating learning through rewards and penalties in intelligent systems. This technique is often employed in robotics when traditional control methods are insufficient or when human intuition does not provide a good solution on how to control robot systems, This project involves training a Segway-style Mobile Inverted Pendulum (MIP) robot to balance and push a box forward. The BeagleBone Blue board is used that includes a built-in Inertial Measurement Unit (IMU) and encoder ports. These sensors enable the system to measure its current state. The goal is to find the optimal leaning …

Advancing Precision And Autonomy In Agriculture And Medical Imaging Through Ai And Computer Visions, Tan-Hanh Pham

Theses and Dissertations

Deep learning has revolutionized numerous fields by enhancing precision, automation, and decision-making capabilities. This dissertation explores its applications in agriculture and medical image processing, introducing novel methodologies to improve accuracy and efficiency in these domains. These fields hold critical societal importance -- agriculture underpins global food security and sustainability, while medical imaging drives advancements in diagnostics and personalized healthcare, both benefiting significantly from data-driven innovations. In agriculture, deep learning is applied to precision spray systems through droplet analysis. Specifically, a generative model is designed to create synthetic droplet images, addressing the challenge of limited training samples, which are expensive …

Training Sensor-Agnostic Deep Learning Models For Remote Sensing: Achieving State-Of-The-Art Cloud And Cloud Shadow Identification With Omnicloudmask, Nicholas J. Wright, John M A Duncan, Nik Callow, Sally E. Thompson, Richard J. George

Natural Resources Research Articles

Deep learning models are widely used to extract features and insights from remotely sensed imagery. However, these models typically perform optimally when applied to the same sensor, resolution and imagery processing level as used during their training, and are rarely used or evaluated on out-of-domain data. This limitation results in duplication of efforts in collecting similar training datasets from different satellites to train sensor-specific models. Here, we introduce a range of techniques to train deep learning models that generalise across various sensors, resolutions, and processing levels. We applied this approach to train OmniCloudMask (OCM), a sensor-agnostic deep learning model that …

Contrastive Representation Learning For Highly Imbalanced Multivariate Time Series With Extreme Instance Strategy, Onur Vural

All Graduate Theses and Dissertations, Fall 2023 to Present

Time series data refers to a sequence of data points collected or recorded at regular time intervals. In many fields including space weather, healthcare, and finance, predicting events from such data is crucial because these predictions can help protect infrastructures, improve healthcare outcomes, and forecast financial trends. However, one challenge in working with time series data is the presence of rare events, which are often underrepresented in the data. This imbalance makes it difficult for traditional prediction methods to provide accurate results, as they tend to focus more on the more frequent events and overlook the rare ones. To tackle …

Time Series Deep Learning Approach For The Intermittent Operational Performance Of A Wellhead Water Treatment And Desalination System, Michael G. Clement

Electronic Theses, Projects, and Dissertations

Distributed water treatment and desalination (DWTD) systems are becoming significant for serving disadvantaged communities that are geographically segregated from centralized water distribution networks. However, given the remote nature of the communities, these systems must operate autonomously adapting to intermittent operations due to varying water use patterns and unavailability of continuous manual labor support. Machine Learning models describing and forecasting system performance are critical, allowing for model-based control, performance forecasting, fault detection, and determination of causal relationships among process attributes. Accordingly, graph convolutional neural networks with an attention mechanism (GATConv) were developed to describe the intermittent operational profiles of a wellhead …

On Bed Posture Recognition Using Deep Learning With Pressure Sensors, Farheen Akhter Ms

Electronic Theses, Projects, and Dissertations

In healthcare applications such as disease prevention, sleep quality evaluation, and patient monitoring, bed posture recognition is essential. Using pressure sensor arrays placed on top of or embedded in mattresses, this study investigates the application of deep learning models for non-invasive posture classification. Although they have been widely employed, traditional machine learning approaches like support vector machines (SVM) and k-nearest neighbors (KNN) sometimes struggle with feature extraction and real-time performance necessitating considerable processing resources. I implemented a model using conventional approaches to get over these restrictions, then fine-tuned it using the following deep learning architectures for bed posture recognition: ResNet-50, …

Modeling Language And Vision At Human Scales, Clayton Fields

Boise State University Theses and Dissertations

The impressive results that have recently been achieved in natural language processing and artificial intelligence have been primarily driven by the introduction of the transformer deep learning architecture, increasingly large models with many parameters and using enormous datasets. The size of models and their training data requirements present costly demands that freeze many researchers out of training with cutting edge models. Beyond these practical implications, current methods learn from text alone, without the rich array of sensory information that human beings use in learning language. This means that language models are often incapable of reasoning about the concrete world that …

Artificial Intelligence Applications For Grid-Connected Solar Inverters, Utkirjon Ubaydullaev, Sarvinoz Mirzaeva, Hasan Mustafoev

Chemical Technology, Control and Management

The increasing global demand for renewable energy has highlighted the importance of grid-connected solar inverters in ensuring efficient and stable power conversion. However, challenges such as fluctuations in solar energy generation, grid disturbances, and power quality issues necessitate advanced control strategies. The integration of artificial intelligence (AI) into solar inverters presents a transformative solution, enhancing performance, adaptability, and reliability in real-world applications.

This review explores the role of AI techniques, including machine learning (ML), deep learning (DL), fuzzy logic, and reinforcement learning (RL), in optimizing key inverter functionalities such as maximum power point tracking (MPPT), fault detection, power quality enhancement, …

New Deep Learning Approaches To Classical Statistical Problems, Shijie Wang

Theses and Dissertations

The field of deep learning (DL) has received considerable attention in recent years. Thanks to rapid growth in computational power, the ability to collect massive datasets, and improvements in software and algorithms, DL is now routinely applied to areas as diverse as computer vision, natural language processing, and bioinformatics. At the same time, DL is only starting to be explored in the context of classical statistical inference problems such as bootstrapping, quantile regression, and mixture modeling. In this dissertation, we develop new DL methodology for three classical statistical problems: 1) weighted M-estimation, 2) joint quantile regression, and 3) mixing density …

Real-Time Active-Learning Method For Audio-Based Anomalous Event Identification And Rare Events Classification For Audio Events Detection, Farkhund Iqbal, Ahmed Abbasi, Ahmad Almadhor, Shtwai Alsubai, Michal Gregus

All Works

Introduction: Audio event detection, the application of scientific methods to analyze audio recordings, can be helpful in examining and analyzing audio recordings to preserve, analyze, and interpret sound evidence. Furthermore, it can be helpful in safety and compliance, security, surveillance, maintenance, and predictive analysis. Audio event detection aims to recover meaningful information from audio recordings, such as determining the authenticity of the recording, identifying the speakers, and reconstructing conversations. However, filtering out noise for better accuracy in audio event detection is a major challenge. A greater sense of public security can be achieved by developing automated event detection systems that …

A Hybrid Deep Learning-Based Approach For Visual Field Test Forecasting, Ashkan Abbasi, Sowjanya Gowrisankaran, Wei-Chun Lin, Xubo Song, Bhavna Josephine Antony, Gadi Wollstein, Joel Schuman, Hiroshi Ishikawa

Wills Eye Hospital Papers

OBJECTIVE: Longitudinal assessment of visual field (VF) testing is essential in glaucoma management. Conventional VF forecasting methods require numerous prior tests, while deep learning techniques have shown promising results with fewer tests. This study introduces a hybrid deep learning framework to enhance flexibility and accuracy in VF test forecasting.

DESIGN: A retrospective longitudinal study using deep learning-based VF forecasting models.

SUBJECTS AND CONTROLS: A total of 1750 subjects (healthy and glaucoma patients) with 19 437 Humphrey VF (24-2 Swedish Interactive Threshold Algorithm) tests collected from longitudinal glaucoma cohorts at the University of Pittsburgh and New York University.

METHODS: Three deep …

Leveraging Attention Mechanism To Unlock Gene And Protein Attributes, Ala Jararweh

Computer Science ETDs

Advancing personalized medicine depends on effectively integrating and interpreting the vast, heterogeneous landscape of biological data, from genomic sequences and transcriptomics to the insights embedded in scientific literature. Current machine learning models often focus on single data modalities, limiting their capacity to capture the multifaceted nature of biological systems. We address this gap by developing three attention-based machine-learning models integrating diverse data modalities. Firstly, DeepVul is a multi-task model that leverages cancer transcriptome data to predict genes critical for cancer survival and their corresponding drugs. Subsequently, LitGene refines gene representations by integrating textual information from the scientific literature. Finally, Protein2Text …

Cutting-Edge Deep Learning Methods For Image-Based Object Detection In Autonomous Driving: In-Depth Survey, Narges Saeedizadeh, Seyed Mohammad Jafar Jalali, Burhan Khan, Shady Mohamed

Research outputs 2022 to 2026

Object detection is a critical aspect of computer vision (CV) applications, especially within autonomous driving systems (AVs), where it is fundamental to ensuring safety and reducing traffic accidents. Recent advancements in computational resources have enabled the widespread adoption of Deep Learning (DL) techniques, significantly enhancing the efficiency and accuracy of object detection tasks. However, the technology for autonomous driving has yet to reach a level of maturity that guarantees consistent performance, reliability, and safety, with several challenges remaining unresolved. This study specifically focuses on 2D image-based object detection methods, which offer several advantages over other modalities, such as cost-effectiveness and …

Exploring Transfer Learning For Deep Learning Polyp Detection In Colonoscopy Images Using Yolov8, Fabian Vazquez Jr., Jose Angel Nuñez, Xiaoyan Fu, Pengfei Gu, Bin Fu

Computer Science Faculty Publications

Deep learning methods have demonstrated strong performance in object detection tasks; however, their ability to learn domain-specific applications with limited training data remains a significant challenge. Transfer learning techniques address this issue by leveraging knowledge from pre-training on related datasets, enabling faster and more efficient learning for new tasks. Finding the right dataset for pre-training can play a critical role in determining the success of transfer learning and overall model performance. In this paper, we investigate the impact of pre-training a YOLOv8n model on seven distinct datasets, evaluating their effectiveness when transferred to the task of polyp detection. We compare …

Application Of A Generative Adversarial Network Algorithm To Filling Blank Strips Of Fractures In Formation Microresistivity Imaging Images, Kang Zhengming, Wu Chensheng, Yang Guodong, Wu Disheng, Wang Ruifei, Yang Xiangyu, Gan Wei

Coal Geology & Exploration

Objective Gaps between the electrodes of formation microresistivity imaging (FMI) imagers lead to blank strips in the resistivity images of borehole walls, significantly influencing the parameter assessment for fractures near borehole walls. The absence of full-borehole images renders it challenging to assess the blank strip filling quality for fractures in FMI images. Using a dataset constructed utilizing both simulated and actual data, this study proposed a generative adversarial network (GAN)-based method for filling the blank strips of fractures in FMI images. Methods First, the resistivity logging responses of a fractured formation were simulated using the 3D finite element method. Actual …

Solar Flare Prediction Using Multivariate Time Series Of Photospheric Magnetic Field Parameters: A Comparative Analysis Of Vector, Time Series, And Graph Data Representations, Onur Vural, Shah Muhammad Hamdi, Soukaina Filali Boubrahimi

Computer Science Student Research

The purpose of this study is to provide a comprehensive resource for the selection of data representations for machine learning-oriented models and components in solar flare prediction tasks. Major solar flares occurring in the solar corona and heliosphere can bring potential destructive consequences, posing significant risks to astronauts, space stations, electronics, communication systems, and numerous technological infrastructures. For this reason, the accurate detection of major flares is essential for mitigating these hazards and ensuring the safety of our technology-dependent society. In response, leveraging machine learning techniques for predicting solar flares has emerged as a significant application within the realm of …

A Deep Sparse Capsule Network For Non-Invasive Blood Glucose Level Estimation Using A Ppg Sensor, Narmatha Chellamani, Saleh Ali Albelwi, Manimurugan Shanmuganathan, Palanisamy Amirthalingam, Emad Muteb Alharbi, Hibah Qasem Salman Alatawi, Kousalya Prabahar, Jawhara Bader Aljabri, Anand Paul

School of Public Health Faculty Publications

Diabetes, a chronic medical condition, affects millions of people worldwide and requires consistent monitoring of blood glucose levels (BGLs). Traditional invasive methods for BGL monitoring can be challenging and painful for patients. This study introduces a non-invasive, deep learning (DL)-based approach to estimate BGL using photoplethysmography (PPG) signals. Specifically, a Deep Sparse Capsule Network (DSCNet) model is proposed to provide accurate and robust BGL monitoring. The proposed model’s workflow includes data collection, preprocessing, feature extraction, and predictions. A hardware module was designed using a PPG sensor and Raspberry Pi to collect patient data. In preprocessing, a Savitzky–Golay filter and moving …

Research On Air Target Threat Assessment Technology Based On Deep Learning, Dawei Jiang, Yangyang Dong, Lidong Zhang, Xiao Lu, Chunxi Dong

Journal of System Simulation

Abstract: In order to realize the effective assessment of air combat targets, a deep learning-based air target threat assessment method is proposed. According to threat characteristics of the air target, the threat attributes of air target faced by electronic countermeasure operation are analyzed from the two perspectives of platform layer and equipment layer, the air target threat assessment index system is constructed, and the air target threat assessment index data set is established. Based on convolutional neural network, a residual structure is introduced to optimize the network, a threat assessment model is established, and the threat ranking of air targets …

Deep Learning Of The Particulate And Mineral-Associated Organic Carbon Fractions Using A Compositional Transform And Mid-Infrared Spectroscopy, Mingxi Zhang, Zefang Shen, Lewis Walden, Farid Sepanta, Zhongkui Luo, Lei Gao, Oscar Serrano, Raphael A. Viscarra Rossel

Research outputs 2022 to 2026

We need soil organic carbon (SOC) and the SOC fractions, the particulate and mineral-associated organic carbon (POC, MAOC), to understand SOC dynamics. They have implications for soil management, carbon sequestration and climate change mitigation. However, conventional laboratory measurements of the SOC fractions, which involve physical or chemical separations, are elaborate, time-consuming and expensive. Mid-infrared (MIR) spectroscopy combined with multivariate modelling can alleviate these limitations because the method can estimate SOC and its fractions rapidly, cost-effectively and accurately. Previous spectroscopic modelling has mostly ignored the compositional nature of the SOC fractions (i.e. SOC = ∑fractions), causing discrepancies in the estimation such …

Smart Highway Construction Site Monitoring Using Artificial Intelligence, Mehran Mazari, Yahaira Nava-Gonzalez, Ly Jacky N. Nhiayi, Mohamad H. Saleh

Mineta Transportation Institute

Construction is a large sector of the economy and plays a significant role in creating economic growth and national development,and construction of transportation infrastructure is critical. This project developed a method to detect, classify, monitor, and track objects during the construction, maintenance, and rehabilitation of transportation infrastructure by using artificial intelligence and a deep learning approach. This study evaluated the performance of AI and deep learning algorithms to compare their performance in detecting and classifying the equipment in various construction scenes. Our goal was to find the optimized balance between the model capabilities in object detection and memory processing requirements. …

A Machine Learning/Deep Learning Investigation On Remote Manufacturing Machine State Classification, Ajeet S. Parmar

Theses and Dissertations

Determining the extent of manufacturing capabilities with respect to adversarial or hostile nations is a topic of significant importance to the Department of Defense. Manufacturing capabilities can serve as indications of a nation's industrial power and its economy of force in warfare. Remotely detecting machine operations via electromagnetic sensors may be possible via Deep Learning (DL) and Machine Learning (ML) algorithms. To predict machine states, sensor data is collected externally from a machine shop on a college campus to monitor the operating states of lathes and mills in individual and concurrent operation. Furthermore, several sensors are placed in various positions, …

Understanding The Oss Communities Of Deep Learning Frameworks: A Comparative Case Study Of Pytorch And Tensorflow, Yunqi Chen, Zhiyuan Wan, Yifei Zhuang, Ning Liu, David Lo, Xiaohu Yang

Research Collection School Of Computing and Information Systems

Over the past two decades, deep learning has received tremendous success in developing software systems across various domains. Deep learning frameworks have been proposed to facilitate the development of such software systems, among which, PyTorch and TensorFlow stand out as notable examples. Considerable attention focuses on exploring software engineering practices and addressing diverse technical aspects in developing and deploying deep learning frameworks and software systems. Despite these efforts, little is known about the open source software communities involved in the development of deep learning frameworks. In this article, we perform a comparative investigation into the open source software communities of …

A Method For Intelligent Information Extraction Of Coal Fractures Based On Μct And Deep Learning, Hu Zhazha, Zhang Xun, Jin Yi, Gong Linxian, Huang Wenhui, Ren Jianji, Norbert Klitzsch

Coal Geology & Exploration

Objective The fine-scale characterization of fractures in coal reservoirs is significant for the exploration and exploitation of coalbed methane (CBM) resources. Given that the size, orientation, and density of fractures directly affect the permeability of coal seams, the accurate information identification and extraction of fractures in coal seams plays a key role in revealing the formation and propagation mechanisms of fracture networks during reservoir volume fracturing. Conventional methods for fracture information extraction typically rely on manual labeling and feature extraction based on image processing techniques, exhibiting significantly limited accuracy and efficiency. Methods This study proposed a method for fracture information …

A Comprehensive Survey Of Data-Driven Solutions For Lorawan: Challenges And Future Directions, Poonam Maurya, Abhishek Hazra, Preti Kumari, Troels Bundgaard Sørensen, Sajal K. Das

Computer Science Faculty Research & Creative Works

Long-range Wide-area Network (LoRaWAN) is an innovative and prominent communication protocol in the domain of Low-power Wide-area Networks (LPWAN), known for its ability to provide long-range communication with low energy consumption. However, the practical implementation of the LoRaWAN protocol, operating at the Medium Access Control layer and specially built to work upon the LoRa physical layer, presents numerous research challenges, including network congestion, interference, optimal resource allocation, collisions, scalability, and security. To mitigate these challenges effectively, the adoption of cutting-edge data-driven technologies such as Deep Learning (DL) and Machine Learning (ML) emerges as a promising approach. Interestingly, very few existing …

Enhancing Online Toxicity Detection On Gaming Networks: A Novel Embeddings-Based Valence Lexicon Approach, Heba Ismail, Ashraf Khalil, Ahmed Jasmy

All Works

Online toxicity and violent speech on gaming networks pose significant threats to societal well-being, particularly among adolescents, and are linked to severe consequences such as suicide. This highlights an urgent need for effective toxicity detection methods tailored to these platforms. Traditional rule-based approaches are inherently limited, and the performance of predictive models in detecting online toxicity is critically dependent on the quality and representativeness of their training data. However, the distinct linguistic characteristics of discourse on gaming networks present unique challenges in curating representative training samples using existing valence lexicons, often resulting in suboptimal detection accuracy. In this study, we …

Artificial Intelligence (Ai) In Pharmacy, Giang Nguyen, Elizabeth Sartschev, John Reyes, Allie Honigford, Marisa Petrunich, Kiley Devoll, Brianna Lu, Joshua Honaker, T'Bony M. Jewell

Pharmacy and Wellness Review

Artificial Intelligence (AI) has transformed the pharmaceutical field by enabling computer software systems to learn and perform human behavior. Specifically, AI has revolutionized chronic diabetes management through continuous glucose monitoring, showcasing its immense potential in healthcare. However, alongside its transformative impact, AI’s increasing role in healthcare has prompted concerns over privacy and its premature integration. Despite these challenges, AI offers limitless opportunities to improve medication management and treatment regimens, driving advancements across various domains. From improving CT imaging to enhancing adenoma detection in colonoscopies and facilitating medication adherence, AI’s impact on healthcare is profound. Furthermore, AI plays a pivotal role …

Deep Learning-Based Auto-Segmentation For Liver Yttrium-90 Selective Internal Radiation Therapy, Jun Li, Wookjin Choi, Rani Anne

Department of Radiation Oncology Faculty Papers

The aim was to evaluate a deep learning-based auto-segmentation method for liver delineation in Y-90 selective internal radiation therapy (SIRT). A deep learning (DL)-based liver segmentation model using the U-Net3D architecture was built. Auto-segmentation of the liver was tested in CT images of SIRT patients. DL auto-segmented liver contours were evaluated against physician manually-delineated contours. Dice similarity coefficient (DSC) and mean distance to agreement (MDA) were calculated. The DL-model-generated contours were compared with the contours generated using an Atlas-based method. Ratio of volume (RV, the ratio of DL-model auto-segmented liver volume to manually-delineated liver volume), and ratio of activity (RA, …